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.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Radar-vision fusion for vehicle detection by means of improved Haar-like feature and AdaBoost approach


    Additional title:

    Verschmelzung von Radar und Computer-Vision für die Fahrzeugerkennung durch verbesserte Haar-ähnliche Features und das AdaBoost-Verfahren


    Contributors:


    Publication date :

    2007


    Size :

    5 Seiten, 5 Bilder, 1 Tabelle, 12 Quellen



    Type of media :

    Conference paper


    Type of material :

    Storage medium


    Language :

    English




    Moving Vehicle Detection Using AdaBoost and Haar-Like Feature in Surveillance Videos

    Moghimi, Mohammad Mahdi / Nayeri, Maryam / Pourahmadi, Majid et al. | ArXiv | 2018

    Free access


    Traffic Signs Detection Based on Haar-Like Features and Adaboost Classifier

    Li, Zhijiang / Dong, Chuan / Zheng, Ling et al. | ASCE | 2013


    Improved Haar Wavelet Feature Extraction Approaches for Vehicle Detection

    Wen, Xuezhi / Yuan, Huai / Yang, Chunyang et al. | IEEE | 2007


    Online Vehicle Detection Using Haar-Like, LBP and HOG Feature Based Image Classifiers with Stereo Vision Preselection

    Neumann, Daniel / Langner, Tobias / Ulbrich, Fritz et al. | British Library Conference Proceedings | 2017