Affiliation:
1. School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China
2. School of Electronic and Information Engineering, Zhongyuan University of Technology, ZhengZhou, China
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.
Funder
NSFC
IRISTHN
Leading talents of Science and Technology in the Central Plain of China
Henan Province Key Science and Technology Research Projects
Reference68 articles.
1. Yolov4: optimal speed and accuracy of object detection;Bochkovskiy,2020
2. TO–YOLOX: a pure CNN tiny object detection model for remote sensing images;Chen;International Journal of Digital Earth,2023
3. SFRNet: fine-grained oriented object recognition via separate feature refinement;Cheng;IEEE Transactions on Geoscience and Remote Sensing,2023
4. Cross-scale feature fusion for object detection in optical remote sensing images;Cheng;IEEE Geoscience and Remote Sensing Letters,2020
5. Anchor-free oriented proposal generator for object detection;Cheng;IEEE Transactions on Geoscience and Remote Sensing,2022