research-article

GazeFCW: Filter Collision Warning Triggers by Detecting Driver's Gaze Area

Authors:

Chengnian LongAuthors Info & Claims

SenSys-ML 2019: Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor Systems

Pages 13 - 18

https://doi.org/10.1145/3362743.3362962

Published: 10 November 2019 Publication History

Abstract

Collision warning is essential in Advanced Driver Assistance Systems. However, all the studies focus on accurate assessment of risky situations without considering the driver's attention mechanism, which causes the proportion of valid warning triggers to be extremely low. In this paper, we present GazeFCW --- a novel system that uses the driver's gaze direction to filter out unnecessary warning triggers. We verified the proposed system against several roads of different conditions. Our evaluation, across different crowded roads, shows a significant enhancement in warning trigger efficiency---compared to the standard system---reflected by an increase in the valid trigger proportion by 42%, a decrease in the invalid trigger proportion from 74.7% down to 32.7%, while adding only 50 ms run time execution overhead and causing negligible missing triggers.

References

[1]

Fridman, Lex and Toyoda, Heishiro and Seaman, Sean and Seppelt, Bobbie and Angell, Linda and Lee, Joonbum and Mehler, Bruce and Reimer, Bryan. 2017. What can be predicted from six seconds of driver glances. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. ACM, 2805--2813.

Digital Library

[2]

Geiger, Andreas and Lenz, Philip and Urtasun, Raquel. 2012. Are we ready for autonomous driving. In Proc. CVPR. 3354--3361.

[3]

Hayward, John C. 1972. Near miss determination through use of a scale of danger. (1972).

[4]

Henriques, João F and Caseiro, Rui and Martins, Pedro and Batista, Jorge. 2014. High-speed tracking with kernelized correlation filters. IEEE transactions on pattern analysis and machine intelligence 37, 3 (2014), 583--596.

[5]

Jiménez, Felipe and Naranjo, José Eugenio. 2011. Improving the obstacle detection and identification algorithms of a laserscanner-based collision avoidance system. Transportation research part C: emerging technologies 19, 4 (2011), 658--672.

[6]

Jung, Heechul and Choi, Min-Kook and Soon, Kwon and Jung, Woo Young. 2018. End-to-end pedestrian collision warning system based on a convolutional neural network with semantic segmentation. In 2018 IEEE International Conference on Consumer Electronics (ICCE). IEEE, 1--3.

[7]

Liang, Zhenwen and Shao, Jie and Zhang, Dongyang and Gao, Lianli. 2018. Small object detection using deep feature pyramid networks. In Pacific Rim Conference on Multimedia. Springer, 554--564.

[8]

Lu, Yuwei and Yuan, Yuan and Wang, Qi. 2018. Forward Vehicle Collision Warning Based on Quick Camera Calibration. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2586--2590.

[9]

Pakdamanian, Erfan and Feng, Lu and Kim, Inki. 2018. The Effect of Whole-Body Haptic Feedback on Driver's Perception in Negotiating a Curve. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Vol. 62. SAGE Publications Sage CA: Los Angeles, CA, 19--23.

[10]

Park, Seonwook and Zhang, Xucong and Bulling, Andreas and Hilliges, Otmar. 2018. Learning to find eye region landmarks for remote gaze estimation in unconstrained settings. In Proceedings of the 2018 ACM Symposium on Eye Tracking Research & Applications. ACM, 21.

Digital Library

[11]

Phillips, Derek J and Aragon, Juan Carlos and Roychowdhury, Anjali and Madigan, Regina and Chintakindi, Sunil and Kochenderfer, Mykel J. 2019. Real-time Prediction of Automotive Collision Risk from Monocular Video. arXiv preprint arXiv:1902.01293 (2019).

[12]

Soto, Ignacio and Jimenez, Felipe and Calderon, Maria and Naranjo, Jose E and Anaya, Jose J. 2019. Reducing Unnecessary Alerts in Pedestrian Protection Systems Based on P2V Communications. Electronics 8, 3 (2019), 360.

[13]

Trivedi, Mohan M and others. 2019. Attention Monitoring and Hazard Assessment with Bio-Sensing and Vision: Empirical Analysis Utilizing CNNs on the KITTI Dataset. arXiv preprint arXiv:1905.00503 (2019).

[14]

Van Der Horst, Richard and Hogema, Jeroen. 1993. Time-to-collision and collision avoidance systems. (1993).

[15]

Wu, Bichen and Iandola, Forrest and Jin, Peter H and Keutzer, Kurt. 2017. Squeezedet: Unified, small, low power fully convolutional neural networks for real-time object detection for autonomous driving. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 129--137.

[16]

Xia, Ye and Kim, Jinkyu and Canny, John and Zipser, Karl and Whitney, David. 2019. Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention. arXiv preprint arXiv:1903.09950 (2019).

Cited By

Kotseruba ITsotsos J(2022)Attention for Vision-Based Assistive and Automated Driving: A Review of Algorithms and DatasetsIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2022.318661323:11(19907-19928)Online publication date: Nov-2022
https://doi.org/10.1109/TITS.2022.3186613

Index Terms

GazeFCW: Filter Collision Warning Triggers by Detecting Driver's Gaze Area
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks
        Activity recognition and understanding
2. Human-centered computing
  1. Human computer interaction (HCI)
    1. HCI design and evaluation methods
      1. Usability testing

Recommendations

Alerting for vehicles demonstrating hazardous driving behavior
MobiDE '12: Proceedings of the Eleventh ACM International Workshop on Data Engineering for Wireless and Mobile Access

Cooperative Collision Warning Systems (CCWSs) have become a major vehicle safety application in intelligent transportation systems. Vehicles organized in a vehicular ad-hoc network use a CCWS communication protocol to propagate emergency messages about ...
Detecting Hazardous Vehicles and Disseminating Their Behavior in Urban Areas
MDM '12: Proceedings of the 2012 IEEE 13th International Conference on Mobile Data Management (mdm 2012)

Speeding cars and motorcycles constantly varying their speed, changing lanes or committing other apparent traffic violations as well as police cars and ambulances responding to incidents, are examples of vehicles that demonstrate hazardous traffic ...
Prediction of Human Driving Behavior Using Dynamic Bayesian Networks

This paper presents a method of predicting future human driving behavior under the condition that its resultant behavior and past observations are given. The proposed method makes use of a dynamic Bayesian network and the junction tree algorithm for ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

SenSys-ML 2019: Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor Systems

November 2019

47 pages

ISBN:9781450370110

DOI:10.1145/3362743

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 10 November 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

National Nature Science Foundation of China

Conference

SenSys '19

Sponsor:

SenSys '19: The 17th ACM Conference on Embedded Networked Sensor Systems

November 10, 2019

NY, New York, USA

Acceptance Rates

SenSys-ML 2019 Paper Acceptance Rate 7 of 14 submissions, 50%;

Overall Acceptance Rate 7 of 14 submissions, 50%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
140
Total Downloads

Downloads (Last 12 months)22
Downloads (Last 6 weeks)0

Reflects downloads up to 03 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Kotseruba ITsotsos J(2022)Attention for Vision-Based Assistive and Automated Driving: A Review of Algorithms and DatasetsIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2022.318661323:11(19907-19928)Online publication date: Nov-2022
https://doi.org/10.1109/TITS.2022.3186613

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten