VIDEO HANDOVER FOR RETRIEVAL IN A UBIQUITOUS ENVIRONMENT USING FLOOR SENSOR DATA (WedPmPO1)

Author(s) : Gamhewage de Silva (University of Tokyo, Japan) Toshihiko Yamasaki (University of Tokyo, Japan) Takayuki Ishikawa (University of Tokyo, Japan) Kiyoharu Aizawa (University of Tokyo, Japan)

Abstract : A system for retrieving video captured in a ubiquitous environment is presented. Data from pressure-based floor sensors are obtained as a supplementary input together with video from multiple stationary cameras. Unsupervised data mining techniques are used to reduce noise present in floor sensor data. An algorithm based on agglomerative hierarchical clustering is used to segment footpaths of individual persons. Two methods of video handover have been implemented for retrieval of video and key frame sequences showing a person moving in the house. Users can query the system based on time and retrieve video or key frames using either of the handover techniques. We compare the results of retrieval using different techniques subjectively. We conclude with suggestions for improvements, and possible future directions.

Menu