Custom Object Detection on Jetson Nano for 4 RTSP

we want to deetct objects ( vehicles masks and pedestrians) from 4 live CCTV feed. And document the Captured objects.

  1. Is there a pipeline which is ready to modify and use?
  2. Can Deepstream directly produce an output in csv/txt etc
  3. Is Kafka needed?

Hi,
We have DeepStream SDK for this usecase. Please check

After the installation, you should see the samples in

/opt/nvidia/deepstream/deepstream-5.0/

The supported source types are listed in
DeepStream Reference Application - deepstream-app — DeepStream DeepStream Version: 5.0 documentation (nvidia.com)

But How to i integrate a custom YOLOV5 with deep stream. What should be the changes in config file

Hi,
We have demonstration for Yolo models:

/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_Yolo

You may refer to the sample and apply your model.