Estimatoin of risky driving situation based on driver gaze behavior modeling

• Project/Area Number: 15K00231
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: Nagoya University
• Principal Investigator: Chiyomi Miyajima 名古屋大学, 未来社会創造機構, 特任准教授 (90335092)
• Co-Investigator(Kenkyū-buntansha): 武田 一哉 名古屋大学, 情報学研究科, 教授 (20273295)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Project Status: Completed (Fiscal Year 2017)
• Budget Amount: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2017: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000); Fiscal Year 2015: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
• Keywords: ドライバ / 視行動 / 運転操作行動 / 危険度推定 / 隠れマルコフモデル / 車線変更 / 運転行動 / 運転データ / 危険状態推定

Outline of Final Research Achievements

We proposed a method to quantify the safety of driver gaze behavior based on the relationship between the gaze directions and the positions and the risk levels of surrounding vehicles. Experimental results showed that driving instructors exhibit safer gaze behavior than other drivers. We also proposed a method of modeling the sequences and co-occurrence of driver gaze behavior and vehicle operation behavior. We modeled safe and risky lane change maneuvers based on gaze directions and discrete acts of vehicle operation behavior using hidden Markov models. We found that there were significant differences between the model parameters of safe and risky behavior. We then detected risky lane changes using the models. The integrated model of gaze and vehicle operation behavior achieved better risky lane change detection performance than the gaze-only and vehicle operation-only models.

