windows下的VOT数据集配置

一、运行环境

Windows 10 x64，
Matlab版本为MATLAB2018a，百度网盘链接：链接：

https://pan.baidu.com/s/1dSoN9rUVjvRqIoueNqn6Fg

提取码：h8qo
VS版本为VS2015,，百度网盘链接：链接：

https://pan.baidu.com/s/11-1wrtwcNnXEeccGUvfdrA

提取码：46bn

二、预先下载

1、VOT-toolkit

VOT是针对跟踪算法的挑战赛，每年举办一次，而且组委会自己制定了一套评价指标和方法用于跟踪器的评分。基于Matlab的工具Vot-tookit官网http://votchallenge.net/，其在github的下载https://github.com/votchallenge/vot-toolkit.git

2、Trax

Trax主要作用就是建立各种语言跟踪器与VOT-toolkit的传输协议，方便对于不同语言的trackers进行统一分析。
github下载为：https://github.com/votchallenge/trax.git

3、ncc

这个有github的下载网站，但是我给整忘了，只有26KB。先放个百度网盘链接，回头找到网站再放过来。链接：https://pan.baidu.com/s/1qJjbN7NXWd0Zxt56AEGvBQ
提取码：5d3t

4、VOT数据集

matlab程序运行会自动检测数据集，没有会自动下载，但是下载很慢，所以建议自己事先下载好数据集，百度网盘会员到期了，懒的上传了，这里放个其他博主的链接(狗头保命)：链接：https://pan.baidu.com/s/1oJdgY5PpfN8Ep85i8nVmdQ
提取码：dlw6
但是后面测试跟踪算法的时候，需要算法的一个list.txt文件，我测试的是VOT2018数据集（VOT2017和VOT2018序列是一样的），减少大家的麻烦，放个百度网盘链接(因为不大)。链接：https://pan.baidu.com/s/1PV0q9_H19tdr6dtFev9ZbQ
提取码：cyh6

三、正文开始

1、文件位置

1.1 将VOT-toolkit压缩包解压在一个位置，然后在其里面新建文件夹native，将Trax-master解压在native文件夹，并将名字修改为trax。
1.2 依次进入tracker>examples>，将下载的ncc中的matlab文件夹放在这里。
1.3 进入workspace，新建文件夹sequences，将数据集解压缩后放在这里，把list.txt文件也放在这里

2、创建workspace

运行toolkit_path.m，添加路径
进入workspace，运行/workspace/workspace_create.m，这一步会创建多个m文件。具体步骤如下：
2.1选择数据集（我选择的是VOT2018）

2.2选择算法（我选择的ncc）

2.3 选择语言（我选择的是Matlab）

2.4 创建成功

3、配置跟踪器

1、这是生成的tracker_ncc.m文件

error('Tracker not configured! Please edit the tracker_ncc.m file.'); % Remove this line after proper configuration

% The human readable label for the tracker, used to identify the tracker in reports
% If not set, it will be set to the same value as the identifier.
% It does not have to be unique, but it is best that it is.
tracker_label = [];

% For MATLAB implementations we have created a handy function that generates the appropritate
% command that will run the matlab executable and execute the given script that includes your
% tracker implementation.
%
% Please customize the line below by substituting the first argument with the name of the
% script (not the .m file but just the name of the script as you would use it in within Matlab)
% of your tracker and also provide the path (or multiple paths) where the tracker sources
% are found as the elements of the cell array (second argument).
tracker_command = generate_matlab_command('', {''});

tracker_interpreter = 'matlab';

% tracker_linkpath = {}; % A cell array of custom library directories used by the tracker executable (optional)

注释error行
tracker_commend写算法文件名字和路径
这是我修改后的tracker_ncc.m（路径的地方加了斜杠\）

% error('Tracker not configured! Please edit the tracker_ncc.m file.'); % Remove this line after proper configuration

% The human readable label for the tracker, used to identify the tracker in reports
% If not set, it will be set to the same value as the identifier.
% It does not have to be unique, but it is best that it is.
tracker_label = ['ncc'];

