Estimation method for time to contact from visual information — A simple approach that requires no recognition of objects

Recently, intelligent safety systems for automobiles, such as autonomous collision avoidance, have attracted considerable attention. Usually, automobiles have distance sensors to detect obstacles. On the other hand, animals and insects can behave adaptively, even in an unknown environment, even though they do not have such sensors. In ecological psychology, it is assumed that animals and insects use information related to the time to contact instead of distance information. This time-to-contact information is called the “τ-margin,” and it is calculated from the apparent size of the approaching object and its temporal change in conventional studies. Therefore, the detection of each object is required before calculating the τ-margin. In this paper, we propose an algorithm to estimate the τ-margin without detecting objects. To verify the effectiveness of the proposed algorithm, we conducted experiments using 1/10-scale automobiles and a real vehicle.

[1]  Yoram Koren,et al.  Real-time obstacle avoidance for fast mobile robots in cluttered environments , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[2]  Kazuyuki Ito,et al.  Determination of time to contact and application to timing control of mobile robot , 2010, 2010 IEEE International Conference on Robotics and Biomimetics.

[3]  Insoo Joung,et al.  Two-Dimensional Depth Data Measurement Using an Active Omni-Directional Range Sensor , 1999 .

[4]  D. N. Lee The optic flow field: the foundation of vision. , 1980, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[5]  Atsushi Yamashita,et al.  3-D MAP GENERATION BY A MOBILE ROBOT EQUIPPED WITH A LASER RANGE FINDER(International Workshop on Advanced Image Technology 2006) , 2006 .

[6]  M. Skolnik,et al.  Introduction to Radar Systems , 2021, Advances in Adaptive Radar Detection and Range Estimation.

[7]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[8]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[9]  Lee Dn,et al.  The optic flow field: the foundation of vision. , 1980 .