arXiv:2512.04883v1 Announce Type: new 
Abstract: Real-time tracking of small unmanned aerial vehicles (UAVs) on edge devices faces a fundamental resolution-speed conflict. Downsampling high-resolution imagery to standard detector input sizes causes small target features to collapse below detectable thresholds. Yet processing native 1080p frames on resource-constrained platforms yields insufficient throughput for smooth gimbal control. We propose SDG-Track, a Sparse Detection-Guided Tracker that adopts an Observer-Follower architecture to reconcile this conflict. The Observer stream runs a high-capacity detector at low frequency on the GPU to provide accurate position anchors from 1920x1080 frames. The Follower stream performs high-frequency trajectory interpolation via ROI-constrained sparse optical flow on the CPU. To handle tracking failures from occlusion or model drift caused by spectrally similar distractors, we introduce Dual-Space Recovery, a training-free re-acquisition mechanism combining color histogram matching with geometric consistency constraints. Experiments on a ground-to-air tracking station demonstrate that SDG-Track achieves 35.1 FPS system throughput while retaining 97.2\% of the frame-by-frame detection precision. The system successfully tracks agile FPV drones under real-world operational conditions on an NVIDIA Jetson Orin Nano. Our paper code is publicly available at https://github.com/Jeffry-wen/SDG-Track

يقدم SDG-Track نظام تتبع جديد يعتمد على تقنية Sparse Detection-Guided Tracker، مصمم لتحسين قدرات تتبع الطائرات بدون طيار الصغيرة (UAV) في الوقت الحقيقي على منصات مدمجة ذات موارد محدودة. يتناول هذا الإطار الصراع الأساسي بين الدقة والسرعة من خلال استخدام بنية Observer-Follower، مما يسمح بتتبع دقيق حتى في الظروف الصعبة.

La introducción de SDG-Track presenta un nuevo Sparse Detection-Guided Tracker diseñado para mejorar las capacidades de seguimiento en tiempo real de pequeños vehículos aéreos no tripulados (UAV) en plataformas embebidas con recursos limitados. Este marco aborda el conflicto inherente entre resolución y velocidad mediante una arquitectura de Observador-Seguidor, permitiendo un seguimiento preciso incluso en condiciones desafiantes.

L'introduction de SDG-Track présente un nouveau Sparse Detection-Guided Tracker conçu pour améliorer les capacités de suivi en temps réel des petits véhicules aériens sans pilote (UAV) sur des plateformes embarquées à ressources limitées. Ce cadre aborde le conflit inhérent entre résolution et vitesse en utilisant une architecture Observer-Follower, permettant un suivi précis même dans des conditions difficiles.

The introduction of SDG-Track presents a novel Sparse Detection-Guided Tracker designed to enhance the real-time tracking capabilities of small unmanned aerial vehicles (UAVs) on resource-constrained embedded platforms. This framework addresses the inherent resolution-speed conflict by utilizing an Observer-Follower architecture, allowing for accurate tracking even in challenging conditions.

SDG-Track: A Heterogeneous Observer-Follower Framework for High-Resolution UAV Tracking on Embedded Platforms

arXiv:2512.08639v1 Announce Type: new 
Abstract: Aerial Vision-and-Language Navigation (VLN) aims to enable unmanned aerial vehicles (UAVs) to interpret natural language instructions and navigate complex urban environments using onboard visual observation. This task holds promise for real-world applications such as low-altitude inspection, search-and-rescue, and autonomous aerial delivery. Existing methods often rely on panoramic images, depth inputs, or odometry to support spatial reasoning and action planning. These requirements increase system cost and integration complexity, thus hindering practical deployment for lightweight UAVs. We present a unified aerial VLN framework that operates solely on egocentric monocular RGB observations and natural language instructions. The model formulates navigation as a next-token prediction problem, jointly optimizing spatial perception, trajectory reasoning, and action prediction through prompt-guided multi-task learning. Moreover, we propose a keyframe selection strategy to reduce visual redundancy by retaining semantically informative frames, along with an action merging and label reweighting mechanism that mitigates long-tailed supervision imbalance and facilitates stable multi-task co-training. Extensive experiments on the Aerial VLN benchmark validate the effectiveness of our method. Under the challenging monocular RGB-only setting, our model achieves strong results across both seen and unseen environments. It significantly outperforms existing RGB-only baselines and narrows the performance gap with state-of-the-art panoramic RGB-D counterparts. Comprehensive ablation studies further demonstrate the contribution of our task design and architectural choices.

تم تقديم إطار عمل جديد للتنقل الجوي باستخدام الرؤية واللغة (VLN) يمكّن الطائرات بدون طيار (UAV) من تفسير التعليمات باللغة الطبيعية والتنقل في البيئات الحضرية باستخدام ملاحظات RGB أحادية العين فقط. تبسط هذه الطريقة عملية التنقل من خلال تحسين الإدراك المكاني، والتفكير في المسار، وتوقع الإجراءات من خلال التعلم متعدد المهام الموجه بالمحفزات.

Se ha introducido un nuevo marco para la navegación aérea mediante visión y lenguaje (VLN), que permite a los vehículos aéreos no tripulados (UAV) interpretar instrucciones en lenguaje natural y navegar por entornos urbanos utilizando únicamente observaciones RGB monoculares egocéntricas. Este enfoque simplifica el proceso de navegación al optimizar la percepción espacial, el razonamiento de trayectorias y la predicción de acciones a través de un aprendizaje multitarea guiado por indicaciones.

Un nouveau cadre pour la navigation aérienne par vision et langage (VLN) a été introduit, permettant aux véhicules aériens sans pilote (UAV) d'interpréter des instructions en langage naturel et de naviguer dans des environnements urbains en utilisant uniquement des observations RGB monoculaires égocentriques. Cette approche simplifie le processus de navigation en optimisant la perception spatiale, le raisonnement de trajectoire et la prédiction d'action grâce à un apprentissage multitâche guidé par des invites.

A new framework for Aerial Vision-and-Language Navigation (VLN) has been introduced, enabling unmanned aerial vehicles (UAVs) to interpret natural language instructions and navigate urban environments using only egocentric monocular RGB observations. This approach simplifies the navigation process by optimizing spatial perception, trajectory reasoning, and action prediction through prompt-guided multi-task learning.

SDG-Track: A Heterogeneous Observer-Follower Framework for High-Resolution UAV Tracking on Embedded Platforms

Was this article worth reading? Share it

Eyeware Beam

AsyncStatus

Guidejar-4eb95b