Koh Kakusho

Major research activity

KohKakushoWith the recent advancement of mobile and ubiquitous sensing technologies, it becomes a great challenge to assist various daily activities of humans in their living environment by observing them with various kinds of sensors. Among the sensors possible to be installed in our living environment, cameras have the advantage that they can capture rich visual information of observed objects without sensing devices attached on the objects. Moreover, those cameras are recently spreading in our living environment as components of video surveillance systems, PCs, cell-phones, game machines, etc. However, continuous observation of human activities by cameras often causes privacy concerns.

Our research goal is to assist human daily activities based on video images obtained from cameras installed in various living environments without interference in those activities and violation of privacy, by recognizing each behavior of humans and inferring their intension while discarding privacy information. Aiming to understand intensions of humans in their daily activities in a broader context, we set our research focus especially on interactive and social behaviors in a group of humans and objects, rather than those by each individual. Our research relates to the fields of image processing, computer vision, computer graphics, embodied agents, and other visual information technologies.

Major relevant publications

  1. S.Kikutani, K.Kakusho, T.Okadome, M.Iiyama, S.Nishiguchi: "Measuring the Arrangement of Multiple Information Devices by Observing Their User's Face," Springer Lecture Notes in Computer Science, Vol.9189, pp.296-304 (2015).
  2. J.Nishikawa1, K.Kakusho, M.Iiyama, S.Nishiguchi, M.Murakami: "Estimating Positions of Students in a Classroom from Camera Images Captured by the Lecturer's PC," Springer Lecture Notes in Computer Science, Vol.9189, pp.518-526 (2015).
  3. N.Yasuda, K.Kakusho, T.Okadome, T.Funatomi, M.Iiyama: "Recognizing Conversation Groups in an Open Space by Estimating Placement of Lower Bodies," Proc. of 2013 IEEE Int. Conf. on Systems, Man, and Cybernetics (SMC), pp.558-564 (2014).
  4. A.Ono, K.Kakusho, T.Funatomi, M.Iiyama: "Replacing a Human Hand by a Virtual Hand and Adjusting its Posture to a Virtual Object for its Manipulation in an AR Environment," Proc. of 2013 Int. Conf. on Cyberworlds (CW), pp.116-119 (2013).
  5. K.Okuuchi, K.Kakusho, T.Kojima, D.Katagami: "Modeling Situation-Dependent Nonverbal Expressions for a Pair of Embodied Agent in a Dialogue Based on Conversations in TV Programs," Springer Lecture Notes in Computer Science, Vol.8007, pp.340-347 (2013).

Home Page