Presentation | 2011-03-11 Person Re-identification at a Room Entrance by Adaptive Feature Selection Takuya HONDA, Daisuke DEGUCHI, Tomokazu TAKAHASHI, Ichiro IDE, Hiroshi MURASE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes a method to re-identify people at a room entrance from a surveillance video. The method allows us to re-identify people in high precision by adaptively selecting features according to the individuals in the room. Recently in the field of a video analysis for marketing, flow analysis of customers is important. It is used in a place such as convenience stores and museums, where an arbitrary number of customers enter and exit ; For example, it can be used for measuring the mean time of stay by monitoring the entrance. Such information can be obtained by re-identifying the individuals (entering and exiting the room) using color features. However, in the case that multiple individuals are dressed in similar colors, it is difficult to re-identify them correctly with only the color features. Therefore, focusing on the difference in local features, the person re-identification accuracy is improved by selecting features effective for re-identification per individual. In this paper, we show the experimental results for evaluating adaptive feature selection. We also measured the number of entry/exit events, and the time of stay for each individual from a 8 days video by using the proposed method. From these, the effectiveness of the proposed method was confirmed. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Person Re-identification / Surveillance camera / Image feature / Time of stay |
Paper # | PRMU2010-279 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2011/3/3(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) | Person Re-identification at a Room Entrance by Adaptive Feature Selection |
Sub Title (in English) | |
Keyword(1) | Person Re-identification |
Keyword(2) | Surveillance camera |
Keyword(3) | Image feature |
Keyword(4) | Time of stay |
1st Author's Name | Takuya HONDA |
1st Author's Affiliation | Graduate School of Information Science, Nagoya University() |
2nd Author's Name | Daisuke DEGUCHI |
2nd Author's Affiliation | Graduate School of Information Science, Nagoya University |
3rd Author's Name | Tomokazu TAKAHASHI |
3rd Author's Affiliation | Graduate School of Information Science, Nagoya University:Faculty of Economics and Information, Gifu Shotoku Gakuen University |
4th Author's Name | Ichiro IDE |
4th Author's Affiliation | Graduate School of Information Science, Nagoya University |
5th Author's Name | Hiroshi MURASE |
5th Author's Affiliation | Graduate School of Information Science, Nagoya University |
Date | 2011-03-11 |
Paper # | PRMU2010-279 |
Volume (vol) | vol.110 |
Number (no) | 467 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |