Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) geforce rtx 3060
• DeepStream Version sdk 7.1
• TensorRT Version 10.3
• NVIDIA GPU Driver Version (valid for GPU only) 560.35.03
I have ran the deepstream-opticalflow.py from the official deepstream_python_apps and used my mp4 video for processing . i am sharing the generated image below ,can someone please explain what is going wrong since i havnt made any alteration to the code.
Why do you think it is wrong?
I am unable to recognize the target objects from the generated image and video.
Can you try to set “preset-level” property of nvof plugin as 2 in the sample code? Gst-nvof — DeepStream documentation
can you give me an idea what does the nvofvisual represents through the colour ? I can see the pixel colour of the stationary background also fluctuating heavily.
The nvofvisual uses some algorithm to map the mv vectors to some color. The algorithm is not open source. What we can tell you is that the more similar vectors may be mapped to the closer colors in the color wheel.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.
