samples/dnn/segmentation.cpp

#include <fstream>
#include <sstream>
 
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
 
#include "common.hpp"
 
std::string keys =
    "{ help h | | Print help message. }"
    "{ @alias | | 模型別名，用於從 models.yml 檔案中提取預處理引數。}"
    "{ zoo | models.yml | 包含預處理引數檔案的可選路徑 }"
    "{ 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 | | 模型原始框架的可選名稱。如果未設定，則自動檢測。}"
    "{ classes | | 包含類別名稱文字檔案的可選路徑。}"
    "{ colors | | 包含每個類別顏色文字檔案的可選路徑。"
                      "每種顏色由BGR通道順序的0到255的三個值表示。}"
    "{ 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）}";
 
using namespace cv;
using namespace dnn;
 
std::vector<std::string> classes;
std::vector<Vec3b> colors;
 
void showLegend();
 
void colorizeSegmentation(const Mat &score, Mat &segm);
 
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執行語義分割深度學習網路。");
    if (argc == 1 || parser.has("help"))
    {
parser.printMessage();
        return 0;
    }
 
    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");
    String model = findFile(parser.get<String>("model"));
    String config = findFile(parser.get<String>("config"));
    String framework = parser.get<String>("framework");
    int backendId = parser.get<int>("backend");
    int targetId = parser.get<int>("target");
 
    // 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, "檔案 " + file + " 未找到");
std::string line;
        while (std::getline(ifs, line))
        {
classes.push_back(line);
        }
    }
 
    // 開啟顏色檔案。
    if (parser.has("colors"))
    {
std::string file = parser.get<String>("colors");
std::ifstream ifs(file.c_str());
        if (!ifs.is_open())
            CV_Error(Error::StsError, "檔案 " + file + " 未找到");
std::string line;
        while (std::getline(ifs, line))
        {
std::istringstream colorStr(line.c_str());
 
            Vec3b color;
            for (int i = 0; i < 3 && !colorStr.eof(); ++i)
colorStr >> color[i];
colors.push_back(color);
        }
    }
 
    if (!parser.check())
    {
parser.printErrors();
        return 1;
    }
 
    CV_Assert(!model.empty());
Net net = readNet(model, config, framework);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
 
    // 建立一個視窗
    static const std::string kWinName = "OpenCV 中的深度學習語義分割";
    namedWindow(kWinName, WINDOW_NORMAL);
 
    VideoCapture cap;
    if (parser.has("input"))
cap.open(parser.get<String>("input"));
    else
cap.open(parser.get<int>("device"));
 
    // 處理幀。
    Mat frame, blob;
    while (waitKey(1) < 0)
    {
cap >> frame;
        if (frame.empty())
        {
            waitKey();
            break;
        }
 
        blobFromImage(frame, blob, scale, Size(inpWidth, inpHeight), mean, swapRB, false);
 
net.setInput(blob);
        Mat score = net.forward();
 
        Mat segm;
colorizeSegmentation(score, segm);
 
        resize(segm, segm, frame.size(), 0, 0, INTER_NEAREST);
        addWeighted(frame, 0.1, segm, 0.9, 0.0, frame);
 
        // 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 毫秒", t);
        putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
 
        imshow(kWinName, frame);
        if (!classes.empty())
showLegend();
    }
    return 0;
}
 
void colorizeSegmentation(const Mat &score, Mat &segm)
{
    const int rows = score.size[2];
    const int cols = score.size[3];
    const int chns = score.size[1];
 
    if (colors.empty())
    {
        // Generate colors.
colors.push_back(Vec3b());
        for (int i = 1; i < chns; ++i)
        {
            Vec3b color;
            for (int j = 0; j < 3; ++j)
color[j] = (colors[i - 1][j] + rand() % 256) / 2;
colors.push_back(color);
        }
    }
    else if (chns != (int)colors.size())
    {
        CV_Error(Error::StsError, format("輸出類別數量與"
                                         "顏色數量不匹配 (%d != %zu)", chns, colors.size()));
    }
 
    Mat maxCl = Mat::zeros(rows, cols, CV_8UC1);
    Mat maxVal(rows, cols, CV_32FC1, score.data);
    for (int ch = 1; ch < chns; ch++)
    {
        for (int row = 0; row < rows; row++)
        {
            const float *ptrScore = score.ptr<float>(0, ch, row);
uint8_t *ptrMaxCl = maxCl.ptr<uint8_t>(row);
            float *ptrMaxVal = maxVal.ptr<float>(row);
            for (int col = 0; col < cols; col++)
            {
                if (ptrScore[col] > ptrMaxVal[col])
                {
ptrMaxVal[col] = ptrScore[col];
ptrMaxCl[col] = (uchar)ch;
                }
            }
        }
    }
 
segm.create(rows, cols, CV_8UC3);
    for (int row = 0; row < rows; row++)
    {
        const uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
        Vec3b *ptrSegm = segm.ptr<Vec3b>(row);
        for (int col = 0; col < cols; col++)
        {
ptrSegm[col] = colors[ptrMaxCl[col]];
        }
    }
}
 
void showLegend();
{
    static const int kBlockHeight = 30;
    static Mat legend;
    if (legend.empty())
    {
        const int numClasses = (int)classes.size();
        if ((int)colors.size() != numClasses)
        {
            CV_Error(Error::StsError, format("輸出類別數量與"
                                             "標籤數量不匹配 (%zu != %zu)", colors.size(), classes.size()));
        }
legend.create(kBlockHeight * numClasses, 200, CV_8UC3);
        for (int i = 0; i < numClasses; i++)
        {
            Mat block = legend.rowRange(i * kBlockHeight, (i + 1) * kBlockHeight);
block.setTo(colors[i]);
            putText(block, classes[i], Point(0, kBlockHeight / 2), FONT_HERSHEY_SIMPLEX, 0.5, Vec3b(255, 255, 255));
        }
        namedWindow("圖例", WINDOW_NORMAL);
        imshow("圖例", legend);
    }
}