Tracking moving objects as spatio-temporal boundary detection

The purpose of this study is to investigate tracking of moving objects in a sequence of images by detecting the surface generated by motion boundaries in the space-time domain. Estimation of this spatio-temporal surface is formulated as a Bayesian image partitioning problem. Minimization of the resulting energy functional seeks a solution biased toward smooth closed surfaces which coincide with motion boundaries, have small area, and partition the image into regions of contrasting motion activity. The Euler-Lagrange partial differential equations of minimization are expressed as level set evolution equations. The formulation does not require estimation of the image motion field and does not assume a known background. It allows multiple non-simultaneous independent motions to occur and, under some assumptions, can account for camera motion without prior estimation of this motion.