BoW算法及DBoW2库简介（二）

std::vector<double> compute_TF(cv::Mat& descriptors, cv::Mat& labels)
{
    std::vector<double> tf(Num_clu, 0.0);
    for (int i = 0; i < descriptors.rows; i++)
    {
        tf[labels.at<int>(i)] ++;
    }

    for (unsigned int i = 0; i < tf.size(); i++)
    {
        tf[i] /= (float)descriptors.rows;
    }
    return tf;
}

std::vector<double> comput_IDF(std::vector<cv::Mat>& descriptors, std::vector<cv::Mat> &labels)
{
    std::vector<double> idf(Num_clu, 1.0);

    for (unsigned int i = 0; i < descriptors.size(); i++)
    {
        std::vector<int> idf_tmp(Num_clu, 0);
        for (int j = 0; j < descriptors[i].rows; j++)
        {
            idf_tmp[labels[i].at<int>(j)] ++;
        }
        for (unsigned int j = 0; j < idf_tmp.size(); j++)
        {
            if (idf_tmp[j] != 0) idf[j] ++;
        }
    }

    for (unsigned int i = 0; i < idf.size(); i++)
    {
        idf[i] = log(Num_img / idf[i]);
    }

    return idf;
}

cv::Mat TrainingBowVector(cv::Mat & centers, std::vector<double>& IDF)
{
    cv::SurfFeatureDetector detector;
    cv::SurfDescriptorExtractor extractor;

    char image_name[50];
    std::vector<cv::Mat> descriptor_all;
    descriptor_all.reserve(Num_img);

    //Find the keypoints and compute the descriptors；
    for (int i = 1; i <= Num_img; i++)
    {
        std::cout << "I:" << i << std::endl;
        sprintf_s(image_name, "D:\DataBase\UKbench\TestImage\%d.jpg", i);
        cv::Mat image = cv::imread(image_name, 0);
        std::vector<cv::KeyPoint> keypoints;
        cv::Mat descriptors;
        detector.detect(image, keypoints);
        std::cout << "Keypoints:" << keypoints.size() << std::endl;
        extractor.compute(image, keypoints, descriptors);
        descriptor_all.push_back(descriptors);
    }

    //Get the training descriptors；
    std::cout << "Get the training descriptors." << std::endl;
    cv::Mat descriptor_train;
    for (int j = 0; j < Num_tra; j++)
        descriptor_train.push_back(descriptor_all[j]);

    cv::Mat labels_k;
    cv::kmeans(descriptor_train, Num_clu, labels_k, cv::TermCriteria(CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 100, 0.01)
        , 3, cv::KMEANS_PP_CENTERS, centers);

    const int tk = 1, Emax = INT_MAX;
    cv::KDTree T(centers, false);
    std::vector<cv::Mat> labels(Num_img);
    for (int i = 0; i < Num_img; i++)
    {
        cv::Mat descriptor_img = descriptor_all[i];
        for (int j = 0; j < descriptor_img.rows; j++)
        {
            std::vector<float> desc_vec(descriptor_img.row(j));
            std::vector<int> idx_tmp(tk);
            T.findNearest(desc_vec, tk, Emax, idx_tmp, cv::noArray(), cv::noArray());
            labels[i].push_back(idx_tmp[0]);
        }
    }

    std::cout << "Compute the TF-IDF." << std::endl;
    cv::Mat BowVec;
    //Compute the TF-IDF for each image;
    IDF = comput_IDF(descriptor_all, labels);
    for (int i = 0; i < Num_img; i++)
    {
        std::vector<double> TF = compute_TF(descriptor_all[i], labels[i]);
        cv::Mat BowVec_tmp;
        for (unsigned int j = 0; j < IDF.size(); j++)
        {
            BowVec_tmp.push_back(TF[j] * IDF[j]);
            //BowVec_tmp.push_back(TF[j]);
        }
        BowVec_tmp = BowVec_tmp.t();
        cv::normalize(BowVec_tmp, BowVec_tmp);
        BowVec.push_back(BowVec_tmp);
    }
    return BowVec;
}

void FrameRecog::ComputeBoW()
{
    //数据类型转换；
    vector<cv::Mat>vFrDesc = Converter::toDescriptorVector(Descriptors);
    //BowVec为BoW特征向量，FeatVec为正向索引；
    pORBVocabulary->transform(vFrDesc, BowVec, FeatVec, 4);
}



