METHODS AND SYSTEMS FOR DETECTING OBJECTS OF INTEREST IN SPATIO-TEMPORAL SIGNALS

摘要

Methods and systems detect objects of interest in a spatio-temporal signal. According to one embodiment, a system (100) processes a digital spatio-temporal input signal containing zero or more foreground objects of interest superimposed on a background. The system comprises a foreground/background separation module (140), a foreground object grouping module (150), an object classification module (160), and a feedback connection. The foreground/background separation module (140) receives the spatio-temporal input signal as an input and, according to one or more adaptable parameters, produces as outputs foreground/background labels designating elements of the spatio-temporal input signal as either foreground or background. The foreground object grouping module (150) is connected to the foreground/background separation module (140) and identifies groups of selected foreground-labeled elements as foreground objects. The object classification module (160) is connected to the foreground object grouping module (150) and generates object-level information related to the foreground object. The object-level information adapts the one or more adaptable parameters of the foreground/background separation module (140), via the feedback connection.