Spatio–Temporal Regularity Flow (SPREF): Its Estimation and Applications

Abstract

Feature selection and extraction is a key operation in video analysis for achieving a higher level of abstraction. In this paper, we introduce a general framework to extract a new spatio-temporal feature that represents the directions in which a video is regular, i.e., the pixel appearances change the least. We propose to model the directions of regular variations with a 3-D vector field, which is referred to as spatio-temporal regularity flow (SPREF). SPREF vectors are designed to have three cross-sectional parallel components F_x, F_y , and F_t for convenient use in different applications. They are estimated using all the frames simultaneously by minimizing an energy functional formulated according to its definition. In this paper, we first introduce translational SPREF (T-SPREF) and then extend our framework to affine SPREF (A-SPREF). The successful use of SPREF in a few applications, including object removal, video inpainting, and video compression, is also demonstrated