Header

UZH-Logo

Maintenance Infos

Monocular simultaneous multi-body motion segmentation and reconstruction from perspective views


Sabzevari, Reza; Scaramuzza, Davide (2014). Monocular simultaneous multi-body motion segmentation and reconstruction from perspective views. In: IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 31 May 2014 - 7 June 2014, 23-30.

Abstract

In this paper, we tackle the problem of mapping multiple 3D rigid structures and estimating their motions from perspective views through a car-mounted camera. The proposed method complements conventional localization and mapping algorithms (such as Visual Odometry and SLAM) to estimate motions of other moving objects in addition to the vehicle's motion. We present a theoretical framework for robust estimation of multiple motions and structures from perspective images. The method is based on the factorization of the projective trajectory matrix without explicit estimation of projective depth values. We exploit the epipolar geometry of calibrated cameras to generate several hypotheses for motion segments. Once the hypotheses are obtained, they are evaluated in an iterative scheme by alternating between estimation of 3D structures and estimation of multiple motions. The proposed framework does not require any knowledge about the number of motions and is robust to noisy image measurements. The method is evaluated on street-level sequences from a car-mounted camera. A benchmark dataset is also used to compare the results with previous works, although most of the related works use synthetic scenes simulating desktop environments.

Abstract

In this paper, we tackle the problem of mapping multiple 3D rigid structures and estimating their motions from perspective views through a car-mounted camera. The proposed method complements conventional localization and mapping algorithms (such as Visual Odometry and SLAM) to estimate motions of other moving objects in addition to the vehicle's motion. We present a theoretical framework for robust estimation of multiple motions and structures from perspective images. The method is based on the factorization of the projective trajectory matrix without explicit estimation of projective depth values. We exploit the epipolar geometry of calibrated cameras to generate several hypotheses for motion segments. Once the hypotheses are obtained, they are evaluated in an iterative scheme by alternating between estimation of 3D structures and estimation of multiple motions. The proposed framework does not require any knowledge about the number of motions and is robust to noisy image measurements. The method is evaluated on street-level sequences from a car-mounted camera. A benchmark dataset is also used to compare the results with previous works, although most of the related works use synthetic scenes simulating desktop environments.

Statistics

Citations

3 citations in Web of Science®
4 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

11 downloads since deposited on 12 Aug 2016
10 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:7 June 2014
Deposited On:12 Aug 2016 07:34
Last Modified:30 Aug 2017 17:09
Publisher:Institute of Electrical and Electronics Engineers
Series Name:IEEE International Conference on Robotics and Automation. Proceedings
ISSN:1050-4729
Publisher DOI:https://doi.org/10.1109/ICRA.2014.6906585
Related URLs:http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6906585 (Publisher)
http://www.icra2014.com/ (Organisation)
Other Identification Number:merlin-id:10210

Download

Download PDF  'Monocular simultaneous multi-body motion segmentation and reconstruction from perspective views'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 2MB
View at publisher