Research Products

• [Journal Article] Integrating driving behavior and traffic context through signal symbolization for data reduction and risky lane change detection (2018)
  • Author(s): Ekim Yurtever, Suguru Yamazaki, Chiyomi Miyajima, Chiyomi, Kazuya Takeda, Masataka Mori, Kentarou Hitomi, and Masumi Egawa
  • Journal Title: IEEE Transactions on Intelligent Vehicles Volume: 印刷中
  • Peer Reviewed
• [Journal Article] 車内音声対話実験車 (2016)
  • Author(s): 武田 一哉, 宮島 千代美
  • Journal Title: 日本音響学会誌 Volume: 72(7) Pages: 402-403
  • NAID: 130007355976
• [Journal Article] Driver-behavior modeling using on-road driving data (2016)
  • Author(s): Chiyomi Miyajima, Kazuya Takeda
  • Journal Title: IEEE Signal Processing Magazine Volume: 33(6) Pages: 14-21
  • DOI: 10.1109/msp.2016.2602377
  • Peer Reviewed
• [Presentation] Estimating subjective driving risk feeling using random forest (2018)
  • Author(s): Naren Bao, Chiyomi Miyajima, Akira Tamamori, Eijiro Takeuchi, and Kazuya Takeda
  • Organizer: 電子情報通信学会総合大会
• [Presentation] Analysis of individual risk perception during highway lane-change scenes (2017)
  • Author(s): Bao Naren, Chiyomi Miyajima, Eijiro Takeuchi Kazuya Takeda
  • Organizer: 情報処理学会第79回全国大会
  • Place of Presentation: 名古屋市
  • Year and Date: 2017-03-16
• [Presentation] Estimating risk levels perceived by individuals for lane change scenes (2017)
  • Author(s): Naren Bao, Chiyomi Miyajima, Eijiro Takeuchi, Kazuya Takeda, Shinichiro Honda, Toshiya Yoshitani, and Masayoshi Ito
  • Organizer: 4th International Symposium on Future Active Safety Technology toward zero traffic accidents (FAST-zero ’17)
  • Int'l Joint Research
• [Presentation] Estimation of driver's risk feeling toward driving environment using neural network (2017)
  • Author(s): Yuan Sheng, Yiyang Li, Chiyomi Miyajima, Eijiro Takeuchi, Kazuya Takeda, Shinichiro Honda, Toshiya Yoshitani, and Masayoshi Ito
  • Organizer: 4th International Symposium on Future Active Safety Technology toward zero traffic accidents (FAST-zero ’17)
  • Int'l Joint Research
• [Presentation] Estimation of risk as perceived by individual drivers (2017)
  • Author(s): Chiyomi Miyajima, Yuan Sheng, and Kazuya Takeda
  • Organizer: The Second Seminar on JSPS Core-to-Core Program, Asia-Africa Science Platforms: Establishment of Research Hub for Compact Mobility Model in the ASEAN Region
  • Int'l Joint Research
• [Presentation] Analysis of driver workload when using speech interfaces (2016)
  • Author(s): Daiki Hayashi, Chiyomi Miyajima, and Kazuya Takeda
  • Organizer: ASA and ASJ 5th Joint Meeting
  • Place of Presentation: Honolulu, USA
  • Year and Date: 2016-11-28
  • Int'l Joint Research
• [Presentation] 瞬目の点過程表現による同乗者の不安状態検出 (2016)
  • Author(s): 林大貴，坪井優幸，宮島千代美，石黒祥生，武田一哉
  • Organizer: 電子情報通信学会基礎・境界ソサイエティ大会
  • Place of Presentation: 札幌市
  • Year and Date: 2016-09-20
• [Presentation] Integrating driving behavior and traffic context through signal symbolization (2016)
  • Author(s): Suguru Yamazaki, Chiyomi Miyajima, Ekim Yurtsever, Kazuya Takeda, Masataka Mori, Kentarou Hitomi, Masumi Egawa
  • Organizer: 2016 IEEE Intelligent Vehicles Symposium
  • Place of Presentation: Gothenburg, Sweden
  • Year and Date: 2016-06-19
  • Int'l Joint Research
• [Presentation] Prediction of individual driving behavior on highway curves (2016)
  • Author(s): Bao Naren, Daiki Hayashi, Chiyomi Miyajima, Kazuya Takeda
  • Organizer: 3rd Workshop on Naturalistic Driving Data Analytics
  • Place of Presentation: Gothenburg, Sweden
  • Int'l Joint Research / Invited
• [Presentation] Tracking driver’s observation using local feature matching and optical flow (2015)
  • Author(s): Chiyomi Miyajima, Katsuya Sakoyama, and Kazuya Takeda
  • Organizer: IEEE/SICE International Symposium on System Integration
  • Place of Presentation: Nagoya, Japan
  • Year and Date: 2015-12-11
  • Int'l Joint Research
• [Presentation] Risky lane change detection based on symbolization of driving data (2015)
  • Author(s): Suguru Yamazaki, Chiyomi Miyajima, Masataka Mori, Takashi Bando, Kazuhito Takenaka, and Kazuya Takeda
  • Organizer: 7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems
  • Place of Presentation: San Francisco, USA
  • Year and Date: 2015-10-14
  • Int'l Joint Research
• [Presentation] Driving scene classification using vehicle motion estimated with smartphone (2015)
  • Author(s): Masayuki Tsuoi, Chiyomi Miyajima, and Kazuya Takeda
  • Organizer: 7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems
  • Place of Presentation: San Francisco, USA
  • Year and Date: 2015-10-14
  • Int'l Joint Research
• [Presentation] Profiting from FOT experiences in deployment (2015)
  • Author(s): Kazuya Takeda
  • Organizer: FOT-Net Data International Workshop
  • Place of Presentation: Bordeaux, France
  • Year and Date: 2015-10-05
  • Int'l Joint Research
• [Presentation] Driving signature extraction (2015)
  • Author(s): Ekim Yurtsever, Chiyoi Miyajima, Selpi, and Kazuya Takeda
  • Organizer: 3rd International Symposium on Future Active Safety Technology toward zero traffic accidents
  • Place of Presentation: Gothenburg, Sweden
  • Year and Date: 2015-09-09
  • Int'l Joint Research
• [Presentation] An experimental study on the difference in drivers’ decision-making behavior during manual and supported driving (2015)
  • Author(s): Hitoshi Terai, Hiroyuki Okuda, Kentaro Hitomi, Takashi Bando, Chiyomi Miyajima, Takatsugu Hirayama, Yuuki Shinohara, Masumi Egawa, and Kazuya Takeda
  • Organizer: 6th International Conference on Applied Hunan Factors and Ergonomics
  • Place of Presentation: Las Vegas, USA
  • Year and Date: 2015-07-26
  • Int'l Joint Research
• [Presentation] Ongoing METI project for NDS-based driver modeling (2015)
  • Author(s): Chiyomi Miyajima
  • Organizer: 2nd Workshop on Naturalistic Driving Data Analytics
  • Place of Presentation: Seoul, Korea
  • Year and Date: 2015-06-28
  • Int'l Joint Research / Invited
• [Presentation] Analyzing driver gaze behavior and consistency of decision making during automated driving (2015)
  • Author(s): Chiyomi Miyajima, Suguru Yamazaki, Takashi Bando, Kentarou Hitomi, Hitoshi Terai , Hiroyuki Okuda, Takatsugu Hirayama, Masumi Egawa, Tatsuya Suzuki, and Kazuya Takeda
  • Organizer: 2015 IEEE Intelligent Vehicles Symposium
  • Place of Presentation: Seoul, Korea
  • Year and Date: 2015-06-28
  • Int'l Joint Research
• [Presentation] Traffic trajectory history and drive path generation using GPS data cloud (2015)
  • Author(s): Ekim Yurtsever, Kazuya Takeda, and Chiyomi Miyajima
  • Organizer: 2015 IEEE Intelligent Vehicles Symposium
  • Place of Presentation: Seoul, Korea
  • Year and Date: 2015-06-28
  • Int'l Joint Research
• [Book] Integrated modeling of driver gaze and vehicle operation behavior during lane changes,” Vehile Systems and Driver Modeling - DSP, Human-to-Vehicle Interfaces, Driver Behavior, and Safety, H. Abut, et al. eds. (2017)
  • Author(s): Chiyomi Miyajima, Masataka Mori, Takatsugu Hirayama, Norihide Kitaoka, and Kazuya Takeda
  • Total Pages: 9
  • Publisher: De Gruyter