from PIL import Image, ImageDraw
import numpy as np
from matplotlib.colors import rgb_to_hsv, hsv_to_rgb
import mathdef rand(a=0, b=1):return np.random.rand() * (b - a) + adef merge_bboxes(bboxes, cutx, cuty):merge_bbox = []for i in range(len(bboxes)):for box in bboxes[i]:tmp_box = []x1, y1, x2, y2 = box[0], box[1], box[2], box[3]if i == 0:if y1 > cuty or x1 > cutx:continueif y2 >= cuty and y1 <= cuty:y2 = cutyif y2 - y1 < 5:continueif x2 >= cutx and x1 <= cutx:x2 = cutxif x2 - x1 < 5:continueif i == 1:if y2 < cuty or x1 > cutx:continueif y2 >= cuty and y1 <= cuty:y1 = cutyif y2 - y1 < 5:continueif x2 >= cutx and x1 <= cutx:x2 = cutxif x2 - x1 < 5:continueif i == 2:if y2 < cuty or x2 < cutx:continueif y2 >= cuty and y1 <= cuty:y1 = cutyif y2 - y1 < 5:continueif x2 >= cutx and x1 <= cutx:x1 = cutxif x2 - x1 < 5:continueif i == 3:if y1 > cuty or x2 < cutx:continueif y2 >= cuty and y1 <= cuty:y2 = cutyif y2 - y1 < 5:continueif x2 >= cutx and x1 <= cutx:x1 = cutxif x2 - x1 < 5:continuetmp_box.append(x1)tmp_box.append(y1)tmp_box.append(x2)tmp_box.append(y2)tmp_box.append(box[-1])merge_bbox.append(tmp_box)return merge_bboxdef get_random_data(annotation_line, input_shape, random=True, hue=.1, sat=1.5, val=1.5, proc_img=True):'''random preprocessing for real-time data augmentation'''
h, w = input_shapemin_offset_x = 0.4min_offset_y = 0.4scale_low = 1 - min(min_offset_x, min_offset_y)scale_high = scale_low + 0.2image_datas = []box_datas = []index = 0place_x = [0, 0, int(w * min_offset_x), int(w * min_offset_x)]place_y = [0, int(h * min_offset_y), int(w * min_offset_y), 0]for line in annotation_line:# 每一行进行分割line_content = line.split()# 打开图片image = Image.open(line_content[0])image = image.convert("RGB")# 图片的大小iw, ih = image.size# 保存框的位置box = np.array([np.array(list(map(int, box.split(',')))) for box in line_content[1:]])# image.save(str(index)+".jpg")# 是否翻转图片flip = rand() < .5if flip and len(box) > 0:image = image.transpose(Image.FLIP_LEFT_RIGHT)box[:, [0, 2]] = iw - box[:, [2, 0]]# 对输入进来的图片进行缩放new_ar = w / hscale = rand(scale_low, scale_high)if new_ar < 1:nh = int(scale * h)nw = int(nh * new_ar)else:nw = int(scale * w)nh = int(nw / new_ar)image = image.resize((nw, nh), Image.BICUBIC)# 进行色域变换hue = rand(-hue, hue)sat = rand(1, sat) if rand() < .5 else 1 / rand(1, sat)val = rand(1, val) if rand() < .5 else 1 / rand(1, val)x = rgb_to_hsv(np.array(image) / 255.)x[..., 0] += huex[..., 0][x[..., 0] > 1] -= 1x[..., 0][x[..., 0] < 0] += 1x[..., 1] *= satx[..., 2] *= valx[x > 1] = 1x[x < 0] = 0image = hsv_to_rgb(x)image = Image.fromarray((image * 255).astype(np.uint8))# 将图片进行放置，分别对应四张分割图片的位置dx = place_x[index]dy = place_y[index]new_image = Image.new('RGB', (w, h), (128, 128, 128))new_image.paste(image, (dx, dy))image_data = np.array(new_image) / 255# Image.fromarray((image_data*255).astype(np.uint8)).save(str(index)+"distort.jpg")index = index + 1box_data = []# 对box进行重新处理if len(box) > 0:np.random.shuffle(box)box[:, [0, 2]] = box[:, [0, 2]] * nw / iw + dxbox[:, [1, 3]] = box[:, [1, 3]] * nh / ih + dybox[:, 0:2][box[:, 0:2] < 0] = 0box[:, 2][box[:, 2] > w] = wbox[:, 3][box[:, 3] > h] = hbox_w = box[:, 2] - box[:, 0]box_h = box[:, 3] - box[:, 1]box = box[np.logical_and(box_w > 1, box_h > 1)]box_data = np.zeros((len(box), 5))box_data[:len(box)] = boximage_datas.append(image_data)box_datas.append(box_data)img = Image.fromarray((image_data * 255).astype(np.uint8))for j in range(len(box_data)):thickness = 3left, top, right, bottom = box_data[j][0:4]draw = ImageDraw.Draw(img)for i in range(thickness):draw.rectangle([left + i, top + i, right - i, bottom - i], outline=(255, 255, 255))img.show()# 将图片分割，放在一起cutx = np.random.randint(int(w * min_offset_x), int(w * (1 - min_offset_x)))cuty = np.random.randint(int(h * min_offset_y), int(h * (1 - min_offset_y)))new_image = np.zeros([h, w, 3])new_image[:cuty, :cutx, :] = image_datas[0][:cuty, :cutx, :]new_image[cuty:, :cutx, :] = image_datas[1][cuty:, :cutx, :]new_image[cuty:, cutx:, :] = image_datas[2][cuty:, cutx:, :]new_image[:cuty, cutx:, :] = image_datas[3][:cuty, cutx:, :]# 对框进行进一步的处理new_boxes = merge_bboxes(box_datas, cutx, cuty)return new_image, new_boxesdef normal_(annotation_line, input_shape):'''random preprocessing for real-time data augmentation'''
line = annotation_line.split()image = Image.open(line[0])box = np.array([np.array(list(map(int, box.split(',')))) for box in line[1:]])iw, ih = image.sizeimage = image.transpose(Image.FLIP_LEFT_RIGHT)box[:, [0, 2]] = iw - box[:, [2, 0]]return image, boxif __name__ == "__main__":with open("2007_train.txt") as f:lines = f.readlines()a = np.random.randint(0, len(lines))# index = 0# line_all = lines[a:a+4]# for line in line_all:#     image_data, box_data = normal_(line,[416,416])#     img = image_data#     for j in range(len(box_data)):#         thickness = 3#         left, top, right, bottom  = box_data[j][0:4]#         draw = ImageDraw.Draw(img)#         for i in range(thickness):#             draw.rectangle([left + i, top + i, right - i, bottom - i],outline=(255,255,255))#     img.show()#     # img.save(str(index)+"box.jpg")#     index = index+1# 传入四张图片# line = lines[a:a + 4]line = lines[0:4]image_data, box_data = get_random_data(line, [416, 416])img = Image.fromarray((image_data * 255).astype(np.uint8))for j in range(len(box_data)):thickness = 3left, top, right, bottom = box_data[j][0:4]draw = ImageDraw.Draw(img)for i in range(thickness):draw.rectangle([left + i, top + i, right - i, bottom - i], outline=(255, 255, 255))img.show()# img.save("box_all.jpg")