Human Action Analysis with Randomized Trees

2015
ISBN: 978-981-287-166-4
Verlag: Springer Nature Singapore

Buch, Englisch, 83 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 1533 g

Reihe: SpringerBriefs in Signal Processing

This book will provide a comprehensive overview on human action analysis with randomized trees. It will cover both the supervised random trees and the unsupervised random trees. When there are sufficient amount of labeled data available, supervised random trees provides a fast method for space-time interest point matching. When labeled data is minimal as in the case of example-based action search, unsupervised random trees is used to leverage the unlabelled data. We describe how the randomized trees can be used for action classification, action detection, action search, and action prediction. We will also describe techniques for space-time action localization including branch-and-bound sub-volume search and propagative Hough voting.

Zielgruppe

Research

Autoren/Hrsg.

Yu, Gang

Liu, Zicheng

Yuan, Junsong

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Mensch-Maschine-Interaktion
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen

Inhaltsverzeichnis

Introduction to Human Action Analysis.- Supervised Trees for Human Action Recognition and Detection.- Unsupervised Trees for Human Action Search.- Propagative Hough Voting to Leverage Contextual Information.- Human Action Prediction with Multi-class Balanced Random Forest.- Conclusion.