Efficient simd implementation of 3x3 non maxima suppression of sparse 2d image feature points

Abstract

This invention transforms a list of feature points in raster scan order into a list of maxima suppressed feature points. A working buffer has two more entries than the width of the original image. Each entry is assigned to an x coordinate of the original image. Each entry stores a combined y coordinate and reliability score for each feature point in the original list. This process involves a forward scan and a backward scan. For each original feature point its x coordinate defines the location within the working buffer where neighbor feature points would be stored if they exist. The working buffer initial data and the y coordinates assure a non suppress comparison result if the potential neighbors are not actual neighbors. For actual neighbor data, the y coordinates match and the comparison result depends solely upon the relative reliability scores.