[原]零基础学习视频解码之同步视频
2014-08-06 00:20 雪夜&流星 阅读(1511) 评论(0) 编辑 收藏 举报在前面几章，我们了解了视频解码的原理，了解了音频解码的原理，也将视频和音频分别放在了相应的解码线程中去了。所以这整个过程中，我们有一个基本无用的电影播放器。它可以播放视频，它也可以播放音频，但是这个并不完整，因为音频和视频并不同步，我们接下来要做的就是将音频和视频同步起来。
音频流有一个采样率，并且视频流具有每秒值的帧。但是，如果我们只是靠只是计算帧和帧速率乘以同步视频，有的情况下，它会声画不同步的。
当我们从av_read_frame()的数据包，它包含了这个包里面的信息的PTS和DTS值。但我们真正想要的是我们的新解码原始帧的PTS，所以我们知道什么时候来显示它。但是，我们从avcodec_decode_video得到的给了我们一个AVFrame，不包含有用的PTS值。然而，ffmpeg的重新排序，使数据包的DTS由avcodec_decode_video（处理的数据包）将永远是相同的因为它返回的帧的PTS。
有另一种方式来找出一帧的PTS，我们可以重新排列数据包。我们保存一帧的第一个包的PTS：这将是最终的帧的PTS。因此，当该流不给我们一个DTS，我们只是用这个保存的。我们可以通过avcodec_decode_video()找出哪些数据包是一个帧的第一个数据包。
虽然这一切都很好，好到什么时候我们应该表现出特定的视频帧。但是我们如何真正做到同步? 这里的想法：我们利用这个框架，计算出下一个应该显示的时候。然后，我们只需设置一个新的超时时间量后，再次刷新视频。正如你所预料的，我们核对系统时钟的下一帧的PTS值，看看我们的超时时间是多久。这种方法有效，但也有需要被处理的两个问题。
第一是知道何时下一个时刻将成为问题。现在，你可能会认为，我们可以在视频速率仅添加到当前PTS - 你会是基本上是正确的。然而，要重复某些种类的视频的帧。这意味着我们应该重复当前帧中的特定的次数。这可能会导致程序太早显示下一帧。因此，我们需要考虑到这一点。
第二个问题是，大量的视频文件都没有我们需要的视频速率。因此，我们有三种选择：同步音频到视频，同步视频到音频，或者两者同步至一个外部时钟（如计算机）。现在，我们将同步视频到音频。
一、添加数据结构，VideoState新增了audio_clock、video_clock，分别用来做相应的音频同步和视频同步
/* ============================================================================ Name : VideoDecodeTutorial5_1.c Author : clarck Version : Copyright : Your copyright notice Description : Hello World in C, Ansi-style ============================================================================ */ #include <stdio.h> #include <stdlib.h> #include <math.h> #include <libavcodec/avcodec.h> #include <libavformat/avformat.h> #include <libavformat/avio.h> #include <libswscale/swscale.h> #include <libavutil/avstring.h> #include <SDL/SDL.h> #include <SDL/SDL_thread.h> #ifdef __MINGW32__ #undef main /* Prevents SDL from overriding main() */ #endif #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 #define AVCODEC_MAX_AUDIO_FRAME_SIZE 192000 // 1 second of 48khz 32bit audio typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; /* source height & width */ int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; AVFrame audio_frame; AVStream *video_st; PacketQueue videoq; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE]; int pictq_size, pictq_rindex, pictq_windex; SDL_mutex *pictq_mutex; SDL_cond *pictq_cond; SDL_Thread *parse_tid; SDL_Thread *video_tid; AVIOContext *io_ctx; struct SwsContext *sws_ctx; char filename[1024]; int quit; } VideoState; int main(int argc, char *argv[]) { return EXIT_SUCCESS; }
二、添加AVPacket排队的操作
/* ============================================================================ Name : VideoDecodeTutorial5_1.c Author : clarck Version : Copyright : Your copyright notice Description : Hello World in C, Ansi-style ============================================================================ */ #include <stdio.h> #include <stdlib.h> #include <math.h> #include <libavcodec/avcodec.h> #include <libavformat/avformat.h> #include <libavformat/avio.h> #include <libswscale/swscale.h> #include <libavutil/avstring.h> #include <SDL/SDL.h> #include <SDL/SDL_thread.h> #ifdef __MINGW32__ #undef main /* Prevents SDL from overriding main() */ #endif #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 #define AVCODEC_MAX_AUDIO_FRAME_SIZE 192000 // 1 second of 48khz 32bit audio typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; /* source height & width */ int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; AVFrame audio_frame; AVStream *video_st; PacketQueue videoq; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE]; int pictq_size, pictq_rindex, pictq_windex; SDL_mutex *pictq_mutex; SDL_cond *pictq_cond; SDL_Thread *parse_tid; SDL_Thread *video_tid; AVIOContext *io_ctx; struct SwsContext *sws_ctx; char filename[1024]; int quit; } VideoState; /* Since we only have one decoding thread, the Big Struct can be global in case we need it. */ VideoState *global_video_state; void packet_queue_init(PacketQueue *q) { memset(q, 0, sizeof(PacketQueue)); q->mutex = SDL_CreateMutex(); q->cond = SDL_CreateCond(); } int packet_queue_put(PacketQueue *q, AVPacket *pkt) { AVPacketList *pkt1; if (av_dup_packet(pkt) < 0) { return -1; } pkt1 = av_malloc(sizeof(AVPacketList)); if (!pkt1) return -1; pkt1->pkt = *pkt; pkt1->next = NULL; SDL_LockMutex(q->mutex); if (!q->last_pkt) q->first_pkt = pkt1; else q->last_pkt->next = pkt1; q->last_pkt = pkt1; q->nb_packets++; q->size += pkt1->pkt.size; SDL_CondSignal(q->cond); SDL_UnlockMutex(q->mutex); return 0; } static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block) { AVPacketList *pkt1; int ret; SDL_LockMutex(q->mutex); for (;;) { if (global_video_state->quit) { ret = -1; break; } pkt1 = q->first_pkt; if (pkt1) { q->first_pkt = pkt1->next; if (!q->first_pkt) q->last_pkt = NULL; q->nb_packets--; q->size -= pkt1->pkt.size; *pkt = pkt1->pkt; av_free(pkt1); ret = 1; break; } else if (!block) { ret = 0; break; } else { SDL_CondWait(q->cond, q->mutex); } } SDL_UnlockMutex(q->mutex); return ret; } int main(int argc, char *argv[]) { return EXIT_SUCCESS; }
三、得到音频时钟
/* ============================================================================ Name : VideoDecodeTutorial5_1.c Author : clarck Version : Copyright : Your copyright notice Description : Hello World in C, Ansi-style ============================================================================ */ #include <stdio.h> #include <stdlib.h> #include <math.h> #include <libavcodec/avcodec.h> #include <libavformat/avformat.h> #include <libavformat/avio.h> #include <libswscale/swscale.h> #include <libavutil/avstring.h> #include <SDL/SDL.h> #include <SDL/SDL_thread.h> #ifdef __MINGW32__ #undef main /* Prevents SDL from overriding main() */ #endif #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 #define AVCODEC_MAX_AUDIO_FRAME_SIZE 192000 // 1 second of 48khz 32bit audio typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; /* source height & width */ int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; AVFrame audio_frame; AVStream *video_st; PacketQueue videoq; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE]; int pictq_size, pictq_rindex, pictq_windex; SDL_mutex *pictq_mutex; SDL_cond *pictq_cond; SDL_Thread *parse_tid; SDL_Thread *video_tid; AVIOContext *io_ctx; struct SwsContext *sws_ctx; char filename[1024]; int quit; } VideoState; /* Since we only have one decoding thread, the Big Struct can be global in case we need it. */ VideoState *global_video_state; void packet_queue_init(PacketQueue *q) { memset(q, 0, sizeof(PacketQueue)); q->mutex = SDL_CreateMutex(); q->cond = SDL_CreateCond(); } int packet_queue_put(PacketQueue *q, AVPacket *pkt) { AVPacketList *pkt1; if (av_dup_packet(pkt) < 0) { return -1; } pkt1 = av_malloc(sizeof(AVPacketList)); if (!pkt1) return -1; pkt1->pkt = *pkt; pkt1->next = NULL; SDL_LockMutex(q->mutex); if (!q->last_pkt) q->first_pkt = pkt1; else q->last_pkt->next = pkt1; q->last_pkt = pkt1; q->nb_packets++; q->size += pkt1->pkt.size; SDL_CondSignal(q->cond); SDL_UnlockMutex(q->mutex); return 0; } static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block) { AVPacketList *pkt1; int ret; SDL_LockMutex(q->mutex); for (;;) { if (global_video_state->quit) { ret = -1; break; } pkt1 = q->first_pkt; if (pkt1) { q->first_pkt = pkt1->next; if (!q->first_pkt) q->last_pkt = NULL; q->nb_packets--; q->size -= pkt1->pkt.size; *pkt = pkt1->pkt; av_free(pkt1); ret = 1; break; } else if (!block) { ret = 0; break; } else { SDL_CondWait(q->cond, q->mutex); } } SDL_UnlockMutex(q->mutex); return ret; } double get_audio_clock(VideoState *is) { double pts; int hw_buf_size, bytes_per_sec, n; pts = is->audio_clock; /* maintained in the audio thread */ hw_buf_size = is->audio_buf_size - is->audio_buf_index; bytes_per_sec = 0; n = is->audio_st->codec->channels * 2; if (is->audio_st) { bytes_per_sec = is->audio_st->codec->sample_rate * n; } if (bytes_per_sec) { pts -= (double) hw_buf_size / bytes_per_sec; } return pts; } int main(int argc, char *argv[]) { return EXIT_SUCCESS; }
四、解码音频包的同时更新音频时钟
/* ============================================================================ Name : VideoDecodeTutorial5_1.c Author : clarck Version : Copyright : Your copyright notice Description : Hello World in C, Ansi-style ============================================================================ */ #include <stdio.h> #include <stdlib.h> #include <math.h> #include <libavcodec/avcodec.h> #include <libavformat/avformat.h> #include <libavformat/avio.h> #include <libswscale/swscale.h> #include <libavutil/avstring.h> #include <SDL/SDL.h> #include <SDL/SDL_thread.h> #ifdef __MINGW32__ #undef main /* Prevents SDL from overriding main() */ #endif #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 #define AVCODEC_MAX_AUDIO_FRAME_SIZE 192000 // 1 second of 48khz 32bit audio typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; /* source height & width */ int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; AVFrame audio_frame; AVStream *video_st; PacketQueue videoq; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE]; int pictq_size, pictq_rindex, pictq_windex; SDL_mutex *pictq_mutex; SDL_cond *pictq_cond; SDL_Thread *parse_tid; SDL_Thread *video_tid; AVIOContext *io_ctx; struct SwsContext *sws_ctx; char filename[1024]; int quit; } VideoState; /* Since we only have one decoding thread, the Big Struct can be global in case we need it. */ VideoState *global_video_state; void packet_queue_init(PacketQueue *q) { memset(q, 0, sizeof(PacketQueue)); q->mutex = SDL_CreateMutex(); q->cond = SDL_CreateCond(); } int packet_queue_put(PacketQueue *q, AVPacket *pkt) { AVPacketList *pkt1; if (av_dup_packet(pkt) < 0) { return -1; } pkt1 = av_malloc(sizeof(AVPacketList)); if (!pkt1) return -1; pkt1->pkt = *pkt; pkt1->next = NULL; SDL_LockMutex(q->mutex); if (!q->last_pkt) q->first_pkt = pkt1; else q->last_pkt->next = pkt1; q->last_pkt = pkt1; q->nb_packets++; q->size += pkt1->pkt.size; SDL_CondSignal(q->cond); SDL_UnlockMutex(q->mutex); return 0; } static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block) { AVPacketList *pkt1; int ret; SDL_LockMutex(q->mutex); for (;;) { if (global_video_state->quit) { ret = -1; break; } pkt1 = q->first_pkt; if (pkt1) { q->first_pkt = pkt1->next; if (!q->first_pkt) q->last_pkt = NULL; q->nb_packets--; q->size -= pkt1->pkt.size; *pkt = pkt1->pkt; av_free(pkt1); ret = 1; break; } else if (!block) { ret = 0; break; } else { SDL_CondWait(q->cond, q->mutex); } } SDL_UnlockMutex(q->mutex); return ret; } double get_audio_clock(VideoState *is) { double pts; int hw_buf_size, bytes_per_sec, n; pts = is->audio_clock; /* maintained in the audio thread */ hw_buf_size = is->audio_buf_size - is->audio_buf_index; bytes_per_sec = 0; n = is->audio_st->codec->channels * 2; if (is->audio_st) { bytes_per_sec = is->audio_st->codec->sample_rate * n; } if (bytes_per_sec) { pts -= (double) hw_buf_size / bytes_per_sec; } return pts; } int audio_decode_frame(VideoState *is, double *pts_ptr) { int len1, data_size = 0, n; AVPacket *pkt = &is->audio_pkt; double pts; for (;;) { while (is->audio_pkt_size > 0) { int got_frame = 0; len1 = avcodec_decode_audio4(is->audio_st->codec, &is->audio_frame, &got_frame, pkt); if (len1 < 0) { /* if error, skip frame */ is->audio_pkt_size = 0; break; } if (got_frame) { data_size = is->audio_frame.linesize[0]; /*av_samples_get_buffer_size(NULL, is->audio_st->codec->channels, is->audio_frame.nb_samples, is->audio_st->codec->sample_fmt, 1);*/ memcpy(is->audio_buf, is->audio_frame.data[0], data_size); } is->audio_pkt_data += len1; is->audio_pkt_size -= len1; if (data_size <= 0) { /* No data yet, get more frames */ continue; } pts = is->audio_clock; *pts_ptr = pts; n = 2 * is->audio_st->codec->channels; is->audio_clock += (double) data_size / (double) (n * is->audio_st->codec->sample_rate); /* We have data, return it and come back for more later */ return data_size; } if (pkt->data) av_free_packet(pkt); if (is->quit) { return -1; } /* next packet */ if (packet_queue_get(&is->audioq, pkt, 1) < 0) { return -1; } is->audio_pkt_data = pkt->data; is->audio_pkt_size = pkt->size; /* if update, update the audio clock w/pts */ if (pkt->pts != AV_NOPTS_VALUE) { is->audio_clock = av_q2d(is->audio_st->time_base) * pkt->pts; } } return 0; } int main(int argc, char *argv[]) { return EXIT_SUCCESS; }
五、同步视频，根据音频时钟计算下显示需要的延时时间，并利用上一篇文章所使用的schedule_refresh来刷新显示的帧。
/* ============================================================================ Name : VideoDecodeTutorial5_1.c Author : clarck Version : Copyright : Your copyright notice Description : Hello World in C, Ansi-style ============================================================================ */ #include <stdio.h> #include <stdlib.h> #include <math.h> #include <libavcodec/avcodec.h> #include <libavformat/avformat.h> #include <libavformat/avio.h> #include <libswscale/swscale.h> #include <libavutil/avstring.h> #include <SDL/SDL.h> #include <SDL/SDL_thread.h> #ifdef __MINGW32__ #undef main /* Prevents SDL from overriding main() */ #endif #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 #define AVCODEC_MAX_AUDIO_FRAME_SIZE 192000 // 1 second of 48khz 32bit audio typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; /* source height & width */ int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; AVFrame audio_frame; AVStream *video_st; PacketQueue videoq; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE]; int pictq_size, pictq_rindex, pictq_windex; SDL_mutex *pictq_mutex; SDL_cond *pictq_cond; SDL_Thread *parse_tid; SDL_Thread *video_tid; AVIOContext *io_ctx; struct SwsContext *sws_ctx; char filename[1024]; int quit; } VideoState; /* Since we only have one decoding thread, the Big Struct can be global in case we need it. */ VideoState *global_video_state; void packet_queue_init(PacketQueue *q) { memset(q, 0, sizeof(PacketQueue)); q->mutex = SDL_CreateMutex(); q->cond = SDL_CreateCond(); } int packet_queue_put(PacketQueue *q, AVPacket *pkt) { AVPacketList *pkt1; if (av_dup_packet(pkt) < 0) { return -1; } pkt1 = av_malloc(sizeof(AVPacketList)); if (!pkt1) return -1; pkt1->pkt = *pkt; pkt1->next = NULL; SDL_LockMutex(q->mutex); if (!q->last_pkt) q->first_pkt = pkt1; else q->last_pkt->next = pkt1; q->last_pkt = pkt1; q->nb_packets++; q->size += pkt1->pkt.size; SDL_CondSignal(q->cond); SDL_UnlockMutex(q->mutex); return 0; } static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block) { AVPacketList *pkt1; int ret; SDL_LockMutex(q->mutex); for (;;) { if (global_video_state->quit) { ret = -1; break; } pkt1 = q->first_pkt; if (pkt1) { q->first_pkt = pkt1->next; if (!q->first_pkt) q->last_pkt = NULL; q->nb_packets--; q->size -= pkt1->pkt.size; *pkt = pkt1->pkt; av_free(pkt1); ret = 1; break; } else if (!block) { ret = 0; break; } else { SDL_CondWait(q->cond, q->mutex); } } SDL_UnlockMutex(q->mutex); return ret; } double get_audio_clock(VideoState *is) { double pts; int hw_buf_size, bytes_per_sec, n; pts = is->audio_clock; /* maintained in the audio thread */ hw_buf_size = is->audio_buf_size - is->audio_buf_index; bytes_per_sec = 0; n = is->audio_st->codec->channels * 2; if (is->audio_st) { bytes_per_sec = is->audio_st->codec->sample_rate * n; } if (bytes_per_sec) { pts -= (double) hw_buf_size / bytes_per_sec; } return pts; } int audio_decode_frame(VideoState *is, double *pts_ptr) { int len1, data_size = 0, n; AVPacket *pkt = &is->audio_pkt; double pts; for (;;) { while (is->audio_pkt_size > 0) { int got_frame = 0; len1 = avcodec_decode_audio4(is->audio_st->codec, &is->audio_frame, &got_frame, pkt); if (len1 < 0) { /* if error, skip frame */ is->audio_pkt_size = 0; break; } if (got_frame) { data_size = is->audio_frame.linesize[0]; /*av_samples_get_buffer_size(NULL, is->audio_st->codec->channels, is->audio_frame.nb_samples, is->audio_st->codec->sample_fmt, 1);*/ memcpy(is->audio_buf, is->audio_frame.data[0], data_size); } is->audio_pkt_data += len1; is->audio_pkt_size -= len1; if (data_size <= 0) { /* No data yet, get more frames */ continue; } pts = is->audio_clock; *pts_ptr = pts; n = 2 * is->audio_st->codec->channels; is->audio_clock += (double) data_size / (double) (n * is->audio_st->codec->sample_rate); /* We have data, return it and come back for more later */ return data_size; } if (pkt->data) av_free_packet(pkt); if (is->quit) { return -1; } /* next packet */ if (packet_queue_get(&is->audioq, pkt, 1) < 0) { return -1; } is->audio_pkt_data = pkt->data; is->audio_pkt_size = pkt->size; /* if update, update the audio clock w/pts */ if (pkt->pts != AV_NOPTS_VALUE) { is->audio_clock = av_q2d(is->audio_st->time_base) * pkt->pts; } } return 0; } void audio_callback(void *userdata, Uint8 *stream, int len) { VideoState *is = (VideoState *) userdata; int len1, audio_size; double pts; while (len > 0) { if (is->audio_buf_index >= is->audio_buf_size) { /* We have already sent all our data; get more */ audio_size = audio_decode_frame(is, &pts); if (audio_size < 0) { /* If error, output silence */ is->audio_buf_size = 1024; memset(is->audio_buf, 0, is->audio_buf_size); } else { is->audio_buf_size = audio_size; } is->audio_buf_index = 0; } len1 = is->audio_buf_size - is->audio_buf_index; if (len1 > len) len1 = len; memcpy(stream, (uint8_t *) is->audio_buf + is->audio_buf_index, len1); len -= len1; stream += len1; is->audio_buf_index += len1; } } static Uint32 sdl_refresh_timer_cb(Uint32 interval, void *opaque) { SDL_Event event; event.type = FF_REFRESH_EVENT; event.user.data1 = opaque; SDL_PushEvent(&event); return 0; /* 0 means stop timer */ } /* schedule a video refresh in 'delay' ms */ static void schedule_refresh(VideoState *is, int delay) { SDL_AddTimer(delay, sdl_refresh_timer_cb, is); } void video_display(VideoState *is) { SDL_Rect rect; VideoPicture *vp; float aspect_ratio; int w, h, x, y; vp = &is->pictq[is->pictq_rindex]; if (vp->bmp) { if (is->video_st->codec->sample_aspect_ratio.num == 0) { aspect_ratio = 0; } else { aspect_ratio = av_q2d(is->video_st->codec->sample_aspect_ratio) * is->video_st->codec->width / is->video_st->codec->height; } if (aspect_ratio <= 0.0) { aspect_ratio = (float) is->video_st->codec->width / (float) is->video_st->codec->height; } h = screen->h; w = ((int) rint(h * aspect_ratio)) & -3; if (w > screen->w) { w = screen->w; h = ((int) rint(w / aspect_ratio)) & -3; } x = (screen->w - w) / 2; y = (screen->h - h) / 2; rect.x = x; rect.y = y; rect.w = w; rect.h = h; SDL_DisplayYUVOverlay(vp->bmp, &rect); } } void video_refresh_timer(void *userdata) { VideoState *is = (VideoState *) userdata; VideoPicture *vp; double actual_delay, delay, sync_threshold, ref_clock, diff; if (is->video_st) { if (is->pictq_size == 0) { schedule_refresh(is, 1); } else { vp = &is->pictq[is->pictq_rindex]; delay = vp->pts - is->frame_last_pts; /* the pts from last time */ if (delay <= 0 || delay >= 1.0) { /* if incorrect delay, use previous one */ delay = is->frame_last_delay; } /* save for next time */ is->frame_last_delay = delay; is->frame_last_pts = vp->pts; /* update delay to sync to audio */ ref_clock = get_audio_clock(is); diff = vp->pts - ref_clock; /* Skip or repeat the frame. Take delay into account FFPlay still doesn't "know if this is the best guess." */ sync_threshold = (delay > AV_SYNC_THRESHOLD) ? delay : AV_SYNC_THRESHOLD; if (fabs(diff) < AV_NOSYNC_THRESHOLD) { if (diff <= -sync_threshold) { delay = 0; } else if (diff >= sync_threshold) { delay = 2 * delay; } } is->frame_timer += delay; /* computer the REAL delay */ actual_delay = is->frame_timer - (av_gettime() / 1000000.0); if (actual_delay < 0.010) { /* Really it should skip the picture instead */ actual_delay = 0.010; } schedule_refresh(is, (int) (actual_delay * 1000 + 0.5)); /* show the picture! */ video_display(is); /* update queue for next picture! */ if (++is->pictq_rindex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_rindex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size--; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } } else { schedule_refresh(is, 100); } } void alloc_picture(void *userdata) { VideoState *is = (VideoState *) userdata; VideoPicture *vp; vp = &is->pictq[is->pictq_windex]; if (vp->bmp) { // we already have one make another, bigger/smaller SDL_FreeYUVOverlay(vp->bmp); } // Allocate a place to put our YUV image on that screen vp->bmp = SDL_CreateYUVOverlay(is->video_st->codec->width, is->video_st->codec->height, SDL_YV12_OVERLAY, screen); vp->width = is->video_st->codec->width; vp->height = is->video_st->codec->height; SDL_LockMutex(is->pictq_mutex); vp->allocated = 1; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } int queue_picture(VideoState *is, AVFrame *pFrame, double pts) { VideoPicture *vp; //int dst_pix_fmt; AVPicture pict; /* wait until we have space for a new pic */ SDL_LockMutex(is->pictq_mutex); while (is->pictq_size >= VIDEO_PICTURE_QUEUE_SIZE && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if (is->quit) return -1; // windex is set to 0 initially vp = &is->pictq[is->pictq_windex]; /* allocate or resize the buffer! */ if (!vp->bmp || vp->width != is->video_st->codec->width || vp->height != is->video_st->codec->height) { SDL_Event event; vp->allocated = 0; /* we have to do it in the main thread */ event.type = FF_ALLOC_EVENT; event.user.data1 = is; SDL_PushEvent(&event); /* wait until we have a picture allocated */ SDL_LockMutex(is->pictq_mutex); while (!vp->allocated && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if (is->quit) { return -1; } } /* We have a place to put our picture on the queue */ /* If we are skipping a frame, do we set this to null but still return vp->allocated = 1? */ if (vp->bmp) { SDL_LockYUVOverlay(vp->bmp); //dst_pix_fmt = PIX_FMT_YUV420P; /* point pict at the queue */ pict.data[0] = vp->bmp->pixels[0]; pict.data[1] = vp->bmp->pixels[2]; pict.data[2] = vp->bmp->pixels[1]; pict.linesize[0] = vp->bmp->pitches[0]; pict.linesize[1] = vp->bmp->pitches[2]; pict.linesize[2] = vp->bmp->pitches[1]; // Convert the image into YUV format that SDL uses sws_scale(is->sws_ctx, (const uint8_t * const *) pFrame->data, pFrame->linesize, 0, is->video_st->codec->height, pict.data, pict.linesize); SDL_UnlockYUVOverlay(vp->bmp); vp->pts = pts; /* now we inform our display thread that we have a pic ready */ if (++is->pictq_windex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_windex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size++; SDL_UnlockMutex(is->pictq_mutex); } return 0; } int main(int argc, char *argv[]) { return EXIT_SUCCESS; }
六、同步video_clock
/* ============================================================================ Name : VideoDecodeTutorial5_1.c Author : clarck Version : Copyright : Your copyright notice Description : Hello World in C, Ansi-style ============================================================================ */ #include <stdio.h> #include <stdlib.h> #include <math.h> #include <libavcodec/avcodec.h> #include <libavformat/avformat.h> #include <libavformat/avio.h> #include <libswscale/swscale.h> #include <libavutil/avstring.h> #include <SDL/SDL.h> #include <SDL/SDL_thread.h> #ifdef __MINGW32__ #undef main /* Prevents SDL from overriding main() */ #endif #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 #define AVCODEC_MAX_AUDIO_FRAME_SIZE 192000 // 1 second of 48khz 32bit audio typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; /* source height & width */ int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; AVFrame audio_frame; AVStream *video_st; PacketQueue videoq; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE]; int pictq_size, pictq_rindex, pictq_windex; SDL_mutex *pictq_mutex; SDL_cond *pictq_cond; SDL_Thread *parse_tid; SDL_Thread *video_tid; AVIOContext *io_ctx; struct SwsContext *sws_ctx; char filename[1024]; int quit; } VideoState; /* Since we only have one decoding thread, the Big Struct can be global in case we need it. */ VideoState *global_video_state; void packet_queue_init(PacketQueue *q) { memset(q, 0, sizeof(PacketQueue)); q->mutex = SDL_CreateMutex(); q->cond = SDL_CreateCond(); } int packet_queue_put(PacketQueue *q, AVPacket *pkt) { AVPacketList *pkt1; if (av_dup_packet(pkt) < 0) { return -1; } pkt1 = av_malloc(sizeof(AVPacketList)); if (!pkt1) return -1; pkt1->pkt = *pkt; pkt1->next = NULL; SDL_LockMutex(q->mutex); if (!q->last_pkt) q->first_pkt = pkt1; else q->last_pkt->next = pkt1; q->last_pkt = pkt1; q->nb_packets++; q->size += pkt1->pkt.size; SDL_CondSignal(q->cond); SDL_UnlockMutex(q->mutex); return 0; } static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block) { AVPacketList *pkt1; int ret; SDL_LockMutex(q->mutex); for (;;) { if (global_video_state->quit) { ret = -1; break; } pkt1 = q->first_pkt; if (pkt1) { q->first_pkt = pkt1->next; if (!q->first_pkt) q->last_pkt = NULL; q->nb_packets--; q->size -= pkt1->pkt.size; *pkt = pkt1->pkt; av_free(pkt1); ret = 1; break; } else if (!block) { ret = 0; break; } else { SDL_CondWait(q->cond, q->mutex); } } SDL_UnlockMutex(q->mutex); return ret; } double get_audio_clock(VideoState *is) { double pts; int hw_buf_size, bytes_per_sec, n; pts = is->audio_clock; /* maintained in the audio thread */ hw_buf_size = is->audio_buf_size - is->audio_buf_index; bytes_per_sec = 0; n = is->audio_st->codec->channels * 2; if (is->audio_st) { bytes_per_sec = is->audio_st->codec->sample_rate * n; } if (bytes_per_sec) { pts -= (double) hw_buf_size / bytes_per_sec; } return pts; } int audio_decode_frame(VideoState *is, double *pts_ptr) { int len1, data_size = 0, n; AVPacket *pkt = &is->audio_pkt; double pts; for (;;) { while (is->audio_pkt_size > 0) { int got_frame = 0; len1 = avcodec_decode_audio4(is->audio_st->codec, &is->audio_frame, &got_frame, pkt); if (len1 < 0) { /* if error, skip frame */ is->audio_pkt_size = 0; break; } if (got_frame) { data_size = is->audio_frame.linesize[0]; /*av_samples_get_buffer_size(NULL, is->audio_st->codec->channels, is->audio_frame.nb_samples, is->audio_st->codec->sample_fmt, 1);*/ memcpy(is->audio_buf, is->audio_frame.data[0], data_size); } is->audio_pkt_data += len1; is->audio_pkt_size -= len1; if (data_size <= 0) { /* No data yet, get more frames */ continue; } pts = is->audio_clock; *pts_ptr = pts; n = 2 * is->audio_st->codec->channels; is->audio_clock += (double) data_size / (double) (n * is->audio_st->codec->sample_rate); /* We have data, return it and come back for more later */ return data_size; } if (pkt->data) av_free_packet(pkt); if (is->quit) { return -1; } /* next packet */ if (packet_queue_get(&is->audioq, pkt, 1) < 0) { return -1; } is->audio_pkt_data = pkt->data; is->audio_pkt_size = pkt->size; /* if update, update the audio clock w/pts */ if (pkt->pts != AV_NOPTS_VALUE) { is->audio_clock = av_q2d(is->audio_st->time_base) * pkt->pts; } } return 0; } void audio_callback(void *userdata, Uint8 *stream, int len) { VideoState *is = (VideoState *) userdata; int len1, audio_size; double pts; while (len > 0) { if (is->audio_buf_index >= is->audio_buf_size) { /* We have already sent all our data; get more */ audio_size = audio_decode_frame(is, &pts); if (audio_size < 0) { /* If error, output silence */ is->audio_buf_size = 1024; memset(is->audio_buf, 0, is->audio_buf_size); } else { is->audio_buf_size = audio_size; } is->audio_buf_index = 0; } len1 = is->audio_buf_size - is->audio_buf_index; if (len1 > len) len1 = len; memcpy(stream, (uint8_t *) is->audio_buf + is->audio_buf_index, len1); len -= len1; stream += len1; is->audio_buf_index += len1; } } static Uint32 sdl_refresh_timer_cb(Uint32 interval, void *opaque) { SDL_Event event; event.type = FF_REFRESH_EVENT; event.user.data1 = opaque; SDL_PushEvent(&event); return 0; /* 0 means stop timer */ } /* schedule a video refresh in 'delay' ms */ static void schedule_refresh(VideoState *is, int delay) { SDL_AddTimer(delay, sdl_refresh_timer_cb, is); } void video_display(VideoState *is) { SDL_Rect rect; VideoPicture *vp; float aspect_ratio; int w, h, x, y; vp = &is->pictq[is->pictq_rindex]; if (vp->bmp) { if (is->video_st->codec->sample_aspect_ratio.num == 0) { aspect_ratio = 0; } else { aspect_ratio = av_q2d(is->video_st->codec->sample_aspect_ratio) * is->video_st->codec->width / is->video_st->codec->height; } if (aspect_ratio <= 0.0) { aspect_ratio = (float) is->video_st->codec->width / (float) is->video_st->codec->height; } h = screen->h; w = ((int) rint(h * aspect_ratio)) & -3; if (w > screen->w) { w = screen->w; h = ((int) rint(w / aspect_ratio)) & -3; } x = (screen->w - w) / 2; y = (screen->h - h) / 2; rect.x = x; rect.y = y; rect.w = w; rect.h = h; SDL_DisplayYUVOverlay(vp->bmp, &rect); } } void video_refresh_timer(void *userdata) { VideoState *is = (VideoState *) userdata; VideoPicture *vp; double actual_delay, delay, sync_threshold, ref_clock, diff; if (is->video_st) { if (is->pictq_size == 0) { schedule_refresh(is, 1); } else { vp = &is->pictq[is->pictq_rindex]; delay = vp->pts - is->frame_last_pts; /* the pts from last time */ if (delay <= 0 || delay >= 1.0) { /* if incorrect delay, use previous one */ delay = is->frame_last_delay; } /* save for next time */ is->frame_last_delay = delay; is->frame_last_pts = vp->pts; /* update delay to sync to audio */ ref_clock = get_audio_clock(is); diff = vp->pts - ref_clock; /* Skip or repeat the frame. Take delay into account FFPlay still doesn't "know if this is the best guess." */ sync_threshold = (delay > AV_SYNC_THRESHOLD) ? delay : AV_SYNC_THRESHOLD; if (fabs(diff) < AV_NOSYNC_THRESHOLD) { if (diff <= -sync_threshold) { delay = 0; } else if (diff >= sync_threshold) { delay = 2 * delay; } } is->frame_timer += delay; /* computer the REAL delay */ actual_delay = is->frame_timer - (av_gettime() / 1000000.0); if (actual_delay < 0.010) { /* Really it should skip the picture instead */ actual_delay = 0.010; } schedule_refresh(is, (int) (actual_delay * 1000 + 0.5)); /* show the picture! */ video_display(is); /* update queue for next picture! */ if (++is->pictq_rindex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_rindex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size--; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } } else { schedule_refresh(is, 100); } } void alloc_picture(void *userdata) { VideoState *is = (VideoState *) userdata; VideoPicture *vp; vp = &is->pictq[is->pictq_windex]; if (vp->bmp) { // we already have one make another, bigger/smaller SDL_FreeYUVOverlay(vp->bmp); } // Allocate a place to put our YUV image on that screen vp->bmp = SDL_CreateYUVOverlay(is->video_st->codec->width, is->video_st->codec->height, SDL_YV12_OVERLAY, screen); vp->width = is->video_st->codec->width; vp->height = is->video_st->codec->height; SDL_LockMutex(is->pictq_mutex); vp->allocated = 1; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } int queue_picture(VideoState *is, AVFrame *pFrame, double pts) { VideoPicture *vp; //int dst_pix_fmt; AVPicture pict; /* wait until we have space for a new pic */ SDL_LockMutex(is->pictq_mutex); while (is->pictq_size >= VIDEO_PICTURE_QUEUE_SIZE && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if (is->quit) return -1; // windex is set to 0 initially vp = &is->pictq[is->pictq_windex]; /* allocate or resize the buffer! */ if (!vp->bmp || vp->width != is->video_st->codec->width || vp->height != is->video_st->codec->height) { SDL_Event event; vp->allocated = 0; /* we have to do it in the main thread */ event.type = FF_ALLOC_EVENT; event.user.data1 = is; SDL_PushEvent(&event); /* wait until we have a picture allocated */ SDL_LockMutex(is->pictq_mutex); while (!vp->allocated && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if (is->quit) { return -1; } } /* We have a place to put our picture on the queue */ /* If we are skipping a frame, do we set this to null but still return vp->allocated = 1? */ if (vp->bmp) { SDL_LockYUVOverlay(vp->bmp); //dst_pix_fmt = PIX_FMT_YUV420P; /* point pict at the queue */ pict.data[0] = vp->bmp->pixels[0]; pict.data[1] = vp->bmp->pixels[2]; pict.data[2] = vp->bmp->pixels[1]; pict.linesize[0] = vp->bmp->pitches[0]; pict.linesize[1] = vp->bmp->pitches[2]; pict.linesize[2] = vp->bmp->pitches[1]; // Convert the image into YUV format that SDL uses sws_scale(is->sws_ctx, (const uint8_t * const *) pFrame->data, pFrame->linesize, 0, is->video_st->codec->height, pict.data, pict.linesize); SDL_UnlockYUVOverlay(vp->bmp); vp->pts = pts; /* now we inform our display thread that we have a pic ready */ if (++is->pictq_windex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_windex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size++; SDL_UnlockMutex(is->pictq_mutex); } return 0; } double synchronize_video(VideoState *is, AVFrame *src_frame, double pts) { double frame_delay; if (pts != 0) { /* if we have pts, set video clock to it */ is->video_clock = pts; } else { /* if we aren't given a pts, set it to the clock */ pts = is->video_clock; } /* update the video clock */ frame_delay = av_q2d(is->video_st->codec->time_base); /* if we are repeating a frame, adjust clock accordingly */ frame_delay += src_frame->repeat_pict * (frame_delay * 0.5); is->video_clock += frame_delay; return pts; } uint64_t global_video_pkt_pts = AV_NOPTS_VALUE; /* These