Event-based Plane-fitting Optical Flow for Dynamic Vision Sensors in FPGA

摘要

Optical flow is a useful signal for mobile agents, both biological and artificial. In this paper we present modification and implementation of a well known "plane-fitting" approach to event-based optical flow estimation for Dynamic Vision Sensors. The optical flow algorithm, as well as all required preprocessing steps are implemented in FPGA. The algorithm achieves sub microsecond latency and is fully pipelined, capable of performing 100M 3 × 3 pixel plane fits per second. The tradeoff between Average Absolute Endpoint Error and the density of optical flow estimates is analyzed and presented, and the FPGA implementation is shown to perform similarly to the previously published full precision software implementation.