Pallet detection using units of physical length

摘要

An image of a physical environment comprising a plurality of pixels is obtained and each pixel includes a depth value corresponding to a two-dimensional pixel location within the image plane and a distance between the area of the physical environment and the image plane. For each pixel, the two-dimensional pixel location and depth values are converted to corresponding three-dimensional points in the physical environment defined by the three coordinate components, each having a value of the physical measurement unit. A set of edge points is determined within a plurality of three-dimensional points based at least in part on the z-coordinate component of the plurality of points and a distance map is generated that includes a matrix of cells. For each cell in the distance map, a distance value is specified that indicates the distance between the cell and the edge point closest to the cell.