Conference Proceeding

Fast Keypoint Recognition in Ten Lines of Code.

01/2007; In proceeding of: 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 18-23 June 2007, Minneapolis, Minnesota, USA
Source: DBLP
0 0
 · 
0 Bookmarks
 · 
46 Views
  • Source
    Article: Visual object tracking by an evolutionary self-organizing neural network.
    José Everardo B. Maia, Guilherme A. Barreto, André L. V. Coelho
    [show abstract] [hide abstract]
    ABSTRACT: In this paper, a recently proposed evolutionary self-organizing map is extended and applied to visual tracking of objects in video sequences. The proposed approach uses a simple geometric template to track an object executing a smooth movement represented by affine transformations. The template is selected manually in the first frame and consists of a small number of keypoints and the neighborhood relations among them. The coordinates of the keypoints are used as the coordinates of the nodes of a non-regular grid defining a self-organizing map that represents the object. The weight vectors of each node in the output grid are updated by an evolutionary algorithm and used to locate the object frame by frame. Qualitative and quantitative evaluations indicate that the proposed approach present better results than those obtained by a direct method approach. Additionally, the proposed approach is evaluated under situations of partial occlusion and self-occlusion, and outliers, also presenting good results.
    Journal of Intelligent and Fuzzy Systems 01/2011; 22:69-81. · 0.56 Impact Factor
  • Source
    Conference Proceeding: Knowing your limits - self-evaluation and prediction in object recognition.
    Michael Zillich, Johann Prankl, Thomas Morwald, Markus Vincze
    2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2011, San Francisco, CA, USA, September 25-30, 2011; 01/2011
  • Source
    Conference Proceeding: Fast and scalable keypoint recognition and image retrieval using binary codes
    J. Ventura, T. Höllerer
    [show abstract] [hide abstract]
    ABSTRACT: In this paper we report an evaluation of keypoint descriptor compression using as little as 16 bits to describe a single keypoint. We use spectral hashing to compress keypoint descriptors, and match them using the Hamming distance. By indexing the keypoints in a binary tree, we can quickly recognize keypoints with a very small database, and efficiently insert new keypoints. Our tests using image datasets with perspective distortion show the method to enable fast keypoint recognition and image retrieval with a small code size, and point towards potential applications for scalable visual SLAM on mobile phones.
    Applications of Computer Vision (WACV), 2011 IEEE Workshop on; 02/2011

Show more

Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.