LV-MHP-v2 数据集解析

本代码用于可视化 LV-MHP-v2 数据集。

注意： 该数据集的标注文件的标签是最后一个通道，并且是一个 rgb 的三通道图片，所有直接以灰度图像的格式读取，会导致标签错误。

import cv2
import numpy as np
import os

读取正常图像

color_image = cv2.imread("val/images/7.jpg")

读取RGB图像

image = cv2.imread('val/parsing_annos/7_02_01.png', cv2.IMREAD_COLOR)
# 提取最后一个通道
label_image = image[:, :, 2]

获取类别数量

num_classes = np.max(label_image) + 1
print(num_classes)

类别名称与颜色映射

label_colors_dict = {
0: (255, 255, 255), # Background - 白色
1: (255, 0, 0), # Cap/hat - 红色
2: (0, 255, 0), # Helmet - 绿色
3: (0, 0, 255), # Face - 蓝色
4: (255, 255, 0), # Hair - 黄色
5: (255, 0, 255), # Left-arm - 紫色
6: (0, 255, 255), # Right-arm - 青色
7: (255, 0, 128), # Left-hand - 粉色
8: (128, 0, 255), # Right-hand - 深紫色
9: (0, 255, 128), # Protector - 青绿色
10: (255, 128, 0), # Bikini/bra - 橙色
11: (128, 255, 0), # Jacket/windbreaker/hoodie - 亮绿色
12: (0, 128, 255), # Tee-shirt - 深蓝色
13: (255, 0, 0), # Polo-shirt - 红色
14: (0, 255, 0), # Sweater - 绿色
15: (0, 0, 255), # Singlet - 蓝色
16: (255, 255, 0), # Torso-skin - 黄色
17: (255, 0, 255), # Pants - 紫色
18: (0, 255, 255), # Shorts/swim-shorts - 青色
19: (255, 0, 128), # Skirt - 粉色
20: (128, 0, 255), # Stockings - 深紫色
21: (0, 255, 128), # Socks - 青绿色
22: (255, 128, 0), # Left-boot - 橙色
23: (128, 255, 0), # Right-boot - 亮绿色
24: (0, 128, 255), # Left-shoe - 深蓝色
25: (255, 0, 0), # Right-shoe - 红色
26: (0, 255, 0), # Left-highheel - 绿色
27: (0, 0, 255), # Right-highheel - 蓝色
28: (255, 255, 0), # Left-sandal - 黄色
29: (255, 0, 255), # Right-sandal - 紫色
30: (0, 255, 255), # Left-leg - 青色
31: (255, 0, 128), # Right-leg - 粉色
32: (128, 0, 255), # Left-foot - 深紫色
33: (0, 255, 128), # Right-foot - 青绿色
34: (255, 0, 0), # Coat - 红色
35: (0, 255, 0), # Dress - 绿色
36: (0, 0, 255), # Robe - 蓝色
37: (255, 255, 0), # Jumpsuit - 黄色
38: (255, 0, 255), # Other-full-body-clothes - 紫色
39: (0, 255, 255), # Headwear - 青色
40: (255, 0, 128), # Backpack - 粉色
41: (128, 0, 255), # Ball - 深紫色
42: (0, 255, 128), # Bats - 青绿色
43: (255, 128, 0), # Belt - 橙色
44: (0, 128, 255), # Bottle - 深蓝色
45: (255, 0, 0), # Carrybag - 红色
46: (0, 255, 0), # Cases - 绿色
47: (0, 0, 255), # Sunglasses - 蓝色
48: (255, 255, 0), # Eyewear - 黄色
49: (255, 0, 255), # Glove - 紫色
50: (0, 255, 255), # Scarf - 青色
51: (255, 128, 0), # Umbrella - 橙色
52: (128, 255, 0), # Wallet/purse - 亮绿色
53: (0, 128, 255), # Watch - 深蓝色
54: (255, 0, 0), # Wristband - 红色
55: (0, 255, 0), # Tie - 绿色
56: (0, 0, 255), # Other-accessory - 蓝色
57: (255, 255, 0), # Other-upper-body-clothes - 黄色
58: (255, 0, 255), # Other-lower-body-clothes - 紫色
59: (128, 128, 128), # Mask - 灰色
}

创建彩色标注图像

label_image_color = cv2.cvtColor(label_image, cv2.COLOR_GRAY2BGR)

Get unique class IDs and their counts

class_ids, class_counts = np.unique(label_image, return_counts=True)

将每个类别的颜色叠加在彩色标注图像上

for class_id in range(1, num_classes):
class_pixels = np.where(label_image == class_id)
label_image_color[class_pixels] = label_colors_dict[class_id]

