Event-based optical flow improves tracking with time slicing
Event-Based Optical Flow Constraint via Time-Sliced Plane Fitting
Computer Vision and Pattern Recognition
Summary
Tracking motion using event-based cameras often assumes objects move at a constant speed, which can miss changes in speed over time. The authors propose a method that splits motion data into smaller time sections and fits planes to track how edges move more accurately over time. This approach helps capture changes in speed, leading to better motion tracking. They also add techniques to correct edge shifts and keep the motion estimates stable. Tests show their method works better than traditional approaches.
What this means in practice
- •For autonomous vehicle engineers: Enhance vehicle perception systems to better detect and track surrounding object movement by capturing time-varying motion.
- •For sports analytics teams: Improve motion tracking of players and equipment by modeling rapid changes in movement over time using event-based sensors.
Authors
Masaki Koike, Yusuke Kameda, Shunichi Sato, Takayuki Hamamoto
Abstract
Event-based optical flow estimation using spatiotemporal planar approximation inherently assumes constant velocity and tends to average out temporal velocity variations. In this paper, we propose a flow estimation method that extends this planar approximation along the temporal axis. The resulting event-based optical flow constraint allows existing variational optical flow formulations to model temporal motion variation. Specifically, we partition the space-time volume into sub-intervals and apply a two-step planar approximation to track object edges consistently. Moreover, a spatial compensation mechanism and a temporal regularization term are incorporated to compensate for edge displacements and temporally stabilize the flow estimation, respectively. The experimental results show that modeling temporal motion variation improves flow estimation accuracy over conventional methods.