How to track and re-identificate human across multicamera scenario using RTSP

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) : Jetson Orin Nano
• DeepStream Version: 7.1
• JetPack Version (valid for Jetson only): 6.2
• TensorRT Version: 10.3.0.30
• 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)

Hi Everyone,

Do you want to tracking object separately between two cameras? Or you want to tracking object across cameras?
I wanna track object across the cameras. Is it possible using deepstream and is there any examples available that i could use as reference?

Best Regards,
Seb

Nvidia has examples of multiple cameras tracking targets, I can’t remember the specific URL

hi @cihn,

Are you referring to the below url?

Best regards

Not this one, I’m talking about the example of “multiple cameras tracking the same target”. I’ll see if I can find the relevant URL tomorrow.

Hi @cihn,

Much appreciated. Thanks

Best regards
Seb

@petertechnologiesplt

Are you looking for something related to Multi-Camera Tracking? I guess MTMC(Multi-Target Multi-Camera ) is what you need.

https://docs.nvidia.com/mms/text/MDX_Multi_Camera_Tracking_App.html#overview

Hi @junshengy,

Thanks you so much for your reply and sharing. I am looking for a Jetson Nano based examples.
The MDX_Multi_camera Tracking_App requires :-

Hardware Recommendations

  • RAM: 120GB
  • CPU: 18 cores
  • GPU: A100, L40, L4, A6000, H100 etc.
  • Storage: 512GB (SSD)

Which i don’t have. Please advice.

Best Regards
Seb

You can ask questions about MTMC on jetson under this topic. I don’t know much about it.
Currently only GPU is supported, probably for accuracy reasons