fps视觉跟踪基准

于 2021-05-08 09:41:19 发布
阅读量401 收藏
点赞数
文章标签： 神经网络 深度学习 pytorch
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_45665426/article/details/116518001
版权

在OTB工具箱中将以下文件复制替换
这里是genperfMat.m

function genPerfMat(seqs, trackers, evalType, nameTrkAll, perfMatPath)

pathAnno = './anno/';
numTrk = length(trackers);

thresholdSetOverlap = 0:0.05:1;
thresholdSetError = 0:50;

switch evalType
    case 'SRE'
        rpAll=['.\results\results_SRE\'];
    case {'TRE'}
        rpAll=['.\results\results_TRE\'];
    case {'OPE'}
        rpAll=['.\results\results_OPE_CVPR13\'];
end

for idxSeq=1:length(seqs)
    s = seqs{idxSeq};
    
    s.len = s.endFrame - s.startFrame + 1;
    s.s_frames = cell(s.len,1);
    nz	= strcat('%0',num2str(s.nz),'d'); %number of zeros in the name of image
    for i=1:s.len
        image_no = s.startFrame + (i-1);
        id = sprintf(nz,image_no);
        s.s_frames{i} = strcat(s.path,id,'.',s.ext);
    end
    
    rect_anno = dlmread([pathAnno s.name '.txt']);
    numSeg = 20;
    [subSeqs, subAnno]=splitSeqTRE(s,numSeg,rect_anno);
    
    nameAll=[];
    for idxTrk=1:numTrk
        
        t = trackers{idxTrk};
        %         load([rpAll s.name '_' t.name '.mat'], 'results','coverage','errCenter');
        
        load([rpAll s.name '_' t.name '.mat'])
        disp([s.name ' ' t.name]);
        
        aveCoverageAll=[];
        aveErrCenterAll=[];
        errCvgAccAvgAll = 0;
        errCntAccAvgAll = 0;
        errCoverageAll = 0;
        errCenterAll = 0;
        
        lenALL = 0;
        
        switch evalType
            case 'SRE'
                idxNum = length(results);
                anno=subAnno{1};
            case 'TRE'
                idxNum = length(results);
            case 'OPE'
                idxNum = 1;
                anno=subAnno{1};
        end
        
        successNumOverlap = zeros(idxNum,length(thresholdSetOverlap));
        successNumErr = zeros(idxNum,length(thresholdSetError));
        
        for idx = 1:idxNum
            
            res = results{idx};
            
            if strcmp(evalType, 'TRE')
                anno=subAnno{idx};
            end
            
            len = size(anno,1);
            
            if isempty(res.res)
                break;
            end
            
            if ~isfield(res,'type')&&isfield(res,'transformType')
                res.type = res.transformType;
                res.res = res.res';
            end
            
            [aveCoverage, aveErrCenter, errCoverage, errCenter] = calcSeqErrRobust(res, anno);
            
            for tIdx=1:length(thresholdSetOverlap)
                successNumOverlap(idx,tIdx) = sum(errCoverage >thresholdSetOverlap(tIdx));
            end
            
            for tIdx=1:length(thresholdSetError)
                successNumErr(idx,tIdx) = sum(errCenter <= thresholdSetError(tIdx));
            end
            
            %%%
            fpsTrk(idx) = res.fps;
            
            lenALL = lenALL + len;
            
        end
        
        
        if strcmp(evalType, 'OPE')
            aveSuccessRatePlot(idxTrk, idxSeq,:) = successNumOverlap/(lenALL+eps);
            aveSuccessRatePlotErr(idxTrk, idxSeq,:) = successNumErr/(lenALL+eps);
            
            %%%
            aveFps(idxTrk, idxSeq) = fpsTrk;
            
        else
            aveSuccessRatePlot(idxTrk, idxSeq,:) = sum(successNumOverlap)/(lenALL+eps);
            aveSuccessRatePlotErr(idxTrk, idxSeq,:) = sum(successNumErr)/(lenALL+eps);
            
