Laser-Camera Based 3D Reconstruction of Indoor Environments

Jamal Atman, Gert F. Trommer

Abstract: Obtaining relevant information as soon and as detailed as possible is a crucial issue in a rescue scenario. Hence, micro air vehicles (MAVs) are becoming more and more attractive due to their flexibility in terms of the place of use and their perception abilities using various sensors. Thus, this paper deals with data processing of particularly a 2D laser rangefinder and a monocular camera in order to reconstruct the explored indoor environment. It is presented how to overcome sparse laser depth information by using additionally camera images. In order to achieve this goal, the generated point cloud is segmented such that local 3D models are found. This makes it possible to reconstruct lines in world frame, which yields further improvement of the geometric representation. Besides that, the found 3D models are enriched with color information by calculating the homography matrix. The results in indoor environment comprising corridor and office show an accurate geometric and chromatic reconstruction. This enables task planners to quickly interpret and coordinate the ongoing situation.
Published in: 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS)
April 23 - 26, 2018
Hyatt Regency Hotel
Monterey, CA
Pages: 254 - 260
Cite this article: Atman, Jamal, Trommer, Gert F., "Laser-Camera Based 3D Reconstruction of Indoor Environments," 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), Monterey, CA, April 2018, pp. 254-260.
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In