Presentation | 1997/11/17 Motion Perception Modeled by Fuzzy Hough Transform Masayuki OKADA, Kiichi URAHAMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A neural network model is presented for motion perception on the basis of the fuzzy Hough transform. Motion data are extracted at first locally by simple correlation between two time frames of images. Extracted local motion data are next locally integrated by neurons with the Gaussian receptive field, and the maximum likelihood motion vector is estimated by winner-takes-all networks. These locally estimated motion data are then integrated globally through cooperative interaction between the WTA neurons. This global spatial integration solves the aperture problems and at the same time preserves motion boundaries. This model is examined for some elementary examples of the barber pole illusion and psychological experimental results are reproduced qualitatively. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | motion perception / barber pole illusion / fuzzy Hough transform / maximum likelihood estimation |
Paper # | NC97-44 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1997/11/17(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Motion Perception Modeled by Fuzzy Hough Transform |
Sub Title (in English) | |
Keyword(1) | motion perception |
Keyword(2) | barber pole illusion |
Keyword(3) | fuzzy Hough transform |
Keyword(4) | maximum likelihood estimation |
1st Author's Name | Masayuki OKADA |
1st Author's Affiliation | Kyushu Institute of Design() |
2nd Author's Name | Kiichi URAHAMA |
2nd Author's Affiliation | Kyushu Institute of Design |
Date | 1997/11/17 |
Paper # | NC97-44 |
Volume (vol) | vol.97 |
Number (no) | 379 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |