AMEA-YOLO: a lightweight remote sensing vehicle detection algorithm based on attention mechanism and efficient architecture

Due to the large computational requirements of object detection algorithms, high-resolution remote sensing vehicle detection always involves numerous small objects, high level of background complexity, and challenges in balancing model accuracy and parameter count. The attention mechanism and effici...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing 2024-05, Vol.80 (8), p.11241-11260
Main Authors: Wang, Shou-Bin, Gao, Zi-Meng, Jin, Deng-Hui, Gong, Shu-Ming, Peng, Gui-Li, Yang, Zi-Jian
Format: Article
Language:English
Subjects:
Algorithms
Compilers
Computer Science
High resolution
Image resolution
Interpreters
Lightweight
Model accuracy
Modules
Object recognition
Processor Architectures
Programming Languages
Remote sensing
Weight reduction
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Due to the large computational requirements of object detection algorithms, high-resolution remote sensing vehicle detection always involves numerous small objects, high level of background complexity, and challenges in balancing model accuracy and parameter count. The attention mechanism and efficient architecture lightweight-YOLO (AMEA-YOLO) is proposed in this paper. A lightweight network as the backbone network of AMEA-YOLO is designed, and it could maintain model accuracy and ensure good lightweight. FasterNet is employed to accelerate model training speed. The enhanced deep second-order channel attention module (EnhancedSOCA) is utilized to improve the image high-resolution. In addition, a lightweight module is devised to further reduce the model’s weight. The implementation of the HardSwish activation function improves model accuracy. The experimental results indicate that the AMEA-YOLO algorithm could ensure model lightweight and accurate performance.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-023-05872-2