            %%%
            aveFps(idxTrk, idxSeq) = fpsTrk/idxNum;
            
        end
        
    end
end
%
dataName1=[perfMatPath 'aveSuccessRatePlot_' num2str(numTrk) 'alg_overlap_' evalType '.mat'];
save(dataName1,'aveSuccessRatePlot','nameTrkAll');

dataName2=[perfMatPath 'aveSuccessRatePlot_' num2str(numTrk) 'alg_error_' evalType '.mat'];
aveSuccessRatePlot = aveSuccessRatePlotErr;
save(dataName2,'aveSuccessRatePlot','nameTrkAll');

dataName3=[perfMatPath 'aveFps_' num2str(numTrk) 'alg_' evalType '.mat'];
save(dataName3,'aveFps','nameTrkAll');

这里是perfPlot.m

clear
close all;
clc

addpath('./util');

attPath = '.\anno\att\'; % The folder that contains the annotation files for sequence attributes

% attName={'illumination variation'	'out-of-plane rotation'	'scale variation'	'occlusion'	'deformation'	'motion blur'	'fast motion'	'in-plane rotation'	'out of view'	'background clutter' 'low resolution'};
% 
% attFigName={'illumination_variations'	'out-of-plane_rotation'	'scale_variations'	'occlusions'	'deformation'	'blur'	'abrupt_motion'	'in-plane_rotation'	'out-of-view'	'background_clutter' 'low_resolution'};
%UAV123
attName={'Scale Variation' 'Aspect Ratio Change' 'Low Resolution' 'Fast Motion' 'Full Occlusion' 'Partial Occlusion' 'Out-of-View' 'Background Clutter' 'Illumination Variation' 'Viewpoint Change' 'Camera Motion' 'Similar Object'};
attFigName={'SV'	'ARC'	'LR'	'FM'	'FOC'	'POC'	'OV'	'BC'	'IV'	'VC'	'CM'	'SOB'};


plotDrawStyleAll={   struct('color',[1,0,0],'lineStyle','-'),...
    struct('color',[0,1,0],'lineStyle','-'),...
    struct('color',[0,0,1],'lineStyle','-'),...
    struct('color',[0,0,0],'lineStyle','-'),...%    struct('color',[1,1,0],'lineStyle','-'),...%yellow
    struct('color',[1,0,1],'lineStyle','-'),...%pink
    struct('color',[0,1,1],'lineStyle','-'),...
    struct('color',[0.5,0.5,0.5],'lineStyle','-'),...%gray-25%
    struct('color',[136,0,21]/255,'lineStyle','-'),...%dark red
    struct('color',[255,127,39]/255,'lineStyle','-'),...%orange
    struct('color',[0,162,232]/255,'lineStyle','-'),...%Turquoise
    struct('color',[163,73,164]/255,'lineStyle','-'),...%purple    %%%%%%%%%%%%%%%%%%%%
    struct('color',[1,0,0],'lineStyle','--'),...
    struct('color',[0,1,0],'lineStyle','--'),...
    struct('color',[0,0,1],'lineStyle','--'),...
    struct('color',[0,0,0],'lineStyle','--'),...%    struct('color',[1,1,0],'lineStyle','--'),...%yellow
    struct('color',[1,0,1],'lineStyle','--'),...%pink
    struct('color',[0,1,1],'lineStyle','--'),...
    struct('color',[0.5,0.5,0.5],'lineStyle','--'),...%gray-25%
    struct('color',[136,0,21]/255,'lineStyle','--'),...%dark red
    struct('color',[255,127,39]/255,'lineStyle','--'),...%orange
    struct('color',[0,162,232]/255,'lineStyle','--'),...%Turquoise
    struct('color',[163,73,164]/255,'lineStyle','--'),...%purple    %%%%%%%%%%%%%%%%%%%
    struct('color',[1,0,0],'lineStyle','-.'),...
    struct('color',[0,1,0],'lineStyle','-.'),...
    struct('color',[0,0,1],'lineStyle','-.'),...
    struct('color',[0,0,0],'lineStyle','-.'),...%    struct('color',[1,1,0],'lineStyle',':'),...%yellow
    struct('color',[1,0,1],'lineStyle','-.'),...%pink
    struct('color',[0,1,1],'lineStyle','-.'),...
    struct('color',[0.5,0.5,0.5],'lineStyle','-.'),...%gray-25%
    struct('color',[136,0,21]/255,'lineStyle','-.'),...%dark red
    struct('color',[255,127,39]/255,'lineStyle','-.'),...%orange
    struct('color',[0,162,232]/255,'lineStyle','-.'),...%Turquoise
    struct('color',[163,73,164]/255,'lineStyle','-.'),...%purple
    };

