Presentation | 2005-09-16 Acquisiton of depth distribution on image based on invariant feature of camera translation for video classification SATOSHI SHIMADA, TOSHIKAZU KARITSUKA, MASASHI MORIMOTO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The depth distribution on an image derived from the distance between camera and projected objects is an effective feature for the image classification. For example, the variance of the distribution is considered small when landscape, large when human upshot. It can also be used for the video shot size discrimination as loose shots, tight shots and so on. This paper proposes an acquisition method of depth distribution on moving images for the video shot classification robustly under perspective projection camera model. The method at first estimates the camera rotation parameters by using invariant feature of camera translation, and sequentially acquires the depth distribution under the assumption of simply camera translation motion. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | video classification / invariant of camera translation / camera motion / structure from motion / 3D model |
Paper # | CQ2005-51,OIS2005-36,IE2005-44 |
Date of Issue |
Conference Information | |
Committee | CQ |
---|---|
Conference Date | 2005/9/9(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 | Communication Quality (CQ) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Acquisiton of depth distribution on image based on invariant feature of camera translation for video classification |
Sub Title (in English) | |
Keyword(1) | video classification |
Keyword(2) | invariant of camera translation |
Keyword(3) | camera motion |
Keyword(4) | structure from motion |
Keyword(5) | 3D model |
1st Author's Name | SATOSHI SHIMADA |
1st Author's Affiliation | NTT Cyber Solutions Laboratories() |
2nd Author's Name | TOSHIKAZU KARITSUKA |
2nd Author's Affiliation | NTT Cyber Solutions Laboratories |
3rd Author's Name | MASASHI MORIMOTO |
3rd Author's Affiliation | NTT Cyber Solutions Laboratories |
Date | 2005-09-16 |
Paper # | CQ2005-51,OIS2005-36,IE2005-44 |
Volume (vol) | vol.105 |
Number (no) | 282 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |