Abstract We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our ...
Most work in human activity recognition is limited to relatively simple behaviors like sitting down, standing up or other dramatic posture changes. Very little has been achieved i...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...
—This paper introduces a new sensory system for the 2-D detection, tracking, and prediction of human motions. Using the data acquired through the sensory system, a model of a hum...
The goal of this article is to present an effective and robust tracking algorithm for nonlinear feet motion by deploying particle filter integrated with Gaussian process latent v...