Advancing Frame-Dropping in Multi-Object Tracking-by-Detection Systems Through Event-Based Detection Triggering

TL;DR

This paper proposes an event-based detection triggering mechanism to improve frame-dropping in multi-object tracking systems for autonomous vehicles, enhancing safety and reducing energy consumption significantly.

Contribution

It introduces an event-based triggering method that mitigates late detections and boosts energy efficiency in tracking-by-detection systems.

Findings

Late object detections are reduced.

Energy consumption decreases by nearly 60 Watt.

System safety and efficiency are improved.

Abstract

With rising computational requirements modern automated vehicles (AVs) often consider trade-offs between energy consumption and perception performance, potentially jeopardizing their safe operation. Frame-dropping in tracking-by-detection perception systems presents a promising approach, although late traffic participant detection might be induced. In this paper, we extend our previous work on frame-dropping in tracking-by-detection perception systems. We introduce an additional event-based triggering mechanism using camera object detections to increase both the system's efficiency, as well as its safety. Evaluating both single and multi-modal tracking methods we show that late object detections are mitigated while the potential for reduced energy consumption is significantly increased, reaching nearly 60 Watt per reduced point in HOTA score.