are called whenever we allocate a frame * buffer. We use this to store the global_pts in * a frame at the time it is allocated. */ int our_get_buffer(struct AVCodecContext *c, AVFrame *pic) { int ret = avcodec_default_get_buffer(c, pic); uint64_t *pts = av_malloc(sizeof(uint64_t)); *pts = global_video_pkt_pts; pic->opaque = pts; return ret; } void our_release_buffer(struct AVCodecContext *c, AVFrame *pic) { if (pic) av_freep(&pic->opaque); avcodec_default_release_buffer(c, pic); } int video_thread(void *arg) { VideoState *is = (VideoState *) arg; AVPacket pkt1, *packet = &pkt1; //int len1; int frameFinished; AVFrame *pFrame; double pts; pFrame = av_frame_alloc(); for (;;) { if (packet_queue_get(&is->videoq, packet, 1) < 0) { // means we quit getting packets break; } pts = 0; // Save global pts to be stored in pFrame in first call global_video_pkt_pts = packet->pts; // Decode video frame //len1 = avcodec_decode_video2(is->video_st->codec, pFrame, &frameFinished, packet); if (packet->dts == AV_NOPTS_VALUE && pFrame->opaque && *(uint64_t*) pFrame->opaque != AV_NOPTS_VALUE) { pts = *(uint64_t *) pFrame->opaque; } else if (packet->dts != AV_NOPTS_VALUE) { pts = packet->dts; } else { pts = 0; } pts *= av_q2d(is->video_st->time_base); // Did we get a video frame? if (frameFinished) { pts = synchronize_video(is, pFrame, pts); if (queue_picture(is, pFrame, pts) < 0) { break; } } av_free_packet(packet); } av_free(pFrame); return 0; } int main(int argc, char *argv[]) { return EXIT_SUCCESS; }
七、视频的其余逻辑处理
/* ============================================================================ Name : player5.c Author : clarck Version : Copyright : Your copyright notice Description : Hello World in C, Ansi-style ============================================================================ */ // tutorial05.c // A pedagogical video player that really works! // // Code based on FFplay, Copyright (c) 2003 Fabrice Bellard, // and a tutorial by Martin Bohme (boehme@inb.uni-luebeckREMOVETHIS.de) // and another tutorial by Stephen Dranger (dranger at gmail dot com) // Tested on Gentoo, CVS version 5/01/07 compiled with GCC 4.1.1 // Use // // gcc -o tutorial05 tutorial05.c -lavformat -lavcodec -lswscale -lz -lm `sdl-config --cflags --libs` // to build (assuming libavformat and libavcodec and libswscale are correctly installed, // and assuming you have sdl-config. Please refer to SDL docs for your installation.) // // Run using // tutorial05 myvideofile.mpg // // to play the video. #include <libavcodec/avcodec.h> #include <libavformat/avformat.h> #include <libavformat/avio.h> #include <libswscale/swscale.h> #include <libavutil/avstring.h> #include <SDL/SDL.h> #include <SDL/SDL_thread.h> #ifdef __MINGW32__ #undef main /* Prevents SDL from overriding main() */ #endif #include <stdio.h> #include <math.h> #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 #define AVCODEC_MAX_AUDIO_FRAME_SIZE 192000 // 1 second of 48khz 32bit audio typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; /* source height & width */ int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; AVFrame audio_frame; AVStream *video_st; PacketQueue videoq; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE]; int pictq_size, pictq_rindex, pictq_windex; SDL_mutex *pictq_mutex; SDL_cond *pictq_cond; SDL_Thread *parse_tid; SDL_Thread *video_tid; AVIOContext *io_ctx; struct SwsContext *sws_ctx; char filename[1024]; int quit; } VideoState; SDL_Surface *screen; /* Since we only have one decoding thread, the Big Struct can be global in case we need it. */ VideoState *global_video_state; void packet_queue_init(PacketQueue *q) { memset(q, 0, sizeof(PacketQueue)); q->mutex = SDL_CreateMutex(); q->cond = SDL_CreateCond(); } int packet_queue_put(PacketQueue *q, AVPacket *pkt) { AVPacketList *pkt1; if (av_dup_packet(pkt) < 0) { return -1; } pkt1 = av_malloc(sizeof(AVPacketList)); if (!pkt1) return -1; pkt1->pkt = *pkt; pkt1->next = NULL; SDL_LockMutex(q->mutex); if (!q->last_pkt) q->first_pkt = pkt1; else q->last_pkt->next = pkt1; q->last_pkt = pkt1; q->nb_packets++; q->size += pkt1->pkt.size; SDL_CondSignal(q->cond); SDL_UnlockMutex(q->mutex); return 0; } static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block) { AVPacketList *pkt1; int ret; SDL_LockMutex(q->mutex); for (;;) { if (global_video_state->quit) { ret = -1; break; } pkt1 = q->first_pkt; if (pkt1) { q->first_pkt = pkt1->next; if (!q->first_pkt) q->last_pkt = NULL; q->nb_packets--; q->size -= pkt1->pkt.size; *pkt = pkt1->pkt; av_free(pkt1); ret = 1; break; } else if (!block) { ret = 0; break; } else { SDL_CondWait(q->cond, q->mutex); } } SDL_UnlockMutex(q->mutex); return ret; } double get_audio_clock(VideoState *is) { double pts; int hw_buf_size, bytes_per_sec, n; pts = is->audio_clock; /* maintained in the audio thread */ hw_buf_size = is->audio_buf_size - is->audio_buf_index; bytes_per_sec = 0; n = is->audio_st->codec->channels * 2; if (is->audio_st) { bytes_per_sec = is->audio_st->codec->sample_rate * n; } if (bytes_per_sec) { pts -= (double) hw_buf_size / bytes_per_sec; } return pts; } int audio_decode_frame(VideoState *is, double *pts_ptr) { int len1, data_size = 0, n; AVPacket *pkt = &is->audio_pkt; double pts; for (;;) { while (is->audio_pkt_size > 0) { int got_frame = 0; len1 = avcodec_decode_audio4(is->audio_st->codec, &is->audio_frame, &got_frame, pkt); if (len1 < 0) { /* if error, skip frame */ is->audio_pkt_size = 0; break; } if (got_frame) { data_size = is->audio_frame.linesize[0]; /*av_samples_get_buffer_size(NULL, is->audio_st->codec->channels, is->audio_frame.nb_samples, is->audio_st->codec->sample_fmt, 1);*/ memcpy(is->audio_buf, is->audio_frame.data[0], data_size); } is->audio_pkt_data += len1; is->audio_pkt_size -= len1; if (data_size <= 0) { /* No data yet, get more frames */ continue; } pts = is->audio_clock; *pts_ptr = pts; n = 2 * is->audio_st->codec->channels; is->audio_clock += (double) data_size / (double) (n * is->audio_st->codec->sample_rate); /* We have data, return it and come back for more later */ return data_size; } if (pkt->data) av_free_packet(pkt); if (is->quit) { return -1; } /* next packet */ if (packet_queue_get(&is->audioq, pkt, 1) < 0) { return -1; } is->audio_pkt_data = pkt->data; is->audio_pkt_size = pkt->size; /* if update, update the audio clock w/pts */ if (pkt->pts != AV_NOPTS_VALUE) { is->audio_clock = av_q2d(is->audio_st->time_base) * pkt->pts; } } return 0; } void audio_callback(void *userdata, Uint8 *stream, int len) { VideoState *is = (VideoState *) userdata; int len1, audio_size; double pts; while (len > 