RGB-D-type sensor based tray identifying and positioning method

Abstract

The invention discloses a pallet recognition and positioning method based on an RGB-D sensor. S1. Acquiring a depth image through a sensor; S2. Carrying out plane segmentation on the point cloud of the depth image to obtain one or more planes to form a plane Set; S3. Determine the relevant planes that may contain pallets from the plane set; S4. Match the relevant planes according to the preset pallet template, identify the position of the pallet in the relevant planes and perform positioning. The invention has the advantages of high recognition efficiency, precise positioning and the like.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a pallet recognition and positioning method based on RGB-D sensors. Background technique [0002] In the past two years, the proportion of my country's total social logistics cost to GDP has remained at about 18%, which is twice that of developed countries and about 6.5 percentage points higher than the global average, which shows that my country's logistics costs are relatively high. According to statistics, from 1977 to 1981, the logistics cost in the US GDP was as high as 16.8%, and by 1997 the logistics cost dropped to 10.9%. An important factor in the renewed prosperity of the US economy. [0003] In automated and semi-automated storage systems, pallet identification and positioning play an important role. Pallet refers to a horizontal platform device for placing goods and products in the process of assembly, stacking, handling and transportation, and is widely u...

AI Technical Summary

Problems solved by technology

However, the method of marking on the end of the pallet limits the circulation of the pallet, and it is easy to wear and tear during the use of the pallet

In addition, from the perspective of economic cost, application promotion involves the transformation of a large number of existing pallets, and the labor cost and time cost are relatively high

2. The method of not modifying the pallet: this method uses the existing features of the pallet itself to complete the identification, for example, detecting two gaps on the end face of the pallet is a common method

However, this method is almost entirely based on the horizontally installed planar lidar, and the planar lidar has a limited field of view in the vertical direction, and the recognition of the pallet requires compensation for the movement of the fork, which is inefficient.

In addition, considering the economic cost, the current cost of lidar is relatively high, which is not conducive to the application and promotion

[0005] According to the sensor used, it is also divided into two types: 1. Use CCD / CMOS camera, but CCD / CMOS camera has high requirements on ambient light conditions, and is not suitable for environments with uneven or frequently changing lighting, and it is very difficult to pass through a single CCD / CMOS camera. Difficult to obtain in-depth information

2. Use lidar sensor, but due to its limited field of view, the recognition efficiency is low

Images