主权项 |
1. A human activity modeling method comprising:
determining, by a controller, principal components of depth images and binary shape images of human activities extracted from video clips, wherein the depth images of the human activities are different images than the binary shape images of the human activities; determining, by the controller, Independent Component Analysis (ICA) representations based on the principal components; determining, by the controller, features through Linear Discriminant Analysis (LDA) based on the ICA representations; determining, by the controller, a codebook using vector quantization; determining, by the controller, observation symbol sequences in the video clips; and identifying, by the controller, human activities using a Hidden Markov Model (HMM) based on a status transition and an observation matrix.
|