Skip to main content

Object Detection

  • Chapter
  • 9355 Accesses

Part of the Undergraduate Topics in Computer Science book series (UTICS)

Abstract

This final chapter provides an introduction into classification and learning, with a detailed description of basic AdaBoost and the use of random forests. These concepts are illustrated by applications for face detection, and for pedestrian detection, respectively.

Keywords

  • Random Forest
  • Object Detection
  • Face Detection
  • Haar Wavelet
  • Weak Classifier

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-1-4471-6320-6_10
  • Chapter length: 39 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   44.99
Price excludes VAT (USA)
  • ISBN: 978-1-4471-6320-6
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   59.99
Price excludes VAT (USA)
Fig. 10.1
Fig. 10.2
Fig. 10.3
Fig. 10.4
Fig. 10.5
Fig. 10.6
Fig. 10.7
Fig. 10.8
Fig. 10.9
Fig. 10.10
Fig. 10.11
Fig. 10.12
Fig. 10.13
Fig. 10.14
Fig. 10.15
Fig. 10.16
Fig. 10.17
Fig. 10.18
Fig. 10.19
Fig. 10.20

Notes

  1. 1.

    In classification theory, a descriptor is usually also called a feature. A feature in an image that, as commonly used in image analysis, combines a keypoint and a descriptor. Thus, we continue to use “descriptor” rather than “feature” for avoiding confusion.

  2. 2.

    This is the error defined in margin-based classifiers such as support vector machines. This error is (usually) not explicitly used in AdaBoost.

  3. 3.

    Shannon’s entropy corresponds to minus the entropy used in thermodynamics.

  4. 4.

    The tree diagram has its root at the top (as is customary). For people who complain that it is misleading to depict a tree with its root at the top, here are two examples: Inside the large Rikoriko Cave in The Poor Knights Islands (New Zealand) some trees are growing down from the roof, and on coastal cliffs around northern New Zealand many large Pohutukawa trees are rooted at the edge of a cliff, with almost all of the tree sprawlings down the cliff, lower than its root.

  5. 5.

    The TUD Multiview Pedestrians database is available at www.d2.mpi-inf.mpg.de/node/428 for free download.

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and Permissions

Copyright information

© 2014 Springer-Verlag London

About this chapter

Cite this chapter

Klette, R. (2014). Object Detection. In: Concise Computer Vision. Undergraduate Topics in Computer Science. Springer, London. https://doi.org/10.1007/978-1-4471-6320-6_10

Download citation

  • DOI: https://doi.org/10.1007/978-1-4471-6320-6_10

  • Publisher Name: Springer, London

  • Print ISBN: 978-1-4471-6319-0

  • Online ISBN: 978-1-4471-6320-6

  • eBook Packages: Computer ScienceComputer Science (R0)