yolov5视频流实时检测实现

yolov5

https://github.com/ultralytics/yolov5

 

对rtsp视频流的支持

https://github.com/ultralytics/yolov5/blob/master/detect.py

 

@smart_inference_mode()
def run(
        weights=ROOT / 'yolov5s.pt',  # model path or triton URL
        source=ROOT / 'data/images',  # file/dir/URL/glob/screen/0(webcam)
        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
        imgsz=(640, 640),  # inference size (height, width)
        conf_thres=0.25,  # confidence threshold
        iou_thres=0.45,  # NMS IOU threshold
        max_det=1000,  # maximum detections per image
        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
        view_img=False,  # show results
        save_txt=False,  # save results to *.txt
        save_conf=False,  # save confidences in --save-txt labels
        save_crop=False,  # save cropped prediction boxes
        nosave=False,  # do not save images/videos
        classes=None,  # filter by class: --class 0, or --class 0 2 3
        agnostic_nms=False,  # class-agnostic NMS
        augment=False,  # augmented inference
        visualize=False,  # visualize features
        update=False,  # update all models
        project=ROOT / 'runs/detect',  # save results to project/name
        name='exp',  # save results to project/name
        exist_ok=False,  # existing project/name ok, do not increment
        line_thickness=3,  # bounding box thickness (pixels)
        hide_labels=False,  # hide labels
        hide_conf=False,  # hide confidences
        half=False,  # use FP16 half-precision inference
        dnn=False,  # use OpenCV DNN for ONNX inference
        vid_stride=1,  # video frame-rate stride
):
    source = str(source)
    save_img = not nosave and not source.endswith('.txt')  # save inference images
    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
    screenshot = source.lower().startswith('screen')
    if is_url and is_file:
        source = check_file(source)  # download

    # Directories
    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

    # Load model
    device = select_device(device)
    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
    stride, names, pt = model.stride, model.names, model.pt
    imgsz = check_img_size(imgsz, s=stride)  # check image size

    # Dataloader
    bs = 1  # batch_size
    if webcam:
        view_img = check_imshow(warn=True)
        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
        bs = len(dataset)
    elif screenshot:
        dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
    vid_path, vid_writer = [None] * bs, [None] * bs

    # Run inference
    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
    for path, im, im0s, vid_cap, s in dataset:
        with dt[0]:
            im = torch.from_numpy(im).to(model.device)
            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
            im /= 255  # 0 - 255 to 0.0 - 1.0
            if len(im.shape) == 3:
                im = im[None]  # expand for batch dim

        # Inference
        with dt[1]:
            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
            pred = model(im, augment=augment, visualize=visualize)

        # NMS
        with dt[2]:
            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)

        # Second-stage classifier (optional)
        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)

        # Process predictions
        for i, det in enumerate(pred):  # per image
            seen += 1
            if webcam:  # batch_size >= 1
                p, im0, frame = path[i], im0s[i].copy(), dataset.count
                s += f'{i}: '
            else:
                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)

            p = Path(p)  # to Path
            save_path = str(save_dir / p.name)  # im.jpg
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
            s += '%gx%g ' % im.shape[2:]  # print string
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
            imc = im0.copy() if save_crop else im0  # for save_crop
            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()

                # Print results
                for c in det[:, 5].unique():
                    n = (det[:, 5] == c).sum()  # detections per class
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

                # Write results
                for *xyxy, conf, cls in reversed(det):
                    if save_txt:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
                        with open(f'{txt_path}.txt', 'a') as f:
                            f.write(('%g ' * len(line)).rstrip() % line + '\n')

                    if save_img or save_crop or view_img:  # Add bbox to image
                        c = int(cls)  # integer class
                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
                        annotator.box_label(xyxy, label, color=colors(c, True))
                    if save_crop:
                        save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)

            # Stream results
            im0 = annotator.result()
            if view_img:
                if platform.system() == 'Linux' and p not in windows:
                    windows.append(p)
                    cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)
                    cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
                cv2.imshow(str(p), im0)
                cv2.waitKey(1)  # 1 millisecond

