| Presentation | 2015-03-20 A Study on Removal of Temporal Objects from Image Sequences Based on Adaptive Background Selection Toru KOTSUKA, Daisuke DEGUCHI, Ichiro IDE, Hiroshi MURASE, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, there is a strong demand for street-view databases that do not include temporal objects. However, it is difficult to obtain a street-view image with no temporal object. Therefore, it is needed to develop a technique that can remove temporal objects and restore the background scene in a street-view image. This report proposes a method to remove temporal objects and restore the background scene by fusion of multiple frontal in-vehicle camera image sequences. When we attempt to remove temporal objects by fusion of frontal in-vehicle camera image sequences, frame alignment and spatial alignment should be performed. To solve these problems, this report proposes a frame alignment method robust to the appearance change caused by the difference of vehicle positions, and a spatial alignment method giving dense pixel correspondences. Furthermore, this report proposes a method to reduce image deterioration by selecting the best reference image automatically for image fusion. Experimental results showed that the proposed method could remove temporal objects and restore the background scenes properly. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | In-vehicle camera / removal of moving objects / background restoration |
| Paper # | BioX2014-66,PRMU2014-186 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2015/3/12(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 | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Study on Removal of Temporal Objects from Image Sequences Based on Adaptive Background Selection |
| Sub Title (in English) | |
| Keyword(1) | In-vehicle camera |
| Keyword(2) | removal of moving objects |
| Keyword(3) | background restoration |
| 1st Author's Name | Toru KOTSUKA |
| 1st Author's Affiliation | Graduate School of Information Science, Nagoya University() |
| 2nd Author's Name | Daisuke DEGUCHI |
| 2nd Author's Affiliation | Information and Communications Headquarters, Nagoya University |
| 3rd Author's Name | Ichiro IDE |
| 3rd Author's Affiliation | Graduate School of Information Science, Nagoya University |
| 4th Author's Name | Hiroshi MURASE |
| 4th Author's Affiliation | Graduate School of Information Science, Nagoya University |
| Date | 2015-03-20 |
| Paper # | BioX2014-66,PRMU2014-186 |
| Volume (vol) | vol.114 |
| Number (no) | 521 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |