next up previous backarrow_motif.gifBack to APL Home Page
Next: Monocular Optical Flow for Up: Available Titles and Abstracts Previous: Dynamically Estimating Pose from

Monocular Optical Flow for Real-Time Vision Systems (Benoit-Ferrie, 96)

Authors: Stephen M. Benoit and Frank P. Ferrie
Download (596 KB)

Abstract: This paper introduces a monocular optical flow algorithm that has been shown to perform well at nearly real-time frame rates (4 FPS on a 100 MHz SGI Indy workstation), using natural image sequences. The system is completely bottom-up, using pixel region-matching techniques. A coordinated gradient descent method is broken down into two stages; pixel region matching error measures are locally minimized, and flow field consistency constraints apply non-linear adaptive diffusion, causing confident measurements to influence their less confident neighbors. Convergence is usually accomplished with one iteration for an image frame pair. Temporal integration and Kalman filtering predicts upcoming flow fields. The algorithm is designed for flexibility: large displacements are tracked as easily as sub-pixel displacements, and higher-level information can feed flow field predictions into the measurement process.


next up previous backarrow_motif.gifBack to APL Home Page
Next: Monocular Optical Flow for Up: Available Titles and Abstracts Previous: Dynamically Estimating Pose from
Gilbert Soucy
2000-04-05