Cascaded Sequential Attention for Object Recognition with Informative Local Descriptors and Q-learning of Grouping Strategies

Lucas Paletta, Gerald Fritz, Christin Seifert

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    43 Downloads (Pure)

    Abstract

    The contribution of this work is to provide a three-stage architecture for sequential attention to provide a system being capable of sensorimotor object detection in real world environments. The first processing stage provides selected foci of interest in the image based on the extraction of information theoretic saliency of local image descriptors (i-SIFT). The second stage investigates the information in the local attention window using a codebook matcher, providing local weak hypotheses about the identity of the object under investigation. The third stage then proposes a shift of attention to a next attention window. The working hypothesis is to expect a better discrimination from the integration of both the individual local FOA patterns and the geometric relation between them, providing a model of more global information representation, and feeding into a recognition state in the Markov Decision Process (MDP). A reinforcement learner (Q-learner) performs then explorative search on useful actions, i.e., shifts of attention, towards locations of salient information, developing a strategy of useful action sequences being directed in state space towards the optimization of discrimination by information maximization. The method is evaluated in experiments using the COIL-20 database (indoor imagery) and the TSG-20 database (outdoor imagery) to demonstrate efficient performance in object detection tasks, proving the method being more accurate and computationally much less expensive than standard SIFT based recognition
    Original languageEnglish
    Title of host publication2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops
    Place of PublicationSan Diego, CA
    PublisherIEEE
    Number of pages8
    ISBN (Print)0-7695-2372-2
    DOIs
    Publication statusPublished - 1 Jun 2005
    Event3rd International Workshop on Attention and Performance in Computational Vision, WAPCV 2005 - San Diego, United States
    Duration: 25 Jun 200525 Jun 2005
    Conference number: 3
    http://dib.joanneum.at/wapcv2005/

    Publication series

    NameProceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
    PublisherIEEE
    Volume2005
    ISSN (Print)2160-7508
    ISSN (Electronic)2160-7516

    Conference

    Conference3rd International Workshop on Attention and Performance in Computational Vision, WAPCV 2005
    Abbreviated titleWAPCV
    CountryUnited States
    CitySan Diego
    Period25/06/0525/06/05
    Internet address

    Fingerprint Dive into the research topics of 'Cascaded Sequential Attention for Object Recognition with Informative Local Descriptors and Q-learning of Grouping Strategies'. Together they form a unique fingerprint.

  • Cite this

    Paletta, L., Fritz, G., & Seifert, C. (2005). Cascaded Sequential Attention for Object Recognition with Informative Local Descriptors and Q-learning of Grouping Strategies. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops (Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR); Vol. 2005). San Diego, CA: IEEE. https://doi.org/10.1109/CVPR.2005.429