Adaptive Confidence Threshold for ByteTrack in Multi-Object Tracking

TL;DR

This paper proposes an adaptive confidence threshold for ByteTrack in multi-object tracking, dynamically adjusting detection confidence levels to improve tracking accuracy without increasing computational cost.

Contribution

It introduces a novel adaptive threshold mechanism for ByteTrack, replacing the fixed threshold to enhance tracking performance in multi-object scenarios.

Findings

Adaptive threshold improves tracking accuracy.

Maintains real-time processing speed.

Effective across various detection conditions.

Abstract

We investigate the application of ByteTrack in the realm of multiple object tracking. ByteTrack, a simple tracking algorithm, enables the simultaneous tracking of multiple objects by strategically incorporating detections with a low confidence threshold. Conventionally, objects are initially associated with high confidence threshold detections. When the association between objects and detections becomes ambiguous, ByteTrack extends the association to lower confidence threshold detections. One notable drawback of the existing ByteTrack approach is its reliance on a fixed threshold to differentiate between high and low-confidence detections. In response to this limitation, we introduce a novel and adaptive approach. Our proposed method entails a dynamic adjustment of the confidence threshold, leveraging insights derived from overall detections. Through experimentation, we demonstrate the effectiveness of our adaptive confidence threshold technique while maintaining running time compared to ByteTrack.