Building a Multi-Camera Media Server for AI Processing on the NVIDIA Jetson Platform

Originally published at: Building a Multi-Camera Media Server for AI Processing on the NVIDIA Jetson Platform | NVIDIA Technical Blog

A media server provides multimedia all-in-one features, such as video capture, processing, streaming, recording, and, in some cases, the ability to trigger actions under certain events, for example, automatically taking a snapshot. For you to make the best out of a media server, it must be scalable, modular, and easy to integrate with other processes.…

Hello , Can I use jetson nano carrier board with raspberry pi2 camera for this type of application ?

Need some sample application for the Multi camera media server.

@sachin.gaikwad yes you can use the Raspberry Pi Camera Module v2 (IMX219) with the Jetson Nano carrier board. You can test it with nvgstcapture-1.0 test program or a simple script like this that uses the nvarguscamerasrc GStreamer element: GitHub - JetsonHacksNano/CSI-Camera: Simple example of using a CSI-Camera (like the Raspberry Pi Version 2 camera) with the NVIDIA Jetson Developer Kit

DeepStream also supports it - I would review the latest DeepStream documentation, as this article you commented on is from 2020.

1 Like

Thanks @dusty_nv . can you suggest which Nvidia kit helps to get more scalable multi camera read and make AI model on the same video .

@sachin.gaikwad I’d recommend looking into Jetson Ecosystem | NVIDIA Developer

There are various camera partners who’ve made breakout boards and carrier boards that support many camera connections (presuming that you need more than 2x MIPI CSI connections that the Nano devkits have)