Pallet detection using units of physical length

摘要

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