使用fillPoly函数将目标贴入背景图

目的：将需要的检测的目标融合到背景图片中，用于丰富目标检测中的负样本和均衡各个类别，效果较好；

背景图片：

目标图片（X光机下的一把美工刀，同时有它的mask坐标标签）：

1.扣取出目标图将要放置在背景图中的背景像素区

cut_bg1 = bg_img[p_y:p_y+ro_h, p_x:p_x+ro_w,:] 域
cv2.imwrite('cut_bg1.jpg', cut_bg1)

 2.得到准备放置目标的区域

#point_obj类型为np.array, 存储方式为[[],[],[],[],...]
I = np.zeros((ro_h, ro_w, 3), dtype=np.uint8)
I = cv2.fillPoly(I, [point_obj], color=(1, 1, 1))
temp1 = I * cut_bg1 
cv2.imwrite('temp1.jpg', temp1)

3.去除放置目标区域的像素

cut_bg = cv2.fillPoly(cut_bg1, [point_obj], color=(0, 0, 0)) 
cv2.imwrite('cut_bg.jpg', cut_bg)

 

4.去除目标以外的边缘信息

temp = I * obj_img 
cv2.imwrite('temp.jpg', temp)

5.将区域内的目标像素和背景像素加和,进行一个像素的融合

ratio = random.randint(90, 99) * 0.01
obj_img_read = (temp * ratio + temp1 * (1-ratio)).astype('uint8') 
cv2.imwrite('obj_img_read.jpg', obj_img_read)

 

 6.将背景区域与目标区域融合

obj_img_read111 =(obj_img_read+cut_bg).astype('uint8')
cv2.imwrite('obj_img_read111.jpg', obj_img_read111)

7.cv格式转换为PIL格式，进行图片区域的融合

pil_img_cut = Image.fromarray(cv2.cvtColor(obj_img_read111, cv2.COLOR_BGR2RGB))
pil_img_bg = Image.fromarray(cv2.cvtColor(bg_img, cv2.COLOR_BGR2RGB))
pil_img_bg.paste(pil_img_cut, (p_x, p_y))

img_path = os.path.join(save_img_dir,'result.jpg')
pil_img_bg.save(img_path)

代码：

import cv2
from Image import PIL
bg_img = cv2.imread(bg) #背景图片
em_h, em_w = bg_img.shape[:2]

obj_img = cv2.imread(obj_img_path)#目标图片
ro_h, ro_w = obj_img.shape[:2]

p_x = random.randint(int(em_w * 0.1), int(0.9 * em_w - ro_w )) #目标图放置的位置
p_y = random.randint(int(em_h * 0.1), int(0.9 * em_h - ro_h))

point_obj = []
for (x_, y_) in zip(x_list, y_list):#point：[(x1,y1),(x2,y2),(x3,y3),...]
    point_obj.append((x_, y_))
point_obj = np.array(point_obj, dtype=np.int32) #point_obj是目标图的mask坐标（多坐标点组成）

I = np.zeros((ro_h, ro_w, 3), dtype=np.uint8)

I = cv2.fillPoly(I, [point_obj], color=(1, 1, 1)) #做一个模板

cut_bg1 = bg_img[p_y:p_y+ro_h, p_x:p_x+ro_w,:] #扣取出目标图将要放置在背景图中的背景像素区域
cv2.imwrite('cut_bg1.jpg', cut_bg1)

temp1 = I * cut_bg1  # 得到准备放置目标的区域
cv2.imwrite('temp1.jpg', temp1)


cut_bg = cv2.fillPoly(cut_bg1, [point_obj], color=(0, 0, 0)) #去除放置目标区域的像素
cv2.imwrite('cut_bg.jpg', cut_bg)


temp = I * obj_img #去除目标以外的边缘信息
cv2.imwrite('temp.jpg', temp)


ratio = random.randint(90, 99) * 0.01
obj_img_read = (temp * ratio + temp1 * (1-ratio)).astype('uint8') #将区域内的目标像素和背景像素加和,进行一个像素的融合
cv2.imwrite('obj_img_read.jpg', obj_img_read)

obj_img_read111 =(obj_img_read+cut_bg).astype('uint8')
cv2.imwrite('obj_img_read111.jpg', obj_img_read111)

#cv格式转换为PIL格式
pil_img_cut = Image.fromarray(cv2.cvtColor(obj_img_read111, cv2.COLOR_BGR2RGB))
pil_img_bg = Image.fromarray(cv2.cvtColor(bg_img, cv2.COLOR_BGR2RGB))
pil_img_bg.paste(pil_img_cut, (p_x, p_y))

img_path = os.path.join(save_img_dir,'result.jpg')
pil_img_bg.save(img_path)