# -*- coding: UTF-8 -*- from flask import Flask, request, jsonify from PIL import Image import io import base64 import time from pathlib import Path import os import cv2 import torch import torch.backends.cudnn as cudnn from numpy import random import copy import numpy as np from models.experimental import attempt_load from utils.datasets import letterbox from utils.general import check_img_size, non_max_suppression_face, apply_classifier, scale_coords, xyxy2xywh, \ strip_optimizer, set_logging, increment_path from utils.plots import plot_one_box from utils.torch_utils import select_device, load_classifier, time_synchronized from utils.cv_puttext import cv2ImgAddText from plate_recognition.plate_rec import get_plate_result, allFilePath, init_model, cv_imread # from plate_recognition.plate_cls import cv_imread from plate_recognition.double_plate_split_merge import get_split_merge clors = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (0, 255, 255)] danger = ['危', '险'] def order_points(pts): # 四个点按照左上 右上 右下 左下排列 rect = np.zeros((4, 2), dtype="float32") s = pts.sum(axis=1) rect[0] = pts[np.argmin(s)] rect[2] = pts[np.argmax(s)] diff = np.diff(pts, axis=1) rect[1] = pts[np.argmin(diff)] rect[3] = pts[np.argmax(diff)] return rect def four_point_transform(image, pts): # 透视变换得到车牌小图 # rect = order_points(pts) rect = pts.astype('float32') (tl, tr, br, bl) = rect widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2)) widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2)) maxWidth = max(int(widthA), int(widthB)) heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2)) heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2)) maxHeight = max(int(heightA), int(heightB)) dst = np.array([ [0, 0], [maxWidth - 1, 0], [maxWidth - 1, maxHeight - 1], [0, maxHeight - 1]], dtype="float32") M = cv2.getPerspectiveTransform(rect, dst) warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight)) return warped def load_model(weights, device): # 加载检测模型 model = attempt_load(weights, map_location=device) # load FP32 model return model def scale_coords_landmarks(img1_shape, coords, img0_shape, ratio_pad=None): # 返回到原图坐标 # Rescale coords (xyxy) from img1_shape to img0_shape if ratio_pad is None: # calculate from img0_shape gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding else: gain = ratio_pad[0][0] pad = ratio_pad[1] coords[:, [0, 2, 4, 6]] -= pad[0] # x padding coords[:, [1, 3, 5, 7]] -= pad[1] # y padding coords[:, :8] /= gain # clip_coords(coords, img0_shape) coords[:, 0].clamp_(0, img0_shape[1]) # x1 coords[:, 1].clamp_(0, img0_shape[0]) # y1 coords[:, 2].clamp_(0, img0_shape[1]) # x2 coords[:, 3].clamp_(0, img0_shape[0]) # y2 coords[:, 4].clamp_(0, img0_shape[1]) # x3 coords[:, 5].clamp_(0, img0_shape[0]) # y3 coords[:, 6].clamp_(0, img0_shape[1]) # x4 coords[:, 7].clamp_(0, img0_shape[0]) # y4 # coords[:, 8].clamp_(0, img0_shape[1]) # x5 # coords[:, 9].clamp_(0, img0_shape[0]) # y5 return coords def get_plate_rec_landmark(img, xyxy, conf, landmarks, class_num, device, plate_rec_model, is_color=False): # 获取车牌坐标以及四个角点坐标并获取车牌号 h, w, c = img.shape Box = {} result_dict = {} tl = 1 or round(0.002 * (h + w) / 2) + 1 # line/font thickness x1 = int(xyxy[0]) y1 = int(xyxy[1]) x2 = int(xyxy[2]) y2 = int(xyxy[3]) height = y2 - y1 landmarks_np = np.zeros((4, 2)) rect = [x1, y1, x2, y2] for i in range(4): point_x = int(landmarks[2 * i]) point_y = int(landmarks[2 * i + 1]) landmarks_np[i] = np.array([point_x, point_y]) class_label = int(class_num) # 车牌的的类型0代表单牌，1代表双层车牌 roi_img = four_point_transform(img, landmarks_np) # 透视变换得到车牌小图 if class_label: # 判断是否是双层车牌，是双牌的话进行分割后然后拼接 roi_img = get_split_merge(roi_img) if