Paper
27 October 2023 Semantic recognition and detection method based on DSM multi-scale image segmentation technology
Shuo Jiang, Xiangtian Ji
Author Affiliations +
Proceedings Volume 12922, Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023); 129222H (2023) https://doi.org/10.1117/12.3008992
Event: Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023), 2023, Xiamen, China
Abstract
This project will study a Digital Surface elevation Model (DSM) and an image semantic segmentation method based on multi-scale weight clustering. Taking the overall partitioning metric as a constraint, the weights are classified step by step using a multi-grid algebraic algorithm. An image processing method based on a single residual method is proposed for high-resolution remote sensing images. Row Height Information Mining with Convolutional Neural Networks is proposed. The method's accuracy can reach 92.33% through the test on the existing public database. The experimental results prove that the method extracts and fuses features of multiple levels and can obtain better semantic segmentation results.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Shuo Jiang and Xiangtian Ji "Semantic recognition and detection method based on DSM multi-scale image segmentation technology", Proc. SPIE 12922, Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023), 129222H (27 October 2023); https://doi.org/10.1117/12.3008992
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Semantics

Image fusion

Remote sensing

Image restoration

Matrices

Data modeling

Back to Top