IMAGE-BASED DETECTION AND TRACKING SYSTEM AND PROCESSING METHOD EMPLOYING CLUTTER MEASUREMENTS AND SIGNAL-TO-CLUTTER RATIOS

摘要

A method (30) for measuring and quantifying clutter, and target detection and tracking systems (10) that employs wavelet-based clutter quantification to generate a clutter number and a signal-to-clutter ratio derived therefrom to achieve improved target detection performance. The method (30) processes video signals representative of an image scene (14) containing a target (15) and background clutter (16) to provide for more accurate tracking of the target (15) by a tracker(s) (21). The method (30) comprises processing (31) the video signals to compute a wavelet clutter number, processing (32) the video signals to compute a signal-to clutter ratio using the wavelet clutter number, and generating (33) a pointer to a lookup table that sets parameters and selects the tracker (21) that is to be used to track the target (15) based upon the computed signal-to clutter ratio. The target detection and tracking system (10) tracks a target (15) located in an image scene (14) containing clutter (16). The system (10) comprises a sensor (11) for generating video signals representative of the image scene (14) that contains the target (15) and the background clutter (16). A tracking computer (12) is coupled to the sensor (11) that comprises a tracker(s) (21) that implement predetermined tracking algorithms that are designed to track different types of targets (15). A wavelet-based signal-to-clutter processor (20) is coupled between the sensor (11) and each of the tracker(s) (21) for processing the video signals to compute the wavelet clutter number and the signal-to clutter ratio using the wavelet clutter number, and for generating a pointer to a lookup table that sets parameters and selects a particular tracker (21) or tracking algorithm that is to be used to track the target (15) based upon the computed signal-to clutter ratio. A display monitor (13) may be coupled to the tracker(s) (21) for viewing the tracked target (15) and the image scene (14). The computed signal-to clutter ratio corresponds to target contrast divided by the clutter number, where the contrast is defined as the difference between a peak gray level (Pt) of the target (15) and a local background gray level ( mu b). IMAGE