% For MATLAB implementations we have created a handy function that generates the appropritate
% command that will run the matlab executable and execute the given script that includes your
% tracker implementation.
%
% Please customize the line below by substituting the first argument with the name of the
% script (not the .m file but just the name of the script as you would use it in within Matlab)
% of your tracker and also provide the path (or multiple paths) where the tracker sources
% are found as the elements of the cell array (second argument).
tracker_command = generate_matlab_command('ncc', {'F:\VOT\c\vot1\tracker\examples\matlab\'});

tracker_interpreter = 'matlab';

% tracker_linkpath = {}; % A cell array of custom library directories used by the tracker executable (optional)

2、run_test.m（这只是为了测试，可以直接跳到下一步）
只需要在run_test.m文件中，路径后面加斜杠
修改完的run_test.m文件为：

% This script can be used to test the integration of a tracker to the
% framework.

addpath('F:\VOT\c\vot1\'); toolkit_path; % Make sure that VOT toolkit is in the path

[sequences, experiments] = workspace_load();

tracker = tracker_load('ncc');

workspace_test(tracker, sequences);

运行run_test.m

选择序列，出现一个十字黑线，鼠标点击一下一帧（只是测试的话，空格可以快速，嘿嘿，拼手速可以忽略）

3、run_experiment.m
为了看是否能跑通，我这里只测试了三个序列(主要是懒)，当然跑多少序列就需要修改/workspace/sequences/list.txt文件，想跑几个就跑几个。
这是我的run_experiments.m(在自动生成的文件中路径加了斜杠)

% This script can be used to execute the experiments for a single tracker
% You can copy and modify it to create another experiment launcher

addpath('F:\VOT\c\vot1\'); toolkit_path; % Make sure that VOT toolkit is in the path

[sequences, experiments] = workspace_load();

tracker = tracker_load('ncc');

workspace_evaluate(tracker, sequences, experiments);

然后我就成功了

这是生成的/workspace/results/文件夹内容。


4、run_analysis.m
这是原始生成的run_analysis.m

% This script can be used to perform a comparative analyis of the experiments
% in the same manner as for the VOT challenge
% You can copy and modify it to create a different analyis

addpath('F:\VOT\c\vot1'); toolkit_path; % Make sure that VOT toolkit is in the path

[sequences, experiments] = workspace_load();

error('Analysis not configured! Please edit run_analysis.m file.'); % Remove this line after proper configuration

trackers = tracker_list('ncc','TODO'); % TODO: add more trackers here

workspace_analyze(trackers, sequences, experiments, 'report_ncc', 'Title', 'Report for vot2018');

在路径后面加斜杠
注释error行
因为我们只比较一个算法，去掉taackers中’TODO’
这是修改后的run_analysis.m

% This script can be used to perform a comparative analyis of the experiments
% in the same manner as for the VOT challenge
% You can copy and modify it to create a different analyis

addpath('F:\VOT\c\vot1\'); toolkit_path; % Make sure that VOT toolkit is in the path

[sequences, experiments] = workspace_load();

% error('Analysis not configured! Please edit run_analysis.m file.'); % Remove this line after proper configuration

trackers = tracker_list('ncc'); % TODO: add more trackers here

workspace_analyze(trackers, sequences, experiments, 'report_ncc', 'Title', 'Report for vot2018');

运行run_analysis.m

在/workspace/reports中生成所有结果的分析图和表，如下图

在images文件夹中存放了算法的整体数据集以及单个序列的AR图，expected_overlaps图和Rank图等。

四、遇到问题

1、

Tracker execution interrupted: Unable to establish connection.
TraX support not detected.
错误使用 tracker_load (line 127)
Tracker has not passed the TraX support test.

解决办法：将vot.m文件copy到测试跟踪算法目录下（因为我测试了别的算法，哈哈）
2、

Tracker execution interrupted: Did not receive response.
错误使用 traxclient
Did not receive response.

解决办法：代码错误，检查代码。我在测试KCF的时候，是读取的问题。
3、如果想重新加载其他数据集，并重新配置workspace.
删除/workspace/configuration.m
删除/cache下的mat文件
删除native文件夹下的除了trax文件夹的其他文件

未完待续

下一步写一写配置自己算法的具体流程

随缘更新。。。