Work

Spatial attention and wide activation-based deep super-resolution scheme for vehicle detection in noisy and low-resolution LEO satellite imagery

Year: 2025

Type: article

Abstract: This paper presents a robust vehicle detection method for Low Earth Orbit satellite imagery degraded by environmental factors. To enhance feature representation from RGB and IR images, a denoising encoder and a multimodal fusion (MF) module with multi-head squeeze excitation are used. To compensate for texture loss in small vehicles at low resolution, a spatial attention module (SAM) is embedded into the YOLOv5 backbone, and a modified wide activation super-resolution (WDSR) branch is attached for learning finer-grained representations. Experiments on degraded images show that the proposed model outperforms the YOLO series and SuperYOLO in terms of mean average precision (mAP).

Source: ICT Express

DOI: 10.1016/j.icte.2025.11.021

Authors: Hyunjin Jo, Nilesh Maharjan, Byung Wook Kim

Institution: Changwon National University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,500

Funder: Changwon National University