High speed, low power VLSI CMOS vision sensor for geometric centre object tracking

In this article an object tracking CMOS sensor is presented. The architecture incorporates photo detection devices and pixel level processing elements for capturing and processing the image data and extracting the object's coordinates. The edges of the image scene are extracted by in-pixel edge detectors and the region (object) of interest, selected by the user, is segmented using a switch network. Coordinates of the desired region are obtained by extracting the geometric centre of the region. Tracking of the selected object is then performed by automatic reselection of the region using the updated coordinates. The proposed design presents less sensitivity to threshold adjustments than binarisation techniques. The sensor has been designed as a 64 x 64 pixel VLSI CMOS chip in the 0.35 μm standard CMOS technology. The proposed structure is analysed with regard to its operation in the presence of mismatches and noise. Features of the sensor are reported and compared with some previous object tracking designs. Because the power dissipation is small, the chip is ideal for low-power applications.