ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Towards Automated Floorplan Generation

Chelani, K and Sidhartha, C and Govindu, VM (2018) Towards Automated Floorplan Generation. In: 11th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2018, 18-22 December 2018, International Institute of Information Technology, Hyderabad.

[img] PDF
ACM-Int-Con-Pro.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy
Official URL: https://dx.doi.org/10.1145/3293353.3293430


In this paper, we propose a pipeline for generating a 2D floorplan using depth cameras. In our pipeline we use an existing approach to recovering the camera motion trajectories from the depth and RGB sequences. Given these motion estimates we construct a full 3D representation of the scanned indoor spaces. For generating a floorplan we need to abstract the large volumes of registered 3D data into a simplified rectilinear representation. We evaluate two approaches to solve this problem, viz slicing the reconstructed volume at a given height and direct segmentation of the 3D point cloud representation into individual planar segments. We also note that the fidelity of our estimated floorplan crucially depends on the accuracy of the estimation of the ground plane orientation. We examine the comparative accuracies of two ground plane estimation methods for each of the above mentioned approaches to rectilinear abstraction. Given the line drawing abstractions of the individual rooms, we merge them into a consistent floorplan. We present results on a real-world floorplan estimation problem and demonstrate its accuracy. Additionally, the implications of errors in the individual components of our pipeline are also studied. © 2018 ACM.

Item Type: Conference Paper
Publication: ACM International Conference Proceeding Series
Publisher: Association for Computing Machinery
Additional Information: cited By 0; Conference of 11th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2018 ; Conference Date: 18 December 2018 Through 22 December 2018; Conference Code:165785
Keywords: Cameras; Computer vision; Pipelines, 3D point cloud; 3d representations; Consistent floorplan; Estimation methods; Estimation problem; Individual components; Motion estimates; Planar segments, Motion estimation
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 12 Jan 2021 05:55
Last Modified: 12 Jan 2021 05:55
URI: http://eprints.iisc.ac.in/id/eprint/67649

Actions (login required)

View Item View Item