Presentation | 2024-01-18 Development of Management Methods against Inappropriate Data Segments in Bus Passenger OD Estimation using Person Tracking Methods Tsubasa Nishiura, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We are advancing the development of a passenger Origin-Destination (OD) estimation system using bus passengerboarding and alighting videos, to collect OD data reflecting passenger movements on route buses. This paper focuses on developing methods for processing inappropriate data segments to improve the estimation accuracy of the passenger OD estimation system. Inappropriate data segments refer to rectangles that may cause accuracy degradation when input into the person tracker from the person detector, and trajectories that include ID switches occurring during person tracking. These nappropriate data segments are factors in reducing the accuracy of person detection and tracking. We develop methods to remove inappropriate data segments based on the size and position of the rectangles and the overlap between trajectories. The application of theinappropriate data segment processing method to the passenger OD estimation system was tested on actual route bus video data, confirming the possibility of improving OD estimation accuracy. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | deep learning / object detection / object tracking / metric learning / OD data / bus |
Paper # | MSS2023-69,SS2023-48 |
Date of Issue | 2024-01-10 (MSS, SS) |
Conference Information | |
Committee | SS / MSS |
---|---|
Conference Date | 2024/1/17(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Kozo Okano(Shinshu Univ.) / Shingo Yamaguchi(Yamaguchi Univ.) |
Vice Chair | Yoshiki Higo(Osaka Univ.) / Toshiyuki Miyamoto(Osaka Inst. of Tech.) |
Secretary | Yoshiki Higo(Shinshu Univ.) / Toshiyuki Miyamoto(Tokyo Inst. of Tech.) |
Assistant | Shinsuke Matsumoto(Osaka Univ.) / Masato Shirai(Shimane Univ.) |
Paper Information | |
Registration To | Technical Committee on Software Science / Technical Committee on Mathematical Systems Science and its Applications |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Development of Management Methods against Inappropriate Data Segments in Bus Passenger OD Estimation using Person Tracking Methods |
Sub Title (in English) | * |
Keyword(1) | deep learning |
Keyword(2) | object detection |
Keyword(3) | object tracking |
Keyword(4) | metric learning |
Keyword(5) | OD data |
Keyword(6) | bus |
1st Author's Name | Tsubasa Nishiura |
1st Author's Affiliation | Hokkaido University(Hokkaido Univ.) |
2nd Author's Name | Soichiro Yokoyama |
2nd Author's Affiliation | Hokkaido University(Hokkaido Univ.) |
3rd Author's Name | Tomohisa Yamashita |
3rd Author's Affiliation | Hokkaido University(Hokkaido Univ.) |
4th Author's Name | Hidenori Kawamura |
4th Author's Affiliation | Hokkaido University(Hokkaido Univ.) |
Date | 2024-01-18 |
Paper # | MSS2023-69,SS2023-48 |
Volume (vol) | vol.123 |
Number (no) | MSS-334,SS-335 |
Page | pp.pp.99-104(MSS), pp.99-104(SS), |
#Pages | 6 |
Date of Issue | 2024-01-10 (MSS, SS) |