Miha Peternel and Aleš Leonardis (2005) Activity Recognition via Autoregressive Prediction of Velocity Distribution. In: International Workshop on Human Activity Recognition and Modelling HAREM'2005, September 9th, 2005, Oxford, UK.
We present a novel approach for view-based learning and recognition of motion patterns of articulated objects. We formulate the intervals of motion as a predictive model of local spatio-temporal receptive field activation. We compute local velocity distribution using a Bayesian approach, and then approximate the local velocity distribution in space and time using a set of Gaussian receptive fields. The activation sequence of receptive fields over time is modeled in a PCA subspace using linear auto-regression to arrive at a model of the motion pattern. Recognition is performed using the MDL principle. We test the approach on a number of human motion patterns to demonstrate the applicability of the proposed approach to simple action recognition and identification.
|Item Type: ||Conference or Workshop Item (Paper)|
|Keywords: ||velocity distribution, Bayesian velocity estimation, Gaussian receptive fields, autoregressive model, subspace prediction, PCA, MDL, activity recognition, action recognition, identification|
|Language of Content: ||English|
|Institution: ||University of Ljubljana|
|Department: ||Faculty of Computer and Information Science|
|Divisions: ||Faculty of Computer and Information Science > Computer Vision Laboratory|
|Item ID: ||192|
|Date Deposited: ||19 Sep 2005|
|Last Modified: ||13 Aug 2011 00:32|
Actions (login required)