[自用代码]MP4视频＞＞图片＞＞labelme的json＞＞VOC的xml_视频如何转换为图片格式,再用labelimg标注为xml文件

• 将视频拆分成图片, 使用labelme标注后, 再将json转换成xml.

1. 视频>>图片

# -*- coding: utf-8 -*-
"""
Created on Wed May 19 22:14:31 2021

@author: 奥利给
"""

from cv2 import VideoCapture
from cv2 import imwrite
 
# 定义保存图片函数
# image:要保存的图片名字
# addr；图片地址与相片名字的前部分
# num: 相片，名字的后缀。int 类型
def save_image(image, addr, num, video_path):
    temp = video_path.split('.')[0]
    address = addr + temp + '_' + str('%05d'%(num)) + '.jpg'
    imwrite(address, image)
 
if __name__ == '__main__':
    
    vid_list = ["001.mp4","002.mp4","003.mp4","004.mp4","005.mp4","006.mp4"]

    for video_path in vid_list:
 
        # video_path = "006.mp4" #视频路径
        out_path = "./all/img_" #保存图片路径+名字
     
        is_all_frame = True #是否取所有的帧
        sta_frame = 1 #开始帧
        end_frame = 40 #结束帧
     
        ######
        time_interval = 1 #时间间隔
     
        # 读取视频文件
        videoCapture = VideoCapture(video_path)
     
        # 读帧
        success, frame = videoCapture.read()
        print(success)
     
        i = 0
        j = 0
        
        if is_all_frame:
            time_interval = 1
     
        while success:
            i = i + 1
            if (i % time_interval == 0):
                if is_all_frame == False:
                    if i >= sta_frame and i <= end_frame:
                        j = j + 1
                        print('save frame:', i)
                        save_image(frame, out_path, j, video_path)
                    elif i > end_frame:
                        break
                else:
                    j = j + 1
                    print('save frame:', i)
                    save_image(frame, out_path, j, video_path)
     
            success, frame = videoCapture.read()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64

2. json>>xml

#!/usr/bin/env python

from __future__ import print_function

import argparse
import glob
import os
import os.path as osp
import sys

import imgviz
import labelme

try:
    import lxml.builder
    import lxml.etree
except ImportError:
    print("Please install lxml:\n\n    pip install lxml\n")
    sys.exit(1)


def main():
    parser = argparse.ArgumentParser(
        formatter_class=argparse.ArgumentDefaultsHelpFormatter
    )
    parser.add_argument("input_dir", help="input annotated directory")
    parser.add_argument("output_dir", help="output dataset directory")
    parser.add_argument("--labels", help="labels file", required=True)
    parser.add_argument(
        "--noviz", help="no visualization", action="store_true"
    )
    args = parser.parse_args()

    if osp.exists(args.output_dir):
        print("Output directory already exists:", args.output_dir)
        sys.exit(1)
    os.makedirs(args.output_dir)
    os.makedirs(osp.join(args.output_dir, "JPEGImages"))
    os.makedirs(osp.join(args.output_dir, "Annotations"))
    if not args.noviz:
        os.makedirs(osp.join(args.output_dir, "AnnotationsVisualization"))
    print("Creating dataset:", args.output_dir)

    class_names = []
    class_name_to_id = {}
    for i, line in enumerate(open(args.labels).readlines()):
        class_id = i - 1  # starts with -1
        class_name = line.strip()
        class_name_to_id[class_name] = class_id
        if class_id == -1:
            assert class_name == "__ignore__"
            continue
        elif class_id == 0:
            assert class_name == "_background_"
        class_names.append(class_name)
    class_names = tuple(class_names)
    print("class_names:", class_names)
    out_class_names_file = osp.join(args.output_dir, "class_names.txt")
    with open(out_class_names_file, "w") as f:
        f.writelines("\n".join(class_names))
    print("Saved class_names:", out_class_names_file)

    for filename in glob.glob(osp.join(args.input_dir, "*.json")):
        print("Generating dataset from:", filename)

        label_file = labelme.LabelFile(filename=filename)

        base = osp.splitext(osp.basename(filename))[0]
        out_img_file = osp.join(args.output_dir, "JPEGImages", base + ".jpg")
        out_xml_file = osp.join(args.output_dir, "Annotations", base + ".xml")
        if not args.noviz:
            out_viz_file = osp.join(
                args.output_dir, "AnnotationsVisualization", base + ".jpg"
            )

        img = labelme.utils.img_data_to_arr(label_file.imageData)
        imgviz.io.imsave(out_img_file, img)

        maker = lxml.builder.ElementMaker()
        xml = maker.annotation(
            maker.folder(),
            maker.filename(base + ".jpg"),
            maker.database(),  # e.g., The VOC2007 Database
            maker.annotation(),  # e.g., Pascal VOC2007
            maker.image(),  # e.g., flickr
            maker.size(
                maker.height(str(img.shape[0])),
                maker.width(str(img.shape[1])),
                maker.depth(str(img.shape[2])),
            ),
            maker.segmented(),
        )

        bboxes = []
        labels = []
        for shape in label_file.shapes:
            if shape["shape_type"] != "rectangle":
                print(
                    "Skipping shape: label={label}, "
                    "shape_type={shape_type}".format(**shape)
                )
                continue

            class_name = shape["label"]
            class_id = class_names.index(class_name)

            (xmin, ymin), (xmax, ymax) = shape["points"]
            # swap if min is larger than max.
            xmin, xmax = sorted([xmin, xmax])
            ymin, ymax = sorted([ymin, ymax])

            bboxes.append([ymin, xmin, ymax, xmax])
            labels.append(class_id)

            xml.append(
                maker.object(
                    maker.name(shape["label"]),
                    maker.pose(),
                    maker.truncated(),
                    maker.difficult(),
                    maker.bndbox(
                        maker.xmin(str(xmin)),
                        maker.ymin(str(ymin)),
                        maker.xmax(str(xmax)),
                        maker.ymax(str(ymax)),
                    ),
                )
            )

        if not args.noviz:
            captions = [class_names[label] for label in labels]
            viz = imgviz.instances2rgb(
                image=img,
                labels=labels,
                bboxes=bboxes,
                captions=captions,
                font_size=15,
            )
            imgviz.io.imsave(out_viz_file, viz)

        with open(out_xml_file, "wb") as f:
            f.write(lxml.etree.tostring(xml, pretty_print=True))


if __name__ == "__main__":
    main()


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148