Giới thiệu
This book deals with the creation of the algorithm backbone that enables a computer to perceive humans in a monitored space, by processing the signals that humans use in order to perform a task, i.e., audio and video. To do so, computers use sensors and algorithms to detect and track multiple interacting humans, by way of their faces and hands or their voices. This application domain is challenging, because audio and visual signals are cluttered by both background and foreground objects.