Comments (17)
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.
Related Issues (20)
- Can I use it to train for Multiple camera Multiple person tracking problem? HOT 14
- CUDA installation HOT 2
- sequence naming of images in TC_Tracker HOT 1
- Track1/6_SPD_EST issues HOT 9
- Code in C or C++ HOT 1
- FPS HOT 1
- How to run the yolo detection with the model provided? HOT 1
- Step 2- Camera calibration old method vs new method HOT 1
- Tracklet clustering HOT 2
- Unable to mark vanishing lines HOT 9
- Arguments 3_YOLO_VEH in file track1.sh
- Core dumped
- one difference between the provided code and the paper HOT 1
- Height of vehicles effect on real distance between 2 frames HOT 2
- Python implementation
- Can we use this on Windows? HOT 1
- Some questions about 2_CAM_CAL HOT 1
- Back projection matrix construction HOT 2
- Coordinate Systems Ambiguity HOT 6
- Inquiries Regarding the Integration of Semantic Features for Enhanced Vehicle Tracking HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from 2018aicity_teamuw.