Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5528 Discussions

Porting 'multi_camera_multi_person_tracking' sample application from Python to C++

KG0001
Beginner
497 Views

Hello Intel Team,

We are from ZOHO corp R&D team, and working on openvino hardware acceleration part of it. 

'multi_camera_multi_person_tracking' sample application is already as part of the openvino demo package and implemented in python language.  But we are in  need of same application in C++ language to do custom changes to obtain more hardware acceleration.

Do you have respective C++ implementation or Could you support for that ?

Regards, Kalyan-G.

 

0 Kudos
1 Solution
Max_L_Intel
Moderator
447 Views

Hi @KG0001 

Do you also get this error message when running Multi-Channel Face Detection C++ Demo and Pedestrian Tracker C++ Demo separately from each other? If not, then this might be related to incorrect input image size, and that the dimensions on your mat objects do not match. You need to check if your ROI is placed within the dimensions of the image.

Please check these topics: Assertion failed roi out of rangewhy am i getting so many roi crashesError with OpenCV ROI.

View solution in original post

4 Replies
Iffa_Intel
Moderator
479 Views

Greetings,


We don't have the exact model for C++ as in Python. However, we do have these 3 samples in C++:


https://docs.openvinotoolkit.org/latest/omz_demos_multi_channel_README.html


Hope this somehow could help with your implementation.


Sincerely,

Iffa


KG0001
Beginner
465 Views

 

Hi,

To bring the multi-channel-multi-person-tracking in C++,  we integrated the 'pedestrian_tracker_demo c++ implementation ' with 'multi_channel_face_detection c++' .

But getting this below error. It seems some pixel issue while parsing the frame. Could you share you comment on this error.

 

terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.3.0-openvino-2020.3.0) ../opencv/modules/core/src/matrix.cpp:466: error: (-215:Assertion failed) 0 <= roi.x && 0 <= roi.width && roi.x + roi.width <= m.cols && 0 <= roi.y && 0 <= roi.height && roi.y + roi.height <= m.rows in function 'Mat'

Max_L_Intel
Moderator
448 Views

Hi @KG0001 

Do you also get this error message when running Multi-Channel Face Detection C++ Demo and Pedestrian Tracker C++ Demo separately from each other? If not, then this might be related to incorrect input image size, and that the dimensions on your mat objects do not match. You need to check if your ROI is placed within the dimensions of the image.

Please check these topics: Assertion failed roi out of rangewhy am i getting so many roi crashesError with OpenCV ROI.

View solution in original post

KG0001
Beginner
428 Views

Thanks for your support.

I will look into this further.. You can close this ticket.

Thanks & Regards,

Kalyan-G.

Reply