Deepstream how to save short video segments while maintaining continuous detection

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU): Jetson AGX Orin
**• DeepStream Version: 6.3
**• JetPack Version (valid for Jetson only): 5.1.3
**• TensorRT Version: 8.5
**• NVIDIA GPU Driver Version (valid for GPU only): CUDA 11.4, cuDNN 8.6
• Issue Type( questions, new requirements, bugs)

We want to use DeepStream to detect when an apple falls from a tree. Upon detecting a fall, we need to save a video clip that includes the 3 seconds before the fall and a few seconds after it. Meanwhile, the system should continue monitoring and detecting any future falls. How can we configure DeepStream to save these short video segments while maintaining continuous detection?

Is your source a live source or a local file source?

It is a live source e.g. camera through rtsp stream.

OK. If there are multiple apples falling from the tree in 3s, do you want to save multiple videos or just one video?

Just save one video. I perfer to extend the video duration if necessary to cover all the falling.

You can refer to our Smart Video Record demo. To record multiple events into one video, you need to implement that in your demo yourself.

1 Like

Ok. Thanks for your help.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.