DocumentCode :
706235
Title :
Radar-vision fusion for vehicle detection by means of improved haar-like feature and AdaBoost approach
Author :
Haselhoff, Anselm ; Kummert, Anton ; Schneider, Georg
Author_Institution :
Fac. of Electr., Inf., & Media Eng., Univ. of Wuppertal, Wuppertal, Germany
fYear :
2007
fDate :
3-7 Sept. 2007
Firstpage :
2070
Lastpage :
2074
Abstract :
This work describes a vehicle detection system that uses fusion of vision and radar data. The radar provides a first estimation of the lateral position of vehicle candidates and the related distance information. This information is used to define a region of interest (ROI) that is subject to verification. A video camera is used for the verification purpose. The projection of the ROI onto the image plane is scanned via an AdaBoost object detection algorithm, and thus radar detection can be verified and more specific data of the vehicle´s 3D position and width can be given. Moreover, the distance information provided by radar is used to choose optimal parameters during the visual detection process, e.g. properties of the scan window and parameters for fusing detections. In addition, mutual information for haar-like feature selection is used to increase detection rates.
Keywords :
Haar transforms; feature selection; object detection; radar detection; vehicles; video cameras; AdaBoost object detection algorithm; Haar-like feature selection; ROI; image plane; radar detection; radar-vision fusion; region of interest; vehicle detection; vehicle detection system; video camera; visual detection process; Feature extraction; Mutual information; Radar imaging; Signal processing algorithms; Training; Vehicles;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Conference, 2007 15th European
Conference_Location :
Poznan
Print_ISBN :
978-839-2134-04-6
Type :
conf
Filename :
7099172
Link To Document :
بازگشت