Presentation | 2013-09-26 Automatic Synthesis of Wide FOV Images from First Person View Videos : Selecting Suitable Images for Stitching Based on Probability Density of Pixel Intensity Kenta MATSUI, Kazuaki KONDO, Takahiro KOIZUMI, Yuichi NAKAMURA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | First person view (FPV) videos often have unsuitable images for stitching, such as including motion blurs, disparities, and temporal changes of the scene. In this paper, we propose a criterion to select suitable image groups from FPV videos and stitch them into wide field of view images. We describe an intensity posterior on each position with observation intensities of multiply overlayed pixels based on the bayesian super-resolution framework. The criterion is conducted by accumlating likelihoods of the intensity posterior, which means degree of intensity consistency and expanding sititched area, simaltanenously. The performance of the criterion has been confirmed through the experiments about its behavior along to degree of unsuitablity and comparison/ranking to selected images groups. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | First person view video / Wide FOV images / Suitable images for stitching / Bayesian super-resolution |
Paper # | MVE2013-21 |
Date of Issue |
Conference Information | |
Committee | MVE |
---|---|
Conference Date | 2013/9/19(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 | Media Experience and Virtual Environment (MVE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Automatic Synthesis of Wide FOV Images from First Person View Videos : Selecting Suitable Images for Stitching Based on Probability Density of Pixel Intensity |
Sub Title (in English) | |
Keyword(1) | First person view video |
Keyword(2) | Wide FOV images |
Keyword(3) | Suitable images for stitching |
Keyword(4) | Bayesian super-resolution |
1st Author's Name | Kenta MATSUI |
1st Author's Affiliation | Kyoto Ubiversity() |
2nd Author's Name | Kazuaki KONDO |
2nd Author's Affiliation | Kyoto Ubiversity |
3rd Author's Name | Takahiro KOIZUMI |
3rd Author's Affiliation | Kyoto Ubiversity |
4th Author's Name | Yuichi NAKAMURA |
4th Author's Affiliation | Kyoto Ubiversity |
Date | 2013-09-26 |
Paper # | MVE2013-21 |
Volume (vol) | vol.113 |
Number (no) | 227 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |