Near-recursive optical flow from weighted image differences

E. Trucco, T. Tommasini, V. Roberto

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    This correspondence derives a formal link between temporally weighted frame differences, or disturbance fields, which carry limited information suitable formotion detection, and the optic flow (OF), which carries richer information on local image motion.We use this link to derive a novel, simple, near-recursive optic flow algorithm based on a recursive-filter formulation. Most quantities involved are computed recursively, using only data from the current and previous frame. We can limit expensive OF calculations to pixels where motion magnitude is sufficiently high using image differences which the algorithm computes anyway. Experimental results with well-known synthetic, ground-truthed test sequences and standard performance metrics indicate good quantitative performance. Tests with real sequences suggest similar or better performance than a well-known, similar algorithm due to Lucas and Kanade (LK).
    Original languageEnglish
    Pages (from-to)124-129
    Number of pages6
    JournalIEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics
    Volume35
    Issue number1
    DOIs
    Publication statusPublished - Feb 2005

    Keywords

    • Disturbance fields
    • Motion analysis
    • Optic flow

    Fingerprint Dive into the research topics of 'Near-recursive optical flow from weighted image differences'. Together they form a unique fingerprint.

  • Cite this