plotDrawStyle10={   struct('color',[1,0,0],'lineStyle','-'),...
    struct('color',[0,1,0],'lineStyle','--'),...
    struct('color',[0,0,1],'lineStyle',':'),...
    struct('color',[0,0,0],'lineStyle','-'),...%    struct('color',[1,1,0],'lineStyle','-'),...%yellow
    struct('color',[1,0,1],'lineStyle','--'),...%pink
    struct('color',[0,1,1],'lineStyle',':'),...
    struct('color',[0.5,0.5,0.5],'lineStyle','-'),...%gray-25%
    struct('color',[136,0,21]/255,'lineStyle','--'),...%dark red
    struct('color',[255,127,39]/255,'lineStyle',':'),...%orange
    struct('color',[0,162,232]/255,'lineStyle','-'),...%Turquoise
    };

seqs=configSeqs;

trackers=configTrackers;

% seqs = seqs(1:10);
% trackers = trackers(1:10);

numSeq=length(seqs);
numTrk=length(trackers);

nameTrkAll=cell(numTrk,1);
for idxTrk=1:numTrk
    t = trackers{idxTrk};
    nameTrkAll{idxTrk}=t.namePaper;
end

nameSeqAll=cell(numSeq,1);
numAllSeq=zeros(numSeq,1);

att=[];
for idxSeq=1:numSeq
    s = seqs{idxSeq};
    nameSeqAll{idxSeq}=s.name;
    
    s.len = s.endFrame - s.startFrame + 1;
    
    numAllSeq(idxSeq) = s.len;
    
    att(idxSeq,:)=load([attPath s.name '.txt']);
end

attNum = size(att,2);

figPath = '.\figs\overall\';

perfMatPath = '.\perfMat\overall\';

if ~exist(figPath,'dir')
    mkdir(figPath);
end

metricTypeSet = {'error', 'overlap'};
evalTypeSet = {'OPE', 'TRE', 'SRE'};

rankingType = 'AUC';%AUC->success, threshold->precision

rankNum = 14;%number of plots to show

if rankNum == 10
    plotDrawStyle=plotDrawStyle10;
else
    plotDrawStyle=plotDrawStyleAll;
end

thresholdSetOverlap = 0:0.05:1;
thresholdSetError = 0:50;

for i=1:length(metricTypeSet)
    metricType = metricTypeSet{i};%error,overlap
    
    switch metricType
        case 'overlap'
            thresholdSet = thresholdSetOverlap;
            rankIdx = 11;
            xLabelName = 'Overlap threshold';
            yLabelName = 'Success rate';
        case 'error'
            thresholdSet = thresholdSetError;
            rankIdx = 21;
            xLabelName = 'Location error threshold';
            yLabelName = 'Precision rate';
    end  
        
    if strcmp(metricType,'error')&strcmp(rankingType,'AUC')
        continue;
    end
    
    tNum = length(thresholdSet);
    
    for j=1:length(evalTypeSet)
        
        evalType = evalTypeSet{j};%SRE, TRE, OPE
        
        plotType = [metricType '_' evalType];
        
        switch metricType
            case 'overlap'
                titleName = ['Success plots of ' evalType];
            case 'error'
                titleName = ['Precision plots of ' evalType];
        end

        dataName = [perfMatPath 'aveSuccessRatePlot_' num2str(numTrk) 'alg_'  plotType '.mat'];
        
