A semantic segmentation method of buildings in remote sensing image based on improved UNet

Zhongyu Li; Yang Liu; Yin Kuang; Huajun Wang; Cheng Liu

doi:10.1117/12.2643556

9 October 2022 A semantic segmentation method of buildings in remote sensing image based on improved UNet

Zhongyu Li, Yang Liu, Yin Kuang, Huajun Wang, Cheng Liu

Proceedings Volume 12246, 2nd International Conference on Signal Image Processing and Communication (ICSIPC 2022); 122461C (2022) https://doi.org/10.1117/12.2643556
Event: 2nd International Conference on Signal Image Processing and Communication (ICSIPC 2022), 2022, Qingdao, China

Abstract

Aiming at the problem of model instability and overfitting of deep neural networks with the deepening of the number of network layers, the current mainstream method is to use batch normalization (BN) to alleviate them. However, since the BN method is more sensitive to batch size when the batch size is small, the model performance will be poor. For a relatively large model, due to the limitation of video memory, the batch size cannot take a large value, limiting the model's performance. Because of the dependence of BN on batch size, this paper adopts group normalization (GN) instead of batch normalization (BN) in the UNet network to alleviate the impact of the model on batch size. Then experiments are carried out on the WHUBuilding dataset. The experimental results show that the improved model (UNet-GN) improves the mean intersection over union (MIoU) and mean pixel accuracy (MPA) by 10.66% and 1.65% respectively compared with the original model (UNet-BN).

Citation Download Citation

Zhongyu Li, Yang Liu, Yin Kuang, Huajun Wang, and Cheng Liu "A semantic segmentation method of buildings in remote sensing image based on improved UNet", Proc. SPIE 12246, 2nd International Conference on Signal Image Processing and Communication (ICSIPC 2022), 122461C (9 October 2022); https://doi.org/10.1117/12.2643556

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available