Cargo pallet detection method and system based on point cloud plane contour matching

Abstract

The invention provides a cargo pallet detection method and system based on point cloud plane contour matching. The method includes the following steps: S1, original point cloud filtering; S2, point cloud plane segmentation; S3, generating a grid map through projection; S4, contour extraction; S5, contour matching; and S6, acquiring the relative position and posture. The system includes an original point cloud filtering module, a point cloud plane segmentation module, a module for generating a grid map through projection, a contour extraction module, a contour matching module, and a relative position and posture acquisition module. The method and the system are of low cost and high detection accuracy, and are basically not affected by illumination. There is no need for label laying or other operation, and there is no need to transform the storage environment. The method and the system are suitable for pallets of various colors and specifications, and have the advantages of high accuracy, low price, strong robustness, and the like.

Description

technical field [0001] The present invention relates to the technical field of industrial robots, in particular to a cargo pallet detection method and system based on point cloud plane profile matching. Background technique [0002] With the development of modern logistics technology, automatic guided vehicles (AGV) are playing an increasingly important role in intelligent warehousing technology, and the detection of cargo pallets is one of the core technologies of AGV. The storage environment has the characteristics of complex background, unstable light conditions, and many dynamic / static obstacles. Accurate and efficient detection and positioning of cargo pallets is an urgent problem to be solved at present. [0003] At present, the detection of cargo pallets mainly adopts visual detection, laser radar detection and other methods. Among them, although the cost of monocular vision is not high, the accuracy is not high and is greatly affected by light; both multi-line lidar...

AI Technical Summary

Problems solved by technology

Among them, although the cost of monocular vision is not high, the accuracy is not high and is greatly affected by light; both multi-line lidar and binocular vision detection have the characteristics of high precision, but multi-line lidar is too expensive, and double-sided vision detection is affected. The impact of light is large; the cost of single-line lidar is relatively low, but the amount of information obtained is insufficient, and false detections are prone to occur; the visual detection method based on feature tags requires relatively high accuracy for label laying, and poor environmental robustness, etc.

[0004] For example, the patent application with publication number CN104777835A and application number CN201510106059.3 discloses an omnidirectional automatic forklift and a 3D stereo vision navigation and positioning method, using binocular stereo vision for pallet positioning, which is vulnerable to complex lighting in the storage environment. Influence; Publication No. CN106044645A, Application No. CN201610620160.5 Patent Application for Invention, which discloses a cargo pallet access system based on two-dimensional code positioning and its access method. The two-dimensional code realizes the positioning of the pallet, but it is only limited to close-range detection scenarios

Images