「图像 cv2.seamlessClone」无中生有制造数据

上一篇博客【「图像 merge」无中生有制造数据 】写的是图片直接融合，此方法生成的图片相对而言比较生硬，虽然目标图片已经透明化处理过了，但是生成的图片依旧很假

除了上述上述的图片叠加融合之外，还有一种更加自然的融合方法，就是 cv2.seamlessClone ，生成的效果图如下图所示
但是 cv2.seamlessClone 并不是万能的，需要根据实际情况测试，页根据目标模版的制作效果有很大关系

注意!
此方法融合图片时，目标区域不能按照目标的边缘进行透明化抠图，需要包含一部分的边缘信息，不然融合效果会很差

此算法的 目标图透明化处理/抠图处理与 【「图像 merge」无中生有制造数据 】一致，相关代码已附在博客中，自行移步查看

#  !/usr/bin/env  python
#  -*- coding:utf-8 -*-
# @Time   :  2023.10
# @Author :  绿色羽毛
# @Email  :  lvseyumao@foxmail.com
# @Blog   :  https://blog.csdn.net/ViatorSun
# @Note   :



import os
import cv2
import random
from random import sample
import numpy as np
import argparse




def read_label_txt(label_dir):
    labels = []
    with open(label_dir) as fp:
        for f in fp.readlines():
            labels.append(f.strip().split(' '))
    return labels

def rescale_yolo_labels(labels, img_shape):
    height, width, nchannel = img_shape
    rescale_boxes = []
    for box in list(labels):
        x_c = float(box[1]) * width
        y_c = float(box[2]) * height
        w = float(box[3]) * width
        h = float(box[4]) * height
        x_left = x_c - w * .5
        y_left = y_c - h * .5
        x_right = x_c + w * .5
        y_right = y_c + h * .5
        rescale_boxes.append([box[0], int(x_left), int(y_left), int(x_right), int(y_right)])
    return rescale_boxes

def xyxy2xywh(image, bboxes):
    height, width, _ = image.shape
    boxes = []
    for box in bboxes:
        if len(box) < 4:
            continue
        cls = int(box[0])
        x_min = box[1]
        y_min = box[2]
        x_max = box[3]
        y_max = box[4]
        w = x_max - x_min
        h = y_max - y_min
        x_c = (x_min + x_max) / 2.0
        y_c = (y_min + y_max) / 2.0
        x_c = x_c / width
        y_c = y_c / height
        w = float(w) / width
        h = float(h) / height
        boxes.append([cls, x_c, y_c, w, h])
    return boxes

def cast_color(img, value):
    img_t = cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
    h,s,v = cv2.split(img_t)
    # 增加图像对比度
    v2 = np.clip(cv2.add(2*v,value),0,255)
    img2 = np.uint8(cv2.merge((h,s,v2)))
    img_cast = cv2.cvtColor(img2,cv2.COLOR_HSV2BGR)             # 改变图像对比度
    return img_cast

def brightness(img, value):
    img_t = cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
    h,s,v = cv2.split(img_t)
    # 增加图像亮度
    v1 = np.clip(cv2.add(1*v,value),0,255)
    img1 = np.uint8(cv2.merge((h,s,v1)))
    img_brightness = cv2.cvtColor(img1,cv2.COLOR_HSV2BGR)       # 改变图像亮度亮度
    return img_brightness



def random_add_patches_on_objects(image, template_lst, rescale_boxes, mask_lst, paste_number):

    img = image.copy()

    new_bboxes = []
    cl = 0

    random.shuffle(rescale_boxes)

    for rescale_bbox in rescale_boxes[:int(len(rescale_boxes) * 0.2)]:      # 待ps图像 目标框中
        num_p = random.randint(0, 50) % len(template_lst)           # 随机挑选 原图和mask
        p_img = template_lst[num_p]
        mask = mask_lst[num_p]
        bbox_h, bbox_w, bbox_c = p_img.shape

        obj_xmin = rescale_bbox[1]
        obj_ymin = rescale_bbox[2]
        obj_xmax = rescale_bbox[3]
        obj_ymax = rescale_bbox[4]
        obj_w = obj_xmax - obj_xmin + 1         # 目标框尺寸
        obj_h = obj_ymax - obj_ymin + 1

        new_bbox_w = bbox_w
        new_bbox_h = bbox_h

        while not (bbox_w < obj_w and bbox_h < obj_h):                  # 如果目标框小于 mask尺寸，对mask进行缩放以确保可以放进 bbox中
            new_bbox_w = int(bbox_w * random.uniform(0.5, 0.8))
            new_bbox_h = int(bbox_h * random.uniform(0.5, 0.8))
            bbox_w, bbox_h = new_bbox_w, new_bbox_h
            
        success_num = 0
        while success_num < paste_number:

