Is it possible to track an object when missing bounding boxes between frames?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) NX
• DeepStream Version 6
• JetPack Version (valid for Jetson only) 4.6
• TensorRT Version 8.0
• NVIDIA GPU Driver Version (valid for GPU only) N/A
• Issue Type( questions, new requirements, bugs) questions
• 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) N/A
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description) N/A

I am running deepstream with tiny yolov4 object detector and nvdcf tracking. My questions is it possible to track an object when some of the bounding boxes are missing between frames say ~100 frames. If possible what settings do I need for the tracker? If not, I just need to improve the object detector.

image

image

3

Yes, you can verify it by set inference interval in nvinfer.

Gst-nvtracker — DeepStream 6.0.1 Release documentation (nvidia.com)

4

Thanks. I already using intervals. I think I need to improve the model so I don’t have missing bounding boxes for up to a 100 frames if I want the same tracker ID.