not is_color: plate_number, rec_prob = get_plate_result(roi_img, device, plate_rec_model, is_color=is_color) # 对车牌小图进行识别 else: plate_number, rec_prob, plate_color, color_conf = get_plate_result(roi_img, device, plate_rec_model, is_color=is_color) Box['X'] = landmarks_np[0][0].tolist() # 车牌角点坐标 Box['Y'] = landmarks_np[0][1].tolist() Box['Width'] = rect[2] - rect[0] Box['Height'] = rect[3] - rect[1] # Box['label'] = plate_number # 车牌号 # Box['rect'] = rect result_dict['rect'] = rect # 车牌roi区域 result_dict['detect_conf'] = conf # 检测区域得分 result_dict['landmarks'] = landmarks_np.tolist() # 车牌角点坐标 result_dict['plate_no'] = plate_number # 车牌号 result_dict['rec_conf'] = rec_prob # 每个字符的概率 result_dict['roi_height'] = roi_img.shape[0] # 车牌高度 result_dict['plate_color'] = "" if is_color: result_dict['plate_color'] = plate_color # 车牌颜色 result_dict['color_conf'] = color_conf # 颜色得分 result_dict['plate_type'] = class_label # 单双层 0单层 1双层 score = conf.tolist() return plate_number, score, Box, result_dict def detect_Recognition_plate(model, orgimg, device, plate_rec_model, img_size, is_color=False): # 获取车牌信息 # Load model # img_size = opt_img_size conf_thres = 0.3 # 得分阈值 iou_thres = 0.5 # nms的iou值 dict_list = [] result_jpg = [] # orgimg = cv2.imread(image_path) # BGR img0 = copy.deepcopy(orgimg) assert orgimg is not None, 'Image Not Found ' h0, w0 = orgimg.shape[:2] # orig hw r = img_size / max(h0, w0) # resize image to img_size if r != 1: # always resize down, only resize up if training with augmentation interp = cv2.INTER_AREA if r < 1 else cv2.INTER_LINEAR img0 = cv2.resize(img0, (int(w0 * r), int(h0 * r)), interpolation=interp) imgsz = check_img_size(img_size, s=model.stride.max()) # check img_size img = letterbox(img0, new_shape=imgsz)[0] # 检测前处理，图片长宽变为32倍数，比如变为640X640 # img =process_data(img0) # Convert img = img[:, :, ::-1].transpose(2, 0, 1).copy() # BGR to RGB, to 3x416x416 图片的BGR排列转为RGB,然后将图片的H,W,C排列变为C,H,W排列 # Run inference t0 = time.time() img = torch.from_numpy(img).to(device) img = img.float() # uint8 to fp16/32 img /= 255.0 # 0 - 255 to 0.0 - 1.0 if img.ndimension() == 3: img = img.unsqueeze(0) # Inference pred = model(img)[0] # Apply NMS pred = non_max_suppression_face(pred, conf_thres, iou_thres) # result_jpg.insert(0, pred) # Process detections for i, det in enumerate(pred): # detections per image if len(det): # Rescale boxes from img_size to im0 size det[:, :4] = scale_coords(img.shape[2:], det[:, :4], orgimg.shape).round() # Print results for c in det[:, -1].unique(): n = (det[:, -1] == c).sum() # detections per class det[:, 5:13] = scale_coords_landmarks(img.shape[2:], det[:, 5:13], orgimg.shape).round() for j in range(det.size()[0]): xyxy = det[j, :4].view(-1).tolist() conf = det[j, 4].cpu().numpy() landmarks = det[j, 5:13].view(-1).tolist() class_num = det[j, 13].cpu().numpy() label, score, Box, result_dict = get_plate_rec_landmark(orgimg, xyxy, conf, landmarks, class_num, device, plate_rec_model, is_color=is_color) dict_list.append(result_dict) result_jpg.append(Box) result_jpg.append(score) result_jpg.append(label) return dict_list, result_jpg # cv2.imwrite('result.jpg', orgimg) def draw_result(orgimg, dict_list, is_color=False): # 车牌结果画出来 result_str = "" for result in dict_list: rect_area = result['rect'] x, y, w, h = rect_area[0], rect_area[1], rect_area[2] - rect_area[0], rect_area[3] - rect_area[1] padding_w = 0.05 * w padding_h = 0.11 * h rect_area[0] = max(0, int(x - padding_w)) rect_area[1] = max(0, int(y - padding_h)) rect_area[2] = min(orgimg.shape[1], int(rect_area[2] + padding_w)) rect_area[3] = min(orgimg.shape[0], int(rect_area[3] + padding_h)) height_area = result['roi_height'] landmarks = result['landmarks'] result_p = result['plate_no'] if result['plate_type'] == 0: # 单层 result_p += " " + result['plate_color'] else: # 双层 result_p += " " + result['plate_color'] + "双层" result_str += result_p + " " for i in range(4): # 关键点 cv2.circle(orgimg, (int(landmarks[i][0]), int(landmarks[i][1])), 5, clors[i], -1) cv2.rectangle(orgimg, (rect_area[0], rect_area[1]), (rect_area[2], rect_area[3]), (0, 0, 255), 2) # 画框 labelSize = cv2.getTextSize(result_p, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1) # 获得字体的大小 if rect_area[0] + labelSize[0][0] > orgimg.shape[1]: # 防止显示的文字越界 rect_area[0] = int(orgimg.shape[1] - labelSize[0][0]) orgimg = cv2.rectangle(orgimg, (rect_area[0], int(rect_area[1] - round(1.6 * labelSize[0][1]))), (int(rect_area[0] + round(1.2 * labelSize[0][0])), rect_area[1] + labelSize[1]), (255, 255, 255), cv2.FILLED) # 画文字框,背景白色 if len(result) >= 1: orgimg = cv2ImgAddText(orgimg, result_p, rect_area[0], int(rect_area[1] - round(1.6 * labelSize[0][1])), (0, 0, 0), 21) # orgimg=cv2ImgAddText(orgimg,result_p,rect_area[0]-height_area,rect_area[1]-height_area-10,(0,255,0),height_area) print(result_str) # 打印结果 return orgimg, result_str def get_second(capture): if capture.isOpened(): rate = capture.get(5) # 帧速率 FrameNumber = capture.get(7) # 视频文件的帧数 duration = FrameNumber / rate # 帧速率/视频总帧数 是时间，除以60之后单位是分钟 return int(rate), int(FrameNumber), int(duration) def process_images(detect_model_path, rec_model_path, is_color, img, img_size, output, video_path): device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 创建保存结果的文件夹 save_path = output if not os.path.exists(save_path): os.mkdir(save_path) # 加载模型 detect_model = load_model(detect_model_path, device) plate_rec_model = init_model(device, rec_model_path, is_color=is_color) # img = cv_imread(image_path) if img.shape[-1] == 4: img = cv2.cvtColor(img, cv2.COLOR_BGRA2BGR) dict_list, result_jpg = detect_Recognition_plate(detect_model, img, device, plate_rec_model, img_size, is_color=is_color) # ori_img = draw_result(img, dict_list) # ori_list=ori_img[0].tolist() # result_jpg.insert(0,ori_list) result_jpg.insert(0, [[1, 0, 0], [0, 1, 0], [0, 0, 1]]) return result_jpg app = Flask(__name__) def base64_to_image(base64_str): # 去掉base64编码中的头部信息 base64_str = base64_str.split(",")[-1] # 解码base64字符串 image_data = base64.b64decode(base64_str) # 转换为numpy数组 nparr = np.frombuffer(image_data, np.uint8) # 解码为OpenCV格式的图片对象 image = cv2.imdecode(nparr, cv2.IMREAD_COLOR) return image @app.route('/upload', methods=['POST']) def upload_image(): try: # 从请求中获取base64编码的图片数据 data = request.json # print(data) base64_str = data.get('image') # print(base64_str) if not base64_str: return jsonify({'error': 'No image data provided'}), 400 # 将base64编码转换为图片 image = base64_to_image(base64_str) result_jpg = process_images( detect_model_path='weights/plate_detect.pt', rec_model_path='weights/plate_rec_color.pth', is_color=True, img=image, img_size=640, output='result', video_path='' # 如果处理图片，视频路径留空 ) # 构建一个字典来存储结果 results = [] # 添加注册矩阵 register_matrix = [ [1, 0, 0], [0, 1, 0], [0, 0, 1] ] results.append({"RegisterMatrix": register_matrix}) # 添加检测结果 for i in range(1, len(result_jpg), 3): box, score, label = result_jpg[i:i + 3] box_data = box detection_result = { "Box": box_data, "Score": score, "label": label } results.append(detection_result) # print(detection_result) # 返回处理结果 return jsonify({"result.jpg": results}) except Exception as e: # 打印异常信息以帮助诊断 print(f"Caught an exception: {type(e).__name__}: {str(e)}") return jsonify({"error_msg": "Content processing is incorrect", "error_code": "AIS.0404"}) if __name__ == '__main__': app.run(debug=True)