新任助教講演会(Lectures from New Assistant Professors)

日時(Datetime) 令和3年6月8日(火)3限 (13:30 -- 15:00), 2021/06/08, Tuesday, 3rd slot
場所(Location) エーアイ大講義室(L1)
司会(Chair) 小林 泰介(Taisuke Kobayashi)

講演者(Presenter) 澤邊 太志(Taishi Sawabe), インタラクティブメディア設計学研究室 (Interactive Media Design Lab.)
題目(Title) Comfort Intelligence for Autonomous Vehicles
概要(Abstract) A variety of robots have been developed in a different use case in our daily life. In the field of Human-Robot Interaction (HRI), considering human comfort design is very important when the person meets real autonomous objects for the first time. In this presentation, the concept of Comfort Intelligence for Human-Robot Interaction will introduce through the example situation in an autonomous vehicle's research. The concept of comfort intelligence includes anxiety (negative state) to the entertainments (positive state) in the real situation of using autonomous vehicles with passengers feeling. In this research field, anxiety reduction is mainly targeted. The anxiety comes from a variety of stress factors. In the field of vehicles, we defined stress in autonomous vehicles as Autonomous Vehicle Stress (AVS) to estimate, classify and consider reduction methods for reducing anxiety in autonomous vehicles. Moreover, anxiety is not only about stress but also have to consider motion sickness. Since many people release from driving, it is difficult to understand vehicles behaviour. In addition, people tend to spend more time on entertainments that will increase car sickness more often. Furthermore, many car accessory companies tend to develop HUD by using VR or AR for better navigation in the future. These trends, however, also increase VR sickness. In our ideas, there will be new motion sickness called Autonomous Vehicle Motion Sickness (AVMS) that is mixed with car sickness and VR sickness in the future autonomous vehicle environment. Therefore, in this presentation, explain the importance of considering comfort intelligence (CI) by looking at previous researches on anxiety, as well as discussing stress and motion sickness perspective.

講演者(Presenter) 藤村 友貴 (Yuki Fujimura), 光メディアインタフェース研究室 (Optical Media Interface Lab.)
題目(Title) 3D Reconstruction in Scattering Media
概要(Abstract) This lecture discusses three-dimensional (3D) reconstruction in scattering media. 3D reconstruction from two-dimensional images is important in computer vision. However, images captured in scattering media, such as fog or murky water, degrade due to light scattering and attenuation caused by suspended particles. Unfortunately, conventional 3D reconstruction methods are affected by this image degradation in scattering media. This lecture presents image formation models for such degradation and proposes methods to enable 3D reconstruction in scattering media. Typical disparity- and shading-based 3D reconstruction methods, i.e., multi-view stereo and photometric stereo, are extended for scattering media with appropriate physics-based scattering models. The effectiveness of the proposed methods is evaluated on real data captured in foggy scenes and underwater.