float score = pORBVocabulary->score(BowVec, vBowVec[i]);

int FrameRecog::FeatMatchByBoW( const int idx )
{
    int nmatches = 0;
    const int TH_LOW = 50;
    const int HISTO_LENGTH = 30;
    const int factor = 1.0f/HISTO_LENGTH;

    const DBoW2::FeatureVector &vFeatVecTD = vFeatVec[idx];
    const DBoW2::FeatureVector &vFeatVecCD = FeatVec; 

    DBoW2::FeatureVector::const_iterator TDit = vFeatVecTD.begin();
    DBoW2::FeatureVector::const_iterator CDit = vFeatVecCD.begin();
    DBoW2::FeatureVector::const_iterator TDend= vFeatVecTD.end();
    DBoW2::FeatureVector::const_iterator CDend= vFeatVecCD.end();

    while( TDit != TDend && CDit != CDend )
    {
               //first为单词的索引，second则对应为该单词索引下的ORB特征集合；
        if( TDit->first == CDit->first)
        {
　　　　　　　　//second是要循环的对象
            const vector<unsigned int> vIndicesTD = TDit->second;
            const vector<unsigned int> vIndicesCD = CDit->second;
　　　　　　　　　　　　　　
　　　　　　　　//循环关键帧和当前帧对应单词下的特征集合，计算相似性；
            for ( size_t iTD = 0; iTD < vIndicesTD.size(); iTD ++ )
            {
                const unsigned int realIdxTD = vIndicesTD[iTD];
                const cv::Mat &dTD = vDescriptors[idx].row(realIdxTD);

                int bestDist1 = 256;
                int bestIdxF  = -1;
                int bestDist2 = 256;

                for ( size_t iCD = 0; iCD < vIndicesCD.size(); iCD ++ )
                {
                    const unsigned int realIdxCD = vIndicesCD[iCD];
                    const cv::Mat &dCD = Descriptors.row(realIdxCD);
                    const int dist = DescriptorDistance(dTD, dCD);
　　　　　　　　　　　　　//这里注意是双阈值；
                    if( dist < bestDist1 )
                    {
                        bestDist2 = bestDist1;
                        bestDist1 = dist;
                        bestIdxF  = realIdxCD;
                    }
                    else if( dist < bestDist2 )
                    {
                        bestDist2 = dist;
                    }
                }

　　　　　　　　　　　//这里有两个输入参数，一个是TH_LOW，是指两个特征的最小距离阈值；
　　　　　　　　　　　//第二个是0.95，它是指相似特征的最小距离小于第二小距离的百分之九十五；
　　　　　　　　　　　//第二个参数的含义是，当该参数越接近于1时，该式越接近于成立，而越小时说明要求越高，
　　　　　　　　　　　//即最小距离远大于第二小距离，所以两特征是相似特征的概率非常大
                if(bestDist1 <= TH_LOW)
                {
                    if( static_cast<float>(bestDist1)<0.95 * static_cast<float>(bestDist2))
                        nmatches ++;
                }
            }
            TDit ++;
            CDit ++;
        }
        else if( TDit->first < CDit->first )
        {
            TDit = vFeatVecTD.lower_bound(CDit->first);
        }
        else
        {
            CDit = vFeatVecCD.lower_bound(TDit->first);
        }
    }

　　　//原函数中还有特征对应的3D地图点的输出，以及根据ORB特征的主方向进一步判断特征是否相似的代码，这里略去；
    return nmatches;
}

int FrameRecog::DescriptorDistance(const cv::Mat &a, const cv::Mat &b)
{
    const int *pa = a.ptr<int32_t>();
    const int *pb = b.ptr<int32_t>();

    int dist = 0;
    for ( int i = 0; i < 8; i ++, pa ++, pb ++ )
    {
        unsigned int v = *pa ^ *pb;
        v = v - ((v>>1) & 0x55555555);
        v = (v & 0x33333333) + ((v >> 2) & 0x33333333);
        dist += (((v + (v >> 4)) & 0xF0F0F0F) * 0x1010101) >> 24;
    }
    return dist;
}