How to add multi camera tracking with deepstream handling

**• Hardware Platform (Jetson / GPU)**nvidia geforce rtx 3060
• DeepStream Version sdk 7.1
• TensorRT Version10.3
• NVIDIA GPU Driver Version (valid for GPU only) 560.35.03
I am working on a project where i need to track objects passing from one camera to another . How can i achieve this using the nv-tracker which uses the nvDCF tracker .

Also i have tried to stitch the multiple streams since the cameras are adjacent to each other with minor overlapping but i have faced an issue since the maximum resolution accepted by deepstream is lower than the stitched stream . how can i overcome this and use the multi streams as a single stitched stream.

Maybe Metropolis Microservices can help you. Metropolis Microservices

Metropolis Microservices — mdx-docs 2.1 documentation

how can i integrate it with my deepstream pipeline. also can you please tell me about the second question.

What does this mean? What is the resolution of the stitched stream?

Do you mean you want to input the multiple streams to DeepStream app and the DeepStream app stitch the streams into one single stream?
If so, current DeepStream does not provide stitching algorithm or component. You may need to develop your own stitch algorithm and implement the algorithm by yourself.