Detecting small objects from UAV-captured aerial imagery is a critical yet challenging task, hindered by factors such as small object size, complex backgrounds, and subtle inter-class differences. Single-modal methods lack the robustness for all-weather operation, while existing multimodal solutions are often too computationally expensive for deployment on resource-constrained UAVs. To this end, we propose TAF-YOLO, a lightweight and efficient multimodal detection framework designed to balance accuracy and efficiency. First, we propose an early fusion module, the Two-branch Adaptive Fusion Network (TAFNet), which adaptively integrates visible and infrared information at both pixel and channel levels before the feature extractor, maximizing complementary data while minimizing redundancy. Second, we propose a Large Adaptive Selective Kernel (LASK) module that dynamically expands the receptive field using multi-scale convolutions and spatial attention, preserving crucial details of small objects during downsampling. Finally, we present an optimized feature neck architecture that replaces PANet’s bidirectional path with a more efficient top-down pathway. This is enhanced by a Dual-Stream Attention Bridge (DSAB) that injects high-level semantics into low-level features, improving localization without significant computational overhead. On the VEDAI benchmark, TAF-YOLO achieves 67.2% mAP₅₀, outperforming the CFT model by 2.7% and demonstrating superior performance against seven other YOLO variants. Our work presents a practical and powerful solution that enables real-time, all-weather object detection on resource-constrained UAVs.

Detecting small objects from UAV-captured aerial imagery is a critical yet challenging task, hindered by factors such as small object size, complex backgrounds, and subtle inter-class differences. Single-modal methods lack the robustness for all-weather operation, while existing multimodal solutions are often too computationally expensive for deployment on resource-constrained UAVs. To this end, we propose TAF-YOLO, a lightweight and efficient multimodal detection framework designed to balance accuracy and efficiency. First, an early fusion module, the Two-branch Adaptive Fusion Network (TAFNet), which adaptively integrates visible and infrared information at both pixel and channel levels before the feature extractor, maximizing complementary data while minimizing redundancy. Second, a Large Adaptive Selective Kernel (LASK) module that dynamically expands the receptive field using multi-scale convolutions and spatial attention, preserving crucial details of small objects during downsampling. Finally, an optimized feature neck architecture that replaces PANet's bidirectional path with a more efficient top-down pathway. This is enhanced by a Dual-Stream Attention Bridge (DSAB) that injects high-level semantics into low-level features, improving localization without significant computational overhead. On the VEDAI benchmark, TAF-YOLO achieves 67.2% mAP50, outperforming the CFT model by 2.7% and demonstrating superior performance against seven other YOLO variants. Our work presents a practical and powerful solution that enables real-time, all-weather object detection on resource-constrained UAVs.

Multimodal object detection is currently a research hotspot in computer vision. However, the fusion of visible and infrared modalities inevitably increases computational complexity, making most high-performance detection models difficult to deploy on resource-constrained UAV edge devices. Although pruning and knowledge distillation are widely used for model compression, applying them independently often leads to an unstable accuracy–efficiency trade-off. Therefore, this paper proposes a hybrid lightweight algorithm named SAMKD, which combines selective activation pruning with masked knowledge distillation in a staged manner to improve efficiency while maintaining detection performance. Specifically, the selective activation network pruning model (SAPM) first reduces redundant computation by dynamically adjusting network weights and the activation state of input data to generate a lightweight student network. Then, the mask binary classification knowledge distillation (MBKD) strategy is introduced to compensate for this degradation by guiding the student network to recover missing representation patterns under masked feature learning. Moreover, MBKD reformulates classification logits into multiple foreground–background binary mappings, effectively alleviating the severe foreground–background imbalance commonly observed in UAV aerial imagery. This paper constructs a multimodal UAV aerial imagery object detection dataset, M2UD-18K, which includes 9 types of targets and over 18,000 pairs. Extensive experiments show that SAMKD performs well on the self-constructed M2UD-18K dataset, as well as the public DroneVehicle dataset, achieving a favorable trade-off between detection accuracy and detection speed.

UAV (Unmanned Aerial Vehicle)-to-satellite self-localization is commonly treated as satellite tile retrieval. This makes large-area search tractable, but it also forces a continuous localization problem into a discrete ranking form. Once the task is defined this way, training naturally relies on hard positive–negative tile labels, and inference tends to read coordinates from the top-ranked tile center. The model, therefore, learns image identity more than geographic continuity, while the final estimate remains vulnerable to tile-center quantization and top-1 retrieval errors. We propose PFIRNet (Probability Field Inference Network), a continuous geographic posterior inference framework that reformulates retrieval outputs as evidence for coordinate estimation rather than discrete tile selection. It uses distance-aware geographic supervision to shape candidate responses according to metric proximity, lifts top-k candidates into a coordinate-space probability field, and applies risk-calibrated multi-peak verification to update the estimate only when an alternative posterior peak is sufficiently supported. On DenseUAV, PFIRNet reduces the median localization error to 9.84 m and outperforms both one-stage retrieval methods and two-stage matching baselines. It also remains more robust under sparse and non-aligned satellite galleries.

Low-light Unmanned Aerial Vehicle (UAV) image enhancement is crucial for downstream tasks such as object detection and navigation. However, low-light UAV images often have complex illumination patterns and high noise levels. Existing mainstream low-light enhancement methods tend to introduce color cast and local overexposure on such images. To address these issues, we propose a Low-light UAV image enhancement network named UAV-LIENet, and we train it with three progressive sub-networks. UAV-LIENet first applies a Non-uniform Luminance Estimation Network (NLEN) to reconstruct a smooth and uniform illumination component. NLEN adopts quantile-clipping normalization and a parallel coarse-and-fine architecture for illumination estimation. Then, UAV-LIENet performs adaptive denoising and color restoration under the guidance of the estimated luminance component. For accurate and stable color restoration, we design an illumination-guided saturation constraint loss, which adaptively constrains saturation in the HSV space to reduce color cast and suppress oversaturation. To evaluate our method systematically, we build a low-light enhancement dataset named UAV-LLIE based on high-fidelity game-engine rendering. UAV-LLIE contains 6 typical aerial scenarios and 6,000 pixel-aligned image pairs. Experiments show that UAV-LIENet outperforms representative existing methods in both quantitative metrics and visual quality.