Eigenfiltering for flexible eigentracking (EFE)

Fernando De La Torre, Jordi Vitria, Petia Radeva, Javier Melenchon

    Research output: Contribution to journalArticleResearchpeer-review

    7 Citations (Scopus)

    Abstract

    Traditional techniques for tracking non-rigid objects such as optical flow, correlation, active contours or color, can not deal with situations where image changes are not due to motion but appearance (e.g. tracking the lips when the teeth appear). Two main contributions for appearance tracking of flexible objects are proposed. The first one is a flexible generalization of Eigentracking within the same robust continuous optimization framework. The second one is a generalization of traditional gray-level eigenspaces, constructing a multiple channel "eigenspace" using filter responses to give robustness against variations in the training conditions such as illumination changes. Additionally, 3D geometric transformations are incorporated, a regularization term is added for numerical stability reasons and the optimization problem is solved in closed form. Experiments on lip tracking are reported. © 2000 IEEE.
    Original languageEnglish
    Pages (from-to)1106-1109
    JournalProceedings-International Conference on Pattern Recognition
    Volume15
    Issue number3
    DOIs
    Publication statusPublished - 1 Jan 2000

    Fingerprint Dive into the research topics of 'Eigenfiltering for flexible eigentracking (EFE)'. Together they form a unique fingerprint.

    Cite this