参考学习来自：使用Python+OpenCV进行数据增广方法综述（附代码演练）

Random Cut

随机裁剪图片中的长款缩放为 scale 倍的区域，resize 到原图大小，bounding box 的坐标也相应的改变

引入了丢弃机制，裁剪后 bbox 的面积如果小于原来的 50%，该 bbox 丢弃

import random
import cv2def randomcrop(img, gt_boxes, scale=0.5, ratio=0.25):'''### Random Crop ###img: imagegt_boxes: format [[obj x1 y1 x2 y2],...]scale: percentage of cropped area'''# Crop imageheight, width = int(img.shape[0]*scale), int(img.shape[1]*scale)# Top Left Coordinatex = random.randint(0, img.shape[1] - int(width))y = random.randint(0, img.shape[0] - int(height))cropped = img[y:y+height, x:x+width]# Visisual bboximg_copy = img.copy()cv2.rectangle(img_copy, (x, y), (x+width, y+height), color=[255, 0, 255], thickness=10)for i in range(len(gt_boxes)):cv2.rectangle(img_copy, (gt_boxes[i][1], gt_boxes[i][2]), (gt_boxes[i][3], gt_boxes[i][4]),color=colors[i], thickness=5)cv2.imwrite("bbox.jpg", img_copy)resized = cv2.resize(cropped, (img.shape[1], img.shape[0]))# Modify annotationnew_boxes = []for box in gt_boxes:obj_name = box[0]x1 = int(box[1])y1 = int(box[2])x2 = int(box[3])y2 = int(box[4])if ratio: # 是否丢弃裁剪过半的 bboxori_area = (y2 - y1) * (x2 - x1)x1_new, y1_new, x2_new, y2_new = x1, y1, x2, y2if x1_new < x:x1_new = xif y1_new < y:y1_new = yif x2_new > x+width:x2_new = x+widthif y2_new > y+height:y2_new = y+heightnew_area = (y2_new-y1_new) * (x2_new-x1_new)if (new_area / ori_area) < ratio:continuex1, x2 = x1-x, x2-xy1, y2 = y1-y, y2-yx1, y1, x2, y2 = x1/scale, y1/scale, x2/scale, y2/scaleif (x1 < img.shape[1] and y1 < img.shape[0]) and (x2 > 0 and y2 > 0):if x1 < 0: x1 = 0if y1 < 0: y1 = 0if x2 > img.shape[1]: x2 = img.shape[1]if y2 > img.shape[0]: y2 = img.shape[0]new_boxes.append([obj_name, x1, y1, x2, y2])return resized, new_boxesif __name__ == "__main__":colors = [[0, 0, 255],[0, 255, 0],[255, 0, 0],[0, 255, 255]]bbox = [["person", 777, 221, 1361, 769],["cat", 1085, 413, 1337, 617],['bird', 413, 273, 625, 581],['bag', 877, 781, 1013, 909]]img = cv2.imread("./1.jpg")resized, new_bbox = randomcrop(img, bbox, scale=0.5, ratio=0.5)print(new_bbox)"""[['person', 1162.0, 164.0, 1920, 1080], ['bird', 434.0, 268.0, 858.0, 884.0]]"""for i in range(len(new_bbox)):cv2.rectangle(resized, (int(new_bbox[i][1]), int(new_bbox[i][2])),(int(new_bbox[i][3]), int(new_bbox[i][4])),color=colors[i], thickness=5)cv2.imwrite("resized.jpg", resized)# cv2.imshow("new bbox", resized)# cv2.waitKey(0)# cv2.destroyAllWindows()

