Papers for

drone surveillance teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

UAV image encryption protects privacy while keeping useful scene details

A Category-Selective Encryption Framework for Privacy Protection of UAV Images

Abstract: Imagery captured by unmanned aerial vehicle (UAV) systems increasingly raises privacy concerns, as UAV aerial surveillance routinely captures sensitive objects such as pedestrians and vehicles alongside ordinary scene content. Existing privacy-preserving approaches typically employ class-agnostic saliency detection to indiscriminately obfuscate all visually salient regions, leading to unnecessary information loss and hindering downstream scene analysis. This paper proposes a category-selective encryption framework for privacy-preserving UAV surveillance. The core advance over prior class-agnostic approaches is semantic-level selectivity: the system first recognizes what is present in the scene via an 80-class detector, then encrypts only user-specified sensitive categories while leaving non-sensitive objects and background intact for downstream analytics. The framework supports two complementary encryption schemes: Thumbnail-Preserving Encryption (TPE), which applies adaptive pixelation with a learnable blend parameter and recovers content through a jointly trained Enhanced U-Net, and XOR stream cipher encryption, which offers parameter-free, mathematically exact reversibility. The architectural design, composite loss formulation, and joint training methodology are presented in detail, establishing a foundation for practical privacy-preserving UAV surveillance that balances protection strength and scene utility.

Mon 26 OctCryptography and SecurityComputer Vision and Pattern Recognition
The gist
Drones capture images that often include sensitive things like people or cars, raising privacy concerns. The authors propose a system that first identifies what objects are in the image, then selectively encrypts only the sensitive categories the user wants to protect. This approach keeps the rest of the image clear, allowing further analysis without losing useful information. Two encryption methods are offered: one that pixelates sensitive parts but can restore details later, and another that fully encrypts data but can be perfectly reversed.
Open → 2610.35729v1

Dynamic budgeting improves tiny object detection speed and accuracy

Dynamic Query as Budgeting for Tiny Object Detection

Abstract: Recent DETR-based tiny object detectors adopt dynamic query mechanisms to handle severe density imbalance. However, existing designs entangle two effects: how many and which queries are decoded. This entanglement obscures what drives the gains and complicates dynamic-query design; additional learned predictors and heuristic filtering also introduce overhead and potential selection errors. We disentangle these effects and show that dynamic query primarily acts as \emph{budgeting}---allocating decoder query capacity according to object density---rather than intricate query selection.Motivated by this view, we formulate a monotonic and conservative budgeting principle and propose a budgeting-based DETR (BUTR), a streamlined framework that uses a lightweight, non-learned budgeter to estimate an input-dependent query budget $K(x)$ from encoder confidences. BUTR retains standard Top-$K(x)$ query initialization without additional learned modules or heuristic filtering in the budgeter.At $800\times800$ resolution, BUTR-L achieves 35.7 AP at 47.8 FPS on AI-TOD-v2 and 29.8 AP at 42.1 FPS on VisDrone on an NVIDIA T4 GPU. Inference-time integration on COCO further demonstrates its applicability to general scenario detection. Code is available at https://github.com/zhangyi-magic/BUTR.

Sat 24 OctComputer Vision and Pattern Recognition
The gist
Detecting tiny objects in images is hard because there are often many more objects than a detector's queries can handle. The authors found that what really matters is deciding how many queries to use based on object density, not which specific queries to select. They designed a simple method called BUTR that adjusts the number of queries automatically using a lightweight budgeter, leading to faster and more accurate detection. This approach works well on tiny object datasets and general detection tasks without adding complexity.
Open → 2610.33430v1

Spectral aware tracking improves UAV multispectral object detection

Spectral-Aware Proposal Enhancement for Diffusion-Based Multispectral UAV Multi-Object Tracking

Abstract: Multispectral UAV multi-object tracking (MOT) with oriented bounding boxes remains challenging due to small targets, cluttered backgrounds, and unstable inter-frame associations. Although diffusion-based MOT provides an effective iterative proposal refinement paradigm, existing diffusion-based trackers lack dedicated designs for exploiting multispectral cues in proposal initialization and confidence calibration, limiting tracking robustness in complex UAV scenarios. This letter proposes DSATrack, a diffusion-guided spectral-aware tracking framework for multispectral UAV MOT. Specifically, a lightweight spectral encoder injects multispectral information into the RPN branch through feature fusion, enabling the RPN head to generate high-quality object-aware proposals. These proposals are then injected into the initial proposal set to provide reliable spatial priors for diffusion refinement. Furthermore, a spectral-saliency confidence modulation strategy recalibrates refined tracking confidence according to local multispectral saliency contrast before score thresholding, enhancing spectrally reliable candidates while suppressing unreliable ones. Without modifying the original diffusion refinement head, DSATrack improves both proposal quality and post-refinement candidate selection. Experiments on the MMOT benchmark demonstrate that DSATrack outperforms the adapted DiffusionTrack baseline by 4.6 HOTA, 9.0 MOTA, and 7.7 IDF1 points, showing its effectiveness for multispectral UAV MOT.

