目标跟踪-VOT2018-VOT工具-VOT toolkit 使用教程-matlab2016b

目标跟踪-VOT2018-VOT工具-VOT toolkit 使用教程

1. 下载地址

VOT toolkit : https://github.com/votchallenge/vot-toolkit
trax : https://github.com/votchallenge/trax

2. 使用说明

2.1 官方说明

http://www.votchallenge.net/howto/workspace.html
http://www.votchallenge.net/howto/integration.html

2.2 csdn文章

https://blog.csdn.net/sgfmby1994/article/details/78776465

3. 我遇到的问题以及解决方法

3.1 使用VOTtoolkit报错：Unable to unpack TraX source code.

https://blog.csdn.net/qq_26623315/article/details/83789807
解决方法：
下载 trax https://github.com/votchallenge/trax
解压之后的内容放到 vot-toolkit-master/native/trax/ 中

3.2 Warning: 提示 gcc版本 不匹配

Warning: You are using gcc version ‘5.4.0’. The version of gcc is not supported. The version currently
supported with MEX is ‘4.9.x’. For a list of currently supported compilers see:
http://www.mathworks.com/support/compilers/current_release.

In compile_mex (line 92)
In initialize_native (line 68)
In workspace_create (line 143)

3.3 VOT-toolkit下载数据集中断后需要重新下载

解决方法参考：
https://blog.csdn.net/u011935830/article/details/84030656

VOT-toolkit下载数据集的时候总是容易卡停，而且重新运行又会重新下载数据集~

去到vot-toolkit/sequence/sequence_load.m把第69到71行的代码取消注释即可，如图：

3.4 matlab 提示错误“version `GLIBCXX_3.4.21’ not found”

运行 出错

tracker_repo_path =

/home/anna/object_track_xu/2.MFT/2.code/MFT-master/

Testing TraX protocol support for tracker DSST.
Tracker execution interrupted: Invalid MEX-file '/home/anna/object_track_xu/5_VOT/vot-toolkit-master/native/traxclient.mexa64': /usr/local/MATLAB/R2016b/bin/glnxa64/../../sys/os/glnxa64/libstdc++.so.6: version `GLIBCXX_3.4.21' not found (required by /home/anna/object_track_xu/5_VOT/vot-toolkit-master/native/traxclient.mexa64).
TraX support not detected.
Error using tracker_load (line 127)
Tracker has not passed the TraX support test.

Error in run_test (line 8)
tracker = tracker_load('DSST');

我采用的解决方法：
LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libstdc++.so.6" /usr/local/MATLAB/R2016b/bin/matlab

参考网页：
https://www.helplib.com/c/mutia_159895

Answer 1 :
Actually i figured out what was wrong, as my system was GCC 5.2.1,
the file/usr/local/MATLAB/R2014a/bin/glnxa64/…/…/sys/os/glnxa64/libstdc++.so.6was designed for GCC 4.4. X so Matlab was actually picking the wrong file.i just made a symbolic link to my system’s libstdc++.so.6 using this on terminal -

ln -s/usr/lib/x86_64-linux-gnu/libstdc++.so.6  /usr/local/MATLAB/R2014a/bin/glnxa64/../../sys/os/glnxa64/libstdc++.so.6

Answer 2 :
It looks like/usr/local/MATLAB/R2014a/bin/glnxa64/…/…/sys/os/glnxa64/libstdc++.so.6is missing the glibc version and not/usr/lib/x86_64-linux-gnu/libstdc++.so.6. now Matlab first tries the libstdc++.so.6 in the Matlab path and fails.
From a post from mathworks the following should work to start matlab with the system libstdc++.so.6

LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libstdc++.so.6"  /usr/local/MATLAB/R2016b/bin/matlab

3.5 无法建立链接

To get started, type one of these: helpwin, helpdesk, or demo.
For product information, visit www.mathworks.com.
 
@@TRAX:hello "trax.image=path;" "trax.region=polygon;" "trax.version=2" "trax.channels=color;" 
CLIENT: Tracker process ID: 4278
CLIENT: Connection with tracker established.
@@TRAX:initialize "file:///home/anna/object_track_xu/5_VOT/vot-workspace/sequences/ants1/00000001.jpg" "137.2100,458.3600,156.8300,460.7800,148.3500,529.4100,128.7200,526.9900" 
    '/home/anna/object_track_xu/5_VOT/vot-workspace/sequences/ants1/0000000...'

CLIENT: Trying to stop process using protocol.
@@TRAX:quit 
CLIENT: Flushing streams

CLIENT: Process should be terminated.
CLIENT: Stopping logger.
CLIENT: Tracker exited normally.
CLIENT: Trying to stop process using protocol.
CLIENT: Cleaning up.
CLIENT: Stopping logger thread
CLIENT: Trying to stop process using protocol.
Tracker execution interrupted: Did not receive response.
Error using traxclient
Did not receive response.

Error in tracker_run (line 77)
    data = traxclient(tracker.command, callback, ...

Error in workspace_test (line 54)
            tracker_run(tracker, @callback, data);

Error in run_test (line 10)
workspace_test(tracker, sequences);

3.5 生成数据分析报告

运行 run_analysis.m

3.6 可视化跟踪结果

运行 run_browse.m