Presentation | 2019-03-05 Tracking Multiple Pedestrians Using the Network of Human Detectors Kyosuke Konishi, Hiroshi Kameda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Tracking indoor pedestrians makes logistics in a factory effective and a security system in a building accurate. Conventional approaches to track pedestrians use the wireless device attatched to pedestrians or use the surveillance camera. However, the field of view of a camera tends to be narrowed in a building, and it is an impractical prerequisite that each of the interested pedestrians has the wireless device. This paper proposes the alternative approach using the network of human detectors. The difficulty of this approach is that a human detector can observe only whether the pedestrians are in its detectable area. To overcome this drawback, the proposed method uses the estimation algorithm based on statistics of Random Finite Sets. This feature makes it possible to estimate individual tracks of pedestrians with human detectors even if false detections and miss detections occur. Simulations are used to verify the our approach. The result of them illustrates that the proposed method achieves better performance than a straightforward method, which makes tracks with connecting positions of human detectors. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | pedestrian / tracking / human detector / Random Finite Sets |
Paper # | ASN2018-112 |
Date of Issue | 2019-02-25 (ASN) |
Conference Information | |
Committee | ASN / MoNA / IPSJ-MBL / IPSJ-UBI |
---|---|
Conference Date | 2019/3/4(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | The University of Tokyo, Komaba Campus |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | General |
Chair | Hiraku Okada(Nagoya Univ.) / Ryoichi Shinkuma(Kyoto Univ.) / / Yoshito Tobe(Tokyo Denki Univ.) |
Vice Chair | Koji Yamamoto(Kyoto Univ.) / Jin Nakazawa(Keio Univ.) / Kazuya Monden(Hitachi) / Shigeaki Tagashira(Kansai Univ.) / Gen Kitagata(Tohoku Univ.) |
Secretary | Koji Yamamoto(NICT) / Jin Nakazawa(Sophia Univ.) / Kazuya Monden(Kanagawa Inst. of Tech.) / Shigeaki Tagashira(Kyushu Univ.) / Gen Kitagata(NEC) / (Kyoto Univ.) / (NTT DOCOMO) |
Assistant | Masafumi Hashimoto(Osaka Univ.) / Tomoyuki Ota(Hiroshima City Univ.) / Tatsuya Kikuzuki(Fujitu Lab.) / Ryo Nakano(HITACHI) / Yoshifumi Hotta(Mitsubishi Electric) / Ken Usui(KDDI Research) / Kenji Kanai(Waseda Univ.) |
Paper Information | |
Registration To | Technical Committee on Ambient intelligence and Sensor Networks / Technical Committee on Mobile Network and Applications / Special Interest Group on Mobile Computing and Ubiquitous Communications / Special Interest Group on Ubiquitous Computing System |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Tracking Multiple Pedestrians Using the Network of Human Detectors |
Sub Title (in English) | |
Keyword(1) | pedestrian |
Keyword(2) | tracking |
Keyword(3) | human detector |
Keyword(4) | Random Finite Sets |
1st Author's Name | Kyosuke Konishi |
1st Author's Affiliation | Mitsubishi Electric Corporation(Mitsubishi Electric Corp.) |
2nd Author's Name | Hiroshi Kameda |
2nd Author's Affiliation | Mitsubishi Electric Corporation(Mitsubishi Electric Corp.) |
Date | 2019-03-05 |
Paper # | ASN2018-112 |
Volume (vol) | vol.118 |
Number (no) | ASN-468 |
Page | pp.pp.203-208(ASN), |
#Pages | 6 |
Date of Issue | 2019-02-25 (ASN) |