Sat 17 OctComputer Vision and Pattern Recognition
The gist
Tracking multiple objects from drones is hard, especially when objects are small and backgrounds are cluttered. The authors propose a new way to use color information beyond visible light, called multispectral data, to help track objects better. Their method improves how initial guesses about object positions are made and how confident the system is about those guesses. Testing shows their approach tracks objects more accurately and reliably from drone videos.
Open → 2610.24642v1

Physical constraints shape adversarial patches for aerial image recognition

Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Bound

Abstract: Adversarial patches for aerial perception are typically evaluated as digital composites, with printing left as an implementation detail. This study imposes three physical constraints during optimization rather than after it: the color range a particular printer can reproduce, the size of the flat panel a vehicle offers, and the loss of fine detail incurred when the patch is imaged from altitude. The principal comparison isolates the ink set. Two patches share all seventeen recorded optimization settings and differ only in the colors available to them. One is constrained to a uniform color cube; the other to a gamut measured by printing and scanning a 216-patch chart. Each was optimized at three seeds and evaluated against thirteen victim conditions, with every rate reported against a size-matched optimized control. The effect of the measured gamut is victim-dependent rather than uniform. Net attack success rises on three of six closed-set segmentation victims, and for these the seed ranges of the two ink sets are disjoint: $+0.120$ on DeepLabv3-R101 and $+0.041$ on SegFormer-B0. The color-cube patch is consistently stronger on the open-vocabulary segmenter and on two of four detectors, though no detector exceeds a net of $+0.026$ under either ink set. The natural explanation is that a printable palette is simply less chromatic and lower in frequency than a digital one. Eleven further patches test this account and it does not hold. Once cardinality is matched, a palette as chromatic as the cube attacks equally well. Cardinality itself shows no trend from three inks to thirty-two. Palettes matched on cardinality, lightness and chroma, and differing only in hue placement, span $0.035$ to $0.136$. A physical evaluation with printed decals did not detect transfer; it bounds the transferred rate at $0.133$, which does not exclude the simulated value of $0.121$.

Sun 27 SeptComputer Vision and Pattern Recognition
The gist
Adversarial patches are patterns designed to confuse aerial image recognition systems, but most studies test these patches digitally, ignoring real-world printing limits. The authors studied how color, size, and viewing conditions affect patch effectiveness when physically printed and viewed from above. They found that using a real printer’s color range can change attack success depending on the target system, but limiting colors alone doesn’t consistently weaken attacks. Physical tests with printed patches showed some differences from simulations, setting a boundary on real-world effectiveness. This work helps better understand how printed adversarial patterns perform in aerial settings compared to purely digital designs.
Open → 2609.33513v1

Event camera method improves tiny drone detection with fewer errors

PointEvent: Rethinking Event-based Tiny Object Detection via Serialized Motion Evidence Accumulation

Abstract: Event cameras offer high temporal resolution and motion sensitivity for tiny UAV detection, yet distant targets generate sparse and fragmented events that are easily overwhelmed by clutter and ego-motion. Existing methods mainly rely on dense event representations or local sparse spatiotemporal modeling, resulting in redundant computation or fragmented modeling of motion continuity across distant asynchronous events. To address this limitation, we introduce serialized motion evidence accumulation, which treats motion continuity as an ordered evidence propagation process. Specifically, the same event stream is organized into locality-preserving spatiotemporal paths and chronology-preserving temporal paths through the latent complementary serializations. Based on this principle, we propose PointEvent, a lightweight event-wise state-space framework that alternates serialized scans across the complementary orders, progressively consolidating fragmented motion evidence beyond fixed local neighborhoods. A high-resolution event branch preserves fine-grained target responses, while compact context modulation suppresses interference. Experiments demonstrate that PointEvent achieves SOTA with the fewest parameters and fastest measured inference among the compared methods. Code: https://github.com/wzz-z/PointEvent