            center_search_space = [obj_xmin, obj_ymin, obj_xmax - new_bbox_w - 1, obj_ymax - new_bbox_h - 1] # 选取生成随机点区域

            if center_search_space[0] >= center_search_space[2] or center_search_space[1] >= center_search_space[3]:
                print('============== center_search_space error!!!! ================')
                success_num += 1
                continue

            new_bbox_x_min = random.randint(center_search_space[0], center_search_space[2])  # 随机生成点坐标
            new_bbox_y_min = random.randint(center_search_space[1], center_search_space[3])
            new_bbox_x_left, new_bbox_y_top, new_bbox_x_right, new_bbox_y_bottom = new_bbox_x_min, new_bbox_y_min, new_bbox_x_min + new_bbox_w - 1, new_bbox_y_min + new_bbox_h - 1
            new_bbox = [cl, int(new_bbox_x_left), int(new_bbox_y_top), int(new_bbox_x_right), int(new_bbox_y_bottom)]
            success_num += 1
            new_bboxes.append(new_bbox)

            mask = cv2.resize(mask, (new_bbox_w, new_bbox_h)) 
            p_img = cv2.resize(p_img, (new_bbox_w, new_bbox_h))

            center = (int(new_bbox_w / 2), int(new_bbox_h / 2))

            img[new_bbox_y_top:new_bbox_y_bottom, new_bbox_x_left:new_bbox_x_right] = cv2.seamlessClone(
                    p_img,
                    image[new_bbox_y_top:new_bbox_y_bottom, new_bbox_x_left:new_bbox_x_right],
                    mask, center, cv2.MONOCHROME_TRANSFER) # NORMAL_CLONE 、MIXED_CLONE 和 MONOCHROME_TRANSFER
                    
    return img, new_bboxes




if __name__ == "__main__":
    # 用来装载参数的容器
    parser = argparse.ArgumentParser(description='PS')
    # 给这个解析对象添加命令行参数
    parser.add_argument('-i', '--images', default= '/media/yinzhe/DataYZ/DataSet/DataSet/bag_model',type=str, help='path of images')
    parser.add_argument('-t', '--templates', default= '/media/yinzhe/DataYZ/DataSet/DataSet/bag_mask',type=str, help='path of templates')
    parser.add_argument('-s', '--saveImage',default= '/media/yinzhe/DataYZ/DataSet/DataSet/bag_save3', type=str, help='path of ')
    parser.add_argument('-n', '--num', default=5, type=str, help='number of img')

    args = parser.parse_args()  # 获取所有参数

    
    templates_path = args.templates
    images_path = args.images
    save_path = args.saveImage
    num = int(args.num)
    template_paths = []

    if not os.path.exists(save_path):
        os.makedirs(save_path)

    for t_path in os.listdir(templates_path):
        template_paths.append(t_path)

    # template_paths = random.shuffle(template_paths) #打乱顺序
    for image_path in os.listdir(images_path) :
        if "txt" in image_path:
            continue
        image = cv2.imread(os.path.join(images_path, image_path))
        pre_name = image_path.split('.')[0]
        labels = read_label_txt(os.path.join(images_path, pre_name + ".txt"))

        if image is None or len(labels) == 0:
            print("empty image !!! or empty label !!!")
            continue

        # yolo txt转化为x1y1x2y2
        rescale_labels = rescale_yolo_labels(labels, image.shape)  # 转换坐标表示

        template_path = sample(template_paths, num)


        template_lst = []
        mask_lst = []

        for i in range(num):
            template = cv2.imread(os.path.join(templates_path, template_path[i]), cv2.IMREAD_UNCHANGED)
            print(template.shape[2])
            if (template.shape[2] != 4):        # RGB alpha
                break

            alpha = template[:, :, 3]
            p_img = cv2.cvtColor(template, cv2.COLOR_BGRA2BGR)

            if (p_img is None):
                print("empty p image !!!", template_path[i])
                continue
            
            mask = np.where(alpha>0, 255, 0)  #满足大于0的值保留，不满足的设为0
            mask = mask.astype(np.uint8)

            mask_lst.append(mask)
            template_lst.append(p_img)

        for i in range(num):

            img, bboxes = random_add_patches_on_objects(image, template_lst, rescale_labels, mask_lst, 1)

            boxes = xyxy2xywh(img, bboxes)
            img_name = pre_name + '_' + str(i) + '.jpg'
            print('handle img:', img_name)
            cv2.imwrite(os.path.join(save_path, img_name), img)

            with open(os.path.join(save_path, img_name[:-4] + ".txt"), 'a') as f:
                for box in boxes:

                    mess = str(3) + " " + str(box[1]) + " " + str(box[2]) + " " + str(box[3] * 0.6) + " " + str(box[4]* 0.6) + "\n"
                    f.write(mess)

    


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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228