How to connect multiple cameras for ML application?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi, I have an application where I would like to process input from up to 4 cameras. At this point I am not sure which type of cameras, whether they will be USB hub based or internet based.

I have just come across the hardware from Nvidia like the Jetson et. al. and while I have seen video demos using multiple camera feeds (I think that the Jetson, running Deepstream can run up to 8 video feeds of some resolution and aspect ratio) I have not seen, so far, configuration information.

Is there a good reference for hardware configuration of external devices to the Jetson?

Thank You
Tom

2

Hi,
You can configure all sources into config file. Please refer to:
[url]https://devtalk.nvidia.com/default/topic/1046315/deepstream-sdk-on-jetson/template-config-file-for-camera-and-rtsp/post/5314984/#5314984[/url]

3

DaneLLL, thank you very much for your reply. What I was seeking information on was the hardware configuration, as in physically, how are multiple cameras attached to the Jetson? Through USB hub or Ethernet or other.

Thank You
Tom

4

Hi,
We have partners making multi-camera boards. Please check

5

e-CAM130_CUXVR is a synchronized multiple 4K camera solution for NVIDIA® Jetson AGX Xavier development kit that has up to four 13 MP 4-Lane MIPI CSI-2 camera boards. Each camera is based on the camera module e-CAM137_CUMI1335_MOD, 1/3.2" AR1335 color CMOS image sensor from ON Semiconductor® and integrated high performance Image Signal Processor (ISP).

For more information, please download: Four Synchronized 4K Cameras for NVIDIA® Jetson AGX Xavier™