samples/dnn/object_detection.cpp

有關更多詳細資訊，請檢視相應的教程

#include <fstream>
#include <sstream>
 
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
 
#if defined(HAVE_THREADS)
#define USE_THREADS 1
#endif
 
#ifdef USE_THREADS
#include <mutex>
#include <thread>
#include <queue>
#endif
 
#include "common.hpp"
 
std::string keys =
    "{ help h | | Print help message. }"
    "{ @alias | | 用於從 models.yml 檔案中提取預處理引數的模型別名。}"
    "{ zoo | models.yml | 包含預處理引數的檔案的可選路徑 }"
    "{ device | 0 | 攝像頭裝置號。}"
    "{ input i | | 輸入影像或影片檔案的路徑。跳過此引數以從攝像頭捕獲幀。}"
    "{ framework f | | 模型的原始框架的可選名稱。如果未設定，則自動檢測。}"
    "{ classes | | 包含用於標記檢測到的物件的類名稱的文字檔案的可選路徑。}"
    "{ thr | .5 | 置信度閾值。}"
    "{ nms | .4 | 非極大值抑制閾值。}"
    "{ backend | 0 | 選擇一個計算後端： "
                         "0: 自動（預設）， "
                         "1: Halide 語言 (http://halide-lang.org/)， "
                         "2: 英特爾深度學習推理引擎 (https://software.intel.com/openvino-toolkit)， "
                         "3: OpenCV 實現， "
                         "4: VKCOM， "
                         "5: CUDA }"
    "{ target | 0 | 選擇一個目標計算裝置： "
                         "0: CPU 目標（預設）， "
                         "1: OpenCL， "
                         "2: OpenCL fp16（半精度浮點）， "
                         "3: VPU， "
                         "4: Vulkan， "
                         "6: CUDA， "
                         "7: CUDA fp16（半精度浮點預處理）}"
    "{ async | 0 | 同時非同步前向的數量。 "
                        "選擇 0 為同步模式 }";
 
using namespace cv;
using namespace dnn;
 
float confThreshold, nmsThreshold;
std::vector<std::string> classes;
 
inline void preprocess(const Mat& frame, Net& net, Size inpSize, float scale,
                       const Scalar& mean, bool swapRB);
 
void postprocess(Mat& frame, const std::vector<Mat>& out, Net& net, int backend);
 
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
 
void callback(int pos, void* userdata);
 
#ifdef USE_THREADS
template <typename T>
class QueueFPS : public std::queue<T>
{
public:
QueueFPS() : counter(0) {}
 
    void push(const T& entry)
    {
std::lock_guard<std::mutex> lock(mutex);
 
std::queue<T>::push(entry);
counter += 1;
        if (counter == 1)
        {
            // 從第二幀開始計數（預熱）。
tm.reset();
tm.start();
        }
    }
 
T get()
    {
std::lock_guard<std::mutex> lock(mutex);
T entry = this->front();
this->pop();
        return entry;
    }
 
    float getFPS()
    {
tm.stop();
        double fps = counter / tm.getTimeSec();
tm.start();
        return static_cast<float>(fps);
    }
 
    void clear()
    {
std::lock_guard<std::mutex> lock(mutex);
        while (!this->empty())
this->pop();
    }
 
    unsigned int counter;
 
private:
    TickMeter tm;
std::mutex mutex;
};
#endif // USE_THREADS
 
int main(int argc, char** argv)
{
    CommandLineParser parser(argc, argv, keys);
 
    const std::string modelName = parser.get<String>("@alias");
    const std::string zooFile = parser.get<String>("zoo");
 
keys += genPreprocArguments(modelName, zooFile);
 
parser = CommandLineParser(argc, argv, keys);
parser.about("使用此指令碼透過 OpenCV 執行物件檢測深度學習網路。");
    if (argc == 1 || parser.has("help"))
    {
parser.printMessage();
        return 0;
    }
 
confThreshold = parser.get<float>("thr");
nmsThreshold = parser.get<float>("nms");
    float scale = parser.get<float>("scale");
    Scalar mean = parser.get<Scalar>("mean");
    bool swapRB = parser.get<bool>("rgb");
    int inpWidth = parser.get<int>("width");
    int inpHeight = parser.get<int>("height");
    size_t asyncNumReq = parser.get<int>("async");
    CV_Assert(parser.has("model"));
std::string modelPath = findFile(parser.get<String>("model"));
std::string configPath = findFile(parser.get<String>("config"));
 
    // 開啟包含類名稱的檔案。
    if (parser.has("classes"))
    {
std::string file = parser.get<String>("classes");
std::ifstream ifs(file.c_str());
        if (!ifs.is_open())
            CV_Error(Error::StsError, "File " + file + " not found");
std::string line;
        while (std::getline(ifs, line))
        {
classes.push_back(line);
        }
    }
 
    // 載入模型。
Net net = readNet(modelPath, configPath, parser.get<String>("framework"));
    int backend = parser.get<int>("backend");
net.setPreferableBackend(backend);
net.setPreferableTarget(parser.get<int>("target"));
std::vector<String> outNames = net.getUnconnectedOutLayersNames();
 
