DLI-2: Digital Library for Human Movement

University Of Illinois At Chicago, Chicago IL

Investigators

Abstract

This project will focus on developing innovative methods for analysis, representation and interpretation of human actions from data repositories containing information which describes human motion. Analysis of human motion is important in many areas including kinesiology, ergonomics, anthropology, medical rehabilitation, creative arts such as dance, and athletic studies. Using motion representations derived from related work in robotics and virtual reality modeling, the project will build user-friendly interfaces and tools which can accept various query forms, such as spatio-temporal specifications and other symbolic descriptors. A second goal for the project is to develop robust and flexible indexing methods which can be used in recognition, reconstruction and retrieval of human actions from video and other motion databases.