Plugin customization with OpenCV

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

I am trying to build a plugin that calculates the Optical Flow between consecutive frames and then apply the matrix transformation to the current frame, i am following the DsExample:

• Hardware Platform (Jetson / GPU) Jetson Nano
• DeepStream Version 6.0
• JetPack Version (valid for Jetson only) 4.6.1 (Linux 32.7.1)
• TensorRT Version 8.2.1.9
• Issue Type( questions, new requirements, bugs) Question
• I am following the right “tutorial” with this code or the stuff i am looking for is something more like a video filter?
• if so, how can i get the current full frame in the “gst_dsexample_transform_ip” and how can i moddify it later to make the output of my modifications so it is the output frame of the plugin.

Any suggestion is welcome.

3

Will the output frame be in different format or resolution comparing to the input frame?

4

Yes, the output frame will be in the same format and resolution as the input frame.

5

The video frame is in the NvBufSurface.NVIDIA DeepStream SDK API Reference: NvBufSurface Struct Reference | NVIDIA Docs

Please refer to DeepStream SDK FAQ - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums for how to modify the NvBufSurface.