Dual Prompt-Driven Feature Encoding for Nighttime UAV Tracking

2026-03-20

AI Summary

This work addresses the limited robustness of existing nighttime UAV tracking methods, which often neglect the joint effects of illumination and viewpoint variations. To overcome this, we propose DPTracker, a dual-prompt-driven feature encoding framework that simultaneously models these factors to learn domain-invariant representations. Specifically, a pyramid illumination prompter extracts multi-scale frequency-aware features, while a dynamic viewpoint prompter adaptively modulates deformable convolution offsets. Furthermore, we introduce a context-aware prompt evolution strategy to enhance the model’s adaptability. Extensive experiments demonstrate that DPTracker significantly outperforms state-of-the-art methods across diverse nighttime UAV tracking scenarios. Ablation studies validate the contribution of each component, and real-world evaluations confirm its strong robustness and practical utility.

Technology Category

• Computer Vision: Motion & Tracking
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

Robust feature encoding constitutes the foundation of UAV tracking by enabling the nuanced perception of target appearance and motion, thereby playing a pivotal role in ensuring reliable tracking. However, existing feature encoding methods often overlook critical illumination and viewpoint cues, which are essential for robust perception under challenging nighttime conditions, leading to degraded tracking performance. To overcome the above limitation, this work proposes a dual prompt-driven feature encoding method that integrates prompt-conditioned feature adaptation and context-aware prompt evolution to promote domain-invariant feature encoding. Specifically, the pyramid illumination prompter is proposed to extract multi-scale frequency-aware illumination prompts. %The dynamic viewpoint prompter adapts the sampling to different viewpoints, enabling the tracker to learn view-invariant features. The dynamic viewpoint prompter modulates deformable convolution offsets to accommodate viewpoint variations, enabling the tracker to learn view-invariant features. Extensive experiments validate the effectiveness of the proposed dual prompt-driven tracker (DPTracker) in tackling nighttime UAV tracking. Ablation studies highlight the contribution of each component in DPTracker. Real-world tests under diverse nighttime UAV tracking scenarios further demonstrate the robustness and practical utility. The code and demo videos are available at https://github.com/yiheng-wang-duke/DPTracker.

Problem

• nighttime UAV tracking
• feature encoding
• illumination cues
• viewpoint variations
• robust perception

Innovation

• dual prompt-driven
• illumination-aware feature encoding
• viewpoint-invariant tracking
• nighttime UAV tracking
• prompt-conditioned adaptation