Target positioning method, device and equipment and computer readable storage medium

Abstract

The invention discloses a target positioning method, device and equipment and a computer readable storage medium. The method comprises the following steps: collecting a 2D image and a 3D image of a to-be-positioned target through a camera group if the to-be-positioned target is detected to enter a photographing range of the camera group; based on a preset image processing function, extracting a region of interest in the 2D image to obtain an image of interest, and inputting the image of interest into a neural network to obtain a target positioning result; based on the 3D image, carrying out plane segmentation on the 3D image to obtain point cloud data corresponding to a plurality of planes; determining a first area intersection ratio of the planes based on the point cloud data and a targetpositioning result; and if the first area intersection ratio is greater than a first preset threshold value and less than a second preset threshold value, outputting the target positioning result toan execution component, so as to enable the execution component to grab the to-be-positioned target. Intensive multiple rectangular logistics parcels can be accurately positioned.

Description

technical field [0001] The present invention relates to the field of vision technology, in particular to a target positioning method, device, equipment and computer-readable storage medium. Background technique [0002] In recent years, with the increasing development of the logistics industry, the problem of labor costs in warehousing logistics, especially bulk transit logistics, has become increasingly prominent. In commercial logistics, most products are packaged in rectangular cartons. With the development of technology, more and more machine technologies are used to handle logistics packages. [0003] The traditional non-vision solution for handling logistics packages needs to specify the stacking type of logistics packages, so that the machine can accurately grab each logistics package. Traditional vision solutions require 3D cameras to provide accurate logistics package edges, extract boundary point data sets, and then fit spatial straight lines through hough transfo...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide a target positioning method, device, equipment and computer-readable storage medium, aiming to solve the technical problem that the existing visual solutions are difficult to locate dense multi-rectangular logistics packages

Images