Background Foreground Segmentation for SLAM


Corcoran, Padraig and Winstanley, Adam C. and Mooney, Peter and Middleton, Rick (2011) Background Foreground Segmentation for SLAM. IEEE Transactions on Intelligent Transportation Systems, 12 (4). ISSN 1524-9050

[img] Download (447kB)



Add this article to your Mendeley library


Abstract

To perform simultaneous localization and mapping (SLAM) in dynamic environments, static background objects must first be determined. This condition can be achieved using a priori information in the form of a map of background objects. Such an approach exhibits a causality dilemma, because such a priori information is the ultimate goal of SLAM. In this paper, we propose a background foreground segmentation method that overcomes this issue. Localization is achieved using a robust iterative closest point implementation and vehicle odometry. Background objects are modeled as objects that are consistently located at a given spatial location. To improve robustness, classification is performed at the object level through the integration of a new segmentation method that is robust to partial object occlusion.

Item Type: Article
Keywords: Background–Foreground segmentation; light detection and ranging; LIDAR;
Academic Unit: Faculty of Science and Engineering > Computer Science
Item ID: 4489
Depositing User: Dr. Adam Winstanley
Date Deposited: 16 Sep 2013 13:57
Journal or Publication Title: IEEE Transactions on Intelligent Transportation Systems
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Refereed: Yes
URI:

Repository Staff Only(login required)

View Item Item control page

Document Downloads

More statistics for this item...