Indexing of Personal Video Captured by a Wearable Imaging System

  • Yasuhito Sawahata
  • Kiyoharu Aizawa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2728)


Digitization of lengthy personal experiences will be made possible by continuous recording using wearable video cameras. It is conceivable that the amount of video content that results will be extraordinarily large. In order to retrieve and browse the desired scenes, a vast amount of video needs to be organized using context information. In this paper, we develop a “Wearable Imaging System” that is capable of constantly capturing data, not only from a wearable video camera, but also from various sensors, such as a GPS, an acceleration sensor and a gyro sensor. The data from these sensors are analyzed using Hidden Markov Model (HMM) to detect various events for efficient video retrieval and browsing. Two kind of browsers are developed which are a chronological viewer and a location based viewer.


Feature Vector Hide Markov Model Sensor Data Video Content Acceleration Sensor 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Mann, S.: ‘WearCam’ (The Wearable Camera): Personal Imaging System for long-term use in wearable tetherless computer-mediated reality and personal Photo/Videographic Memory Prosthesis, Proceedings of ISWC98, IEEE, pp 124–131, Oct. 1998Google Scholar
  2. [2]
    Healey, J. and Picard, R.W.: A Cybernetic Wearable Camera, Proceedings of ISWC98, IEEE, pp 42–49, Oct. 1998Google Scholar
  3. [3]
    Lamming, M. and Flynn, M.: ‘Forget-me-not’ Intimate Computing in Support of Human Memory, in Proceedings of FRIEND21,’ 94 International Symposium on Next Generation Human Interface, Feb., 1994Google Scholar
  4. [4]
    Rabiner, L.: A tutorial on hidden Markov models and selected applications in speech recognition, Proceedings of the IEEE, 77(2):257–286, Feb. 1989CrossRefGoogle Scholar
  5. [5]
    Clarkson, B. and Pentland, A.: Unsupervised Clustering of Ambulatory Audio and Video, Proceedings of ICASSP’99, 1999Google Scholar
  6. [6]
    Aizawa, K., Ishijima, K-I. and Shiina, M.: Summarizing Wearable Video, Proceedings of ICIP 2001, IEEE, pp 398–401, Oct. 2001Google Scholar
  7. [7]
    Ng, H.W., Sawahata, Y. and Aizawa, K.: Summarization of wearable videos using support vector machine, Proceedings of IEEE ICME 2002, Aug. 2002Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Yasuhito Sawahata
    • 1
  • Kiyoharu Aizawa
    • 1
  1. 1.Dept. of Frontier Informatics and Dept. of Elec. Eng.University of TokyoTokyoJapan

Personalised recommendations