Space Subdivision of Indoor Mobile Laser Scanning Data Based on the Scanner Trajectory

Ahmed Elseicy,Sander Oude Elberink,Shayan Nikoohemat,Michael Peter

doi:10.3390/rs10111815

Abstract

State-of-the-art indoor mobile laser scanners are now lightweight and portable enough to be carried by humans. They allow the user to map challenging environments such as multi-story buildings and staircases while continuously walking through the building. The trajectory of the laser scanner is usually discarded in the analysis, although it gives insight about indoor spaces and the topological relations between them. In this research, the trajectory is used in conjunction with the point cloud to subdivide the indoor space into stories, staircases, doorways, and rooms. Analyzing the scanner trajectory as a standalone dataset is used to identify the staircases and to separate the stories. Also, the doors that are traversed by the operator during the scanning are identified by processing only the interesting spots of the point cloud with the help of the trajectory. Semantic information like different space labels is assigned to the trajectory based on the detected doors. Finally, the point cloud is semantically enriched by transferring the labels from the annotated trajectory to the full point cloud. Four real-world datasets with a total of seven stories are used to evaluate the proposed methods. The evaluation items are the total number of correctly detected rooms, doors, and staircases.

Highlights

Representing indoor environments in a digital form has become an essential input for many domains such as architecture, engineering, and construction (AEC), robotics, and emergency response planning
Four mobile laser scanner datasets with a total of seven stories are used to evaluate the proposed approaches. They all provide the point cloud beside the scanner trajectory, and the two datasets are related by timestamps
The size of the trajectory dataset is smaller than the point cloud dataset in terms of the total number of points

Summary

Introduction

Representing indoor environments in a digital form has become an essential input for many domains such as architecture, engineering, and construction (AEC), robotics, and emergency response planning. Emergency planning for indoor environments depends on up-to-date interior semantic maps, and the determination of obstacle-free navigation routes [7]. Indoor mobile laser scanners (IMLSs) have become more lightweight and portable, and their mobility enables the user to capture complex buildings while walking through the environment. They can help the user to regularly update the models, due to their fast acquisition time. While the point cloud data is usually processed to extract information, the trajectory data is discarded or used for visualization only [10]

Objectives

Methods

Results

Conclusion