将标注图像叠加在正常图像上

blended_image = cv2.addWeighted(color_image, 0.7, label_image_color, 0.6, 0)

显示或保存叠加后的图像

cv2.imshow("Blended Image", blended_image)
cv2.waitKey(0)
# cv2.imwrite("path/to/save/blended_image.png", blended_image)
cv2.destroyAllWindows()

切出来目标区域用于训练分类模型代码：

-- encoding: utf-8 --

'''
@File : parsing.py
@Time : 2023/07/05 17:53:23
@Author :
@Version : 1.0
@Contact :
@License :
@Desc : 把分割的区域切出来用于分类图像。
'''

here put the import lib

import cv2
import numpy as np
import os
from tqdm import tqdm
import multiprocessing
from functools import partial

def create_directory(path):
if not os.path.exists(path): # 判断目录是否存在
os.makedirs(path) # 递归创建目录
print("Directory created:", path)

def save_class_regions(label_path, image_dir, class_ids, out_dir):
# 读取图像和标签图像
# 读取RGB图像
image = cv2.imread(label_path, cv2.IMREAD_COLOR)
# 提取最后一个通道
label_image = image[:, :, 2]
label_filename = os.path.basename(label_path)
# 构建对应的 JPG 文件路径
jpg_filename = label_filename.split('_')[0] + '.jpg'
image_path = os.path.join(image_dir, jpg_filename)
image = cv2.imread(image_path)

对每个指定的类别进行处理

for class_id in class_ids:
if class_id > np.max(label_image) or np.sum(label_image == class_id) == 0:
continue

创建一个与原图像大小相同的全黑图像

class_region_seg = np.zeros_like(image)

将类别区域的像素值设置为原图像对应位置的像素值

class_region_seg[label_image == class_id] = image[label_image == class_id]

创建一个二值图像，将目标类别设置为白色，其他类别设置为黑色

class_mask = np.where(label_image == class_id, 255, 0).astype(np.uint8)

使用类别掩码获得类别区域的轮廓

contours, _ = cv2.findContours(class_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

计算最大边界框的初始值

x_min = y_min = float('inf')
x_max = y_max = 0

遍历每个轮廓

for contour in contours:
# 找到当前轮廓的边界框
x, y, w, h = cv2.boundingRect(contour)

更新最大边界框的坐标

x_min = min(x_min, x)
y_min = min(y_min, y)
x_max = max(x_max, x + w)
y_max = max(y_max, y + h)

切割原始图像中的区域

class_region = image[y_min:y_max, x_min:x_max]

获取 seg 区域

seg_class_region = class_region_seg[y_min:y_max, x_min:x_max]

生成保存图像的文件名

out_detect_dir = os.path.join(out_dir, 'detect', class_ids[class_id])
create_directory(out_detect_dir)
detect_path = os.path.join(out_detect_dir, jpg_filename)
# 保存类别区域图像
cv2.imwrite(detect_path, class_region)

out_detect_dir = os.path.join(out_dir, 'seg', class_ids[class_id])
create_directory(out_detect_dir)
seg_path = os.path.join(out_detect_dir, jpg_filename)

# 保存 seg 类别区域图像

cv2.imwrite(seg_path, seg_class_region)

def get_selected_classes():
selected_classes = {
1: 'Cap_hat',
4: 'Hair',
11: 'Jacket_windbreaker_hoodie',
12: 'Tee-shirt',
13: 'Polo-shirt',
14: 'Sweater',
15: 'Singlet',
19: 'Skirt',
34: 'Coat',
35: 'Dress',
37: 'Jumpsuit',
38: 'Other-full-body-clothes',
47: 'Sunglasses',
57: 'Other-upper-body-clothes'
}
return selected_classes

if name == "main":
selected_classes = get_selected_classes()
skirt_class_id = selected_classes[19]
print(skirt_class_id) # 输出为 Skirt
image_dir = 'val/images'
label_dir = 'val/parsing_annos'
out_dir = 'val_cls'

label_files = []
for entry in os.scandir(label_dir):
if entry.is_file() and entry.name.endswith('.png'):
label_files.append(entry.path)

print("数据读取完成！")

with multiprocessing.Pool(processes=multiprocessing.cpu_count()) as pool: # 使用CPU核心数作为进程数
total_files = len(label_files)
process_func = partial(save_class_regions, image_dir=image_dir, class_ids=selected_classes, out_dir=out_dir)
with tqdm(total=total_files, desc='Processing files') as pbar:
for _ in pool.imap_unordered(process_func, label_files):
pbar.update(1)