Fast concurrent object localization and recognition
Name
Yeh-2009-Fast concurrent object localization and recognition.pdf
Size
1.35 MB
Format
Adobe PDF
Checksum (MD5)
90dbb38bb0a0eb43cdc415d087d8579c
Author(s)
Yeh, Tom
Lee, John J.
Darrell, Trevor J.
Date Issued
August 2009
Journal
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009.
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Yeh, T., J.J. Lee, and T. Darrell. “Fast Concurrent Object Localization and Recognition.” IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE, 2009. 280–287. © Copyright 2009 IEEE
Version
Final published version
Abstract
Object localization and recognition are important problems in computer vision. However, in many applications, exhaustive search over all object models and image locations is computationally prohibitive. While several methods have been proposed to make either recognition or localization more efficient, few have dealt with both tasks simultaneously. This paper proposes an efficient method for concurrent object localization and recognition based on a data-dependent multi-class branch-and-bound formalism. Existing bag-of-features recognition techniques which can be expressed as weighted combinations of feature counts can be readily adapted to our method. We present experimental results that demonstrate the merit of our algorithm in terms of recognition accuracy, localization accuracy, and speed, compared to baseline approaches including exhaustive search, implicit-shape model (ISM), and efficient sub-window search (ESS). Moreover, we develop two extensions to consider non-rectangular bounding regions-composite boxes and polygons-and demonstrate their ability to achieve higher recognition scores compared to traditional rectangular bounding boxes.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPRW.2009.5206805
