Sep 2026· International Conference on Internet of Things, Communication Engineering, and Artificial Intelligence· Vol 14373, pp. 143730R - 143730R-8· 0 citations· 20 references
Engineering
TL;DR
This work introduces a novel architecture termed LAI-YOLO, integrating attention mechanisms into a compact design that achieves 34.8% mAP50 on the VisDrone2019 dataset with only 2.38M parameters.
Abstract
Identifying miniature targets within drone-captured visuals continues to be a demanding task, primarily driven by restricted image clarity, intricate environmental contexts, and the scarce computational power available on flight platforms. In response to such bottlenecks, we introduce a novel architecture termed LAI-YOLO. By integrating attention mechanisms into a compact design, this model successfully strikes an optimal equilibrium between computational swiftness and recognition precision. The key improvements are summarized as follows: 1) In the backbone, a Cross-stage partial Shiftwise Partitioning Dynamic Patch-aware attention (C_SPDP) block is introduced to enhance the detection accuracy. 2) In the neck, a Hierarchical Feature Pyramid Network (HFPN) is constructed to reduce model parameters. 3) For the detection head, we introduce a Lightweight Scale-aware Convolutional Detection with Localization Quality Estimation (LSCD_LQE) structure to reduce computational overhead and enhance localization consistency. 4) Moreover, a new loss function, Wise-Inner-ShapeIoU (WISIoU), is developed to refine bounding-box regression through shape consistency constraints and adaptive gradient scaling. The proposed LAI-YOLO achieves 34.8% mAP50 on the VisDrone2019 dataset with only 2.38M parameters. Furthermore, its generalization capability is validated on the UAVDT, AI-TOD, and CODrone datasets, demonstrating the robustness and effectiveness of our method.
This work proposes LSO-YOLO, a novel real-time detector optimized for UAV-based small-object detection that significantly reduces parameter count and computational cost by approximately 67% and 18.18%, respectively, while maintaining a high inference speed of 126 FPS on an NVIDIA RTX 3060 GPU, meeting the requirements...
Peng-Fei Dai, Liang Chen, Yang-Wu Lian et al.· Journal of Real-Time Image P...· 0 citations
An improved model based on YOLOv11n, named RMD-YOLO11n, is proposed, which significantly improves multi-scale object detection performance in complex scenarios and effectively reduces the missed detection rate under complex backgrounds.
Jian-Chao Zhao, Lie-Ping Zhang· Engineering Research Express· 0 citations
This work proposes RAD-YOLO, a YOLOv8s-based small-object detector, and develops an edge-deployable variant named RAD-YOLO-Slim, which provides a practical balance of accuracy, speed and energy efficiency on the RK3576 platform.
Shuai-Jie Nie, Jia-Jian Yang, Xin He et al.· Engineering Research Express· 0 citations
The proposed WTM-YOLOv11 enhances the detection performance of small and occluded targets in drone aerial imagery, providing a robust and feasible solution for intelligent public security surveillance systems.
Small-object detection in unmanned aerial vehicle (UAV) imagery remains challenging due to small target scales, dense target distributions, complex backgrounds, and limited onboard computational resources. To address these coupled problems, this paper proposes ASE-YOLO11, a lightweight improved detector based on YOLO11...
Shi-Hua Hou· 2026 7th International Confe...· 0 citations
These results support improved accuracy under the specified controlled RGB corruptions, while not establishing universal real-weather or cross-modal robustness, while not establishing universal real-weather or cross-modal robustness.
Yang Zhong, Xiu-Zai Zhang, Juan-Juan Ji et al.· Remote Sensing· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.