        %%%
        dataNameFps = [perfMatPath 'aveFps_' num2str(numTrk) 'alg_'  evalType '.mat'];
        
        % If the performance Mat file, dataName, does not exist, it will call
        % genPerfMat to generate the file.
        if ~exist(dataName)
            genPerfMat(seqs, trackers, evalType, nameTrkAll, perfMatPath);
        end        
        
        load(dataName);
        
        %%%
        load(dataNameFps);
        
        
        numTrk = size(aveSuccessRatePlot,1);        
        
        if rankNum > numTrk | rankNum <0
            rankNum = numTrk;
        end
        
        figName= [figPath 'quality_plot_' plotType '_' rankingType];
        idxSeqSet = 1:length(seqs);
        
        % draw and save the overall performance plot
        plotDrawSave(numTrk,plotDrawStyle,aveSuccessRatePlot,aveFps,idxSeqSet,rankNum,rankingType,rankIdx,nameTrkAll,thresholdSet,titleName, xLabelName,yLabelName,figName,metricType);
        
        % draw and save the performance plot for each attribute
        attTrld = 0;
        for attIdx=1:attNum
            
            idxSeqSet=find(att(:,attIdx)>attTrld);
            
            if length(idxSeqSet) < 2
                continue;
            end
            disp([attName{attIdx} ' ' num2str(length(idxSeqSet))])
            
            figName=[figPath attFigName{attIdx} '_'  plotType '_' rankingType];
            titleName = ['Plots of ' evalType ': ' attName{attIdx} ' (' num2str(length(idxSeqSet)) ')'];
            
            switch metricType
                case 'overlap'
                    titleName = ['Success plots of ' evalType ' - ' attName{attIdx} ' (' num2str(length(idxSeqSet)) ')'];
                case 'error'
                    titleName = ['Precision plots of ' evalType ' - ' attName{attIdx} ' (' num2str(length(idxSeqSet)) ')'];
            end
            plotDrawSave(numTrk,plotDrawStyle,aveSuccessRatePlot,aveFps,idxSeqSet,rankNum,rankingType,rankIdx,nameTrkAll,thresholdSet,titleName, xLabelName,yLabelName,figName,metricType);
        end        
    end
end

这里是plotDrawSave.m

function plotDrawSave(numTrk,plotDrawStyle,aveSuccessRatePlot,aveFps,idxSeqSet,rankNum,rankingType,rankIdx,nameTrkAll,thresholdSet,titleName,xLabelName,yLabelName,figName,metricType)

aveSuccessRate11=[];

scrsz = get(0,'ScreenSize');

for idxTrk=1:numTrk
    %each row is the sr plot of one sequence
    tmp=aveSuccessRatePlot(idxTrk, idxSeqSet,:);
    aa=reshape(tmp,[length(idxSeqSet),size(aveSuccessRatePlot,3)]);
    aa=aa(sum(aa,2)>eps,:);
    bb=mean(aa);
    switch rankingType
        case 'AUC'
            perf(idxTrk) = mean(bb);
        case 'threshold'
            perf(idxTrk) = bb(rankIdx);
    end
end

[tmp,indexSort]=sort(perf,'descend');

i=1;
AUC=[];

fontSize = 16;
fontSizeLegend = 10;

figure1 = figure;

axes1 = axes('Parent',figure1,'FontSize',14);

%%%
fpsTrk = mean(aveFps,2);


for idxTrk=indexSort(1:rankNum)

    tmp=aveSuccessRatePlot(idxTrk,idxSeqSet,:);
    aa=reshape(tmp,[length(idxSeqSet),size(aveSuccessRatePlot,3)]);
    aa=aa(sum(aa,2)>eps,:);
    bb=mean(aa);
    
    switch rankingType
        case 'AUC'
            score = mean(bb);
            tmp=sprintf('%.3f', score);
        case 'threshold'
            score = bb(rankIdx);
            tmp=sprintf('%.3f', score);
    end
    
    %%%
    fps = sprintf('%.2f', fpsTrk(idxTrk));
    tmpName{i} = [nameTrkAll{idxTrk} ' [' tmp ']-' fps 'fps'];
    
