■ 주제: A Real-Time Augmented Reality System to See-Through Cars

■ 연사: Francois Rameau, PostDoc, Robotics and Computer Vision laboratory (RCV lab), KAIST.

■ 일시: 2016년 10월 19일 (수) 오후 4시

■ 장소: KI 빌딩 3층 B301호

■ 주관: KAIST 증강현실연구센터(ARRC)

■ 요약
One of the most hazardous driving scenario is the overtaking of a slower vehicle, indeed, in this case the front vehicle (being overtaken) can occlude an important part of the field of view of the rear vehicle's driver. This lack of visibility is the most probable cause of accidents in this context. Recent research works tend to prove that augmented reality applied to assisted driving can significantly reduce the risk of accidents. In this talk, I will present a real-time marker-less system to see through cars. For this purpose, two cars are equipped with cameras and an appropriate wireless communication system. The stereo vision system mounted on the front car allows to create a sparse 3D map of the environment where the rear car can be localized. Using this inter-car pose estimation, a synthetic image is generated to overcome the occlusion and to create a seamless see-through effect which preserves the structure of the scene. Furthermore, I will shortly introduce several ongoing computer vision works closely related to AR developed in RCVlab.

■ 약력
Francois Rameau received his Bachelor degree in Electronic, Signal and Image processing in 2009 and his Master degree in Vision and Robotics (VIBOT) from University of Burgundy in 2011. He completed his PhD degree untitled “Hybrid foveated vision system for video surveillance and robotic navigation” in December 2014. In 2015, he worked as a full time postdoctoral researcher in RCVlab in KAIST (Daejeon, South Korea). He is nowadays a postdoctoral fellow in RCVlab funded by the National Research Foundation of Korea (NRF) under the supervision of Prof. Kweon. His research interests include 3D reconstruction, assisted and cooperative driving, robotics, visual tracking and omnidirectional vision.