Developing a more accurate method for individual plant segmentation of urban tree and shrub communities using LiDAR technology

Abstract

Application of LiDAR technology has greatly enhanced tree segmentation and phenotypic analysis. There are few studies in urban green spaces using tree segmentation methods. Our aim is to improve the single-plant segmentation accuracy in tree and shrub communities through segmenting algorithm optimisation based on TLS LiDAR data of the urban green space. We developed a multi-round comparative shortest-path algorithm (M-CSP) to achieve the objectives: a) tree and shrub plant layer pre-division (TSPD); b) shrub type classifications (STC) into spherical, cylindrical, and rectangular shapes. The overall detection kappa value using M-CSP is 0.933, which is 18% higher than the CSP value of 0.790. M-CSP-based overall segmentation accuracy value (F-score) is 0.886, which is 13% higher than the CSP value of 0.783. The shrub F-score using M-CSP is 0.817, which is 26% higher than the CSP (0.646). M-CSP should provide a more accurate, faster, and less costly tool to study plant communities in urban green spaces.

Keywords:

• Terrestrial LiDAR
• point cloud segmentation
• comparative shortest-path
• tree and shrub plant communities
• urban green spaces
• landscape ecology

Acknowledgments

This work is supported by Henan Provincial Joint International Research Laboratory of Landscape Architecture, Zhengzhou Green Expo Park Management Center.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by THE Key Projects of the Henan Provincial Department of Education under Grant [number 21A220002]; THE Henan Province Science and Technology Research Project under Grant [number 212102310581 and 222102520031]; THE Funding Project for Young Backbone Teachers of Higher Education Institutions in Henan Province under Grant [number 2020GGJS049]; THE Henan Province Higher Education Teaching Reform Research and Practice Project under Grant [number 2021SJGLX162Y]; THE Henan Province International Cooperation Research Project under Grant [number HNGD2021035]; THE Henan Province University Discipline Innovation Base under Grant [number CXJD2021004].

Notes on contributors

Yang Liu

Yang Liu is Lecturer of Landscape Architecture at Henan Agricultural University’s College of Landscape Architecture and Art in China. His research interests are digital landscape and plant modelling based on LiDAR data, landscape management and maintenance. His papers have appeared in Chinese Landscape Architecture, Forestry, Journal of Environmental Engineering and Landscape Management and IntechOpen.

Xuguang Zhang

Xuguang Zhang, Zitong Ma and Dongbo Xie are postgraduate students in Landscape Architecture at Henan Agricultural University’s College of Landscape Architecture and Art in China. Their research interests are digital landscape and plant modelling based on LiDAR data, landscape ecology.

Zitong Ma

Xuguang Zhang, Zitong Ma and Dongbo Xie are postgraduate students in Landscape Architecture at Henan Agricultural University’s College of Landscape Architecture and Art in China. Their research interests are digital landscape and plant modelling based on LiDAR data, landscape ecology.

Nalin Dong

Nalin Dong is Lecturer of Landscape Architecture at Henan Agricultural University’s College of Landscape Architecture and Art in China. Her research interests are landscape planning and design, analysis of landscape spatial pattern based on GIS technology. She is the author of four scientific publications.

Dongbo Xie

Xuguang Zhang, Zitong Ma and Dongbo Xie are postgraduate students in Landscape Architecture at Henan Agricultural University’s College of Landscape Architecture and Art in China. Their research interests are digital landscape and plant modelling based on LiDAR data, landscape ecology.

Rui Li

Rui Li is a PhD student in Landscape Architecture at Henan Agricultural University’s College of Landscape Architecture and Art in China. Her research interests are landscape digitisation and visualisation, landscape ecological. She is the author of one scientific publication.

Douglas M. Johnston

Douglas M. Johnston is Professor and Chair in Civil and Environmental Engineering at College of Environmental Science and Forestry, State University of New York’s Department of Landscape Architecture in the USA. His research interests are landscape digitisation and visualisation, urban forestry ecosystem services. He is the author of more than 40 scientific publications.

Yu Gary Gao

Yu Gary Gao is Professor in Environmental Sciences at The Ohio State University’s South Centres, College of Food, Agricultural and Environmental Sciences in the USA. His research interests are ecological research and environmental science, carbon peak and carbon neutral. He is the author of more than 15 scientific publications.

Yonghua Li

Yonghua Li is Professor and Associate Dean in Landscape Horticulture at Henan Agricultural University’s College of Landscape Architecture and Art in China. His research interests are plant resource utilisation, landscape plant design. He is the author of 16 scientific publications.

Yakai Lei

Yakai Lei is Associate Professor in Urban and Rural Planning at Henan Agricultural University’s College of Landscape Architecture and Art in China. His research interests are landscape planning and ecological restoration, natural reserve planning and design. He is the author of 45 scientific publications.