%     tmpName{i} = [nameTrkAll{idxTrk} ' [' tmp ']'];
    h(i) = plot(thresholdSet,bb,'color',plotDrawStyle{i}.color, 'lineStyle', plotDrawStyle{i}.lineStyle,'lineWidth', 4,'Parent',axes1);
    hold on
    i=i+1;
end


legend1=legend(tmpName,'Interpreter', 'none','fontsize',fontSizeLegend);
title(titleName,'fontsize',fontSize);
xlabel(xLabelName,'fontsize',fontSize);
ylabel(yLabelName,'fontsize',fontSize);
% legend1=legend(tmpName(1:round(length(tmpName)/2)),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','NorthWest');
% legend2=legend(tmpName(round(length(tmpName)/2)+1:end),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','SouthEast');

%for too many
%plots--------------------------------------------------------------

% switch metricType
%     case 'error'
%         ah1 = gca;
%         %         legend1=legend(ah1,h(1:round(length(tmpName)/2)),tmpName(1:round(length(tmpName)/2)),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','NorthWest');
%         legend1=legend(ah1,h(1:5),tmpName(1:5),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','NorthWest');
%         
%         title(titleName,'fontsize',fontSize);
%         xlabel(xLabelName,'fontsize',fontSize);
%         ylabel(yLabelName,'fontsize',fontSize);
%         
%         ah2=axes('position',get(gca,'position'), 'visible','off');
%         legend2=legend(ah2,h(6:end),tmpName(6:end),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','SouthEast');
%     case 'overlap'
%         ah1 = gca;
%         legend1=legend(ah1,h(1:5),tmpName(1:5),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','NorthEast');
%         title(titleName,'fontsize',fontSize);
%         xlabel(xLabelName,'fontsize',fontSize);
%         ylabel(yLabelName,'fontsize',fontSize);
%         
%         ah2=axes('position',get(gca,'position'), 'visible','off');
%         legend2=legend(ah2,h(6:end),tmpName(6:end),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','SouthWest');
% end

%     switch metricType
%         case 'error'
%             ah1 = gca;
%             %         legend1=legend(ah1,h(1:round(length(tmpName)/2)),tmpName(1:round(length(tmpName)/2)),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','NorthWest');
% %             legend1=legend(ah1,h(1:round(length(tmpName)/2)),tmpName(1:round(length(tmpName)/2)),'Interpreter', 'none','fontsize',fontSizeLegend,'Position',[0.55 0.1 0.1 0.4]);
% 
%             legend1=legend(ah1,h,tmpName,'Interpreter', 'none','fontsize',fontSizeLegend,'Location','SouthEast');
%             title(titleName,'fontsize',fontSize);
%             xlabel(xLabelName,'fontsize',fontSize);
%             ylabel(yLabelName,'fontsize',fontSize);
% 
% %             ah2=axes('position',get(gca,'position'), 'visible','off');
% %             legend2=legend(ah2,h(round(length(tmpName)/2)+1:end),tmpName(round(length(tmpName)/2)+1:end),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','SouthEast');
%         case 'overlap'
%             ah1 = gca;
% %             legend1=legend(ah1,h(1:round(length(tmpName)/2)),tmpName(1:round(length(tmpName)/2)),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','NorthEast');
%             legend1=legend(ah1,h,tmpName,'Interpreter', 'none','fontsize',fontSizeLegend,'Location','SouthWest');
%             title(titleName,'fontsize',fontSize);
%             xlabel(xLabelName,'fontsize',fontSize);
%             ylabel(yLabelName,'fontsize',fontSize);
% 
% %             ah2=axes('position',get(gca,'position'), 'visible','off');
% %             legend2=legend(ah2,h(round(length(tmpName)/2)+1:end),tmpName(round(length(tmpName)/2)+1:end),'Interpreter', 'none','fontsize',fontSizeLegend,'Location','SouthWest');
%     end
%     
%     axes('fontsize',14);
%     set(legend1,'FontSize',fontSizeLegend);
%     set(legend2,'FontSize',fontSizeLegend);
%     set(legend1,'Interpreter','none',...
%     'Position',[0.800694444444435 0.117313517441224 0.0984375 0.521055753262159],...
%     'FontSize',fontSizeLegend);
hold off

