Cubic object recognition method based on depth image

Abstract

The invention provides a cubic object recognition method based on a depth image. The method comprises: S1, acquiring the depth image of a target and gradient maps of the target in the X direction andthe Y direction; S2, classifying pixel points in the gradient map according to the gradient map to obtain an edge point map; S3, obtaining segmented images of the upper surface, the left vertical plane and the right vertical plane of the target in the depth image according to the result; S4, performing edge line detection on the edge point graph, and clustering and combining all detected edge lines to obtain a collinear edge line group set; S5, extracting angular points according to the longest edge line of each group in the collinear edge line group set; S6, pairing the extracted corner points to obtain a quadrangle; S7, determining the upper surface and the overall contour of the cubic object; and S8, obtaining left and right vertical planes corresponding to each upper surface quadrangleto realize cubic object positioning. The method is applied to the logistics industry, the problems of volume measurement limitation and time consumption of targets such as cubic object-shaped packages are solved, and the package sorting efficiency is improved.

Description

technical field [0001] The invention relates to the field of target recognition of depth images, in particular to a method for recognizing cubic objects based on depth images. Background technique [0002] Depth image, also known as distance image, refers to an image that takes the distance from the image collector to each point in the scene as a pixel value, and it directly reflects the geometry of the visible surface of the target. Therefore, depth-based images are widely used. Especially in the logistics industry. At present, the throughput of domestic logistics, port shipping, and airport shipping is very large and showing an increasing trend. The measurement of the volume of parcels, goods, containers, etc. by each sorting center is relatively limited and time-consuming, which reduces transportation efficiency. [0003] In the existing technology, most of the packages are in the shape of a cube. The volume measurement of the package is mainly by comparing the depth ima...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of limitations and time-consuming volume measurement of objects such as cube-shaped packages, goods, and containers in the prior art, the present invention proposes a method for recognizing cubes based on depth images