利用OpenCV玩转YOLOv3

1# 推荐安装外挂版
2pip install opencv-contrib-python
3
4# 或者安装正常版
5pip install opencv-python

 1 1// Process frames.
 2 2while (waitKey(1) < 0)
 3 3{
 4 4    // get frame from the video
 5 5    cap >> frame;
 6 6
 7 7    // Stop the program if reached end of video
 8 8    if (frame.empty()) {
 9 9        cout << "Done processing !!!" << endl;
1010        cout << "Output file is stored as " << outputFile << endl;
1111        waitKey(3000);
1212        break;
1313    }
1414    // Create a 4D blob from a frame.
1515    blobFromImage(frame, blob, 1/255.0, cvSize(inpWidth, inpHeight), Scalar(0,0,0), true, false);
1616
1717    //Sets the input to the network
1818    net.setInput(blob);
1919
2020    // Runs the forward pass to get output of the output layers
2121    vector<Mat> outs;
2222    net.forward(outs, getOutputsNames(net));
2323
2424    // Remove the bounding boxes with low confidence
2525    postprocess(frame, outs);
2626
2727    // Put efficiency information. The function getPerfProfile returns the 
2828    // overall time for inference(t) and the timings for each of the layers(in layersTimes)
2929    vector<double> layersTimes;
3030    double freq = getTickFrequency() / 1000;
3131    double t = net.getPerfProfile(layersTimes) / freq;
3232    string label = format("Inference time for a frame : %.2f ms", t);
3333    putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 255));
3434
3535    // Write the frame with the detection boxes
3636    Mat detectedFrame;
3737    frame.convertTo(detectedFrame, CV_8U);
3838    if (parser.has("image")) imwrite(outputFile, detectedFrame);
3939    else video.write(detectedFrame);
4040
4141}

 1while cv.waitKey(1) < 0:
 2
 3    # get frame from the video
 4    hasFrame, frame = cap.read()
 5
 6    # Stop the program if reached end of video
 7    if not hasFrame:
 8        print("Done processing !!!")
 9        print("Output file is stored as ", outputFile)
10        cv.waitKey(3000)
11        break
12
13    # Create a 4D blob from a frame.
14    blob = cv.dnn.blobFromImage(frame, 1/255, (inpWidth, inpHeight), [0,0,0], 1, crop=False)
15
16    # Sets the input to the network
17    net.setInput(blob)
18
19    # Runs the forward pass to get output of the output layers
20    outs = net.forward(getOutputsNames(net))
21
22    # Remove the bounding boxes with low confidence
23    postprocess(frame, outs)
24
25    # Put efficiency information. The function getPerfProfile returns the 
26    # overall time for inference(t) and the timings for each of the layers(in layersTimes)
27    t, _ = net.getPerfProfile()
28    label = 'Inference time: %.2f ms' % (t * 1000.0 / cv.getTickFrequency())
29    cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
30
31    # Write the frame with the detection boxes
32    if (args.image):
33        cv.imwrite(outputFile, frame.astype(np.uint8));
34    else:
35        vid_writer.write(frame.astype(np.uint8))

1python object_detection_yolo.py --image=bird.jpg

1python object_detection_yolo.py --image=person.jpg

1python object_detection_yolo.py --video=run.mp4