Automated visual perception of the real world by computers requires classification of observed physical objects into semantically meaningful categories (such as 'car' or 'person'). We propose a partially-supervised learning framework for classification of moving objects-mostly vehicles and pedestrians-that are detected and tracked in a variety of far-field video sequences, captured by a static, uncalibrated camera. We introduce the use of scene-specific context features (such as image-position of objects) to improve classification performance in any given scene. At the same time, we design a scene-invariant object classifier, along with an algorithm to adapt this classifier to a new scene. Scene-specific context information is extracted through passive observation of unlabelled data. Experimental results are demonstrated in the context of outdoor visual surveillance of a wide variety of scenes.


    Access

    Download


    Export, share and cite



    Title :

    Classifying tracked objects in far-field video surveillance


    Contributors:

    Publication date :

    2004


    Size :

    70 pages , 2893857 byte , 2893665 byte


    Remarks:

    Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2004.
    Includes bibliographical references (p. 67-70).


    Type of media :

    Theses


    Type of material :

    Electronic Resource


    Language :

    English




    Classifying potentially stationary objects tracked by radar

    DANG WENBING / SCHIFFMANN JAN K / VISHWAJEET KUMAR et al. | European Patent Office | 2021

    Free access

    CLASSIFYING POTENTIALLY STATIONARY OBJECTS TRACKED BY RADAR

    DANG WENBING / SCHIFFMANN JAN K / VISHWAJEET KUMAR et al. | European Patent Office | 2020

    Free access

    METHOD OF VIDEO SURVEILLANCE OF OBJECTS

    BASHINSKIJ ANTON EVGENEVICH / PETRIJ IGOR SERGEEVICH / KAZANDAEV IGOR VLADIMIROVICH | European Patent Office | 2019

    Free access

    Classifying dynamic objects

    Luber, M. | British Library Online Contents | 2009


    Track segment cleaning of tracked objects

    LUBING ZHOU / JIONG YANG / YILUAN GUO | European Patent Office | 2023

    Free access