Identification and risk level prediction of plastic sheds along transmission corridors with improved SegFormer-based high-resolution remote sensing imagery

Sihang Zhang; Xiaojun Dou; Zhi Yang; Te Li; Shaohua Wang; Xiao Tan; Gang Qiu

doi:10.1117/12.3032176

3 June 2024 Identification and risk level prediction of plastic sheds along transmission corridors with improved SegFormer-based high-resolution remote sensing imagery

Sihang Zhang, Xiaojun Dou, Zhi Yang, Te Li, Shaohua Wang, Xiao Tan, Gang Qiu

Author Affiliations +

Proceedings Volume 13170, International Conference on Remote Sensing, Surveying, and Mapping (RSSM 2024); 131701P (2024) https://doi.org/10.1117/12.3032176
Event: Third International Conference on Remote Sensing, Surveying, and Mapping (RSSM 2024), 2024, Wuhan, China

Abstract

With the rapid development of facility agriculture in China, the distribution of plastic greenhouses is becoming more and more extensive. Plastic greenhouses along transmission channels are easy to float, which is one of the main external breakage hazards of transmission lines, and it is of great significance to carry out remote sensing identification of plastic greenhouses along transmission channels for the management of external breakage hazards. This study proposes an improved Segformer model based on the Segformer decoder. In it, high-level semantic information is fused by the feature fusion module to realize the deep mining of implicit features of multi-scale feature maps. Then, the accurate reduced representation of image spatial details is realized by the inverse convolutional upsampling module. Experiments are carried out in a study area along a transmission corridor in Lianyungang City, Jiangsu Province, China, where the overall accuracy and the intersection and concurrency ratio of the improved Segformer are 0.876 and 0.849, respectively. The ablation experiments demonstrate that both designed modules play a positive role and the maximum accuracy can be achieved by using them jointly. The study analyzes the identification results and the distance to the transmission lines to predict them into high, medium and low risk classes. The study shows that based on high-resolution satellite remote sensing images, it is feasible and effective to use the model to carry out the identification of plastic sheds in the areas along transmission corridors, which can provide a decision-making basis for the comprehensive management of external breakage hazards.

Citation Download Citation

Sihang Zhang, Xiaojun Dou, Zhi Yang, Te Li, Shaohua Wang, Xiao Tan, and Gang Qiu "Identification and risk level prediction of plastic sheds along transmission corridors with improved SegFormer-based high-resolution remote sensing imagery", Proc. SPIE 13170, International Conference on Remote Sensing, Surveying, and Mapping (RSSM 2024), 131701P (3 June 2024); https://doi.org/10.1117/12.3032176

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Plastics

Atmospheric modeling

Remote sensing

Image segmentation

Semantics

Deep learning

Feature fusion

Show All Keywords

Keywords/Phrases

Search In:

Publication Years