Obtain tracker features in DeepStream

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) NVIDIA GeForce RTX 3090
• DeepStream Version 6.3
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.6.1.6
• NVIDIA GPU Driver Version (valid for GPU only) 535.113.01
• Issue Type( questions, new requirements, bugs) Question
• 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)

I am using the deepstream-demux-multi-in-multi-out sample app from deepstream_python_apps. My goal is to develop an application that has multiple cameras as inputs and performs a tracking. Not only an individual tracking for each camera, but also a global, in case a same object is in multiple cameras to identify it as unique (same ID in all of them).

I have developed a small program in PyCharm that has a Yolo detector and a DeepSORT tracker. In order to assign the same ID to the same objects I compare the features that the tracker gives me:

correlation = distance = np.linalg.norm(track2_features[i][0] - track1_features[j][0])

Is there any way to get those features from the DeepStream tracker? I mean, just as I can get the bboxes from the detector (for example, obj_meta.detector_bbox_info.org_bbox_coords.left), can I get the features obtained by the tracker?

Thank you,

Mikel

Yes. Please refer this topic: How to access Re-ID tensor for cross camera re-id - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums

Perfect, thank you!

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.