视频分帧【截取图片】（YOLO目标检测【生成数据集】）

高效率制作数据集【按这个流程走，速度很顶】

本次制作，1059张图片【马路上流动车辆】
几乎就是全自动了，只要视频拍得好，YOLO辅助制作数据集就效率极高

视频中的图片抽取：
【由于视频内存过大，遇到报错执行失败，解决方法已附加在代码下面】

import cv2
import os
import pdb
import numpy as np
#from glob2 import glob


videos_src_path = 'F:\\testkk\\vivivi\\'  # 提取图片的视频文件夹

# 筛选文件夹下MP4格式的文件
# videos = os.listdir(videos_src_path)  # 用于返回指定的文件夹包含的文件或文件夹的名字的列表。
# videos = filter(lambda x: x.endswith('mp4'), videos)
dirs = os.listdir(videos_src_path)  # 获取指定路径下的文件
count = 0
# 写入txt
f = "F:\\testkk\\images\\data.txt"
with open(f, "w+") as file:
    file.write("-----start-----\n")

# 循环读取路径下的文件并操作
for video_name in dirs:

    outputPath = "F:\\testkk\\images\\"+video_name[:-4] + "\\"
    # os.mkdir(outputPath)

    print("start\n")
    print(videos_src_path + video_name)
    vc = cv2.VideoCapture(videos_src_path + video_name)

    # 初始化,并读取第一帧
    # rval表示是否成功获取帧
    # frame是捕获到的图像
    rval, frame = vc.read()

    # 获取视频fps
    fps = vc.get(cv2.CAP_PROP_FPS)
    # 获取每个视频帧数
    frame_all = vc.get(cv2.CAP_PROP_FRAME_COUNT)
    
    print("[INFO] 视频FPS: {}".format(fps))
    print("[INFO] 视频总帧数: {}".format(frame_all))

    # 每隔n帧保存一张图片
    frame_interval = 30
    # 统计当前帧
    frame_count = 1
    # count=0

    while rval:

        rval, frame = vc.read()

        # 隔n帧保存一张图片
        if frame_count % frame_interval == 0:

            # 当前帧不为None，能读取到图片时
            if frame is not None:
                filename = outputPath + "Kidney_tumors_{}.jpg".format(count)

                # 水平、垂直翻转
                frame = cv2.flip(frame, 0)
                frame = cv2.flip(frame, 1)

                # 旋转180°
                frame = np.rot90(frame)
                frame = np.rot90(frame)
                cv2.imwrite(filename, frame)
                count += 1
                print("保存图片:{}".format(filename))
        frame_count += 1

    # 将成功抽帧的视频名称写入txt文件，方便检查
    file = open(f, "a")
    file.write(video_name + "\n")

    # 关闭视频文件
    vc.release()
    print("[INFO] 总共保存：{}张图片\n".format(count))

遇到问题：
global cap_ffmpeg_impl.hpp:1541 grabFrame packet read max attempts exceeded, if your video have multiple streams (video, audio) try to increase attempt limit by setting environment variable OPENCV_FFMPEG_READ_ATTEMPTS (current value is 4096)
解决方法：
给OPENCV_FFMPEG_READ_ATTEMPTS 设置一个和视频大小一样的value值，然后重启电脑，再来执行，就解决了。

抽出来的图片，接下来用YOLO的目标检测模型预测，得到坐标文件

from ultralytics import YOLO

# 读取模型，这里传入训练好的模型
model = YOLO('yolov8m.pt')

# 模型预测，save=True 的时候表示直接保存yolov8的预测结果
metrics = model.predict(source='F:\\testkk\\images\\GH040001',
                        imgsz=640,
                        project='runs/detect',
                        save=True)

【预测结果已经还OK了，几乎不用咋修改标注文件了】

然后：【txt转json】

import os
import json
import base64
import cv2

def read_txt_file(txt_file):
    with open(txt_file, 'r') as f:
        lines = f.readlines()
    data = []
    for line in lines:
        line = line.strip().split()
        class_name = line[0]
        bbox = [coord for coord in line[1:]]
        data.append({'class_name': class_name, 'bbox': bbox})
    return data

def convert_to_labelme(data, image_path, image_size):
    labelme_data = {
        'version': '4.5.6',
        'flags': {},
        'shapes': [],
        'imagePath': json_image_path,
        'imageData': None,
        'imageHeight': image_size[0],
        'imageWidth': image_size[1]
    }
    for obj in data:
        dx = obj['bbox'][0]
        dy = obj['bbox'][1]
        dw = obj['bbox'][2]
        dh = obj['bbox'][3]

        w = eval(dw) * image_size[1]
        h = eval(dh) * image_size[0]
        center_x = eval(dx) * image_size[1]
        center_y = eval(dy) * image_size[0]
        x1 = center_x - w/2
        y1 = center_y - h/2
        x2 = center_x + w/2
        y2 = center_y + h/2
        # x1 = eval(obj['bbox'][0]) * image_size[1]
        # y1 = eval(obj['bbox'][1]) * image_size[0]
        # x2 = eval(obj['bbox'][2]) * image_size[1]
        # y2 = eval(obj['bbox'][3]) * image_size[0]

        if obj['class_name'] == '0': #判断对应的标签名称，写入json文件中
            label = str('person')
        elif obj['class_name'] == '2':
            label = str('car')
        else:
            continue
        shape_data = {
            'label': label,
            'points': [[x1, y1], [x2, y2]],
            'group_id': None,
            'shape_type': 'rectangle',
            'flags': {}
        }
        labelme_data['shapes'].append(shape_data)
    return labelme_data

def save_labelme_json(labelme_data, image_path, output_file):
    with open(image_path, 'rb') as f:
        image_data = f.read()
    labelme_data['imageData'] = base64.b64encode(image_data).decode('utf-8')

    with open(output_file, 'w') as f:
        json.dump(labelme_data, f, indent=4)

# 设置文件夹路径和输出文件夹路径
txt_folder = "D:\\yoloProject\\ultralytics-registry\\runs\\detect\\predict5\\labels"  # 存放LabelImg标注的txt文件的文件夹路径
output_folder = "F:\\testkk\\images\\GH040001_json"  # 输出LabelMe标注的json文件的文件夹路径
img_folder = "F:\\testkk\\images\\GH040001" #存放对应标签的图片文件夹路径

# 创建输出文件夹
if not os.path.exists(output_folder):
    os.makedirs(output_folder)

# 遍历txt文件夹中的所有文件
for filename in os.listdir(txt_folder):
    if filename.endswith('.txt'):
        # 生成对应的输出文件名
        output_filename = os.path.splitext(filename)[0] + '.json'

        # 读取txt文件
        txt_file = os.path.join(txt_folder, filename)
        data = read_txt_file(txt_file)

        # 设置图片路径和尺寸
        image_filename = os.path.splitext(filename)[0] + '.jpg'  # 图片文件名与txt文件名相同，后缀为.jpg
        image_path = os.path.join(img_folder, image_filename)
        # image_size = (1280, 720)  # 根据实际情况修改
        json_image_path = image_path.split('\\')[-1]
        image_size = cv2.imread(image_path).shape

        # 转化为LabelMe格式
        labelme_data = convert_to_labelme(data, image_path, image_size)

        # 保存为LabelMe JSON文件
        output_file = os.path.join(output_folder, output_filename)
        save_labelme_json(labelme_data, image_path, output_file)

最后：修改OK后，再把JSON转TXT，作为样本数据集：
https://blog.csdn.net/weixin_43624549/article/details/139532142