0) { if (is->audio_buf_index >= is->audio_buf_size) { /* We have already sent all our data; get more */ audio_size = audio_decode_frame(is, &pts); if (audio_size < 0) { /* If error, output silence */ is->audio_buf_size = 1024; memset(is->audio_buf, 0, is->audio_buf_size); } else { is->audio_buf_size = audio_size; } is->audio_buf_index = 0; } len1 = is->audio_buf_size - is->audio_buf_index; if (len1 > len) len1 = len; memcpy(stream, (uint8_t *) is->audio_buf + is->audio_buf_index, len1); len -= len1; stream += len1; is->audio_buf_index += len1; } } static Uint32 sdl_refresh_timer_cb(Uint32 interval, void *opaque) { SDL_Event event; event.type = FF_REFRESH_EVENT; event.user.data1 = opaque; SDL_PushEvent(&event); return 0; /* 0 means stop timer */ } /* schedule a video refresh in 'delay' ms */ static void schedule_refresh(VideoState *is, int delay) { SDL_AddTimer(delay, sdl_refresh_timer_cb, is); } void video_display(VideoState *is) { SDL_Rect rect; VideoPicture *vp; float aspect_ratio; int w, h, x, y; vp = &is->pictq[is->pictq_rindex]; if (vp->bmp) { if (is->video_st->codec->sample_aspect_ratio.num == 0) { aspect_ratio = 0; } else { aspect_ratio = av_q2d(is->video_st->codec->sample_aspect_ratio) * is->video_st->codec->width / is->video_st->codec->height; } if (aspect_ratio <= 0.0) { aspect_ratio = (float) is->video_st->codec->width / (float) is->video_st->codec->height; } h = screen->h; w = ((int) rint(h * aspect_ratio)) & -3; if (w > screen->w) { w = screen->w; h = ((int) rint(w / aspect_ratio)) & -3; } x = (screen->w - w) / 2; y = (screen->h - h) / 2; rect.x = x; rect.y = y; rect.w = w; rect.h = h; SDL_DisplayYUVOverlay(vp->bmp, &rect); } } void video_refresh_timer(void *userdata) { VideoState *is = (VideoState *) userdata; VideoPicture *vp; double actual_delay, delay, sync_threshold, ref_clock, diff; if (is->video_st) { if (is->pictq_size == 0) { schedule_refresh(is, 1); } else { vp = &is->pictq[is->pictq_rindex]; delay = vp->pts - is->frame_last_pts; /* the pts from last time */ if (delay <= 0 || delay >= 1.0) { /* if incorrect delay, use previous one */ delay = is->frame_last_delay; } /* save for next time */ is->frame_last_delay = delay; is->frame_last_pts = vp->pts; /* update delay to sync to audio */ ref_clock = get_audio_clock(is); diff = vp->pts - ref_clock; /* Skip or repeat the frame. Take delay into account FFPlay still doesn't "know if this is the best guess." */ sync_threshold = (delay > AV_SYNC_THRESHOLD) ? delay : AV_SYNC_THRESHOLD; if (fabs(diff) < AV_NOSYNC_THRESHOLD) { if (diff <= -sync_threshold) { delay = 0; } else if (diff >= sync_threshold) { delay = 2 * delay; } } is->frame_timer += delay; /* computer the REAL delay */ actual_delay = is->frame_timer - (av_gettime() / 1000000.0); if (actual_delay < 0.010) { /* Really it should skip the picture instead */ actual_delay = 0.010; } schedule_refresh(is, (int) (actual_delay * 1000 + 0.5)); /* show the picture! */ video_display(is); /* update queue for next picture! */ if (++is->pictq_rindex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_rindex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size--; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } } else { schedule_refresh(is, 100); } } void alloc_picture(void *userdata) { VideoState *is = (VideoState *) userdata; VideoPicture *vp; vp = &is->pictq[is->pictq_windex]; if (vp->bmp) { // we already have one make another, bigger/smaller SDL_FreeYUVOverlay(vp->bmp); } // Allocate a place to put our YUV image on that screen vp->bmp = SDL_CreateYUVOverlay(is->video_st->codec->width, is->video_st->codec->height, SDL_YV12_OVERLAY, screen); vp->width = is->video_st->codec->width; vp->height = is->video_st->codec->height; SDL_LockMutex(is->pictq_mutex); vp->allocated = 1; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } int queue_picture(VideoState *is, AVFrame *pFrame, double pts) { VideoPicture *vp; //int dst_pix_fmt; AVPicture pict; /* wait until we have space for a new pic */ SDL_LockMutex(is->pictq_mutex); while (is->pictq_size >= VIDEO_PICTURE_QUEUE_SIZE && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if (is->quit) return -1; // windex is set to 0 initially vp = &is->pictq[is->pictq_windex]; /* allocate or resize the buffer! */ if (!vp->bmp || vp->width != is->video_st->codec->width || vp->height != is->video_st->codec->height) { SDL_Event event; vp->allocated = 0; /* we have to do it in the main thread */ event.type = FF_ALLOC_EVENT; event.user.data1 = is; SDL_PushEvent(&event); /* wait until we have a picture allocated */ SDL_LockMutex(is->pictq_mutex); while (!vp->allocated && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if (is->quit) { return -1; } } /* We have a place to put our picture on the queue */ /* If we are skipping a frame, do we set this to null but still return vp->allocated = 1? */ if (vp->bmp) { SDL_LockYUVOverlay(vp->bmp); //dst_pix_fmt = PIX_FMT_YUV420P; /* point pict at the queue */ pict.data[0] = vp->bmp->pixels[0]; pict.data[1] = vp->bmp->pixels[2]; pict.data[2] = vp->bmp->pixels[1]; pict.linesize[0] = vp->bmp->pitches[0]; pict.linesize[1] = vp->bmp->pitches[2]; pict.linesize[2] = vp->bmp->pitches[1]; // Convert the image into YUV format that SDL uses sws_scale(is->sws_ctx, (const uint8_t * const *) pFrame->data, pFrame->linesize, 0, is->video_st->codec->height, pict.data, pict.linesize); SDL_UnlockYUVOverlay(vp->bmp); vp->pts = pts; /* now we inform our display thread that we have a pic ready */ if (++is->pictq_windex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_windex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size++; SDL_UnlockMutex(is->pictq_mutex); } return 0; } double synchronize_video(VideoState *is, AVFrame *src_frame, double pts) { double frame_delay; if (pts != 0) { /* if we have pts, set video clock to it */ is->video_clock = pts; } else { /* if we aren't given a pts, set it to the clock */ pts = is->video_clock; } /* update the video clock */ frame_delay = av_q2d(is->video_st->codec->time_base); /* if we are repeating a frame, adjust clock accordingly */ frame_delay += src_frame->repeat_pict * (frame_delay * 0.5); is->video_clock += frame_delay; return pts; } uint64_t global_video_pkt_pts = AV_NOPTS_VALUE; /* These are called whenever we allocate a frame * buffer. We use this to store the global_pts in * a frame at the time it is allocated. */ int our_get_buffer(struct AVCodecContext *c, AVFrame *pic) { int ret = avcodec_default_get_buffer(c, pic); uint64_t *pts = av_malloc(sizeof(uint64_t)); *pts = global_video_pkt_pts; pic->opaque = pts; return ret; } void our_release_buffer(struct