Back to Search Start Over

Adaptive adjacent context negotiation network for object detection in remote sensing imagery

Authors :
Yan Dong
Yundong Liu
Yuhua Cheng
Guangshuai Gao
Kai Chen
Chunlei Li
Source :
PeerJ Computer Science, Vol 10, p e2199 (2024)
Publication Year :
2024
Publisher :
PeerJ Inc., 2024.

Abstract

Accurate localization of objects of interest in remote sensing images (RSIs) is of great significance for object identification, resource management, decision-making and disaster relief response. However, many difficulties, like complex backgrounds, dense target quantities, large-scale variations, and small-scale objects, which make the detection accuracy unsatisfactory. To improve the detection accuracy, we propose an Adaptive Adjacent Context Negotiation Network (A2CN-Net). Firstly, the composite fast Fourier convolution (CFFC) module is given to reduce the information loss of small objects, which is inserted into the backbone network to obtain spectral global context information. Then, the Global Context Information Enhancement (GCIE) module is given to capture and aggregate global spatial features, which is beneficial for locating objects of different scales. Furthermore, to alleviate the aliasing effect caused by the fusion of adjacent feature layers, a novel Adaptive Adjacent Context Negotiation network (A2CN) is given to adaptive integration of multi-level features, which consists of local and adjacent branches, with the local branch adaptively highlighting feature information and the adjacent branch introducing global information at the adjacent level to enhance feature representation. In the meantime, considering the variability in the focus of feature layers in different dimensions, learnable weights are applied to the local and adjacent branches for adaptive feature fusion. Finally, extensive experiments are performed in several available public datasets, including DIOR and DOTA-v1.0. Experimental studies show that A2CN-Net can significantly boost detection performance, with mAP increasing to 74.2% and 79.2%, respectively.

Details

Language :
English
ISSN :
23765992
Volume :
10
Database :
Directory of Open Access Journals
Journal :
PeerJ Computer Science
Publication Type :
Academic Journal
Accession number :
edsdoj.9121eb141249433ebc2b89b7c1a89bb1
Document Type :
article
Full Text :
https://doi.org/10.7717/peerj-cs.2199