Extraction of Objects from Terrestrial Laser Scans by Integrating Geometry Image and Intensity Data with Demonstration on Trees

Shahar Barnea,Sagi Filin

doi:10.3390/rs4010088

Shahar Barnea, Sagi Filin

Open Access

https://doi.org/10.3390/rs4010088

Copy DOI

Journal: Remote sensing	Publication Date: Jan 5, 2012
Citations: 48	License type: CC BY 3.0

Affiliation: Technion – Israel Institute of Technology

Abstract

Terrestrial laser scanning is becoming a standard for 3D modeling of complex scenes. Results of the scan contain detailed geometric information about the scene; however, the lack of semantic details still constitutes a gap in ensuring this data is usable for mapping. This paper proposes a framework for recognition of objects in laser scans; aiming to utilize all the available information, range, intensity and color information integrated into the extraction framework. Instead of using the 3D point cloud, which is complex to process since it lacks an inherent neighborhood structure, we propose a polar representation which facilitates low-level image processing tasks, e.g., segmentation and texture modeling. Using attributes of each segment, a feature space analysis is used to classify segments into objects. This process is followed by a fine-tuning stage based on graph-cut algorithm, which considers the 3D nature of the data. The proposed algorithm is demonstrated on tree extraction and tested on scans containing complex objects in addition to trees. Results show a very high detection level and thereby the feasibility of the proposed framework.

Highlights

Autonomous extraction of objects from terrestrial laser scanners becomes relevant when considering the data volume and the difficulty of interacting with irregularly distributed three dimensional point clouds
The scans were acquired by the Riegl LMS Z360i laser scanner
This paper presented a methodology for the extraction of spatial objects from terrestrial laser scanning data

Summary

Introduction

Autonomous extraction of objects from terrestrial laser scanners becomes relevant when considering the data volume and the difficulty of interacting with irregularly distributed three dimensional point clouds. Object extraction from terrestrial laser scanners has been a research domain in recent years, ranging from reverse engineering problems to building reconstruction, forestry applications, and others [1]. Bienert et al [3] propose an ad hoc approach for tree detection, which is based on trimming the laser data at a certain height to separate the canopy from the ground and searching for stem patches. Such approaches cannot be generalized to other objects, and usually assume a well defined object shape. The extraction models are focused on a single type of object and assume high domain-knowledge

Methods

Results

Conclusion