Enhancing Nighttime UAV Tracking with Light Distribution Suppression

TL;DR

This paper introduces LDEnhancer, a novel light distribution suppression method that improves nighttime UAV tracking by effectively enhancing images with uneven illumination, validated on a new challenging dataset and real-world tests.

Contribution

The work presents a new enhancer with a content refinement module and light distribution generation, plus a collaborative pixel-wise adjustment, addressing uneven light in low-light UAV images.

Findings

Outperforms state-of-the-art low-light enhancers on UAV benchmarks.

Demonstrates effectiveness on the new NAT2024-2 dataset.

Proves practicality and efficiency in real-world UAV platform tests.

Abstract

Visual object tracking has boosted extensive intelligent applications for unmanned aerial vehicles (UAVs). However, the state-of-the-art (SOTA) enhancers for nighttime UAV tracking always neglect the uneven light distribution in low-light images, inevitably leading to excessive enhancement in scenarios with complex illumination. To address these issues, this work proposes a novel enhancer, i.e., LDEnhancer, enhancing nighttime UAV tracking with light distribution suppression. Specifically, a novel image content refinement module is developed to decompose the light distribution information and image content information in the feature space, allowing for the targeted enhancement of the image content information. Then this work designs a new light distribution generation module to capture light distribution effectively. The features with light distribution information and image content information are fed into the different parameter estimation modules, respectively, for the parameter map prediction. Finally, leveraging two parameter maps, an innovative interweave iteration adjustment is proposed for the collaborative pixel-wise adjustment of low-light images. Additionally, a challenging nighttime UAV tracking dataset with uneven light distribution, namely NAT2024-2, is constructed to provide a comprehensive evaluation, which contains 40 challenging sequences with over 74K frames in total. Experimental results on the authoritative UAV benchmarks and the proposed NAT2024-2 demonstrate that LDEnhancer outperforms other SOTA low-light enhancers for nighttime UAV tracking. Furthermore, real-world tests on a typical UAV platform with an NVIDIA Orin NX confirm the practicality and efficiency of LDEnhancer. The code is available at https://github.com/vision4robotics/LDEnhancer.