DeepStream get cv::mat by

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

I want to load the GStreamer command line in OpenCV to use hard decoding（example nvn4l2decoder） to get image data for AI inference（my AI SDK not in nvinfer plugin）？ What can I do to get the highest performance？

**• Hardware Platform (Jetson / GPU)**xavier nx
• DeepStream Version5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

3

The HW decoder output is Nvidia customized format, it can not be used outside DeepStream pipeline. You may try to use pipeline “video src => nvv4l2decoder ==> nvvideoconvert ==> appsink” to output decoded frames outside gstreamer pipeline.
You don’t want to use DeepStream for inferrence, right? So it is not a DeepStream topic.

4

Just Use HW decoder

5

openCV can run gstreamer pipeline, but the pipeline must be complete(from src to sink), the pipeline is a closed loop, no video data is available outside the pipeline.

6

OpenCV has CUDA codec interfaces for video. OpenCV: opencv2/cudacodec.hpp File Reference

This is not DeepStream or even Gstreamer related, you need to refer to openCV resources.