how we compile in linux about 2018aicity_teamuw HOT 17 CLOSED

This issue may be caused by the misalignment between C++ compilers in Windows and Linux. For this specific error, here is a possible solution. Or you can rewrite the vector initialization by using push_back() instead.

from 2018aicity_teamuw.

Actually I have tested with other compilers like std 11,std 14 and also std 98

from 2018aicity_teamuw.

@dahlan77 Can you try to change the initialization by using push_back() instead?

from 2018aicity_teamuw.

Hi zhengthomas,,I finally can compile the speed but I must do camera calibration first ,but in calibration tutorial I still confuse the procedure

but when i compiler with
g++ -std=c++11 -o camtest main.cpp pkg-config opencv --cflags --libs

the output is
/tmp/cctyn5r3.o: In function main': main.cpp:(.text+0x12da): undefined reference to CCamCal::CCamCal()'
main.cpp:(.text+0x12e9): undefined reference to CCfg::CCfg()' main.cpp:(.text+0x12f8): undefined reference to CCfg::ldCfgFl()'
main.cpp:(.text+0x1519): undefined reference to CCamCal::initialize(CCfg, cv::Mat)' main.cpp:(.text+0x1528): undefined reference to CCfg::~CCfg()'
main.cpp:(.text+0x157f): undefined reference to oVanLnSel' main.cpp:(.text+0x1584): undefined reference to CVanLnSel::initialize(CCfg, cv::Mat)'
main.cpp:(.text+0x1593): undefined reference to CCfg::~CCfg()' main.cpp:(.text+0x15ae): undefined reference to oVanLnSel'
main.cpp:(.text+0x15b6): undefined reference to CVanLnSel::process()' main.cpp:(.text+0x15e8): undefined reference to CCamCal::process(std::vector<cv::Point_, std::allocator<cv::Point_ > >)'
main.cpp:(.text+0x161a): undefined reference to CCfg::~CCfg()' main.cpp:(.text+0x1629): undefined reference to CCamCal::~CCamCal()'
main.cpp:(.text+0x168c): undefined reference to CCfg::~CCfg()' main.cpp:(.text+0x16b4): undefined reference to CCfg::~CCfg()'
main.cpp:(.text+0x1704): undefined reference to CCfg::~CCfg()' main.cpp:(.text+0x1718): undefined reference to CCamCal::~CCamCal()'
collect2: error: ld returned 1 exit status

from 2018aicity_teamuw.

@dahlan77 You will need to link the other source files in 2018AICity_TeamUW/Track1/CAM_CAL_IPL/CAM_CAL_IPL/src/ during compilation. Another option for camera calibration is here. But please note that the output format is 3x3 homography matrix instead of 3x4 projection matrix.

from 2018aicity_teamuw.

Error: configuration file not opened

after i compiled the CAM calibration but the out put is above

from 2018aicity_teamuw.

By default, the configuration file cfg.json is under .\\data\\ (in Linux you will need to change the backslashes into slashes). You can check Cfg.cpp for more details.

from 2018aicity_teamuw.

Vanishing point (right): (300000,500)
Vanishing point (left): (926,-100)

The output for cam calibration but the output for speed still configuration

the out put for speed : Error: camera parameters not loaded

from 2018aicity_teamuw.

@dahlan77 I am not sure about your issue/question. Please check in cfg.json and the code that all the \\ in file paths have been changed into /.

from 2018aicity_teamuw.

Actually I have changed the configure in cfg.json..

and the result is

Vanishing point (right): (300000,500)
Vanishing point (left): (926,-100)
Start EDA optimization for camera calibration
==== generation 0: ====
25%...50%...75%...100%!
current error mean = 2634.767281
current error standard deviation = 21089.085288

==== generation 1: ====
25%...50%...75%...100%!
current error mean = 16.639031
current error standard deviation = 7.898482

==== generation 2: ====
25%...50%...75%...100%!
current error mean = 6.162161
current error standard deviation = 2.477083

==== generation 3: ====
25%...50%...75%...100%!
current error mean = 3.504104
current error standard deviation = 0.844408

==== generation 4: ====
25%...50%...75%...100%!
current error mean = 2.835919
current error standard deviation = 0.332255

==== generation 5: ====
25%...50%...75%...100%!
current error mean = 2.605511
current error standard deviation = 0.146056

==== generation 6: ====
25%...50%...75%...100%!
current error mean = 2.500789
current error standard deviation = 0.061076

==== generation 7: ====
25%...50%...75%...100%!
current error mean = 2.474164
current error standard deviation = 0.039133

==== generation 8: ====
25%...50%...75%...100%!
current error mean = 2.457497
current error standard deviation = 0.026974
Reprojection error is small enough. Stop generation.
..and it will be save in camParam.text and connected with Speed Estimation but still have no good result with Error: camera parameters not loaded

in cfg.json I changed into my configuration folder

"inFrmPth": "/home/dahlan/AICITY/Track1/CAM_CAL_IPL/CAM_CAL_IPL/data/frm.png",
// path of output text file of camera parameters
"outCamParamPth": "/home/dahlan/AICITY/Track1/CAM_CAL_IPL/CAM_CAL_IPL/data/camParam.txt",

So,am i missing something?

from 2018aicity_teamuw.

@dahlan77 Sorry for the inconvenience, but please change the file/directory paths at Lines 214, 220, 226, 232, 238 and 244 of Track1/SPD_EST_IPL/SPD_EST_IPL/src/main.cpp.

from 2018aicity_teamuw.

I am sorry before,,how we got track2d.txt and track1.txt?

from 2018aicity_teamuw.

@dahlan77 track2d.txt gives the 2D tracking results. You can use our tracklet-clustering-based method to get the 2D tracking results or your own chosen methods. track1.txt is the output file.

from 2018aicity_teamuw.

so its okay we create track2d.txt with empty files,because that text is the result?

from 2018aicity_teamuw.

@dahlan77 The track2d.txt file cannot be empty. 3D tracking requires the camera projection matrix and also the 2D tracking results, so that the 2D trajectories can be projected to 3D in order to measure 3D speed. However, you do not need to create those output files such as track1.txt.

from 2018aicity_teamuw.

Okay I see,am I missing something,,because I don't got the track2d.txt ,what should I compile to got track2d.txt

Thank you for your helping zheng thomas..

from 2018aicity_teamuw.

@dahlan77 You can use our provided YOLO package YOLO_VEH_IPL to run vehicle detection, and then use the tracklet-based tracking method TC_tracker for tracking-by-detection. Sorry for making things complicated..

from 2018aicity_teamuw.