| Item type |
SIG Technical Reports(1) |
| 公開日 |
2017-08-28 |
| タイトル |
|
|
タイトル |
車載魚眼カメラ画像の超解像における入力画像枚数とブラー量に着目した最適化の検討 |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Study on Optimization for Super Resolution of On-Vehicle Fisheye Camera based on the Number and Blur Size of Input Images |
| 言語 |
|
|
言語 |
jpn |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
東京大学 |
| 著者所属 |
|
|
|
東京大学 |
| 著者所属 |
|
|
|
鹿児島大学 |
| 著者所属 |
|
|
|
九州大学 |
| 著者所属 |
|
|
|
東京大学 |
| 著者所属(英) |
|
|
|
en |
|
|
The University of Tokyo |
| 著者所属(英) |
|
|
|
en |
|
|
The University of Tokyo |
| 著者所属(英) |
|
|
|
en |
|
|
Kagoshima University |
| 著者所属(英) |
|
|
|
en |
|
|
Kyusyu University |
| 著者所属(英) |
|
|
|
en |
|
|
The University of Tokyo |
| 著者名 |
高野, 照久
小野, 晋太郎
松下, 脩暉
川崎, 洋
池内, 克史
|
| 著者名(英) |
Teruhisa, Takano
Shintaro, Ono
Yuuki, Matsushita
Hiroshi, Kawasaki
Katsushi, Ikeuchi
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
A fisheye camera or a super wide-angle camera is widely used for on-vehicle camera of general cars, since it can capture wide area by itself. We assume to set such a camera on a vehicle, and to use the captvued images as inputs to perform super resolution of a region within the images. The captured images have distortion and lower resolution especially in peripheral area of the sight. Therefore, under a practical condition, i.e., the number of captured images relative to displacement of the camera is finite, there is a trade-off between the number of input images for the super resolution and their image quality. In this report, we discuss the differences of input image quality and result of the super resolution, and consider the optimal choice of input images based on the amount of blur in the input images. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
A fisheye camera or a super wide-angle camera is widely used for on-vehicle camera of general cars, since it can capture wide area by itself. We assume to set such a camera on a vehicle, and to use the captvued images as inputs to perform super resolution of a region within the images. The captured images have distortion and lower resolution especially in peripheral area of the sight. Therefore, under a practical condition, i.e., the number of captured images relative to displacement of the camera is finite, there is a trade-off between the number of input images for the super resolution and their image quality. In this report, we discuss the differences of input image quality and result of the super resolution, and consider the optimal choice of input images based on the amount of blur in the input images. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA11515904 |
| 書誌情報 |
研究報告高度交通システムとスマートコミュニティ（ITS）
巻 2017-ITS-70,
号 2,
p. 1-5,
発行日 2017-08-28
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8965 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-ITS17070002.pdf (3.7 MB)
