Skip to main navigation Skip to search Skip to main content

Learning Randomized Decision Trees for Human Behavior Capture

  • Zhen-Peng Bian
  • , Cheen-Hau Tan
  • , Junhui Hou
  • , Lap-Pui Chau

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 12 - Chapter in an edited book (Author)peer-review

Abstract

This chapter focuses on recent research in Randomized Decision Tree (RDT) algorithm; in particular, how to classify human face and body using pixelwise classification of depth image. Similar to popular machine learning algorithms, training of RDT is also computation intensive. This chapter shows a more efficient technique to reduce the training time of the RDT algorithm. Hence, it is suitable for power-constrained devices. Besides, two applications are presented in this chapter to show the efficiency of the technique:(i) a fall detection system that monitor human fall down; (ii) ahuman-computer interface system that enable human to use nose and mouth to control computer mouse. The applications end with experimental results and performance evaluations.
Original languageEnglish
Title of host publicationLearning Approaches in Signal Processing
EditorsWan-Chi Siu, Lap-Pui Chau, Liang Wang, Tieniu Tang
PublisherPan Stanford Publishing Pte. Ltd.
Chapter12
Pages435-470
Edition1st
ISBN (Electronic)978-0-429- 06114-1
ISBN (Print)978-981-4800-51-8
Publication statusPublished - 28 Nov 2018

Publication series

NamePan Stanford Series on Digital Signal Processing
Volume2

Bibliographical note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Fingerprint

Dive into the research topics of 'Learning Randomized Decision Trees for Human Behavior Capture'. Together they form a unique fingerprint.

Cite this