Estimation of Multiple Periodic Motions from Video

Abstract

Abstract. The analysis of periodic or repetitive motions is useful in many applications, both in the natural and the man-made world. An important example is the recognition of human and animal activities. Existing methods for the analysis of periodic motions first extract motion trajectories, e.g. via correlation, or feature point matching. We present a new approach, which takes advantage of both the frequency and spatial information of the video. The 2D spatial Fourier transform is applied to each frame, and time-frequency distributions are then used to estimate the time-varying object motions. Thus, multiple periodic trajectories are extracted and their periods are estimated. The period information is finally used to segment the periodically moving objects. Unlike existing methods, our approach estimates multiple periodicities simultaneously, it is robust to deviations from strictly periodic motion, and estimates periodicities superposed on translations. Experiments with synthetic and real sequences display the capabilities and limitations of this approach. Supplementary material is provided, showing the video sequences used in the experiments.

Phase Estimation of a Single Quasi-Periodic Signal

“…To confirm the effectiveness of the proposed phase estimation, we conducted experiments using simulation data 4 .…”

“…Fundamentally, periodic signals play quite an important role in many applications ranging from data transmission via a radio carrier wave [1], [2] in electronic communications to periodic motion detection from video [3], [4], periodic action recognition [5] (e.g., walking and running), and person authentication or identification from periodic action (e.g., gait-based person identification [6]) in the computer vision and pattern recognition fields.…”

Joint Spatial and Frequency Domain Motion Analysis

“…Some of these problems can be handled by using alternative representations. For example, a frequency domain representation, e.g., using the Fourier Transform, or Time-Frequency Distributions (TFDs) [6], [3], has strengths that are complementary to those of the spatial domain representations. Some advantages of the frequency approach include: (1) It is robust to global illumination changes.…”