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'image':
                    cv2.imwrite(save_path, im0)
                else:  # 'video' or 'stream'
                    if vid_path[i] != save_path:  # new video
                        vid_path[i] = save_path
                        if isinstance(vid_writer[i], cv2.VideoWriter):
                            vid_writer[i].release()  # release previous video writer
                        if vid_cap:  # video
                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
                        else:  # stream
                            fps, w, h = 30, im0.shape[1], im0.shape[0]
                        save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                    vid_writer[i].write(im0)

        # Print time (inference-only)
        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")

    # Print results
    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
    if save_txt or save_img:
        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
    if update:
        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)

 

https://github.com/ultralytics/yolov5/blob/master/utils/dataloaders.py

class LoadStreams:
    # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP streams`
    def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True, transforms=None, vid_stride=1):
        torch.backends.cudnn.benchmark = True  # faster for fixed-size inference
        self.mode = 'stream'
        self.img_size = img_size
        self.stride = stride
        self.vid_stride = vid_stride  # video frame-rate stride
        sources = Path(sources).read_text().rsplit() if os.path.isfile(sources) else [sources]
        n = len(sources)
        self.sources = [clean_str(x) for x in sources]  # clean source names for later
        self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
        for i, s in enumerate(sources):  # index, source
            # Start thread to read frames from video stream
            st = f'{i + 1}/{n}: {s}... '
            if urlparse(s).hostname in ('www.youtube.com', 'youtube.com', 'youtu.be'):  # if source is YouTube video
                # YouTube format i.e. 'https://www.youtube.com/watch?v=Zgi9g1ksQHc' or 'https://youtu.be/Zgi9g1ksQHc'
                check_requirements(('pafy', 'youtube_dl==2020.12.2'))
                import pafy
                s = pafy.new(s).getbest(preftype="mp4").url  # YouTube URL
            s = eval(s) if s.isnumeric() else s  # i.e. s = '0' local webcam
            if s == 0:
                assert not is_colab(), '--source 0 webcam unsupported on Colab. Rerun command in a local environment.'
                assert not is_kaggle(), '--source 0 webcam unsupported on Kaggle. Rerun command in a local environment.'
            cap = cv2.VideoCapture(s)
            assert cap.isOpened(), f'{st}Failed to open {s}'
            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
            fps = cap.get(cv2.CAP_PROP_FPS)  # warning: may return 0 or nan
            self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf')  # infinite stream fallback
            self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30  # 30 FPS fallback

            _, self.imgs[i] = cap.read()  # guarantee first frame
            self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
            LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
            self.threads[i].start()
        LOGGER.info('')  # newline

        # check for common shapes
        s = np.stack([letterbox(x, img_size, stride=stride, auto=auto)[0].shape for x in self.imgs])
        self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
        self.auto = auto and self.rect
        self.transforms = transforms  # optional
        if not self.rect:
            LOGGER.warning('WARNING ⚠️ Stream shapes differ. For optimal performance supply similarly-shaped streams.')

    def update(self, i, cap, stream):
        # Read stream `i` frames in daemon thread
        n, f = 0, self.frames[i]  # frame number, frame array
        while cap.isOpened() and n < f:
            n += 1
            cap.grab()  # .read() = .grab() followed by .retrieve()
            if n % self.vid_stride == 0:
                success, im = cap.retrieve()
                if success:
                    self.imgs[i] = im
                else:
                    LOGGER.warning('WARNING ⚠️ Video stream unresponsive, please check your IP camera connection.')
                    self.imgs[i] = np.zeros_like(self.imgs[i])
                    cap.open(stream)  # re-open stream if signal was lost
            time.sleep(0.0)  # wait time

    def __iter__(self):
        self.count = -1
        return self

    def __next__(self):
        self.count += 1
        if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'):  # q to quit
            cv2.destroyAllWindows()
            raise StopIteration

        im0 = self.imgs.copy()
        if self.transforms:
            im = np.stack([self.transforms(x) for x in im0])  # transforms
        else:
            im = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0] for x in im0])  # resize
            im = im[..., ::-1].transpose((0, 3, 1, 2))  # BGR to RGB, BHWC to BCHW
            im = np.ascontiguousarray(im)  # contiguous

        return self.sources, im, im0, None, ''

    def __len__(self):
        return len(self.sources)  # 1E12 frames = 32 streams at 30 FPS for 30 years