Skip to main content

Prototype-Based Methods for Human Movement Modeling

  • Reference work entry
  • First Online:
Computer Vision

Synonyms

Action prototype trees

Definition

Human movement modeling is a static and dynamic human appearance representation with feature descriptors. Typical feature descriptors include local and holistic descriptors. Local descriptors mean sparse features extracted locally, i.e., local features [4] or local space-time features [6]; holistic descriptors means dense features extracted inside a human bounding region, i.e., shape/appearance descriptors [9], and motion descriptors [1, 3].

Prototype-based methods [2, 7, 13, 14] are a category of approaches representing original feature descriptors with a finite set of indices through feature quantization. Given a large number of descriptors extracted from training images or videos, a vector quantization (or data clustering) algorithm is used to divide the feature space into nonoverlapping cells where each cell is uniquely represented with an integer index. Given the quantization, each test feature can be mapped to an integer index...

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 649.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 899.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Efros AA, Berg AC, Mori G, Malik J (2003) Recognizing action at a distance. In: Proceedings of the international conference on computer vision (ICCV), Nice, pp 726–733

    Google Scholar 

  2. Thurau C, Hlavac V (2008) Pose primitive based human action recognition in videos or still images. In: Proceedings of the computer vision and pattern recognition (CVPR), Anchorage

    Google Scholar 

  3. Fathi A, Mori G (2008) Action recognition by learning mid-level motion features. In: Proceedings of the computer vision and pattern recognition (CVPR), Anchorage

    Google Scholar 

  4. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110

    Article  Google Scholar 

  5. Laptev I, Perez P (2007) Retrieving actions in movies. In: Proceedings of the international conference on computer vision (ICCV), Rio de Janeiro

    Google Scholar 

  6. Dollar P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatio-temporal features. In: Proceedings of the VS-PETS, Beijing, pp 65–72

    Google Scholar 

  7. Weinland D, Boyer E (2008) Action Recognition Using Exemplar-based Embedding. In: Proceedings of computer vision and pattern recognition (CVPR), Anchorage

    Google Scholar 

  8. Mikolajczyk K, Uemura H (2008) Action Recognition with motion-appearance vocabulary forest. In: Proceedings of the computer vision and pattern recognition (CVPR), Anchorage

    Google Scholar 

  9. Dalal N, Triggs B (2005) Histograms of oriented gradients for Human detection. In: Proceedings of the computer vision and pattern recognition (CVPR), San Diego, pp 886–893

    Google Scholar 

  10. Nister D, Stewenius H (2006) Scalable recognition with a vocabulary tree. In: Proceedings of the computer vision and pattern recognition (CVPR), New York, NY, pp 2161–2168

    Google Scholar 

  11. Yuan J, Liu Z, Wu Y (2009) Discriminative Subvolume Search for Efficient Action Detection. In: Proceedings of the computer vision and pattern recognition (CVPR), Miami

    Google Scholar 

  12. Liu J, Luo J, Shah M (2009) Recognizing realistic actions from videos in the wild. In: Proceedings of the computer vision and pattern recognition (CVPR), Miami

    Google Scholar 

  13. Lin Z, Jiang Z, Davis LS (2009) Recognizing actions by shape-motion prototype trees. In: Proceedings of the international conference on computer vision (ICCV), Kyoto

    Google Scholar 

  14. Jiang Z, Lin Z, Davis LS (2010) A tree-based approach to integrated action localization, recognition and segmentation. In: Proceedings of the 3rd workshop on Human motion, Crete, Greece

    Google Scholar 

  15. Yao A, Gall J, Gool LV (2010) A hough transform-based voting framework for action recognition. In: Proceedings of the computer vision and pattern recognition (CVPR), San Francisco

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer Science+Business Media New York

About this entry

Cite this entry

Lin, Z., Jiang, Z., Davis, L.S. (2014). Prototype-Based Methods for Human Movement Modeling. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_378

Download citation

Publish with us

Policies and ethics