加速这一段代码例程#include <thread> #include <mutex> // 用于保护m_vpdEdgePoints和m_vdEdgeGradient的锁 std::mutex g_mutex; void process_edges(const cv::Mat& RoiMat, const std::vectorcv::Point2d& m_vpdEquinoxPoints, const double m_dMeasureLength, const double m_dMeasureHeight, const double m_dSigma, const int m_nThresholdCircle, const int m_nTranslationCircle, const std::vector<double>& m_vdMeasureAngle, std::vectorcv::Point2d& m_vpdEdgePoints, std::vector<double>& m_vdEdgeGradient, int start_idx, int end_idx, Extract1DEdgeCircle Extract1DEdgeCircle) { std::vector<Edge1D_Result> edges; for (int i = start_idx; i < end_idx; i++) { edges = Extract1DEdgeCircle.Get1DEdge(RoiMat, m_vpdEquinoxPoints[i], m_dMeasureLength, m_dMeasureHeight,m_vdMeasureAngle[i], m_dSigma, m_nThresholdCircle, m_nTranslationCircle == 1 ? Translation::Poisitive : Translation::Negative, Selection::Strongest); // 使用锁保护m_vpdEdgePoints和m_vdEdgeGradient //std::lock_guardstd::mutex lock(g_mutex); for (int j = 0; j < edges.size(); j++) { m_vpdEdgePoints.push_back(edges[j].m_pdEdgePoint); m_vdEdgeGradient.push_back(edges[j].m_dGradient); } } } int main() { int m = m_vpdEquinoxPoints.size(); const int num_threads = 10; std::vectorstd::thread threads(num_threads); std::vectorstd::vectorcv::Point2d edge_points(num_threads); std::vector<std::vector<double>> edge_gradients(num_threads); for (int i = 0; i < num_threads; i++) { int start_idx = i * m / num_threads; int end_idx = (i + 1) * m / num_threads; threads[i] = std::thread(process_edges, std::ref(RoiMat), std::ref(m_vpdEquinoxPoints), m_dMeasureLength, m_dMeasureHeight, m_dSigma, m_nThresholdCircle, m_nTranslationCircle, std::ref(m_vdMeasureAngle), std::ref(edge_points[i]), std::ref(edge_gradients[i]), start_idx, end_idx, Extract1DEdgeCircle); } for (int i = 0; i < num_threads; i++) { threads[i].join(); // 合并结果 m_vpdEdgePoints.insert(m_vpdEdgePoints.end(), edge_points[i].begin(), edge_points[i].end()); m_vdEdgeGradient.insert(m_vdEdgeGradient.end(), edge_gradients[i].begin(), edge_gradients[i].end()); } return 0; }

可以尝试使用 OpenMP 或者 TBB 等并行编程库来进行加速。具体实现方式如下：

1. 使用 OpenMP

在循环中添加 `#pragma omp parallel for` 来开启并行化，代码如下：

void process_edges(const cv::Mat& RoiMat, const std::vector<cv::Point2d>& m_vpdEquinoxPoints, const double m_dMeasureLength, const double m_dMeasureHeight, const double m_dSigma, const int m_nThresholdCircle, const int m_nTranslationCircle, const std::vector<double>& m_vdMeasureAngle, std::vector<cv::Point2d>& m_vpdEdgePoints, std::vector<double>& m_vdEdgeGradient, int start_idx, int end_idx, Extract1DEdgeCircle Extract1DEdgeCircle) {
    std::vector<Edge1D_Result> edges;
    #pragma omp parallel for
    for (int i = start_idx; i < end_idx; i++) {
        edges = Extract1DEdgeCircle.Get1DEdge(RoiMat, m_vpdEquinoxPoints[i], m_dMeasureLength, m_dMeasureHeight,m_vdMeasureAngle[i], m_dSigma, m_nThresholdCircle, m_nTranslationCircle == 1 ? Translation::Poisitive : Translation::Negative, Selection::Strongest);
        // 使用锁保护m_vpdEdgePoints和m_vdEdgeGradient
        std::lock_guard<std::mutex> lock(g_mutex);
        for (int j = 0; j < edges.size(); j++) {
            m_vpdEdgePoints.push_back(edges[j].m_pdEdgePoint);
            m_vdEdgeGradient.push_back(edges[j].m_dGradient);
        }
    }
}

int main() {
    int m = m_vpdEquinoxPoints.size();
    const int num_threads = 10;
    std::vector<std::vector<cv::Point2d>> edge_points(num_threads);
    std::vector<std::vector<double>> edge_gradients(num_threads);