saveas(gcf,figName,'png');

end
Mr-Trying
关注
OTB 2013 使用教程
Shmilysi的博客
11-25 1万+
下载完benchmark后会看到在文件中包含4个.m文件，main_running.m、perfPlot.m、genPerfMat.m、drawResultBB.m 第一种： 1 把自己的算法放到benchmark的文件夹trackers中。 2 打开main_running.m文件，在14和16行 分别打开configSeqs.m文件和configTrackers.m文件。conf
OTB使用教程
omgxxg的博客
04-01 4364
OTB使用教程 一、OTB使用教程，不加入自己代码之前也能一次性成功出结果 下载压缩后的otb文件我们主要关注下面这几个文件 1 configSeqs.m主要选择测试视频，需要注意以下几点 为了测试方便我们最好自己新建一个语句，至少保留两个视频用于测试，太多会使后面运行main_running.m函数过慢，太少会导致后面运行perfPlot.m报下面的错误 有下标的赋值维度不匹配。出错 pl...
ECO跑UAV数据集填坑
Jabber_Jagger的博客
03-03 533
ECO跑UAV数据集填坑 首先有读懂以下解决方案的基础： https://blog.csdn.net/qq_33970986/article/details/105496382 按照这种方式修改之后，仍然出现error 遇到这种情况，主要是因为tracker中最后一行[seq, results] = get_sequence_results(seq)的问题，打开这个函数， function [seq, results] = get_sequence_results(seq) % »ñÈ¡Ðò
【DDFD】《Multi-view Face Detection Using Deep Convolutional Neural Networks》
bryant_meng
03-14 661
ICMR-2015 International Conference on Multimedia Retrieval 计算机图形学与多媒体 B 类会议 文章目录1 Background and Motivation2 Advantages / Contributions3 Method4 Experiments4.1 Datasets4.2 Comparison with R-CNN5 C...
tracker_benchmark的perfPlot函数解析
zh_ch_yu的博客
04-27 1604
这个函数主要实在使用数据集跑完自己的算法之后，利用统计的结果进行画图的函数 前面会先定义一些东西，比如： metricTypeSet = { ‘overlap’}; valTypeSet = {‘OPE’}; 等等，这些参数后面都会用到。 函数的主体从这里开始： for i=1:length(metricTypeSet) 一般metricTypeSet当中有error,overlap两个属性，是精...
Overlap
weixin_34258782的博客
07-16 546
Open the images in ImageJ Adjust the contrast if neceesary: Image/Adjust/BrightnessConstrast Change or check all Images are in 8-bit format. Image/Type/8-bit Image/Color/Merge Channels and the Me...
大数据技术分享 Spark技术讲座 基于视觉机器的基准标记跟踪 共23页.pdf
最新发布
07-18
### 大数据技术分享：Spark技术讲座与基于视觉机器的基准标记跟踪 #### 一、引言 在当今数字化时代，大数据技术的应用日益广泛，它不仅推动了信息技术的进步，也为科学研究提供了强有力的支持。本篇文章将从一个...
HOOT: 严重遮挡目标跟踪基准
48300HOOT: 重遮挡目标跟踪基准0Gozde Sahin南加州大学洛杉矶分校0gsahin@usc.edu0Laurent Itti南加州大学洛杉矶分校0itti@usc.edu0摘要0在本文中，我们介绍了 HOOT，即 H eavy O cclusions inO bject T...
CDTB：一个RGB-D视觉目标跟踪数据集和基准
10013CDTB：一个颜色和... fri.uni-lj.si摘要提出了一种新的颜色和深度通用视觉目标跟踪基准（CDTB）。CDTB由几种被动和主动RGB-D设置记录，包含在阳光直射下采集的室内和室外序列。CDTB数据集是用于RGB-D跟踪的最大和
BCOT：无标记高精度3D物体跟踪基准
