A multi-scale feature likelihood map for direct evaluation of object hypotheses
2001 (English)In: SCALE-SPACE AND MORPHOLOGY IN COMPUTER VISION, PROCEEDINGS, Springer Berlin/Heidelberg, 2001, Vol. 2106, 98-110 p.Conference paper (Refereed)
This paper develops and investigates a new approach for evaluating feature based object hypotheses in a direct way. The idea is to compute a feature likelihood map (FLM), which is a function normalized to the interval [0, 1], and which approximates the likelihood of image features at all points in scale-space. In our case, the FLM is defined from Gaussian derivative operators and in such a way that it assumes its strongest responses near the centers of symmetric blob-like or elongated ridge-like structures and at scales that reflect the size of these structures in the image domain. While the FLM inherits several advantages of feature based image representations, it also (i) avoids the need for explicit search when matching features in object models to image data, and (ii) eliminates the need for thresholds present in most traditional feature based approaches. In an application presented in this paper, the FLM is applied to simultaneous tracking and recognition of hand models based on particle filtering. The experiments demonstrate the feasibility of the approach, and that real time performance can be obtained by a pyramid implementation of the proposed concept.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2001. Vol. 2106, 98-110 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 2106
Computer and Information Science Mathematics Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-40248ISI: 000174659600009ISBN: 3-540-42317-6OAI: oai:DiVA.org:kth-40248DiVA: diva2:440691
3rd International Conference on Scale-Space 2001 Location: VANCOUVER, CANADA Date: JUL 07-08, 2001
QC 201109132011-09-132011-09-132013-04-23Bibliographically approved