Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments 英文参考文献.docVIP

Sensors 2010, 10, 8865-8887; doi:10.3390/s101008865 OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article Stereo Vision Tracking of Multiple Objects in Complex Indoor Environments Marta Marrón-Romera 1,*, Juan C. García 1, Miguel A. Sotelo 1, Daniel Pizarro 1, Manuel Mazo 1, José M. Ca?as 2, Cristina Losada 1 and álvaro Marcos 1 1 Electronics Department, University of Alcalá, Campus Universitario s/n, 28805, Alcalá de Henares, Madrid, Spain; E-Mails: jcarlos@depeca.uah.es (J.G.); sotelo@depeca.uah.es (M.S.); pizarro@depeca.uah.es (D.P.); mazo@depeca.uah.es (M.M.); losada@depeca.uah.es (C.L.); alvaro.marcos@depeca.uah.es (A.M.) 2 Departamento de Sistemas Telemáticos y Computación, Universidad Rey Juan Carlos, C/Tulipán s/n, 28933, Móstoles, Madrid, Spain; E-Mail: jmplaza@gsyc.es (J.C.) * Author to whom correspondence should be addressed; E-Mail: marta@depeca.uah.es; Tel.: +34-918856586; Fax: +34-918856591. Received: 31 August 2010; in revised form: 7 September 2010 / Accepted: 25 September 2010 / Published: 28 September 2010 Abstract: This paper presents a novel system capable of solving the problem of tracking multiple targets in a crowded, complex and dynamic indoor environment, like those typical of mobile robot applications. The proposed solution is based on a stereo vision set in the acquisition step and a probabilistic algorithm in the obstacles position estimation process. The system obtains 3D position and speed information related to each object in the robot’s environment; then it achieves a classification between building elements (ceiling, walls, columns and so on) and the rest of items in robot surroundings. All objects in robot surroundings, both dynamic and static, are considered to be obstacles but the structure of the environment itself. A combination of a Bayesian algorithm and a deterministic clustering process is used in order to obtain a multimodal representation of spee