我正在尝试仅为 block 计算 HOG 特征。我探索了 opencv/module/gpu/src/ 下列出的 hog.cpp。下面是我更改为仅计算 block 特征的代码。

void cv::gpu::HOGDescriptor::getDescriptors(const GpuMat& img, Size win_stride, GpuMat& descriptors, int descr_format)
{
    CV_Assert(win_stride.width % block_stride.width == 0 && win_stride.height % block_stride.height == 0);

    computeBlockHistograms(img);
    // give block back

/*
    const size_t block_hist_size = getBlockHistogramSize();
    Size blocks_per_win = numPartsWithin(win_size, block_size, block_stride);
    Size wins_per_img   = numPartsWithin(img.size(), win_size, win_stride);

    descriptors.create(wins_per_img.area(), static_cast<int>(blocks_per_win.area() * block_hist_size), CV_32F); */

    switch (descr_format)
    {
    case DESCR_FORMAT_ROW_BY_ROW:
        hog::extract_descrs_by_rows(win_size.height, win_size.width, block_stride.height, block_stride.width,
                                    win_stride.height, win_stride.width, img.rows, img.cols, block_hists.ptr<float>(), descriptors);
        break;
    case DESCR_FORMAT_COL_BY_COL:
        hog::extract_descrs_by_cols(win_size.height, win_size.width, block_stride.height, block_stride.width,
                                    win_stride.height, win_stride.width, img.rows, img.cols, block_hists.ptr<float>(), descriptors);
        break;
    default:
        CV_Error(CV_StsBadArg, "Unknown descriptor format");
    }
}

这也是 computeBlockHistograms 代码。

void cv::gpu::HOGDescriptor::computeBlockHistograms(const GpuMat& img)
{
    computeGradient(img, grad, qangle);

    size_t block_hist_size = getBlockHistogramSize();
    Size blocks_per_img = numPartsWithin(img.size(), block_size, block_stride);

    //   block_hists.create(1, block_hist_size * blocks_per_img.area(), CV_32F);
    block_hists = getBuffer(1, static_cast<int>(block_hist_size * blocks_per_img.area()), CV_32F, block_hists_buf);

    hog::compute_hists(nbins, block_stride.width, block_stride.height, img.rows, img.cols,
                        grad, qangle, (float)getWinSigma(), block_hists.ptr<float>());

    hog::normalize_hists(nbins, block_stride.width, block_stride.height, img.rows, img.cols,
                         block_hists.ptr<float>(), (float)threshold_L2hys);
}

编辑:我还包括 hog.cpp

void cv::gpu::HOGDescriptor::getDescriptors(const GpuMat& img, Size win_stride, GpuMat& descriptors, int descr_format)
{
    CV_Assert(win_stride.width % block_stride.width == 0 && win_stride.height % block_stride.height == 0);

    computeBlockHistograms(img);

    const size_t block_hist_size = getBlockHistogramSize();
    Size blocks_per_win = numPartsWithin(win_size, block_size, block_stride);
    Size wins_per_img   = numPartsWithin(img.size(), win_size, win_stride);

    descriptors.create(wins_per_img.area(), static_cast<int>(blocks_per_win.area() * block_hist_size), CV_32F);

    switch (descr_format)
    {
    case DESCR_FORMAT_ROW_BY_ROW:
        hog::extract_descrs_by_rows(win_size.height, win_size.width, block_stride.height, block_stride.width,
                                    win_stride.height, win_stride.width, img.rows, img.cols, block_hists.ptr<float>(), descriptors);
        break;
    case DESCR_FORMAT_COL_BY_COL:
        hog::extract_descrs_by_cols(win_size.height, win_size.width, block_stride.height, block_stride.width,
                                    win_stride.height, win_stride.width, img.rows, img.cols, block_hists.ptr<float>(), descriptors);
        break;
    default:
        CV_Error(CV_StsBadArg, "Unknown descriptor format");
    }
}

