Machine Learning for Vision-Based Motion Analysis Theory and Techniques

Techniques of vision-based motion analysis aim to detect, track, identify, and generally understand the behavior of objects in image sequences. With the growth of video data in a wide range of applications from visual surveillance to human-machine interfaces, the ability to automatically analyze and...

Full description

Bibliographic Details
Other Authors: Wang, Liang (Editor), Zhao, Guoying (Editor), Cheng, Li (Editor), Pietikäinen, Matti (Editor)
Format: eBook
Published: London Springer London 2011, 2011
Edition:1st ed. 2011
Series:Advances in Computer Vision and Pattern Recognition
Online Access:
Collection: Springer eBooks 2005- - Collection details see MPG.ReNa
Table of Contents:
  • Part I: Manifold Learning and Clustering/Segmentation
  • Practical Algorithms of Spectral Clustering: Toward Large-Scale Vision-Based Motion Analysis
  • Riemannian Manifold Clustering and Dimensionality Reduction for Vision-based Analysis
  • Manifold Learning for Multi-dimensional Auto-regressive Dynamical Models
  • Part II: Tracking
  • Mixed-state Markov Models in Image Motion Analysis
  • Learning to Detect Event Sequences in Surveillance Streams at Very Low Frame Rate
  • Discriminative Multiple Target Tracking
  • A Framework of Wire Tracking in Image Guided Interventions
  • Part III: Motion Analysis and Behavior Modeling
  • An Integrated Approach to Visual Attention Modeling for Saliency Detection in Videos
  • Video-based Human Motion Estimation by Part-whole Gait Manifold Learning
  • Spatio-temporal Motion Pattern Models of Extremely Crowded Scenes
  • Learning Behavioral Patterns of Time Series for Video-surveillance
  • Part IV: Gesture and Action Recognition
  • Recognition of Spatiotemporal Gestures in Sign Language using Gesture Threshold HMMs
  • Learning Transferable Distance Functions for Human Action Recognition