Avi Singh • 5/27/2015

Recognizing Human Activities with Kinect - Choosing a temporal model

This technical article discusses the selection of temporal models for sequence classification in a human activity recognition project using RGBD data from a Kinect. It compares popular models like Hidden Markov Models (HMMs), Maximum Entropy Markov Models (MEMMs), and Conditional Random Fields (CRFs), explaining their advantages and disadvantages. The content is based on a graduate-level machine learning course project and serves as an introduction for those starting with sequence classification.

0 comments

#Machine Learning #Kinect #Sequence Classification