谁能帮我获得仅 block 的 HOG 功能。 已编辑:我只对计算不同窗口大小的 HOG 特征感兴趣，同时保持单元格和 block 的特征相同。

最佳答案

我修改了以下函数以仅计算 block 的 HOG 描述符。

void cv::gpu::HOGDescriptor::getDescriptorsBlock(const GpuMat& img, Size win_stride, GpuMat& descriptors, FileStorage fs3, string fileName, double scale, int width, int height, size_t lev)
{
    CV_Assert(win_stride.width % block_stride.width == 0 && win_stride.height % block_stride.height == 0);

    size_t block_hist_size = getBlockHistogramSize();
    computeBlockHistograms(img);
    Size blocks_per_img = numPartsWithin(img.size(), block_size, block_stride);

    // Size blocks_per_win = numPartsWithin(win_size, block_size, block_stride);
    // Size wins_per_img   = numPartsWithin(img.size(), win_size, win_stride);

    // copy block_hists from GPU to CPU/

    float dest_ptr[block_hist_size * blocks_per_img.area()];

    cudaMemcpy( &dest_ptr[0], block_hists.ptr<float>(), block_hist_size *blocks_per_img.area()*sizeof(CV_32F),        cudaMemcpyDeviceToHost); 

    std::cout<<"( "<<width<< " ," << height<< ")"<< std::endl;
    std::cout <<lev<< std::endl;

    // write to yml file

    int level = lev;

    fs3<<"Scale"<<scale;
    fs3 <<"Level"<<level;
    fs3<<"Width"<<width<<"Height"<<height;
    fs3 << "features" << "[";
    for (unsigned int i = 0; i < (block_hist_size * blocks_per_img.area()) ; i++ )
    {
     fs3  << dest_ptr[i];
    }
    fs3 << "]";
}

下面是计算多尺度图像的 HOG 描述符。

void cv::gpu::HOGDescriptor::getDescriptorsMultiScale(const GpuMat& img,
                                              Size win_stride, double scale0, unsigned int count)
{

    CV_Assert(img.type() == CV_8UC1 || img.type() == CV_8UC4);

    vector<double> level_scale;
    double scale = 1.;
    int levels = 0;

    for (levels = 0; levels < nlevels; levels++)
    {
        level_scale.push_back(scale);
        if (cvRound(img.cols/scale) < win_size.width ||
            cvRound(img.rows/scale) < win_size.height || scale0 <= 1)
            break;
        scale *= scale0;
    }
    levels = std::max(levels, 1);
    level_scale.resize(levels);
    image_scales.resize(levels);

    // open yml file with image ID

    FileStorage fs3;
    char fileName[20];
    GpuMat descriptors;
    sprintf (fileName, "%04d", count);
    fs3.open(fileName, FileStorage::WRITE);

    for (size_t i = 0; i < level_scale.size(); i++)
    {
        scale = level_scale[i];
        Size sz(cvRound(img.cols / scale), cvRound(img.rows / scale));
        GpuMat smaller_img;

        if (sz == img.size())
            smaller_img = img;
        else
        {
            image_scales[i].create(sz, img.type());
            switch (img.type())
            {
                case CV_8UC1: hog::resize_8UC1(img, image_scales[i]); break;
                case CV_8UC4: hog::resize_8UC4(img, image_scales[i]); break;
            }
            smaller_img = image_scales[i];
        }
        std::cout<<"scale "<<level_scale[i]<<std::endl;

        // calculate descriptors for blocks 
        getDescriptorsBlock( smaller_img, win_stride, descriptors, fs3, fileName, scale, smaller_img.cols, smaller_img.rows, i);

        // detect(smaller_img, locations, hit_threshold, win_stride, padding);
    }
    // close yml file
    fs3.release();

} 

不要忘记在中添加这两个函数的定义 opencv/modules/gpu/include/opencv2/gpu/gpu.hpp

关于c++ - 仅 block 的 HoG 特征，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/31158790/