Vision based obstacle tracking in urban traffic environments

Author

Bota, Silviu ; Nedevschi, Sergiu

Author_Institution

Tech. Univ. of Cluj-Napoca, Cluj-Napoca, Romania

fYear

2011

fDate

25-27 Aug. 2011

Firstpage

231

Lastpage

238

Abstract

Stereo vision based sensors provide large amounts of data, a fact which is advantageous when trying to extract semantic information about the imaged scene. However, this data is corrupted by errors, caused especially by the uncertainties in the stereo reconstruction process. Temporal information can be used in order to minimize these errors. This paper presents an advanced object model, a novel association mechanism and the design of a Kalman filter based tracking algorithm, for tracking multiple objects, in complex, urban traffic scenarios.

Keywords

Kalman filters; computer vision; feature extraction; natural scenes; object tracking; road traffic; stereo image processing; traffic engineering computing; Kalman filter based tracking algorithm; advanced object model; association mechanism; error minimization; multiple object tracking; natural scene; semantic information extraction; stereo reconstruction process; stereo vision based sensor; temporal information; urban traffic environment; vision based obstacle tracking; Adaptive optics; Covariance matrix; Kalman filters; Optical imaging; Optical sensors; Prediction algorithms; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computer Communication and Processing (ICCP), 2011 IEEE International Conference on

Conference_Location

Cluj-Napoca

Print_ISBN

978-1-4577-1479-5

Electronic_ISBN

978-1-4577-1481-8

Type

conf

DOI

10.1109/ICCP.2011.6047874

Filename

6047874