Presentation | 2020-01-27 Extraction of Artificial Fiber Pattern from Video Using Deep Learning technique Noda Tomo, Kaneda Kitahiro, Iwamura Keiichi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We are studying the realization of a human monitoring system that collects human movements by detecting a unique ID embedded in daily necessities such as clothing through multiple surveillance cameras. In previous research, we proposed an information embedding method that can recognize changes in content but has low visibility , and realized information embedding in fiber materials. This is defined as an artificial fiber pattern. In this paper, we selected T-shirts, which are generally used as a medium for embedding the artificial fiber pattern, and verified the embedding potential. In addition, we realized an end to end system that extracts information from surveillance camera images by using deep learning. As a result, By majority decision between frames, we achieved 100% extraction rate under specific conditions. This makes it possible to distinguish clothes of the same color, which were difficult to recognize with conventional object detection technology. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Data Hiding / Artificial Fiber Pattern / Deep Learning / Object Detection |
Paper # | EMM2019-100 |
Date of Issue | 2020-01-20 (EMM) |
Conference Information | |
Committee | EMM |
---|---|
Conference Date | 2020/1/27(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Tohoku Univ. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Sense of Presence, Universal Media, Digital Entertainment, etc. |
Chair | Masaki Kawamura(Yamaguchi Univ.) |
Vice Chair | Motoi Iwata(Osaka Prefecture Univ.) / Tetsuya Kojima(NIT,Tokyo College) |
Secretary | Motoi Iwata(NIT, Nagano College) / Tetsuya Kojima(Nagase) |
Assistant | Masaki Inamura(Tokyo Denki Univ.) / Kazuhiro Kono(Kansai Univ.) |
Paper Information | |
Registration To | Technical Committee on Enriched MultiMedia |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Extraction of Artificial Fiber Pattern from Video Using Deep Learning technique |
Sub Title (in English) | |
Keyword(1) | Data Hiding |
Keyword(2) | Artificial Fiber Pattern |
Keyword(3) | Deep Learning |
Keyword(4) | Object Detection |
1st Author's Name | Noda Tomo |
1st Author's Affiliation | Tokyo University of Science(Tokyo Univ. of Science) |
2nd Author's Name | Kaneda Kitahiro |
2nd Author's Affiliation | Tokyo University of Science(Tokyo Univ. of Science) |
3rd Author's Name | Iwamura Keiichi |
3rd Author's Affiliation | Tokyo University of Science(Tokyo Univ. of Science) |
Date | 2020-01-27 |
Paper # | EMM2019-100 |
Volume (vol) | vol.119 |
Number (no) | EMM-396 |
Page | pp.pp.31-36(EMM), |
#Pages | 6 |
Date of Issue | 2020-01-20 (EMM) |