输入图片

案例1

bbox.jpg，粉色框是随机裁剪的区域，其他框是目标

resized.jpg，粉色区域也被缩放成原图大小，可以看到猫的框裁剪过半，被舍弃了

案例2

未出现裁剪过半的矩形框，所有目标都被保留

案例3

人和海鸥裁剪均过半，被舍弃，猫和包裁剪未过半，得以保留

resize 到原图大小

Cutout

import random
import cv2def cutout(img, gt_boxes, amount=0.5):'''### Cutout ###img: imagegt_boxes: format [[obj x1 y1 x2 y2],...]amount: num of masks / num of objects '''out = img.copy()ran_select = random.sample(gt_boxes, round(amount*len(gt_boxes)))for box in ran_select:x1 = int(box[1])y1 = int(box[2])x2 = int(box[3])y2 = int(box[4])mask_w = int((x2 - x1)*0.5)mask_h = int((y2 - y1)*0.5)mask_x1 = random.randint(x1, x2 - mask_w)mask_y1 = random.randint(y1, y2 - mask_h)mask_x2 = mask_x1 + mask_wmask_y2 = mask_y1 + mask_hcv2.rectangle(out, (mask_x1, mask_y1), (mask_x2, mask_y2), (0, 0, 0), thickness=-1)return outif __name__ == "__main__":colors = [[0, 0, 255],[0, 255, 0],[255, 0, 0],[0, 255, 255]]bbox = [["person", 777, 221, 1361, 769],["cat", 1085, 413, 1337, 617],['bird', 413, 273, 625, 581],['bag', 877, 781, 1013, 909]]img = cv2.imread("./1.jpg")out = cutout(img, bbox)for i in range(len(bbox)):cv2.rectangle(out, (bbox[i][1], bbox[i][2]), (bbox[i][3], bbox[i][4]),color=colors[i], thickness=5)cv2.imwrite("cutout.jpg", out)

在目标中进行 mask，随机左上角，h和w固定为设定值——1/2

输入图片

输出结果

可以观察到，人形框和小猫框被 mask 掉了 1/4 区域

Color Jitter

import random
import cv2
import numpy as npdef colorjitter(img, cj_type="b"):'''### Different Color Jitter ###img: imagecj_type: {b: brightness, s: saturation, c: constast}'''if cj_type == "b":# value = random.randint(-50, 50)value = np.random.choice(np.array([-50, -40, -30, 30, 40, 50]))hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)h, s, v = cv2.split(hsv)if value >= 0:lim = 255 - valuev[v > lim] = 255v[v <= lim] += valueelse:lim = np.absolute(value)v[v < lim] = 0v[v >= lim] -= np.absolute(value)final_hsv = cv2.merge((h, s, v))img = cv2.cvtColor(final_hsv, cv2.COLOR_HSV2BGR)return imgelif cj_type == "s":# value = random.randint(-50, 50)value = np.random.choice(np.array([-50, -40, -30, 30, 40, 50]))hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)h, s, v = cv2.split(hsv)if value >= 0:lim = 255 - values[s > lim] = 255s[s <= lim] += valueelse:lim = np.absolute(value)s[s < lim] = 0s[s >= lim] -= np.absolute(value)final_hsv = cv2.merge((h, s, v))img = cv2.cvtColor(final_hsv, cv2.COLOR_HSV2BGR)return imgelif cj_type == "c":brightness = 10contrast = random.randint(40, 100)dummy = np.int16(img)dummy = dummy * (contrast/127+1) - contrast + brightnessdummy = np.clip(dummy, 0, 255)img = np.uint8(dummy)return imgif __name__ == "__main__":img = cv2.imread("./1.jpg")img1 = colorjitter(img, "b")img2 = colorjitter(img, "s")img3 = colorjitter(img, "c")cv2.imwrite("b.jpg", img1)cv2.imwrite("s.jpg", img2)cv2.imwrite("c.jpg", img3)

输入图片

输出结果

b.jpg 亮度增广

c.jpg 对比度增广

s.jpg 饱和度增广

Add Noisy

import cv2
import numpy as npdef noisy(img, noise_type="gauss"):'''### Adding Noise ###img: imagecj_type: {gauss: gaussian, sp: salt & pepper}'''if noise_type == "gauss":image=img.copy() mean=0st=0.7gauss = np.random.normal(mean,st,image.shape)gauss = gauss.astype('uint8')image = cv2.add(image,gauss)return imageelif noise_type == "sp":image=img.copy() prob = 0.05if len(image.shape) == 2:black = 0white = 255            else:colorspace = image.shape[2]if colorspace == 3:  # RGBblack = np.array([0, 0, 0], dtype='uint8')white = np.array([255, 255, 255], dtype='uint8')else:  # RGBAblack = np.array([0, 0, 0, 255], dtype='uint8')white = np.array([255, 255, 255, 255], dtype='uint8')probs = np.random.random(image.shape[:2])image[probs < (prob / 2)] = blackimage[probs > 1 - (prob / 2)] = whitereturn imageif __name__ == "__main__":img = cv2.imread("./1.jpg")img1 = noisy(img, "gauss")img2 = noisy(img, "sp")cv2.imwrite("gauss.jpg", img1)cv2.imwrite("sp.jpg", img2)

输入图片

gauss.jpg 高斯噪声

sp.jpg 椒盐噪声