小kiss！Yolov3的汽车车牌定位python实现

　　1 说明：
　　=====
　　1.1 对于强大的yolov3来说，汽车车牌的定位，太简单了！
　　1.2 技术要点：对蓝底和白底车牌超强定位，正面的、侧面的均可。
　　1.3 环境：yolov3+python3.8+OpenCV4.2.0+华为笔记本电脑+deepin-linux操作系统。
　　1.4 图片来自今日头条正版免费图库，仅供学习，注释讲解，小白秒懂。
　　pic1：原图
　　pic2：定位图
　　pic3：原图
　　pic4：定位图
　　pic5：原图
　　pic6：定位图
　　2 yolov3的三个文件：
　　===============
　　2.1 下载地址：https://www.kaggle.com/achrafkhazri/yolo-weights-for-licence-plate-detector #下载速度超级快
　　2.2 图：
　　2.3 文件结构：
　　2.4 操作示范：
　　图片定位，视频省略
　　3 main.py代码：
　　===========
　　3.1 注意本代码可以进行图片车牌定位，也可以进行视频和摄像头视频定位。强！！
　　3.2 完整代码：#第1步：使用说明 #文件所在目录下终端输入 # Usage example:  python3 main.py --video=car.mp4 #                 python3 main.py --image=test.jpeg #本机：python3.8 main.py --image=test.jpeg   #第2步：模块导入 import cv2 as cv import argparse import sys import numpy as np import os.path  #第3步：初始化参数 Initialize the parameters confThreshold = 0.5  #Confidence threshold 过滤弱检测的最小概率 nmsThreshold = 0.4  #Non-maximum suppression threshold 非最大值抑制阈值  inpWidth = 416  #608     #Width of network＂s input image inpHeight = 416 #608     #Height of network＂s input image  #argparse库可以让我们直接在命令行中就可以向程序中传入参数并让程序运行 parser = argparse.ArgumentParser(description=＂Object Detection using YOLO in OPENCV＂) parser.add_argument(＂--image＂, help=＂Path to image file.＂) parser.add_argument(＂--video＂, help=＂Path to video file.＂) args = parser.parse_args()  #第4步：加载yolov3文件 classesFile = ＂classes.names＂  #在图片或视频上框上的名字  classes = None with open(classesFile, ＂rt＂) as f:     classes = f.read().rstrip(＂ ＂).split(＂ ＂)  modelConfiguration = ＂darknet-yolov3.cfg＂ modelWeights = ＂lapi.weights＂;    # 加载网络、配置权重 net = cv.dnn.readNetFromDarknet(modelConfiguration, modelWeights) #一般情况都是使用opencv dnn作为后台计算 net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV) #表示在CPU设备上使用 net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)  #第5步：函数定义 # Get the names of the output layers # 获取名字：车牌仅仅一个：LP def getOutputsNames(net):     # Get the names of all the layers in the network     layersNames = net.getLayerNames()     # Get the names of the output layers, i.e. the layers with unconnected outputs     return [layersNames[i[0] - 1] for i in net.getUnconnectedOutLayers()]  #画预测绿色框box # Draw the predicted bounding box def drawPred(classId, conf, left, top, right, bottom):     # Draw a bounding box.     cv.rectangle(frame, (left, top), (right, bottom), (0, 255, 0), 3)      label = ＂%.2f＂ % conf      # Get the label for the class name and its confidence     if classes:         assert(classId < len(classes))         label = ＂%s:%s＂ % (classes[classId], label)      #Display the label at the top of the bounding box     labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1)     top = max(top, labelSize[1])     #红色文字框     cv.rectangle(frame, (left, top - round(1.5*labelSize[1])), (left + round(1.5*labelSize[0]), top + baseLine), (0, 0, 255), cv.FILLED)     #黑色文字显示     cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0,0,0), 2)  #定位过程函数 def postprocess(frame, outs):     #获取宽和高     frameHeight = frame.shape[0]     frameWidth = frame.shape[1]          #初始化三个列表     classIds = []     confidences = []     boxes = []          #类似yolov3的目标检测读取     for out in outs:         print(＂out.shape : ＂, out.shape)         for detection in out:              scores = detection[5:]             classId = np.argmax(scores)              confidence = scores[classId]             if detection[4]>confThreshold:                 print(detection[4], ＂ - ＂, scores[classId], ＂ - th : ＂, confThreshold)                 print(detection)             if confidence > confThreshold:                 center_x = int(detection[0] * frameWidth)                 center_y = int(detection[1] * frameHeight)                 width = int(detection[2] * frameWidth)                 height = int(detection[3] * frameHeight)                 left = int(center_x - width / 2)                 top = int(center_y - height / 2)                 classIds.append(classId)                 confidences.append(float(confidence))                 boxes.append([left, top, width, height])      indices = cv.dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold)      for i in indices:         i = i[0]         box = boxes[i]         left = box[0]         top = box[1]         width = box[2]         height = box[3]         #画出预测框：绿色框和文字框         drawPred(classIds[i], confidences[i], left, top, left + width, top + height)  #第6步：图片和视频判定 #如果是视频，则在根目录下动态显示目标检测或者车牌检测的视频 outputFile = ＂yolo_out_py.avi＂  #图片判定 if (args.image):     # Open the image file     if not os.path.isfile(args.image):         print(＂Input image file ＂, args.image, ＂ doesn＂t exist＂)         sys.exit(1)     cap = cv.VideoCapture(args.image)     #在当前目录下输出     outputFile = args.image[:-4]+＂_yolo_out_py.jpg＂  #视频判断 elif (args.video):     # Open the video file     if not os.path.isfile(args.video):         print(＂Input video file ＂, args.video, ＂ doesn＂t exist＂)         sys.exit(1)     cap = cv.VideoCapture(args.video)     #当前目录下输出完成后的视频     outputFile = args.video[:-4]+＂_yolo_out_py.avi＂  #摄像头判断 else:     # Webcam input     cap = cv.VideoCapture(0)  #如果不是图片，那么写入视频设置 # Get the video writer initialized to save the output video if (not args.image):     vid_writer = cv.VideoWriter(outputFile, cv.VideoWriter_fourcc(＂M＂,＂J＂,＂P＂,＂G＂), 30, (round(cap.get(cv.CAP_PROP_FRAME_WIDTH)),round(cap.get(cv.CAP_PROP_FRAME_HEIGHT))))   #第7步：循环 while cv.waitKey(1) < 0:     #视频类判定     # get frame from the video     hasFrame, frame = cap.read()     # Stop the program if reached end of video     if not hasFrame:         print(＂Done processing !!!＂)         print(＂Output file is stored as ＂, outputFile)         cv.waitKey(3000)         break      # Create a 4D blob from a frame.     blob = cv.dnn.blobFromImage(frame, 1/255, (inpWidth, inpHeight), [0,0,0], 1, crop=False)      # Sets the input to the network     net.setInput(blob)      # Runs the forward pass to get output of the output layers     outs = net.forward(getOutputsNames(net))      # Remove the bounding boxes with low confidence     postprocess(frame, outs)      # Put efficiency information. The function getPerfProfile returns the overall time for inference(t) and the timings for each of the layers(in layersTimes)     t, _ = net.getPerfProfile()     label = ＂Inference time: %.2f ms＂ % (t * 1000.0 / cv.getTickFrequency())     #左上角输出红色的文字：耗时，暂时注释掉     #cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))      #写入设置     if (args.image):         cv.imwrite(outputFile, frame.astype(np.uint8))     else:         vid_writer.write(frame.astype(np.uint8))