Aug 2026· International Conference on Digital Image Processing· Vol 14351, pp. 143510E - 143510E-9· 0 citations· 26 references
Engineering
TL;DR
DAR-Track is proposed, a novel framework that harmonizes dynamic computation with generative modeling and outperforms state-of-the-art methods, including MixFormer and SGLATrack, while maintaining superior inference speeds suitable for real-time aerial robotics.
Abstract
Striking an optimal balance between robust tracking performance and real-time computational efficiency remains a significant challenge in the field of Unmanned Aerial Vehicle (UAV) tracking. UAV operational environments are characterized by rapid viewpoint changes, severe occlusions, and stringent onboard energy constraints, which impose rigorous demands on tracking algorithms. While recent generative trackers formulated as sequence interpretation tasks have achieved remarkable accuracy, their heavy autoregressive computations often result in high latency. Conversely, lightweight discriminative trackers frequently lack the temporal context required to handle long-term occlusions. To bridge this gap, we propose DAR-Track, a novel framework that harmonizes dynamic computation with generative modeling. First, we introduce an Adaptive Depth Gating (ADG) strategy to optimize the backbone encoder. This mechanism acts as an intelligent regulator, dynamically quantifying feature redundancy via inter-layer Euclidean distances and selectively bypassing saturated Transformer layers. Second, instead of traditional regression heads, we design a Prompt-Guided Autoregressive Decoder (PGAD). This module leverages historical coordinate sequences as spatio-temporal prompts to guide the generation of current target tokens. Furthermore, we employ a decoupled parallel attention mechanism to accelerate the decoding process. Extensive experiments on four authoritative benchmarks demonstrate that DAR-Track outperforms state-of-the-art methods, including MixFormer and SGLATrack, while maintaining superior inference speeds suitable for real-time aerial robotics.
Robust state estimation in GPS-denied environments remains a primary challenge for Visual-Inertial Odometry (VIO). Traditional VIO pipelines relying on hand-crafted features often experience drift or tracking failure under rapid motion and dynamic lighting. While deep learning-based local features offer improved robustness, high computational costs frequently limit their adoption in real-time, resource-constrained systems. In this work, we propose XVINS, a hybrid VIO frontend integrating XFeat—a lightweight deep feature extractor—into the optimization-based VINS-Fusion framework. The system employs a dual-strategy tracking mechanism: computationally efficient KLT optical flow is utilized for high-frequency temporal tracking, while XFeat in-ference is dynamically triggered for feature replenishment during tracking degradation. We evaluate this architecture across the 11 sequences of the EuRoC MAV dataset. The results indicate improved robustness to motion blur, reducing absolute trajectory error by up to 82.7% in highly dynamic scenarios compared to baseline methods. Furthermore, we analyze the theoretical and practical tradeoffs between deep feature quantization and classical sub-pixel precision, presenting XVINS as a viable, real-time state estimation solution for agile Micro-Aerial Vehicles (MAVs) and mobile platforms.
Thura Peou, Sarot Srang, Lychek Keo· E3S Web of Conferences· 0 citations
: To tackle critical visual tracking difficulties arising in UAV tracking tasks, including frequent target occlusion and abrupt fast motion during high-altitude inspection, we propose an adaptive correlation filter tracking algorithm incorporating a motion smoothing module and adaptive residual regularization, named MACF. The tracker is constructed via multi-strategy fusion of two elaborately designed components at the algorithmic modeling level. First, we design a Motion Smoothing Module (MSM) that conducts weighted fusion of historical motion trends in the modeling pipeline. It suppresses search window jitter arising from instantaneous positioning errors and lowers target drift risk by providing precise spatial priors for search center prediction. Second, we embed an Adaptive Residual (AR) regularization term into the objective function of the correlation filter model, which analyzes temporal feature fluctuations to suppress contextual interference and avoid misleading caused by sporadic distractors. The synergistic effect of the motion smoothing module and adaptive residual regularization enables the filter to adapt to various feature changes, thereby maintaining tracking continuity under target occlusion, rapid motion and blurring.
Yu-Feng Yu, Xiaoying Tan, Qirong Wu et al.· Computer Modeling in Enginee...· 0 citations
Visual localization is vital for autonomous systems but remains challenging under dynamic conditions. Transformers offer strong temporal modeling at quadratic cost, while CNNs are efficient yet limited in long-range dependencies. Existing methods also lack robustness to illumination, weather, and seasonal changes, constraining real-world applicability. To address this, this paper proposes AdapseqNet, a dual-branch architecture that integrates stabilized state-space modeling with differential temporal enhancement. First, a stabilized state-space formulation featuring Lyapunov-constrained parameterization and adaptive discretization is proposed, ensuring asymptotic stability and linear computational complexity for reliable processing of extended sequences. Second, a selective Mamba architecture is developed to combine temporal-state modeling with content-aware gating, enabling adaptive feature selection that emphasizes discriminative cues while suppressing redundancy. Third, a differential enhancement module is designed to extract motion-invariant representations through symmetric temporal differencing and LSTM-based refinement, enhancing resilience to appearance variations caused by lighting, weather, and seasonal changes. Beyond architectural design, multi-scale feature fusion and output distribution control are incorporated to optimize representation quality and ensure consistency for similarity-based retrieval. Extensive experiments on multiple benchmarks demonstrate that AdapseqNet achieves a better localization accuracy across diverse and challenging conditions. Note to Practitioners—Visual localization is crucial for autonomous robots but often fails under varying lighting, weather, or seasonal conditions. We propose a dual-path approach: one path captures long-term patterns using control-inspired stable modeling, while the other extracts motion cues that remain consistent despite appearance changes. This combination enables accurate place recognition even in extreme environments. Our system operates efficiently on standard hardware and was tested on an indoor robot, achieving centimeter-level accuracy. This approach can enhance existing navigation systems without requiring additional sensors. Future work will focus on real-time optimization for outdoor deployment.
