TAE: Target-aware enhancer for nighttime UAV tracking

2026-05-28

AI Summary

This work addresses the significant performance degradation of single-object tracking on drones under nighttime low-light conditions, where generic image enhancement methods often introduce noise or distort target features. To tackle this challenge, the authors propose a target-aware low-light enhancement framework that, for the first time, leverages bounding boxes from the tracker as weak supervision to guide region-focused enhancement. They further design an adaptive RGB multi-curve fusion mechanism to enable fine-grained modeling of both foreground and background regions. Key contributions include the introduction of a target-aware enhancement strategy, the construction of DarkSOT—the first benchmark dataset for nighttime drone tracking comprising 268 sequences—and substantial improvements in tracking robustness and generalization, demonstrated on both DarkSOT and UAVDark135.

Abstract

Severe image degradation under low-light nighttime conditions constitutes a core bottleneck preventing all-day applications for UAV-based single object tracking. Existing image enhancement methods often struggle to distinguish between target and background regions, which can easily lead to amplified background noise or compromise target features. To overcome this limitation, we propose TAE, a target-aware low-light enhancement framework tailored for nighttime object tracking. Guided explicitly by weak supervisory signals from tracking bounding boxes, the framework performs region-aware enhancement to ensure operations focus on the target area. It further adopts an adaptive RGB multi-curve fusion mechanism to achieve refined modeling and adaptive adjustment across different regions. To facilitate research in this domain, we also contribute DarkSOT, a new benchmark for nighttime UAV tracking, comprising 268 sequences across 9 target categories. Experimental results on the DarkSOT and UAVDark135 demonstrate that TAE significantly improves tracking performance in low-light nighttime scenarios, exhibiting strong robustness and generalization. The DarkSOT dataset is available at https://github.com/Fu0511/DarkSOT-Dataset.

Problem

• nighttime UAV tracking
• low-light image enhancement
• target-aware enhancement
• image degradation
• object tracking

Innovation

• target-aware enhancement
• low-light image enhancement
• nighttime UAV tracking
• adaptive RGB multi-curve fusion
• weak supervision