I could run facial expression detection on imx8mq evk(5.4.24 bsp) with input image. Same i tried to run with video source but its thowing error. Here are the logs:
INFO: Created TensorFlow Lite delegate for NNAPI.
Applied NNAPI delegate.
Using /dev/video2 as video device
Resolution not supported. Using 640x480 instead.
[ WARN:0] global /usr/src/debug/opencv/4.2.0.imx-r0/git/modules/videoio/src/cap_gstreamer.cpp (713) open OpenCV | GStreamer warning: Error opening bin: no element "imxvideoconvert_g2d"
[ WARN:0] global /usr/src/debug/opencv/4.2.0.imx-r0/git/modules/videoio/src/cap_gstreamer.cpp (480) isPipelinePlaying OpenCV | GStreamer warning: GStreamer: pipeline have not been created
Your video device could not be initialized. Exiting...
As per my understanding imx8mq evk doesn't support g2d. So what can be done here to make it working?
Would like to here from you asap.
I could not reproduce this issue as you mentioned that you are using the latest BSP, do not why is try to open imagevideoconvertg2d since is not supported in MX8M, but in my test it works from imxcompositor, maybe you are playing with nonsupported camera.
Not getting error if using flag "--video_fwk=opencv". But with live streaming detection is not happening with camera ov5640(MINISASTOCSI), same working with USB webcam. How NXP camera could cause detection issue, sometime false detection happening. Tried recording a video by ov5640 also & tested it by passing as parameter but same no detection. How its differentiating with NXP ov5640 camera & usb web cam?