High-Frame-Rate Optical Flow System

Abstract

In this paper, we develop a high-frame-rate (HFR) vision system that can estimate the optical flow in real time at 1000 f/s for 1024×1024 pixel images via the hardware implementation of an improved optical flow detection algorithm on a high-speed vision platform. Based on the Lucas-Kanade method, we adopt an improved gradient-based algorithm that can adaptively select a pseudo-variable frame rate according to the amplitude of the estimated optical flow to accurately detect the optical flow for objects moving at high and low speeds in the same image. The performance of our developed HFR optical flow system was verified through experimental results for high-speed movements such as a top's spinnning motion and a human's pitching motion.

Keywords

This publication has 14 references indexed in Scilit:

FPGA-based Real-time Optical Flow Algorithm Design and Implementation
Journal of Multimedia, 2007
955-fps Real-time Shape Measurement of a Moving/Deforming Object using High-speed Vision for Numerous-point Analysis
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2007
Realtime FPGA-Based Vision System
Journal of Robotics and Mechatronics, 2005
Hardware implementation of optical flow constraint equation using FPGAs
Computer Vision and Image Understanding, 2005
Computing two motions from three frames
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Accuracy vs Efficiency Trade-offs in Optical Flow Algorithms
Computer Vision and Image Understanding, 1998
Performance of optical flow techniques
International Journal of Computer Vision, 1994
A programmable artificial retina
IEEE Journal of Solid-State Circuits, 1993
Processing translational motion sequences
Computer Vision, Graphics, and Image Processing, 1983
Determining optical flow
Artificial Intelligence, 1981