AssertionError on using 2 cameras for python_demos/multi_camera_multi_target_tracking

[Calincan]

multi_camera_multi_target_tracking Demo not working when using web camera and IP camera, and returning below error, But working separately - by running only -i: webcam or running -i IP cam:

python3 /opt/intel/openvino_2021/inference_engine/demos/python_demos/multi_camera_multi_target_tracking/multi_camera_multi_target_tracking.py \-i rtsp://mass:pass@112.132.1.125:532/live/ch0 0 \--m_detector /home/mircea/projects/multi_camera_multi_target_tracking/intel/person-detection-retail-0013/FP16/person-detection-retail-0013.xml \--m_reid /home/mircea/models/public/person-reidentification-retail-0103/person-reidentification-retail-0103.xml \--config /opt/intel/openvino_2021/inference_engine/demos/python_demos/multi_camera_multi_target_tracking/configs/person.py
INFO: 2021-04-04 16:25:45: Reading configuration file /opt/intel/openvino_2021/inference_engine/demos/python_demos/multi_camera_multi_target_tracking/configs/person.py
INFO: 2021-04-04 16:25:45: Opening file rtsp://mass:pass@112.132.1.125:532/live/ch0
INFO: 2021-04-04 16:25:48: Opening file 0
[ WARN:0] global ../opencv/modules/videoio/src/cap_gstreamer.cpp (734) open OpenCV | GStreamer warning: Error opening bin: no element "0"
[ WARN:0] global ../opencv/modules/videoio/src/cap_gstreamer.cpp (501) isPipelinePlaying OpenCV | GStreamer warning: GStreamer: pipeline have not been created
libva info: VA-API version 1.8.0
libva info: User environment variable requested driver 'iHD'
libva info: Trying to open /opt/intel/mediasdk/lib64/iHD_drv_video.so
libva info: Found init function __vaDriverInit_1_8
libva info: va_openDriver() returns 0
MFX: Unsupported extension: 0
/usr/lib/python3/dist-packages/apport/report.py:13: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
import fnmatch, glob, traceback, errno, sys, atexit, locale, imp, stat
Traceback (most recent call last):
File "/opt/intel/openvino_2021/inference_engine/demos/python_demos/multi_camera_multi_target_tracking/multi_camera_multi_target_tracking.py", line 277, in <module>
main()
File "/opt/intel/openvino_2021/inference_engine/demos/python_demos/multi_camera_multi_target_tracking/multi_camera_multi_target_tracking.py", line 247, in main
capture = MulticamCapture(args.i)
File "/opt/intel/openvino_2021.2.185/deployment_tools/open_model_zoo/demos/python_demos/multi_camera_multi_target_tracking/utils/video.py", line 44, in __init__
assert cap.isOpened()
AssertionError

[Peh_Intel · Accepted solution]

Hi Calincan,

Thanks for reaching out to us.

For this multi_camera_multi_target_tracking demo, the inputs can be multiple cameras but limited to same type of channel.

However, there are three multi channels demos (face_detection_demo, human_pose_estimation_demo, object_detection_demo_yolov3) which are available for you to use webcam and IP cam at the same time to execute the demo.

Regards,

Peh

[Calincan]

Many thanks for the feedback, I will follow your recommendation!
But what is the lines of code which is missing to have the same capability?

[Peh_Intel]

Hi Calincan,

For your information, multi_camera_multi_target_tracking demo is written in Python while multi-channels demos are written in CPP. Next, looking deeply into one of the multi-channels demo’s script, the demo includes multichannel_params.hpp which is available here.

Regards,

Peh

[Peh_Intel]

Hi Calincan,

This thread will no longer be monitored since this issue has been resolved. If you need any additional information from Intel, please submit a new question.

Regards,

Peh