    // 建立一個視窗
    static const std::string kWinName = "OpenCV 中的深度學習物件檢測";
    namedWindow(kWinName, WINDOW_NORMAL);
    int initialConf = (int)(confThreshold * 100);
    createTrackbar("置信度閾值, %", kWinName, &initialConf, 99, callback);
 
    // 開啟影片檔案或影像檔案或攝像頭流。
    VideoCapture cap;
    if (parser.has("input"))
cap.open(parser.get<String>("input"));
    else
cap.open(parser.get<int>("device"));
 
#ifdef USE_THREADS
    bool process = true;
 
    // 幀捕獲執行緒
QueueFPS<Mat> framesQueue;
std::thread framesThread([&](){
        Mat frame;
        while (process)
        {
cap >> frame;
            if (!frame.empty())
framesQueue.push(frame.clone());
            else
                break;
        }
    });
 
    // 幀處理執行緒
QueueFPS<Mat> processedFramesQueue;
QueueFPS<std::vector<Mat> > predictionsQueue;
std::thread processingThread([&](){
std::queue<AsyncArray> futureOutputs;
        Mat blob;
        while (process)
        {
            // 獲取下一幀
            Mat frame;
            {
                if (!framesQueue.empty())
                {
frame = framesQueue.get();
                    if (asyncNumReq)
                    {
                        if (futureOutputs.size() == asyncNumReq)
frame = Mat();
                    }
                    else
framesQueue.clear(); // 跳過剩餘幀
                }
            }
 
            // 處理幀
            if (!frame.empty())
            {
preprocess(frame, net, Size(inpWidth, inpHeight), scale, mean, swapRB);
processedFramesQueue.push(frame);
 
                if (asyncNumReq)
                {
futureOutputs.push(net.forwardAsync());
                }
                else
                {
std::vector<Mat> outs;
net.forward(outs, outNames);
predictionsQueue.push(outs);
                }
            }
 
            while (!futureOutputs.empty() &&
futureOutputs.front().wait_for(std::chrono::seconds(0)))
            {
                AsyncArray async_out = futureOutputs.front();
futureOutputs.pop();
                Mat out;
async_out.get(out);
predictionsQueue.push({out});
            }
        }
    });
 
    // 後處理和渲染迴圈
    while (waitKey(1) < 0)
    {
        if (predictionsQueue.empty())
            continue;
 
std::vector<Mat> outs = predictionsQueue.get();
        Mat frame = processedFramesQueue.get();
 
        postprocess(frame, outs, net, backend);
 
        if (predictionsQueue.counter > 1)
        {
std::string label = format("攝像頭: %.2f FPS", framesQueue.getFPS());
            putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
 
label = format("網路: %.2f FPS", predictionsQueue.getFPS());
            putText(frame, label, Point(0, 30), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
 
label = format("跳過的幀數: %d", framesQueue.counter - predictionsQueue.counter);
            putText(frame, label, Point(0, 45), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
        }
        imshow(kWinName, frame);
    }
 
process = false;
framesThread.join();
processingThread.join();
 
#else // USE_THREADS
    if (asyncNumReq)
        CV_Error(Error::StsNotImplemented, "僅推理引擎後端支援非同步前向。");
 
    // 處理幀。
    Mat frame, blob;
    while (waitKey(1) < 0)
    {
cap >> frame;
        if (frame.empty())
        {
            waitKey();
            break;
        }
 
preprocess(frame, net, Size(inpWidth, inpHeight), scale, mean, swapRB);
 
std::vector<Mat> outs;
net.forward(outs, outNames);
 
        postprocess(frame, outs, net, backend);
 
        // 顯示效率資訊。
std::vector<double> layersTimes;
        double freq = getTickFrequency() / 1000;
        double t = net.getPerfProfile(layersTimes) / freq;
std::string label = format("推理時間: %.2f ms", t);
        putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
 
        imshow(kWinName, frame);
    }
#endif // USE_THREADS
    return 0;
}
 
inline void preprocess(const Mat& frame, Net& net, Size inpSize, float scale,
                       const Scalar& mean, bool swapRB)
{
    static Mat blob;
    // 從幀建立 4D blob。
    if (inpSize.width <= 0) inpSize.width = frame.cols;
    if (inpSize.height <= 0) inpSize.height = frame.rows;
    blobFromImage(frame, blob, 1.0, inpSize, Scalar(), swapRB, false, CV_8U);
 
    // 執行模型。
net.setInput(blob, "", scale, mean);
    if (net.getLayer(0)->outputNameToIndex("im_info") != -1) // Faster-RCNN 或 R-FCN
    {
        resize(frame, frame, inpSize);
        Mat imInfo = (Mat_<float>(1, 3) << inpSize.height, inpSize.width, 1.6f);
net.setInput(imInfo, "im_info");
    }
}
 
void postprocess(Mat& frame, const std::vector<Mat>& outs, Net& net, int backend)
{
    static std::vector<int> outLayers = net.getUnconnectedOutLayers();
    static std::string outLayerType = net.getLayer(outLayers[0])->type;
 
