Presentation | 2018-07-02 Detection of Abnormal Behavior Based on Driver Area of In-Car Movie by Deep Learning Ryo Kidoguchi, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, due to frequent occurrence of accidents caused by abnormal behaviors of bus and truck drivers, efforts are being made to utilize the video of the driving situation of the driver recorded by the drive recorder in the management and guidance of the driver.In addition, Depending on the circumstances of directly managing and guiding the video of the drive recorder, it is directly connected with the performance of the company.But for this, however, it is necessary to watch the video of the drive recorder for a long time, It is a heavy burden on the responsible person to judge the behavior of the driver who leads to the accident.Therefore, from the movie over a long period of time, abnormal behaviors the driver should check should be confirmed Aiming at semi-automation of confirmation work such as extracting the part being taken, we construct a mechanism to classify the behavior of the driver using convolution neural network Also improve the detection accuracy by improving the accuracy of driver region extraction. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | abnormal behaviors / deep learning / in-car video / drive recorder / Driver area |
Paper # | AI2018-10 |
Date of Issue | 2018-06-25 (AI) |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2018/7/2(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Tsunenori Mine(Kyushu Univ.) |
Vice Chair | Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.) |
Secretary | Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.) |
Assistant | Yuko Sakurai(AIST) |
Paper Information | |
Registration To | Technical Committee on Artificial Intelligence and Knowledge-Based Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Detection of Abnormal Behavior Based on Driver Area of In-Car Movie by Deep Learning |
Sub Title (in English) | |
Keyword(1) | abnormal behaviors |
Keyword(2) | deep learning |
Keyword(3) | in-car video |
Keyword(4) | drive recorder |
Keyword(5) | Driver area |
1st Author's Name | Ryo Kidoguchi |
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 | 2018-07-02 |
Paper # | AI2018-10 |
Volume (vol) | vol.118 |
Number (no) | AI-116 |
Page | pp.pp.53-59(AI), |
#Pages | 7 |
Date of Issue | 2018-06-25 (AI) |