I am working with a hailo15 sbc.
Using a rtsp link I am collecting the video from the camera to the hailo and here I perform the model inference and send it to my pc.
Everything is working correctly except that the video is very very slow when doing the inference and sending it. I think that the hailo accelerator is not being used. How can I fix this?
I comment here the pipelines that I have used.
For the pc
gst-launch-1.0 udpsrc port=5000 caps=“application/x-rtp,media=video,encoding-name=H264” ! rtph264depay ! avdec_h264 ! videoconvert ! autovideosink ! autovideosink
For the hailo
gst-launch-1.0 rtspsrc location=rtsp://usr:pass@ip/Streaming/channels/1/ ! decodebin ! videoconvert ! videoscale ! video/x-raw,format=NV12,width=1920,height=1080 ! hailonet hef-path=/home/root/apps/detection/resources/yolov5m_wo_spp_60p_nv12_fhd. hef ! hailofilter function-name=yolov5 config-path=/home/root/apps/detection/resources/configs/yolov5.json so-path=/usr/lib/hailo-post-processes/libyolo_post.so qos=false ! hailooverlay ! videoconvert ! x264enc tune=zerolatency ! rtph264pay pt=96 config-interval=1 ! udpsink host=ip port=5000