Computer Vision

Living Edition

Ego-Motion and EPI Analysis

  • Masanobu YamamotoEmail author
Living reference work entry
DOI: https://doi.org/10.1007/978-3-030-03243-2_873-1
  • 18 Downloads

Synonyms

Related Concepts

Definition

Stacking up a sequence of images in the order of shooting time, a 3D image having a time axis which is the thickness direction of just one book is obtained. This 3D image is called a spatiotemporal image. If the temporal change of the image is slow, the spatiotemporal image has continuity in the time axis direction as strong as in the image axis directions. An epipolar plane is composed of two camera viewpoints at the start and end times of the moving images and a 3D point on the object. If the camera moves in translation, this object point is constrained on the epipolar plane. When the spatiotemporal image is cut along the epipolar plane, the projection of the object point draws a locus on this cross section. This spatiotemporal cross-sectional image is called an epipolar plane image (EPI). By analyzing the EPI, it is possible to track the objects...

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

References

  1. 1.
    Yamamoto M (1981) Motion analysis by visualised locus method. Trans Inf Process Soc Jpn 22(5):442–449. (Japanese edition)Google Scholar
  2. 2.
    Yamamoto M (1986) Determning three-dimensional structure from image sequences given by horizontal and vertical moving camera. Trans Inst Electron Inf Commun Eng J69-D(11):1631–1638. (Japanese Edition)CrossRefGoogle Scholar
  3. 3.
    Bolls RC, Harlyn Baker H, Mariomont DH (1987) Epipolar-plane image analysis: an approach to determining structure from motion. Int J Comput Vis 1(1):7–55CrossRefGoogle Scholar
  4. 4.
    Cipolla R, Yamamoto M (1990) Stereoscopic tracking of bodies in motion. Image Vis Comput 8(1): 85–90CrossRefGoogle Scholar
  5. 5.
    Kawasaki H, Ikeuchi K, Sakauchi M (2000) Spatio-temporal analysis of Omni image. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition (CVPR00), vol 2, pp 577–584Google Scholar
  6. 6.
    Sugimoto S, Okutomi M (1999) Shape estimation of rotating object using spacio – temporal images. Trans Inf Process Soc Jpn 40(6):2717–2724. (Japanese edition)Google Scholar
  7. 7.
    Fukugawa Y, Zheng JY, Tanaka K, Abe N (1996) Recovering 3D models from highlight motion. Trans Inst Electron Inf Commun Eng J79-DII(5):719–726. (Japanese edition)Google Scholar
  8. 8.
    Rav-Acha A, Pritch Y, Lischinski D, Peleg S, Trees blowing in the wind. http://www.vision.huji.ac.il/dynmos/page2.html
  9. 9.
    Rav-Acha A, Pritch Y, Lischinski D, Peleg S (2007) Dynamosaicing: mosaicing of dynamic scenes. IEEE Trans Pattern Anal Mach Intell 29(10):1789–1801CrossRefGoogle Scholar
  10. 10.
    Sato T, Uchida G, Lescroart MD, Kitazono J, Okada M, Tanifuji M (2013) Object representation in inferior temporal cortex is organized hierarchically in a mosaic-like structure. J Neurosci 33(42):16642–16656CrossRefGoogle Scholar
  11. 11.
    Sun P, Ueno K, Waggoner RA, Gardner JL, Tanaka K, Cheng K (2007) A temporal frequency-dependent functional architecture in human V1 revealed by high-resolution FMRI. Nat Neurosci 10:1404–1406CrossRefGoogle Scholar
  12. 12.
    Harlyn Baker H, Bolles RC (1989) Generalizing epipolar-plane image analysis on the spatiotemporal surface. Int J Comput Vis 3(1):33–49CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Niigata UniversityNiigataJapan

Section editors and affiliations

  • Wenjun Zeng
    • 1
  • Sing Bing Kang
    • 2
  1. 1.Microsoft ResearchBeijingChina
  2. 2.Microsoft ResearchRedmondUSA