Organizations: Pratt School of Engineering, Duke University, Durham 27705, United States · School of Mechanical Engineering, Tongji University, Shanghai 201804, China · Shanghai Key Laboratory of Wearable Robotics and Human Machine Interaction, Tongji University, Shanghai 201804, China · School of Computing and Data Science, The University of Hong Kong, Hong Kong, 999077, China
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.
Figures & tables
Fig. 1: The overall comparison between the SOTA method and the proposed DPTracker. With prompt-feature interaction, DPTracker learns adaptive features and outperforms SOTA trackers in nighttime UAV tracking.
Fig. 2: Overall model architecture of DPTracker. The interaction between prompt tokens and features integrates prompt semantics into the features while updating the prompt tokens, thereby enhancing nighttime UAV tracking with more adaptive representations. The images are from NAT2021- test [ 4 ] .
Fig. 3: The architecture of the pyramid illumination prompter and the dynamic viewpoint prompter. The illumination prompter leverages a learnable pyramid network to decompose images and aggregate multi-scale features, while the dynamic viewpoint prompter combines standard and deformable convolutions to adaptively capture viewpoint information under UAV perspectives. The images are from DarkTrack2021 [ 8 ] .
Fig. 4: Tracking result visualization of DPTracker-B along with other top trackers [ 20 , 18 , 9 , 4 , 21 ] . The sequences are selected from UAVDark135 [ 22 ] . The proposed DPTracker-B shows more robust and precise tracking performance under diverse nighttime UAV tracking scenarios.
Fig. 5: Attribute-based tracking performance evaluation. As shown in the left figure, DPTracker-T consistently achieves the best performance across all 8 attributes on NAT2021-test [ 4 ] , outperforming 5 other lightweight trackers [ 23 , 24 , 25 , 26 , 5 ] . In the right figure, DPTracker-B also demonstrates substantial performance improvements compared to other well-performing trackers [ 21 , 4 , 9 , 18 , 20 ] .
Fig. 6: Real-world UAV tracking tests under nighttime conditions. Regions in blue, where the CLE is less than 20, are regarded as successful tracking cases, while the orange regions represent challenging tracking conditions.
Visual object tracking follows objects across video frames, maintaining their locations and identities despite motion, occlusion, and changing appearance.
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.
Yanyan Chen, Ruigang Fu, Yu Song +1
College of Electrical Science and Technology, National University of Defense Technology
Given the real-time demands of UAV tracking, many methods simplify the backbone to reduce computation, but this often weakens feature representation and degrades performance in complex scenarios. To alleviate this issue, we propose EATrack, an efficient and asymmetric UAV tracking framework centered around a teacher-guided dual-branch distillation strategy that enhances the feature expressiveness of the lightweight student model. Specifically, EATrack investigates two complementary perspectives of knowledge transfer: spatially focused feature-level distillation that compensates for weakened representations by guiding the student to learn strong target representations, and prediction-level distillation that enhances spatial localization by learning the teacher's capability for accurate target localization. Furthermore, to enhance robustness against appearance variations, we introduce a fine-grained target-aware distillation strategy that selectively transfers the teacher's target modeling capacity to the student. A temporal adaptation module is incorporated at inference to enhance robustness over time. Experiments on five UAV benchmarks demonstrate that EATrack achieves a favorable balance between accuracy and speed. Code: https://github.com/GXNU-ZhongLab/EATrack
Hongtao Yang, Bineng Zhong, Qihua Liang +4
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, 541004, China · Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, China · Nanjing University of Science and Technology +1
UAV-ground visual tracking (UGVT) aims to simultaneously track the same object from both the UAV and the ground view. However, existing two-stream methods suffer from isolated feature extraction and rely heavily on implicit appearance matching, which struggles to establish reliable correspondence under drastic view differences, leading to tracking unreliability. To address these limitations, we propose VL-UniTrack, a fully unified framework enhanced by visual-language prompts. By encoding features from both views within a single shared encoder, our method breaks the barrier of feature isolation to facilitate sufficient cross-view interaction. To overcome the ambiguity caused by relying solely on appearance matching, we design visual-language geometric prompting module, which fuses language descriptions with visual features to generate learnable prompts. These prompts are then fed into our prompt-guided cross-view adapter module to enable sufficient cross-view feature interaction and to guide the learning of view-specific feature representations. Furthermore, a confidence-modulated mutual distillation loss is proposed to regularize the training by mitigating noise propagation. Extensive experiments demonstrate that our method achieves state-of-the-art performance on the latest benchmark. The code can be downloaded in https://github.com/xuboyue1999/VL-UniTrack.git
Boyue Xu, Ruichao Hou, Tongwei Ren +1
State Key Laboratory for Novel Software Technology, Nanjing University