Identification of trees and their trunks from mobile laser scanning data of roadway scenes. Issue 4 (16th February 2020)

• Record Type: Journal Article
• Authors: Yadav, Manohar; Lohani, Bharat
• Is Part Of: International journal of remote sensing. Volume 41:Issue 4(2020)
• Page Start: 1233
• Page End: 1258
• Publication Date: 2020-02-16
• Subjects: Remote sensing -- Periodicals; Télédétection -- Périodiques; 621.3678
• DOI: 10.1080/01431161.2019.1662966
• Languages: English
• ISSNs: 0143-1161

Abstract

ABSTRACT: Trees along the roads are important assets, which need continuous assessment and maintenance. The mobile laser scanning (MLS) has been adopted as mainstream mapping technique for three-dimensional data acquisition along the roads. In this study, an automated method was developed to identify trees and their trunks from MLS data. A bottom-up search in two stages is adopted in the cylinders, which are formed by partitioning of normalized MLS data. Tree trunk is identified first based on linearity and data distribution homogeneity along lower section of object clusters lying near to the respective cylinder's base centre. Then, crown of tree is retrieved for respective identified trunk using compactness index for circular or near-circular cross section of crown and its axial symmetry about trunk axis. The object cluster composed of trunk and crown both are identified as tree. The proposed method was tested and validated on MLS data of two different roadway test sites that were acquired at different point spacing. The results reveal that the performance of proposed method in these two sites in terms of average completeness, correctness, and F 1 measure was 94.4%, 100%, and 97.1%, respectively. The correctness did not change in both sites and it was 100% and stable, which showed that none of the non-tree objects was falsely identified as tree and correctness in trees identification was independent of the test site complexity. The proposed method holds great potential for identifying trees from MLS data of various roadway site conditions, where shapes and sizes of trees in their 3D data get distorted due to occlusions, and partial overlap presents among objects. Furthermore, the proposed method was implemented in the graphics processing unit-based parallel computing framework and runtime was dramatically minimized on MLS datasets of two test sites.