使用OpenCV自带的预训练模型YOLOv3调用摄像头进行目标检测【超少代码！懒人必备！】

想要跑一个使用摄像头进行目标检测的模型玩一玩，想要简单又想要酷炫，想要少写代码，有想要足够好的效果！那不如就来看一看这一篇，相比之下，抖音那些人脸追踪特效简直弱爆了！目标检测还得是咱们YOLO啊！


真的超级傻瓜，甚至不用安装TensorFlow和pytorch，让我们开始吧！

首先调入我们这次实验需要的包

import cv2 as cv
import argparse
import sys
import numpy as np
import os.path

没错！，你没有看错！我们只需要这些包！就足够啦！

接下来让我们初始化一些参数

# Initialize the parameters
confThreshold = 0.5  #Confidence threshold
nmsThreshold = 0.4   #Non-maximum suppression threshold
inpWidth = 416       #Width of network's input image
inpHeight = 416      #Height of network's input image

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()

接下来读入class文件，得到每个输出字符与类别之间的对应关系，如果看过上篇Faster RCNN的小朋友应该对这里不会陌生啦！

classes_path = 'classes.txt'
classes_path = os.path.expanduser(classes_path)
with open(classes_path) as f:
    class_names = f.readlines()
classes = [c.strip() for c in class_names]

不过需要注意，这里用到的“class.txt”和我们上次用到的并不一样，我等下也会把这个TXT文件和完整项目一起上传CSDN项目，我来看一下能不能设置成免费，大家可以去下载。

那么接下来，就是我们的模型啦！

modelConfiguration = "yolov3.cfg";
modelWeights = "yolov3.weights";

net = cv.dnn.readNetFromDarknet(modelConfiguration, modelWeights)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)

“yolov3.cfg”是模型的架构

“yolov3.weights”是预训练权重，可以在GitHub上面下载哦！

这两个就是我们所需要用到的所有需要自己准备的东西啦！如果在GitHub上面找不到可以私信我，就是我不常在，我也会和完整项目一起打包上传，不过”yolov3.weights”有点大，不知道能不能传上来。

接下来，就是一些检测和画图输出的函数啦！

# Get the names of the output layers
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()]

# Draw the predicted bounding box
def drawPred(classId, conf, left, top, right, bottom):
    # Draw a bounding box.
    cv.rectangle(frame, (left, top), (right, bottom), (147, 20, 255), 1)
    
    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])
    cv.rectangle(frame, (left, top - round(1.5*labelSize[1])), (left + round(1.5*labelSize[0]), top + baseLine), (255, 255, 255), cv.FILLED)
    cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0,0,0), 1)

# Remove the bounding boxes with low confidence using non-maxima suppression
def postprocess(frame, outs):
    frameHeight = frame.shape[0]
    frameWidth = frame.shape[1]

    # Scan through all the bounding boxes output from the network and keep only the
    # ones with high confidence scores. Assign the box's class label as the class with the highest score.
    classIds = []
    confidences = []
    boxes = []
    for out in outs:
        for detection in out:
            scores = detection[5:]
            classId = np.argmax(scores)
            confidence = scores[classId]
            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])

    # Perform non maximum suppression to eliminate redundant overlapping boxes with
    # lower confidences.
    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]
        drawPred(classIds[i], confidences[i], left, top, left + width, top + height)

# Process inputs
winName = 'Deep learning object detection in OpenCV'
#cv.namedWindow(winName, cv.WINDOW_NORMAL)

最后，我们使用OpenCV来调用摄像头，开始目标检测和输出：

cap = cv.VideoCapture(0)
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))))

while cv.waitKey(1) < 0:
    
    # 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())
    cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))

    # Write the frame with the detection boxes
    if (args.image):
        cv.imwrite(outputFile, frame.astype(np.uint8));
    else:
        vid_writer.write(frame.astype(np.uint8))

    #cv.imshow(winName, frame)

完整代码如下：

# This code is written at BigVision LLC. It is based on the OpenCV project. It is subject to the license terms in the LICENSE file found in this distribution and at http://opencv.org/license.html

# Usage example:  python3 object_detection_yolo.py --video=run.mp4
#                 python3 object_detection_yolo.py --image=bird.jpg

import cv2 as cv
import argparse
import sys
import numpy as np
import os.path

# Initialize the parameters
confThreshold = 0.5  #Confidence threshold
nmsThreshold = 0.4   #Non-maximum suppression threshold
inpWidth = 416       #Width of network's input image
inpHeight = 416      #Height of network's input image

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()


classes_path = 'classes.txt'
classes_path = os.path.expanduser(classes_path)
with open(classes_path) as f:
    class_names = f.readlines()
classes = [c.strip() for c in class_names]
# Give the configuration and weight files for the model and load the network using them.
modelConfiguration = "yolov3.cfg";
modelWeights = "yolov3.weights";

net = cv.dnn.readNetFromDarknet(modelConfiguration, modelWeights)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)

# Get the names of the output layers
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()]

# Draw the predicted bounding box
def drawPred(classId, conf, left, top, right, bottom):
    # Draw a bounding box.
    cv.rectangle(frame, (left, top), (right, bottom), (147, 20, 255), 1)
    
    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])
    cv.rectangle(frame, (left, top - round(1.5*labelSize[1])), (left + round(1.5*labelSize[0]), top + baseLine), (255, 255, 255), cv.FILLED)
    cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0,0,0), 1)

# Remove the bounding boxes with low confidence using non-maxima suppression
def postprocess(frame, outs):
    frameHeight = frame.shape[0]
    frameWidth = frame.shape[1]

    # Scan through all the bounding boxes output from the network and keep only the
    # ones with high confidence scores. Assign the box's class label as the class with the highest score.
    classIds = []
    confidences = []
    boxes = []
    for out in outs:
        for detection in out:
            scores = detection[5:]
            classId = np.argmax(scores)
            confidence = scores[classId]
            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])

    # Perform non maximum suppression to eliminate redundant overlapping boxes with
    # lower confidences.
    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]
        drawPred(classIds[i], confidences[i], left, top, left + width, top + height)

# Process inputs
winName = 'Deep learning object detection in OpenCV'
#cv.namedWindow(winName, cv.WINDOW_NORMAL)

outputFile = "yolo_out_py.avi"
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)
    outputFile = args.image[:-4]+'_yolo_out_py.jpg'
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)
    outputFile = args.video[:-4]+'_yolo_out_py.avi'
else:
    # Webcam input
    cap = cv.VideoCapture(0)

# 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))))

while cv.waitKey(1) < 0:
    
    # 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())
    cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))

    # Write the frame with the detection boxes
    if (args.image):
        cv.imwrite(outputFile, frame.astype(np.uint8));
    else:
        vid_writer.write(frame.astype(np.uint8))

    cv.imshow(winName, frame)