Thu 17 SeptComputer Vision and Pattern RecognitionArtificial Intelligence
The gist
Detecting tiny drones far away can be hard because special event cameras produce scattered signals that are noisy or incomplete. The authors propose a new method called PointEvent that looks at these signals in a clever order to piece together the motion better. This approach uses less computing power but keeps important details, helping it detect small moving objects more accurately and quickly than previous methods. Their tests show it works well and runs fast.
Open → 2609.20066v1

Semi supervised visible infrared object detection with aligned consensus teacher

Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagery

Abstract: Visible-infrared object detection (VIOD) detects objects with oriented bounding boxes from paired visible and infrared images. Existing methods depend on costly dual-modality annotations. Semi-supervised learning can reduce this burden, but extending it from single-modal detection to VIOD is challenging. In the practical image-pair-level setting considered here, only a few pairs are labeled in both modalities, while the rest are completely unlabeled. This limited supervision creates three challenges: (i) too few labeled boxes for robust cross-modal alignment; (ii) pseudo-label errors caused by branch-wise misses accumulate during self-training; and (iii) tail-class annotations become critically scarce as the labeling budget decreases. We propose Aligned Consensus Teacher (ACT) for label-efficient VIOD in this setting. Its Cycle-Consistent Region Alignment (CRA) combines cycle consistency and sparse anchors with reliability-weighted regional matching. Cross-Modal Consensus Mean-Teacher (CMC-MT) forms consensus pseudo labels under pair-preserving views to recover branch-wise misses and supervise unlabeled pairs. Text-Guided Cross-Modal Instance Augmentation (TG-CMIA) uses a vision-language scene prior to compose tail-class instance pairs while preserving RGB--IR offsets. To the best of our knowledge, ACT is the first framework to study semi-supervised VIOD under this image-pair-level setting. Experiments on DroneVehicle and VEDAI show consistent gains across annotation ratios. With 10\% labeled pairs on DroneVehicle, ACT reaches 94.3\% of the mAP obtained by the same detector under full supervision. Code and models will be available on GitHub to facilitate future work.

Wed 16 SeptComputer Vision and Pattern Recognition
The gist
Detecting objects in images taken by both regular cameras and infrared cameras usually needs lots of detailed labels, which are expensive to get. The authors developed a method called Aligned Consensus Teacher that uses only a small amount of labeled image pairs and many unlabeled pairs to learn accurately. Their approach smartly aligns objects between visible and infrared images and improves predictions by combining knowledge from both types of images. This method works well even when only a small fraction of the image pairs are labeled, achieving performance close to fully labeled training.
Open → 2609.18124v1

UAV swarm tracking improved by motion prior guided feature correction

EECTracker: Swarm Motion Prior-Guided Feature Compensation for Airborne Optical UAV Swarm Tracking

Abstract: Airborne optical tracking of uncrewed aerial vehicle (UAV) swarms is challenging due to extremely small target scales, rapid viewpoint changes, and cluttered backgrounds, which can weaken target feature responses and lead to intermittent or temporarily missing detector responses. Existing multi-object tracking methods generally depend on reliable target-specific detector responses to maintain target states and identities across frames. When such responses become unreliable, target states cannot be reliably updated and cross-frame association cues become ambiguous, resulting in fragmented trajectories and identity switches. To address this problem, we propose EECTracker, a swarm-motion-prior-guided joint detection-and-tracking framework for airborne optical UAV swarm tracking. EECTracker constructs a probabilistic swarm motion prior from reliable historical tracklets to capture the shared short-term image-plane motion tendency of the swarm and its uncertainty, providing spatial guidance for cross-frame feature compensation. Building on this prior, we introduce Energy--Entropy Consistency Activation (EEC Activation) to evaluate motion-prior-conditioned feature consistency using feature residual energy and local residual entropy. The resulting Local EEC score guides pixel-level feature compensation by enhancing motion-prior-consistent feature responses in potential target regions while suppressing inconsistent background responses. Experiments on AIRMOT and UAVSwarm show that EECTracker achieves superior overall tracking performance compared with state-of-the-art methods. Compared with the strongest competing method SCT-MOT, EECTracker improves MOTA/IDF1 by 3.89/1.79 percentage points on AIRMOT and by 2.81/1.74 percentage points on UAVSwarm, while maintaining online inference speed.

Mon 14 SeptComputer Vision and Pattern Recognition
The gist
Tracking groups of drones using cameras is hard because drones look very small and move quickly against busy backgrounds, which makes it tough to keep track of each one. The authors designed a new method called EECTracker that learns how the drone swarm tends to move together and uses that information to fix and improve the features used for tracking. Their method helps avoid losing track of drones or confusing their identities, leading to better overall tracking accuracy compared to previous approaches.
Open → 2609.15171v1