Next Article in Journal / Special Issue
An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data
Previous Article in Journal
Using Content Analysis to Probe the Cognitive Image of Intangible Cultural Heritage Tourism: An Exploration of Chinese Social Media
Article

High-Resolution Remote Sensing Image Segmentation Framework Based on Attention Mechanism and Adaptive Weighting

1
Department of Electrical Engineering & Information Technology, Shandong University of Science and Technology, Jinan 250031, China
2
Fujian Anta Logistics Information Technology Co. Ltd., Quanzhou 362200, China
3
Department of Finance and Economics, Shandong University of Science and Technology, Jinan 250031, China
*
Author to whom correspondence should be addressed.
Academic Editors: Wolfgang Kainz and Davide Buscaldi
ISPRS Int. J. Geo-Inf. 2021, 10(4), 241; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10040241
Received: 11 February 2021 / Revised: 25 March 2021 / Accepted: 4 April 2021 / Published: 7 April 2021
Semantic segmentation has been widely used in the basic task of extracting information from images. Despite this progress, there are still two challenges: (1) it is difficult for a single-size receptive field to acquire sufficiently strong representational features, and (2) the traditional encoder-decoder structure directly integrates the shallow features with the deep features. However, due to the small number of network layers that shallow features pass through, the feature representation ability is weak, and noise information will be introduced to affect the segmentation performance. In this paper, an Adaptive Multi-Scale Module (AMSM) and Adaptive Fuse Module (AFM) are proposed to solve these two problems. AMSM adopts the idea of channel and spatial attention and adaptively fuses three-channel branches by setting branching structures with different void rates, and flexibly generates weights according to the content of the image. AFM uses deep feature maps to filter shallow feature maps and obtains the weight of deep and shallow feature maps to filter noise information in shallow feature maps effectively. Based on these two symmetrical modules, we have carried out extensive experiments. On the ISPRS Vaihingen dataset, the F1-score and Overall Accuracy (OA) reached 86.79% and 88.35%, respectively. View Full-Text
Keywords: multi-scale convolutional; computer vision; semantic segmentation; remote sensing; neural network; ISPRS Vaihingen multi-scale convolutional; computer vision; semantic segmentation; remote sensing; neural network; ISPRS Vaihingen
Show Figures

Figure 1

MDPI and ACS Style

Liu, Y.; Zhu, Q.; Cao, F.; Chen, J.; Lu, G. High-Resolution Remote Sensing Image Segmentation Framework Based on Attention Mechanism and Adaptive Weighting. ISPRS Int. J. Geo-Inf. 2021, 10, 241. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10040241

AMA Style

Liu Y, Zhu Q, Cao F, Chen J, Lu G. High-Resolution Remote Sensing Image Segmentation Framework Based on Attention Mechanism and Adaptive Weighting. ISPRS International Journal of Geo-Information. 2021; 10(4):241. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10040241

Chicago/Turabian Style

Liu, Yifan; Zhu, Qigang; Cao, Feng; Chen, Junke; Lu, Gang. 2021. "High-Resolution Remote Sensing Image Segmentation Framework Based on Attention Mechanism and Adaptive Weighting" ISPRS Int. J. Geo-Inf. 10, no. 4: 241. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10040241

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop