Recent studies in object detection have shown that a component-based approach is more resilient to partial occlusions of objects, and more robust to natural pose variations, than the traditional global holistic approach. In this thesis, we consider the task of building a component-based detector in a more difficult domain: cars in natural images of street scenes. We demonstrate reasonable results for two different component-based systems, despite the large inherent variability of cars in these scenes. First, we present a car classification scheme based on learning similarities to features extracted by an interest operator. We then compare this system to traditional global approaches that use Support Vector Machines (SVMs). Finally, we present the design and implementation of a system to locate cars based on the detections of human-specified components.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Component-based car detection in street scene images


    Beteiligte:

    Erscheinungsdatum :

    2004


    Format / Umfang :

    71 pages , 3329317 byte , 3336431 byte


    Anmerkungen:

    Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2004.
    Includes bibliographical references (p. 67-71).


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Point-Based Neural Scene Rendering for Street Views

    Li, Zhuopeng / Zhu, Jianke | IEEE | 2024


    Scene structure in the saturation component of color images

    Thomas, Bruce A. / Strickland, Robin N. | SPIE | 1996


    New street scene for pedestrians and drivers

    Branimir Stanić / Smiljan Vukanovic / Miroslav Osoba | DOAJ | 2005

    Freier Zugriff

    New street scene for pedestrians and drivers

    S. Vukanovic / B. Stanić / M. Osoba | DOAJ | 2005

    Freier Zugriff

    DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection

    Chen, Shuo / Yang, Kailun / Stiefelhagen, Rainer | IEEE | 2021