Visual Analysis Of Behaviour: From Pixels To Semantics

This book presents a comprehensive treatment of visual analysis of behaviour from computational-modelling and algorithm-design perspectives. Topics: covers learning-group activity models, unsupervised behaviour profiling, hierarchical behaviour discovery, learning behavioural context, modelling rare behaviours, and ?an-in-the-loop?active learning; examines multi-camera behaviour correlation, person re-identification, and ?onnecting-the-dots?for abnormal behaviour detection; discusses Bayesian information criterion, Bayesian networks, ?ag-of-words?representation, canonical correlation analysis, dynamic Bayesian networks, Gaussian mixtures, and Gibbs sampling; investigates hidden conditional random fields, hidden Markov models, human silhouette shapes, latent Dirichlet allocation, local binary patterns, locality preserving projection, and Markov processes; explores probabilistic graphical models, probabilistic topic models, space-time interest points, spectral clustering, and support vector machines.

• • Author: Shaogang Gong, Tao Xiang
• • Publisher: Springer
• • Publication Date: Aug 31, 2014
• • Number of Pages: 375 pages
• • Language: English
• • Binding: Paperback
• • ISBN-10: 1447161246
• • ISBN-13: 9781447161240