Zhenyu Li, Tianyi Shang· IEEE Transactions on Automat...· 0 citations
With the rapid advancement of unmanned aerial vehicle (UAV) technology, UAV-based visual object tracking has emerged as a significant research focus, particularly in the domain of remote sensing. However, low-light conditions at night severely degrade the accuracy and robustness of tracking algorithms, limiting the effective deployment of UAVs in nocturnal environments. Most existing trackers are primarily designed for normal lighting conditions and struggle to extract discriminative representations of degraded target features in low-light scenes. To address these challenges, we propose a novel spatial–frequency synergistic Transformer tracking (SFSTrack) model. The key of this model lies in the design of a spatial–frequency feature synergist (SFFS), which mainly consists of two components: a multilevel spatial residual enhancement (MSRE) block and a frequency-aware adaptive feature refinement (FAFR) block. On one side, the spatial layer improves features in dark regions under low-light conditions through iterative learning. On the other side, the frequency-domain refinement branch is constructed by integrating the Fourier transform, allowing the model to suppress noise interference while also enhancing high-frequency details. In addition, a confidence-weighted temporal feature fusion (CWTF) mechanism is designed, which adaptively integrates reliable target appearance information from historical frames, thereby reducing tracking drift caused by feature degradation in the current frame or large changes in target appearance. Experiments on public nighttime tracking benchmarks, including NAT2021, NAT2021L, DarkTrack2021, and UAVDark135, show that the proposed algorithm outperforms existing state-of-the-art methods, thus verifying the effectiveness and robustness of SFSTrack for UAV object tracking in nighttime low-light conditions.
Lifan Sun, Yuxuan Du, Yang Liu et al.· IEEE Transactions on Geoscie...· 0 citations
Thermal infrared (TIR) imaging is essential for UAV swarm operations in visually degraded environments. However, tracking tiny UAVs remains challenging due to limited appearance cues, frequent occlusions, and rapid maneuvers. Despite significant progress driven by benchmarks such as the Anti-UAV challenge, existing methods primarily prioritize accuracy while overlooking the computational constraints of real-time edge deployment. The standard Kalman Filter (KF) offers the efficiency required for edge devices, yet its constant-velocity assumption often breaks down under highly dynamic UAV motion and thermal sensor jitter. More sophisticated nonlinear estimators can improve robustness but often introduce additional computational costs. To address this gap, we propose an edge-aware online tracking pipeline centered on the Adaptive Kinematic Kalman Filter (AKKF), which augments the linear KF with state-dependent kinematic modeling while preserving real-time efficiency. Combined with transient false-positive suppression and kinematics-driven predictive coasting, the presented pipeline improves trajectory continuity under challenging TIR conditions. Experiments on the Beyond Strong Baseline (BSB) benchmark provide a starting point for edge-aware UAV tracking by jointly evaluating tracking performance and computational efficiency, offering insights toward future real-time deployment.
Unmanned Aerial Vehicle (UAV) object tracking has emerged as a popular research field with broad practical applications. Modern UAVs are increasingly equipped with both visible light and thermal infrared sensors. However, due to constraints in communication bandwidth, computational resources and power consumption, current systems often activate one modality and switch between modalities to maintain robust tracking in complex scenarios. Such modality switch inevitably leads to significant appearance change and sudden spatial shift, posing great challenges for existing tracking algorithms. To handle this problem, we propose a novel State-Aware Representation Learning Approach called SARLA, which perceives the inconsistent modality states of current frame with template and last frame in the target representations to adapt to the sudden changes in both appearance and position, for robust cross-modal object tracking. In particular, we propose the Modality State Aware Representation Module (MSARM) and Spatial State Aware Representation Module (SSARM). MSARM guides the model to learn appearance correlation, bridging the modality gap, while SSARM models cross-frame spatial correlation to mitigate sudden spatial shift impacts. In addition, we design a spatial shift prediction loss to further handle the effects of spatial variation caused by modality switch. To promote the development of this research field, we establish a large-scale video benchmark called CM-UOT, which consists of 1079 cross-modal sequences with an average video length greater than 621 frames and encompasses over 671K frames in total. Extensive experiments on CM-UOT dataset demonstrate the superior performance of the proposed SARLA against 20 excellent tracking methods. The source code, datasets, and evaluation protocols associated with this work are publicly available at: https://github.com/hongsmile365/sarla-.
Yun Xiao, Zhihong Hong, Jiandong Jin et al.· 0 citations