AVCodecContext *c, AVFrame *pic) { if (pic) av_freep(&pic->opaque); avcodec_default_release_buffer(c, pic); } int video_thread(void *arg) { VideoState *is = (VideoState *) arg; AVPacket pkt1, *packet = &pkt1; //int len1; int frameFinished; AVFrame *pFrame; double pts; pFrame = av_frame_alloc(); for (;;) { if (packet_queue_get(&is->videoq, packet, 1) < 0) { // means we quit getting packets break; } pts = 0; // Save global pts to be stored in pFrame in first call global_video_pkt_pts = packet->pts; // Decode video frame //len1 = avcodec_decode_video2(is->video_st->codec, pFrame, &frameFinished, packet); if (packet->dts == AV_NOPTS_VALUE && pFrame->opaque && *(uint64_t*) pFrame->opaque != AV_NOPTS_VALUE) { pts = *(uint64_t *) pFrame->opaque; } else if (packet->dts != AV_NOPTS_VALUE) { pts = packet->dts; } else { pts = 0; } pts *= av_q2d(is->video_st->time_base); // Did we get a video frame? if (frameFinished) { pts = synchronize_video(is, pFrame, pts); if (queue_picture(is, pFrame, pts) < 0) { break; } } av_free_packet(packet); } av_free(pFrame); return 0; } int stream_component_open(VideoState *is, int stream_index) { AVFormatContext *pFormatCtx = is->pFormatCtx; AVCodecContext *codecCtx; AVCodec *codec; SDL_AudioSpec wanted_spec, spec; if (stream_index < 0 || stream_index >= pFormatCtx->nb_streams) { return -1; } // Get a pointer to the codec context for the video stream codecCtx = pFormatCtx->streams[stream_index]->codec; if (codecCtx->codec_type == AVMEDIA_TYPE_AUDIO) { // Set audio settings from codec info wanted_spec.freq = codecCtx->sample_rate; wanted_spec.format = AUDIO_S16SYS; wanted_spec.channels = codecCtx->channels; wanted_spec.silence = 0; wanted_spec.samples = SDL_AUDIO_BUFFER_SIZE; wanted_spec.callback = audio_callback; wanted_spec.userdata = is; if (SDL_OpenAudio(&wanted_spec, &spec) < 0) { fprintf(stderr, "SDL_OpenAudio: %s\n", SDL_GetError()); return -1; } is->audio_hw_buf_size = spec.size; } codec = avcodec_find_decoder(codecCtx->codec_id); if (!codec || (avcodec_open2(codecCtx, codec, NULL) < 0)) { fprintf(stderr, "Unsupported codec!\n"); return -1; } switch (codecCtx->codec_type) { case AVMEDIA_TYPE_AUDIO: is->audioStream = stream_index; is->audio_st = pFormatCtx->streams[stream_index]; is->audio_buf_size = 0; is->audio_buf_index = 0; memset(&is->audio_pkt, 0, sizeof(is->audio_pkt)); packet_queue_init(&is->audioq); SDL_PauseAudio(0); break; case AVMEDIA_TYPE_VIDEO: is->videoStream = stream_index; is->video_st = pFormatCtx->streams[stream_index]; is->sws_ctx = sws_getContext(is->video_st->codec->width, is->video_st->codec->height, is->video_st->codec->pix_fmt, is->video_st->codec->width, is->video_st->codec->height, AV_PIX_FMT_YUV420P, SWS_FAST_BILINEAR, NULL, NULL, NULL); is->frame_timer = (double) av_gettime() / 1000000.0; is->frame_last_delay = 40e-3; packet_queue_init(&is->videoq); is->video_tid = SDL_CreateThread(video_thread, is); codecCtx->get_buffer = our_get_buffer; codecCtx->release_buffer = our_release_buffer; break; default: break; } return 0; } int decode_interrupt_cb(void *opaque) { return (global_video_state && global_video_state->quit); } int decode_thread(void *arg) { VideoState *is = (VideoState *) arg; AVFormatContext *pFormatCtx = NULL; AVPacket pkt1, *packet = &pkt1; int video_index = -1; int audio_index = -1; int i; is->videoStream = -1; is->audioStream = -1; AVIOInterruptCB interupt_cb; global_video_state = is; // will interrupt blocking functions if we quit! interupt_cb.callback = decode_interrupt_cb; interupt_cb.opaque = is; if (avio_open2(&is->io_ctx, is->filename, 0, &interupt_cb, NULL)) { fprintf(stderr, "Cannot open I/O for %s\n", is->filename); return -1; } // Open video file if (avformat_open_input(&pFormatCtx, is->filename, NULL, NULL) != 0) return -1; // Couldn't open file is->pFormatCtx = pFormatCtx; // Retrieve stream information if (avformat_find_stream_info(pFormatCtx, NULL) < 0) return -1; // Couldn't find stream information // Dump information about file onto standard error av_dump_format(pFormatCtx, 0, is->filename, 0); // Find the first video stream for (i = 0; i < pFormatCtx->nb_streams; i++) { if (pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO && video_index < 0) { video_index = i; } if (pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO && audio_index < 0) { audio_index = i; } } if (audio_index >= 0) { stream_component_open(is, audio_index); } if (video_index >= 0) { stream_component_open(is, video_index); } if (is->videoStream < 0 || is->audioStream < 0) { fprintf(stderr, "%s: could not open codecs\n", is->filename); goto fail; } // main decode loop for (;;) { if (is->quit) { break; } // seek stuff goes here if (is->audioq.size > MAX_AUDIOQ_SIZE || is->videoq.size > MAX_VIDEOQ_SIZE) { SDL_Delay(10); continue; } if (av_read_frame(is->pFormatCtx, packet) < 0) { if (is->pFormatCtx->pb->error == 0) { SDL_Delay(100); /* no error; wait for user input */ continue; } else { break; } } // Is this a packet from the video stream? if (packet->stream_index == is->videoStream) { packet_queue_put(&is->videoq, packet); } else if (packet->stream_index == is->audioStream) { packet_queue_put(&is->audioq, packet); } else { av_free_packet(packet); } } /* all done - wait for it */ while (!is->quit) { SDL_Delay(100); } fail: { SDL_Event event; event.type = FF_QUIT_EVENT; event.user.data1 = is; SDL_PushEvent(&event); } return 0; } int main(int argc, char *argv[]) { SDL_Event event; VideoState *is; is = av_mallocz(sizeof(VideoState)); char filePath[] = "./src/a.mp4"; // Register all formats and codecs av_register_all(); if (SDL_Init(SDL_INIT_VIDEO | SDL_INIT_AUDIO | SDL_INIT_TIMER)) { fprintf(stderr, "Could not initialize SDL - %s\n", SDL_GetError()); exit(1); } // Make a screen to put our video #ifndef __DARWIN__ screen = SDL_SetVideoMode(640, 480, 0, 0); #else screen = SDL_SetVideoMode(640, 480, 24, 0); #endif if (!screen) { fprintf(stderr, "SDL: could not set video mode - exiting\n"); exit(1); } av_strlcpy(is->filename, filePath, sizeof(is->filename)); is->pictq_mutex = SDL_CreateMutex(); is->pictq_cond = SDL_CreateCond(); schedule_refresh(is, 40); is->parse_tid = SDL_CreateThread(decode_thread, is); if (!is->parse_tid) { av_free(is); return -1; } for (;;) { SDL_WaitEvent(&event); switch (event.type) { case FF_QUIT_EVENT: case SDL_QUIT: SDL_CondSignal(is->audioq.cond); SDL_CondSignal(is->videoq.cond); is->quit = 1; SDL_Quit(); exit(0); break; case FF_ALLOC_EVENT: alloc_picture(event.user.data1); break; case FF_REFRESH_EVENT: video_refresh_timer(event.user.data1); break; default: break; } } return 0; }
