Design of a Monocular Multi-Spectral Skin Detection, Melanin Estimation, and False-Alarm Suppression System

摘要

A real-time skin detection, false-alarm reduction, and melanin estimation system is designed targeting search and rescue (SAR) with application to special operations for manhunting and human measurement and signatures intelligence. A mathematical model of the system is developed and used to determine how the physical system performs under illumination, target- to-sensor distance, and target-type scenarios. This aspect is important to the SAR community to gain an understanding of the deployability in different operating environments. A multi-spectral approach is developed and consists of two short-wave infrared cameras and two visible cameras. Through an optical chain of lenses, custom designed and fabricated dichroic mirrors, and filters, each camera receives the correct spectral information to perform skin detection, melanin estimation, and false-alarm suppression. To get accurate skin detections under several illumination conditions, the signal processing is accomplished in reflectance space, which is estimated from known reflectance objects in the scene. Model-generated output of imaged skin, when converted to estimated reflectance, indicates a good correspondence with skin reflectance. Furthermore, measured and modeled estimates of skin reflectance indicate a good correspondence with skin reflectance.