    #pragma omp parallel num_threads(num_threads)
    {
        int tid = omp_get_thread_num();
        int start_idx = tid * m / num_threads;
        int end_idx = (tid + 1) * m / num_threads;
        process_edges(RoiMat, m_vpdEquinoxPoints, m_dMeasureLength, m_dMeasureHeight, m_dSigma, m_nThresholdCircle, m_nTranslationCircle, m_vdMeasureAngle, edge_points[tid], edge_gradients[tid], start_idx, end_idx, Extract1DEdgeCircle);
    }

    // 合并结果
    for (int i = 0; i < num_threads; i++) {
        m_vpdEdgePoints.insert(m_vpdEdgePoints.end(), edge_points[i].begin(), edge_points[i].end());
        m_vdEdgeGradient.insert(m_vdEdgeGradient.end(), edge_gradients[i].begin(), edge_gradients[i].end());
    }

    return 0;
}

2. 使用 TBB

在循环中使用 `tbb::parallel_for` 来开启并行化，代码如下：

#include <tbb/parallel_for.h>

void process_edges(const cv::Mat& RoiMat, const std::vector<cv::Point2d>& m_vpdEquinoxPoints, const double m_dMeasureLength, const double m_dMeasureHeight, const double m_dSigma, const int m_nThresholdCircle, const int m_nTranslationCircle, const std::vector<double>& m_vdMeasureAngle, std::vector<cv::Point2d>& m_vpdEdgePoints, std::vector<double>& m_vdEdgeGradient, int start_idx, int end_idx, Extract1DEdgeCircle Extract1DEdgeCircle) {
    std::vector<Edge1D_Result> edges;
    tbb::parallel_for(start_idx, end_idx, [&](int i) {
        edges = Extract1DEdgeCircle.Get1DEdge(RoiMat, m_vpdEquinoxPoints[i], m_dMeasureLength, m_dMeasureHeight,m_vdMeasureAngle[i], m_dSigma, m_nThresholdCircle, m_nTranslationCircle == 1 ? Translation::Poisitive : Translation::Negative, Selection::Strongest);
        // 使用锁保护m_vpdEdgePoints和m_vdEdgeGradient
        std::lock_guard<std::mutex> lock(g_mutex);
        for (int j = 0; j < edges.size(); j++) {
            m_vpdEdgePoints.push_back(edges[j].m_pdEdgePoint);
            m_vdEdgeGradient.push_back(edges[j].m_dGradient);
        }
    });
}

int main() {
    int m = m_vpdEquinoxPoints.size();
    const int num_threads = 10;
    std::vector<std::vector<cv::Point2d>> edge_points(num_threads);
    std::vector<std::vector<double>> edge_gradients(num_threads);

    tbb::parallel_for(0, num_threads, [&](int tid) {
        int start_idx = tid * m / num_threads;
        int end_idx = (tid + 1) * m / num_threads;
        process_edges(RoiMat, m_vpdEquinoxPoints, m_dMeasureLength, m_dMeasureHeight, m_dSigma, m_nThresholdCircle, m_nTranslationCircle, m_vdMeasureAngle, edge_points[tid], edge_gradients[tid], start_idx, end_idx, Extract1DEdgeCircle);
    });

    // 合并结果
    for (int i = 0; i < num_threads; i++) {
        m_vpdEdgePoints.insert(m_vpdEdgePoints.end(), edge_points[i].begin(), edge_points[i].end());
        m_vdEdgeGradient.insert(m_vdEdgeGradient.end(), edge_gradients[i].begin(), edge_gradients[i].end());
    }

    return 0;
}

需要注意的是，在使用锁时，应该使用 `std::lock_guard<std::mutex>` 或者 `std::unique_lock<std::mutex>` 来保护临界区域。