66970BCOT：一种无标记高精度3D物体跟踪基准0Jiachen Li 1，Bin Wang 1，Shiqiang Zhu 2，Xin Cao 1，Fan Zhong 1，Wenxuan Chen 2，Te Li 2 *，Jason Gu3和Xueying Qin 1 *01山东大学2浙江实验...
不需配置OTB_benchmark，也能得到你想要的结果
weixin_41809552的博客
12-21 437
@# 本文以2015_CVPR_DAT_USABLE算法为例，在使用其他算法时，在相应处做修改即可。 `` clear;clc; close all; %将2015_CVPR_DAT_USABLE算法使用的文件添加进来 addpath(’.\src’); %数据集路径路径 base_path = ‘F:\my_second_paper_result\files_used_for_my_seco...
otb 数据集评估代码注释
论文学习笔记-《Fast Online Object Tracking and Segmentation- A Unifying Approach》
04-16 2352
main_running.m
python中图例legend标签内容_关于python 的legend图例,参数使用说明
weixin_39640911的博客
11-20 814
刚才画散点图要用到图例，可是matplotlib.pyplot.plot(x,y,'.')画出的散点图中图例是两个点（因为plot默认画的是线，需要两个端点来表示线，所以是两个点），matplotlib.pyplot.scatter(x,y,'.')画出的散点图中图例是三个点（这个我理解不了为什么，scatter散点的大小可以自己设置，我猜可能跟这个有关）。我画两个例子，大家看看。import n...
近几年目标跟踪算法发展综述（中）
热门推荐
00_00_07
04-19 2万+
2014 今年可谓是算法发展的一年，今年的主要的亮点就是相关滤波CF类算法。 在介绍各个算法之前不得不介绍一下今年的一个新的标准VOT【VOT】的问世，VOT选取了25个序列集，使用的标准和Benchmark有略微的差别，使用精度，鲁棒性，总的误差率，速度等。接下来介绍今年的论文 High-Speed Tracking with Kernelized Correlation Filters
python显示图例方法_matplotlib图例legend语法及设置的方法
weixin_39607090的博客
12-05 3407
1.图例legend基础语法及用法legend语法参数如下: matplotlib.pyplot.legend(*args,**kwargs)KeywordDescriptionlocLocation code string, or tuple (see below).图例所有figure位置propthe font property字体参数fontsizethe font size (used...
RoboMaster视觉教程（5）目标位置解算（通过像素点获取转角）
江达小记
07-29 1万+
RoboMaster视觉教程（5）目标位置解算（通过像素点获取转角）概览直接使用像素坐标的缺陷摄像头标定根据小孔成像原理得到需要的转角角度测量验证 概览 在识别到目标后，有一个很重要的问题：我们的最终目的是瞄准、跟踪、打击，怎样利用识别到目标后得到的目标在图像中的像素坐标来确定在真实世界中目标的位置呢？更清楚点说就是我识别得到的是图像中点的坐标，而我要输出告诉下位机的是它应该旋转或者移动到的目的地...
第一人称FPS视角跟随（Unity3D官方script）
JoeyHuangzx的专栏
10-27 7028
Unity官方版本都已经更新的2017.2的了，官方的案例和使用脚本还是挺给力的，而且还经常有更新优化脚本。今天把官方的一个FPS视角脚本贴出来，同时加上了自己的一些理解注释。 想要获得完整的官方案例（[Standard Assets Example](https://unity3d.com/cn/get-unity/download/archive?_ga=2.42565285.10319038.
基于局部结构的高效实时视觉跟踪算法
在实际应用中，提出的算法在以45帧每秒（fps）的速度运行时，能够在多个基准数据集上展现出与当前最先进的跟踪算法相当甚至更好的性能。 总结来说，本文的主要贡献在于提出了一种新颖的深度学习框架，通过关注目标...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

Mr-Trying

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付：¥1
获取中
扫码支付

您的余额不足，请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值