opencv/samples/dnn/ssd_object_detection.cpp

#include <opencv2/dnn.hpp>
#include <opencv2/dnn/shape_utils.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace cv::dnn;

#include <fstream>
#include <iostream>
#include <cstdlib>
using namespace std;

const size_t width = 300;
const size_t height = 300;

static Mat getMean(const size_t& imageHeight, const size_t& imageWidth)
{
    Mat mean;

    const int meanValues[3] = {104, 117, 123};
    vector<Mat> meanChannels;
    for(int i = 0; i < 3; i++)
    {
        Mat channel((int)imageHeight, (int)imageWidth, CV_32F, Scalar(meanValues[i]));
        meanChannels.push_back(channel);
    }
    cv::merge(meanChannels, mean);
    return mean;
}

static Mat preprocess(const Mat& frame)
{
    Mat preprocessed;
    frame.convertTo(preprocessed, CV_32F);
    resize(preprocessed, preprocessed, Size(width, height)); //SSD accepts 300x300 RGB-images

    Mat mean = getMean(width, height);
    cv::subtract(preprocessed, mean, preprocessed);

    return preprocessed;
}

const char* classNames[] = {"background",
                            "aeroplane", "bicycle", "bird", "boat",
                            "bottle", "bus", "car", "cat", "chair",
                            "cow", "diningtable", "dog", "horse",
                            "motorbike", "person", "pottedplant",
                            "sheep", "sofa", "train", "tvmonitor"};

const char* about = "This sample uses Single-Shot Detector "
                    "(https://arxiv.org/abs/1512.02325) "
                    "to detect objects on camera/video/image.\n"
                    ".caffemodel model's file is available here: "
                    "https://github.com/weiliu89/caffe/tree/ssd#models\n"
                    "Default network is 300x300 and 20-classes VOC.\n";

const char* params
    = "{ help           | false | print usage         }"
      "{ proto          |       | model configuration }"
      "{ model          |       | model weights       }"
      "{ camera_device  | 0     | camera device number}"
      "{ video          |       | video or image for detection}"
      "{ min_confidence | 0.5   | min confidence      }";

int main(int argc, char** argv)
{
    cv::CommandLineParser parser(argc, argv, params);

    if (parser.get<bool>("help"))
    {
        cout << about << endl;
        parser.printMessage();
        return 0;
    }

    String modelConfiguration = parser.get<string>("proto");
    String modelBinary = parser.get<string>("model");

    //! [Initialize network]
    dnn::Net net = readNetFromCaffe(modelConfiguration, modelBinary);
    //! [Initialize network]

    if (net.empty())
    {
        cerr << "Can't load network by using the following files: " << endl;
        cerr << "prototxt:   " << modelConfiguration << endl;
        cerr << "caffemodel: " << modelBinary << endl;
        cerr << "Models can be downloaded here:" << endl;
        cerr << "https://github.com/weiliu89/caffe/tree/ssd#models" << endl;
        exit(-1);
    }

    VideoCapture cap;
    if (parser.get<String>("video").empty())
    {
        int cameraDevice = parser.get<int>("camera_device");
        cap = VideoCapture(cameraDevice);
        if(!cap.isOpened())
        {
            cout << "Couldn't find camera: " << cameraDevice << endl;
            return -1;
        }
    }
    else
    {
        cap.open(parser.get<String>("video"));
        if(!cap.isOpened())
        {
            cout << "Couldn't open image or video: " << parser.get<String>("video") << endl;
            return -1;
        }
    }

    for (;;)
    {
        cv::Mat frame;
        cap >> frame; // get a new frame from camera/video or read image

        if (frame.empty())
        {
            waitKey();
            break;
        }

        if (frame.channels() == 4)
            cvtColor(frame, frame, COLOR_BGRA2BGR);

        //! [Prepare blob]
        Mat preprocessedFrame = preprocess(frame);

        Mat inputBlob = blobFromImage(preprocessedFrame, 1.0f, Size(), Scalar(), false); //Convert Mat to batch of images
        //! [Prepare blob]

        //! [Set input blob]
        net.setInput(inputBlob, "data"); //set the network input
        //! [Set input blob]

        //! [Make forward pass]
        Mat detection = net.forward("detection_out"); //compute output
        //! [Make forward pass]

        vector<double> layersTimings;
        double freq = getTickFrequency() / 1000;
        double time = net.getPerfProfile(layersTimings) / freq;
        ostringstream ss;
        ss << "FPS: " << 1000/time << " ; time: " << time << " ms";
        putText(frame, ss.str(), Point(20,20), 0, 0.5, Scalar(0,0,255));

        Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());

        float confidenceThreshold = parser.get<float>("min_confidence");
        for(int i = 0; i < detectionMat.rows; i++)
        {
            float confidence = detectionMat.at<float>(i, 2);

            if(confidence > confidenceThreshold)
            {
                size_t objectClass = (size_t)(detectionMat.at<float>(i, 1));

                int xLeftBottom = static_cast<int>(detectionMat.at<float>(i, 3) * frame.cols);
                int yLeftBottom = static_cast<int>(detectionMat.at<float>(i, 4) * frame.rows);
                int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols);
                int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows);

                ss.str("");
                ss << confidence;
                String conf(ss.str());

                Rect object(xLeftBottom, yLeftBottom,
                            xRightTop - xLeftBottom,
                            yRightTop - yLeftBottom);

                rectangle(frame, object, Scalar(0, 255, 0));
                String label = String(classNames[objectClass]) + ": " + conf;
                int baseLine = 0;
                Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
                rectangle(frame, Rect(Point(xLeftBottom, yLeftBottom - labelSize.height),
                                      Size(labelSize.width, labelSize.height + baseLine)),
                          Scalar(255, 255, 255), CV_FILLED);
                putText(frame, label, Point(xLeftBottom, yLeftBottom),
                        FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0,0,0));
            }
        }

        imshow("detections", frame);
        if (waitKey(1) >= 0) break;
    }

    return 0;
} // main