Spatiotemporal Beamforming for Passive Visual Monitoring: Background Modeling and Target SegmentationÂ
In this chapter, we address video background extraction and moving object detection for passive visual monitoring by establishing a novel conceptual relationship between sensor array beamforming and computer vision. We treat image sequences as virtual array snapshots via interchanging time and space domains, and consider the background and moving objects as the interested incoming signal and impulsive noise. With the unit-element ``steering vector", the received signals with the impulsive noise removal is used to formulate a novel beamforming model for background extraction and moving object detection, which is jointly solved by alternating direction method of multipliers and fixed-point iteration. To further improve the robustness of the proposed model in the presence of steering vector errors resulted from uncertain factors (e.g., varying illumination), we develop a robust variant that embeds a Lagrange Programming Neural Network (LPNN) within the ADMM framework, enhancing its capabilities for background reconstruction and foreground separation in passive visual monitoring applications.