A low-complexity algorithm for the on-chip moment computation of binary images

A fast, low-complexity algorithm has been developed for the computation of the geometric moments of binary images derived from pictures taken by low-cost, low-power consumption CMOS cameras. The complete algorithm is executed on the limited CPU and RAM resources that are available in the microprocessor chip that comes integrated with this type of cameras. We intend to utilize this moment-based approach to find the position and orientation of objects in the image plane, which has a wide range of applications from networked embedded robotics to the medical care field. In medical care applications it is envisioned that camera systems with on-chip processing of algorithms, such as the one described in this paper, will work in conjunction with a wireless body area network (WBAN) that measures vitals signs. The final goal is to have an accurate and cost effective system able to provide timely information to the medical personnel that is responsible for the care of the patients.