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
    if (outLayerType == "DetectionOutput")
    {
        // 網路生成形狀為 1x1xNx7 的輸出 blob，其中 N 是檢測的數量，
        // 每個檢測都是一個值向量
        // [batchId, classId, confidence, left, top, right, bottom]
        CV_Assert(outs.size() > 0);
        for (size_t k = 0; k < outs.size(); k++)
        {
            float* data = (float*)outs[k].data;
            for (size_t i = 0; i < outs[k].total(); i += 7)
            {
                float confidence = data[i + 2];
                if (confidence > confThreshold)
                {
                    int left = (int)data[i + 3];
                    int top = (int)data[i + 4];
                    int right = (int)data[i + 5];
                    int bottom = (int)data[i + 6];
                    int width = right - left + 1;
                    int height = bottom - top + 1;
                    if (width <= 2 || height <= 2)
                    {
left = (int)(data[i + 3] * frame.cols);
top = (int)(data[i + 4] * frame.rows);
right = (int)(data[i + 5] * frame.cols);
bottom = (int)(data[i + 6] * frame.rows);
width = right - left + 1;
height = bottom - top + 1;
                    }
classIds.push_back((int)(data[i + 1]) - 1); // 跳過第 0 個背景類 ID。
boxes.push_back(Rect(left, top, width, height));
confidences.push_back(confidence);
                }
            }
        }
    }
    else if (outLayerType == "Region")
    {
        for (size_t i = 0; i < outs.size(); ++i)
        {
            // 網路生成形狀為 NxC 的輸出 blob，其中 N 是檢測到的物件數量，
            // C 是類數量 + 4，前 4 個數字為
            // [center_x, center_y, width, height]
            float* data = (float*)outs[i].data;
            for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols)
            {
                Mat scores = outs[i].row(j).colRange(5, outs[i].cols);
                Point classIdPoint;
                double confidence;
                minMaxLoc(scores, 0, &confidence, 0, &classIdPoint);
                if (confidence > confThreshold)
                {
                    int centerX = (int)(data[0] * frame.cols);
                    int centerY = (int)(data[1] * frame.rows);
                    int width = (int)(data[2] * frame.cols);
                    int height = (int)(data[3] * frame.rows);
                    int left = centerX - width / 2;
                    int top = centerY - height / 2;
 
classIds.push_back(classIdPoint.x);
confidences.push_back((float)confidence);
boxes.push_back(Rect(left, top, width, height));
                }
            }
        }
    }
    else
        CV_Error(Error::StsNotImplemented, "未知輸出層型別: " + outLayerType);
 
    // NMS 僅在 DNN_BACKEND_OPENCV 的 Region 層內部使用，對於其他後端，我們需要在示例中
    // 使用 NMS，或者當輸出數量 > 1 時需要 NMS
    if (outLayers.size() > 1 || (outLayerType == "Region" && backend != DNN_BACKEND_OPENCV))
    {
std::map<int, std::vector<size_t> > class2indices;
        for (size_t i = 0; i < classIds.size(); i++)
        {
            if (confidences[i] >= confThreshold)
            {
class2indices[classIds[i]].push_back(i);
            }
        }
std::vector<Rect> nmsBoxes;
std::vector<float> nmsConfidences;
std::vector<int> nmsClassIds;
        for (std::map<int, std::vector<size_t> >::iterator it = class2indices.begin(); it != class2indices.end(); ++it)
        {
std::vector<Rect> localBoxes;
std::vector<float> localConfidences;
std::vector<size_t> classIndices = it->second;
            for (size_t i = 0; i < classIndices.size(); i++)
            {
localBoxes.push_back(boxes[classIndices[i]]);
localConfidences.push_back(confidences[classIndices[i]]);
            }
std::vector<int> nmsIndices;
            NMSBoxes(localBoxes, localConfidences, confThreshold, nmsThreshold, nmsIndices);
            for (size_t i = 0; i < nmsIndices.size(); i++)
            {
                size_t idx = nmsIndices[i];
nmsBoxes.push_back(localBoxes[idx]);
nmsConfidences.push_back(localConfidences[idx]);
nmsClassIds.push_back(it->first);
            }
        }
boxes = nmsBoxes;
classIds = nmsClassIds;
confidences = nmsConfidences;
    }
 
    for (size_t idx = 0; idx < boxes.size(); ++idx)
    {
        Rect box = boxes[idx];
drawPred(classIds[idx], confidences[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame);
    }
}
 
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
{
    rectangle(frame, Point(left, top), Point(right, bottom), Scalar(0, 255, 0));
 
std::string label = format("%.2f", conf);
    if (!classes.empty())
    {
        CV_Assert(classId < (int)classes.size());
label = classes[classId] + ": " + label;
    }
 
    int baseLine;
    Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
 
top = max(top, labelSize.height);
    rectangle(frame, Point(left, top - labelSize.height),
              Point(left + labelSize.width, top + baseLine), Scalar::all(255), FILLED);
    putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.5, Scalar());
}
 
void callback(int pos, void*)
{
confThreshold = pos * 0.01f;
}