Segmentation of street trees from MLS point clouds by dimensional feature analysis and improved FCM algorithm

Jingzhong Xu; Ge Wang

doi:10.1117/12.2574739

5 November 2020 Segmentation of street trees from MLS point clouds by dimensional feature analysis and improved FCM algorithm

Jingzhong Xu, Ge Wang

Author Affiliations +

Proceedings Volume 11562, AOPC 2020: Advanced Laser Technology and Application; 1156207 (2020) https://doi.org/10.1117/12.2574739
Event: Applied Optics and Photonics China (AOPC 2020), 2020, Beijing, China

Abstract

Street trees are important elements of urban ecological environment. Due to the complex shape of trees, there is still no effective means to identify trees from Mobile Laser Scanning (MLS) point clouds. Aims to segment single street tree from MLS point clouds, this study proposed a new method of extracting street trees by dimensional feature analysis and improved FCM method. After filtering MLS point clouds, dimensional features are introduced to detect candidate tree trunk and tree canopy points. Then, region growing method and cross-validation method are used to extract street tree points according to tree semantic rules. Thirdly, tree positions are taken as initial values for the FCM algorithm to cluster tree points, which also are used to limit the change of the cluster center during cluster process to improve the segmentation effect of trees with overlapping canopies. To evaluate the performance of the method, datasets with different size street trees are tested in the experiment and results show that the proposed method can segment single street trees from MLS point clouds effectively.

Citation Download Citation

Jingzhong Xu and Ge Wang "Segmentation of street trees from MLS point clouds by dimensional feature analysis and improved FCM algorithm", Proc. SPIE 11562, AOPC 2020: Advanced Laser Technology and Application, 1156207 (5 November 2020); https://doi.org/10.1117/12.2574739

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