Bbox inaccurate via nvdsanalytics

[Newbie98]

• Hardware Platform (Jetson / GPU): dPU A40.
• DeepStream Version: 6.4-triton-multiarch.
• TensorRT Version: 8.6.1.6.
• NVIDIA GPU Driver Version (valid for GPU only): 535.146.02.
• Issue Type( questions, new requirements, bugs): 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)

I am using yolov8 model for people detection and I am using nvdaanlytics for line crossing .
so the main issue is some time bbox change or new tracker id assigned to tracked person.

I have person enter the line crossing, and when arrive to exit line crossing its bbox changed and count as exit the line but he in the enter direction!!

[junshengy]

I think this problem depends on the configuration, try the following configuration options.

gst-nvdsanalytics is open source, you can try to debug it.

#LC modes supported:
#loose   : counts all crossing without strong adherence to direction
#balanced: Strict direction adherence expected compared to mode=loose
#strict  : Strict direction adherence expected compared to mode=balanced
mode=loose

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks