LECF: A Lightweight Edge-Aware and Context-Gated Feature Fusion Network for Multiscale UAV Object Detection

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Unmanned aerial vehicle (UAV) object detection remains challenging because of the substantial scale variations, frequent small objects, and complex backgrounds present in aerial imagery. In this paper, LECF, a lightweight edge-aware and context-gated feature fusion network designed for multiscale UAV detection, is presented. The network integrates three modules: (1) a multiscale edge feature fusion-enhanced module (MEFFEM) that strengthens edge cues and nonlinear feature representations; (2) a lightweight efficient upsampling-based multibranch feature pyramid network (LEMFPN) that is equipped with an efficient upsampling and spatial shifting (EUSS) component to enhance the cross-scale semantic aggregation process; and (3) a selective gate-based convolution enhancement module (SGCE) that refines feature responses by suppressing redundant activations. When evaluated on VisDrone and SeaDronesSee, compared with YOLOv11s, the AP and AP50 of the LECF model are improved by 2.5% and 3.4% on VisDrone, and by 2.4% and 2.0% on SeaDronesSee, respectively, while the number of required parameters is reduced by 28.7%. The LECF model also provides consistent improvements across multiscale categories and maintains comparable computational complexity, offering a practical lightweight alternative for use in UAV scenarios.
Funding Information
  • College of Computing, Khon Kaen University, Thailand
  • Khon Kaen University, Thailand

This publication has 49 references indexed in Scilit: