DocumentCode :
2540462
Title :
Tracking objects of arbitrary shape using expectation-maximization algorithm
Author :
Zeng, Shuqing ; Li, Yuanhong ; Shen, Yantao
Author_Institution :
R&D, Electr. & Controls Integration Lab., Gen. Motors, Warren, MI, USA
fYear :
2011
fDate :
25-30 Sept. 2011
Firstpage :
4575
Lastpage :
4580
Abstract :
We address the general object tracking with arbitrary shape using rangefinders, which is a key module for detecting surrounding traffic and infrastructure for an autonomous driving vehicle. An Expectation-Maximization (EM) algorithm with locally matching is proposed for motion estimation between two consecutive range images. The complexity of the algorithm is O(N) with N the numbers of scan points. Quantitative performance evaluation of the algorithm using a benchmarking vehicular data set. Results of road tests show the effectiveness and efficiency of the implemented system.
Keywords :
computational complexity; expectation-maximisation algorithm; motion estimation; object tracking; O(N) algorithm; arbitrary shape; autonomous driving vehicle; expectation-maximization algorithm; motion estimation; object tracking; Cameras; Computational modeling; Global Positioning System; Robustness; Shape; Tracking; Vehicles;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on
Conference_Location :
San Francisco, CA
ISSN :
2153-0858
Print_ISBN :
978-1-61284-454-1
Type :
conf
DOI :
10.1109/IROS.2011.6094409
Filename :
6094409
Link To Document :
بازگشت