The following example demonstrates use of the vvas_xoverlay plug-in with the vvas_xinfer and vvas_xmetaconvert plug-ins for overlaying classification text. The vvas_xinfer plug-in produces an inference result and stores it in the GstInferenceMeta structure. This metadata is parsed and translated into the GstVvasOverlayMeta structure that is understood by the vvas_xoverlay plug-in to overlay the classification information. This translation of the metadata is done by the vvas_xmetaconvert plug-in.
Note
The following JSON examples are only samples. Ensure
model-pathis set to point to your available model before running.
gst-launch-1.0 filesrc location=<INPUT>.bgr \
! rawvideoparse format=bgr width=<INPUT_WIDTH> height=<INPUT_HEIGHT> \
! queue \
! vvas_xinfer config-file=/etc/vvas/configs/infer/resnet50_onnxrt.json \
! vvas_xmetaconvert config-location=/etc/vvas/configs/metaconvert/metaconvert_config.json \
! vvas_xoverlay ! filesink location=out_overlay_resnet50.bgr