视频截取--命名--xml转txt

python工具–将视频按帧截取

https://www.cnblogs.com/bob-jianfeng/p/11140444.html

需要注意的是：

‘–input’的路径可以有中文，但是‘–output’的路径不能有中文。否则只能运行，但是得不到图片。

视频截取

import cv2
import argparse
import os
def parse_args():
    """
    Parse input arguments
    """
    parser = argparse.ArgumentParser(description='Process pic')
    parser.add_argument('--input', help='video to process', dest='input', default=None, type=str)
    parser.add_argument('--output', help='pic to store', dest='output', default=None, type=str)
    #default为间隔多少帧截取一张图片
    parser.add_argument('--skip_frame', dest='skip_frame', help='skip number of video', default=100, type=int)
    #input为输入视频的路径 ，output为输出存放图片的路径
    args = parser.parse_args(['--input','','--output',''])
    return args

def process_video(i_video, o_video, num):
    cap = cv2.VideoCapture(i_video)
    num_frame = cap.get(cv2.CAP_PROP_FRAME_COUNT)
    expand_name = '.jpg'
    if not cap.isOpened():
        print("Please check the path.")
    cnt = 0
    count = 0
    while 1:
        ret, frame = cap.read()
        cnt += 1
        #  how
        # many
        # frame
        # to
        # cut
        if cnt % num == 0:
            count += 1
            cv2.imwrite(os.path.join(o_video, str(count) + expand_name), frame)

        if not ret:
            break

if __name__ == '__main__':
    args = parse_args()
    if not os.path.exists(args.output):
        os.makedirs(args.output)
    print('Called with args:')
    print(args)
    process_video(args.input, args.output, args.skip_frame)

重新命名

# -*- coding:utf8 -*-

import os


class BatchRename():
    '''
    批量重命名文件夹中的图片文件

    '''

    def __init__(self):
        self.path = 'E:\clip_pic\datasets\Image07'  # 表示需要命名处理的文件夹

    def rename(self):
        filelist = os.listdir(self.path)  # 获取文件路径
        total_num = len(filelist)  # 获取文件长度（个数）
        #print("文件长度:" + int(total_num))
        i = 700  # 表示文件的命名是从1开始的
        for item in filelist:
            if item.endswith('.jpg'):  # 初始的图片的格式为jpg格式的（或者源文件是png格式及其他格式，后面的转换格式就可以调整为自己需要的格式即可）
                src = os.path.join(os.path.abspath(self.path), item)
                # dst = os.path.join(os.path.abspath(self.path), ''+str(i) + '.jpg')#处理后的格式也为jpg格式的，当然这里可以改成png格式
                dst = os.path.join(os.path.abspath(self.path),
                                   '0' + format(str(i), '0>3s') + '.jpg')  # 这种情况下的命名格式为0000000.jpg形式，可以自主定义想要的格式
                try:
                    os.rename(src, dst)
                    print('converting %s to %s ...' % (src, dst))
                    i = i + 1
                except:
                    continue
        print('total %d to rename & converted %d jpgs' % (total_num, i))


if __name__ == '__main__':
    demo = BatchRename()
    demo.rename()

xml转换txt

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join


# classes = ['hard_hat', 'other', 'regular', 'long_hair', 'braid', 'bald', 'beard']


def convert(size, box):
    # size=(width, height)  b=(xmin, xmax, ymin, ymax)
    # x_center = (xmax+xmin)/2        y_center = (ymax+ymin)/2
    # x = x_center / width            y = y_center / height
    # w = (xmax-xmin) / width         h = (ymax-ymin) / height

    x_center = (box[0] + box[1]) / 2.0
    y_center = (box[2] + box[3]) / 2.0
    x = x_center / size[0]
    y = y_center / size[1]

    w = (box[1] - box[0]) / size[0]
    h = (box[3] - box[2]) / size[1]

    # print(x, y, w, h)
    return (x, y, w, h)


def convert_annotation(xml_files_path, save_txt_files_path, classes):
    xml_files = os.listdir(xml_files_path)
    print(xml_files)
    for xml_name in xml_files:
        print(xml_name)
        xml_file = os.path.join(xml_files_path, xml_name)
        out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
        out_txt_f = open(out_txt_path, 'w')
        tree = ET.parse(xml_file)
        root = tree.getroot()
        size = root.find('size')
        w = int(size.find('width').text)
        h = int(size.find('height').text)

        for obj in root.iter('object'):
            difficult = obj.find('difficult').text
            cls = obj.find('name').text
            if cls not in classes or int(difficult) == 1:
                continue
            cls_id = classes.index(cls)
            xmlbox = obj.find('bndbox')
            b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
                 float(xmlbox.find('ymax').text))
            # b=(xmin, xmax, ymin, ymax)
            print(w, h, b)
            bb = convert((w, h), b)
            out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


if __name__ == "__main__":
    # 测试程序
    # classes = ['hard_hat', 'other', 'regular', 'long_hair', 'braid', 'bald', 'beard']
    # xml_files = r'D:\ZF\1_ZF_proj\3_脚本程序\2_voc格式转yolo格式\voc_labels'
    # save_txt_files = r'D:\ZF\1_ZF_proj\3_脚本程序\2_voc格式转yolo格式\yolo_labels'
    # convert_annotation(xml_files, save_txt_files, classes)

    # ====================================================================================================
    # 把帽子头发胡子的voc的xml标签文件转化为yolo的txt标签文件
    # 1、帽子头发胡子的类别
    classes1 = ['A', 'B']
    # 2、voc格式的xml标签文件路径
    xml_files1 = r'F:\数据集\AB\Anotations02'
    # 3、转化为yolo格式的txt标签文件存储路径
    save_txt_files1 = r'F:\数据集\AB\labels02'

    convert_annotation(xml_files1, save_txt_files1, classes1)