Explanation of the Sense of Visual Perception in Cornering Based on Gaze Position and Optical Flows

In the recently developed self-driving technologies, users often experience strangeness when performing cornering control such as in lane-keeping assist. To realize human-centered cornering control, we had proposed a human perception model that considers optical flow and gaze position for cornering. In this paper, we propose a divergence point detection method for identifying the target position on the spherical image corresponding to the gaze position. We first discuss the relationship between optical flow and gaze movement in cornering, and we identify optical flows radiating outward from the gaze position. Next, we explain a divergence point detection method that uses optical flow vectors based on particle swarm optimization. For verifying the proposed method, we perform an experiment using an actual vehicle; the results show that the divergence detection method can detect a divergence point.

[1]  J. Gibson.  The Ecological Approach to the Visual Perception of Pictures , 1978 .

[2]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[3]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[4]  A. Hendrickson,et al.  Human photoreceptor topography , 1990, The Journal of comparative neurology.

[5]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[6]  N. Taniguchi,et al.  2. 3D simulation of the plane impinging jet , 1998 .

[7]  H. Bülthoff,et al.  Driving in the future: temporal visuomotor adaptation and generalization. , 2001, Journal of vision.

[8]  Hisanao Komine,et al.  Study on improving angular acceleration feel of the driving simulator and its effects on drivers' behaviors , 2006 .

[9]  Mohan M. Trivedi,et al.  Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation , 2006, IEEE Transactions on Intelligent Transportation Systems.

[10]  Yasuhiro Seya,et al.  Measurement of Visual Attention and Useful Field of View During Driving Tasks Using a Driving Simulator , 2007 .

[11]  Eiichi Ono,et al.  Improvement of Vehicle Dynamics Based on Human Sensitivity , 2007 .

[12]  Andries Petrus Engelbrecht,et al.  Particle swarm optimization with spatially meaningful neighbours , 2008, 2008 IEEE Swarm Intelligence Symposium.

[13]  Michiteru Kitazaki,et al.  Study on Device Controlling Visual Information to Improve Driver's Performance , 2008 .

[14]  Michiteru Kitazaki,et al.  A Study on a Device for Controlling Visual Information to Improve Driver Performance , 2009 .

[15]  Vorapoj Patanavijit,et al.  Tutorial of Motion Estimation Based on Horn-Schunk Optical Flow Algorithm in MATLAB® , 2011 .

[16]  Chi K. Tse,et al.  Network-Structured Particle Swarm Optimizer That Considers Neighborhood Distances and Behaviors , 2014 .

[17]  Junmin Wang,et al.  Sensitivity analysis of human driving characteristics on road and driving conditions for active vehicle control systems , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[18]  F. Hecht,et al.  Efficient Identification of HIV Serodiscordant Couples by Existing HIV Testing Programs in South Brazil , 2015, PloS one.

[19]  Otto Lappi,et al.  Driver Gaze Behavior Is Different in Normal Curve Driving and when Looking at the Tangent Point , 2015, PloS one.

[20]  Takanori Fukao,et al.  Development of Automatic Steering System by Modeling Human Behavior Based on Optical Flow , 2015, J. Robotics Mechatronics.

[21]  Aakash Arora,et al.  A Roadmap to Safer Driving Through Advanced Driver Assistance Systems , 2016 .

[22]  Hiroyuki Masuta,et al.  A Study of Optical Flow in Peripheral Vision Area While Vehicle Cornering , 2018, 2018 Joint 10th International Conference on Soft Computing and Intelligent Systems (SCIS) and 19th International Symposium on Advanced Intelligent Systems (ISIS).

[23]  Hiroyuki Masuta,et al.  Spherical optical flow in automatically controlled vehicle while cornering , 2018, 2018 IEEE Symposium Series on Computational Intelligence (SSCI).