how to use nvdsosd? Or there is a bug in the nvdsosd ?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi,ALL

I wanted to save video as a file, and show the boundingBox info on the screen. So i got a pipeline as bellows, why I can find boundingBox info in the test.mp4.

gst-launch-1.0
nvstreammux name=streammux width=1920 height=1080 batch-size=1 batched-push-timeout=4000000
nvstreamdemux name=streamdemux
streammux. ! streamdemux.
v4l2src device=/dev/video0 num-buffers=300 ! “video/x-raw,format=UYVY” !
videoconvert ! “video/x-raw,format=RGBA” !
nvvideoconvert ! “video/x-raw(memory:NVMM),format=RGBA” !
streammux.sink_0
streamdemux.src_0 !
queue ! nvinfer config-file-path=“…txt” !
queue ! tee name=t
t. ! queue !
nvvideoconvert ! “video/x-raw(memory:NVMM),format=I420” !
nvv4l2h264enc ! h264parse ! qtmux ! filesink location=test.mp4 sync=false
t. ! queue ! nvdsosd ! nvoverlaysink \

2

Hi,
We suggest you run deepstream-app and enable a sink of type=3.
https://docs.nvidia.com/metropolis/deepstream/dev-guide/index.html#page/DeepStream_Development_Guide%2Fdeepstream_app_config.3.2.html%23wwpID0ENHA

We have sample config files in

deepstream_sdk_v4.0.1_jetson\samples\configs\deepstream-app

If you use Jetson Nano, you can enable [sink1] in source8_1080p_dec_infer-resnet_tracker_tiled_display_fp16_nano.txt