A real-time detection method for pallet carton stacking type

A real-time detection and carton technology, applied in image analysis, image enhancement, instruments, etc., can solve the problems of not very mature stacking shape, manual destacking, and small gaps in the middle.

Active Publication Date: 2021-10-22
BEIJING INFORMATION SCI & TECH UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the detection methods for stack shape are not very mature, and most of them are manually unstacked, which is time-consuming and labor-intensive.
Moreover, the linkage with the current fast logistics is not strong, because there are too many stacked styles, and the stacking method is very flexible
Machine vision often has a big problem in identifying the shape of the stack. In order to save space, the stacked boxes are placed tightly in the warehouse, and the gap in the middle is very small, which makes it difficult to complete the automatic recognition of the stacking shape.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A real-time detection method for pallet carton stacking type
  • A real-time detection method for pallet carton stacking type
  • A real-time detection method for pallet carton stacking type

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] Since the pixels of the depth image and the RGB image are different from each other, they are processed separately. Because there is some noise in the image collected by kinect, the image is first preprocessed. For example, the contrast of the color image is improved after Gaussian filtering, and because the depth There are some blind spots of vision obtained by infrared rays in the image, so after blurring and binarization, some opening operations are performed to remove the blind spots of vision caused by infrared rays, and then closing operations are performed to fill the gaps between boxes to obtain a complete image. The outermost contour of the stack type. The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0014] Such as figure 1 As shown, the present invention provides a kind of pallet carton stack type real-time detection method, and it comprises the following steps:

[0015] 1) The depth ima...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method for real-time detection of pallet and carton stacks, the steps of which are: acquire depth images and RGB images of all boxes in the stack by a depth camera and a color camera, and preprocess the depth images to obtain a depth map containing only boxes The resulting binary image; use a progressive method to find the gray threshold of the top layer of boxes in the stack, and perform binarization to obtain an outermost contour that only contains the topmost carton; extract the edge contour and use the binary image Obtain the edge contour of the straight line, extract all the coordinates of the edge contour to obtain the edge point of the uppermost carton; map the coordinates of the edge point on the depth image to the RGB image; segment the RGB image obtained by the coordinate mapping, and obtain the RGB image All the pixel information of the overall area of ​​the uppermost carton; the coordinates of the 4 corners of each box are obtained according to the stacking type of the box and the outline of the box placement, and then the center coordinates of each box are calculated by the center point theorem to complete the pallet alignment Real-time detection of stack type.

Description

technical field [0001] The invention relates to a stack type detection method in the field of logistics, in particular to a real-time detection method for pallet carton stack types. Background technique [0002] In the era of Industry 4.0 and the era of the Internet, more and more smart products are constantly growing, and logistics has increasingly become the theme of people's lives. Logistics companies such as JD.com, Alibaba, and Amazon have gradually emerged one by one. However, due to China's national conditions and population factors, the pressure on logistics is increasing. Therefore, the concept of an unmanned warehouse was born from this. Through the combination of artificial intelligence and vision, it is finally possible to achieve rapid sorting and shipment in the warehouse even if there is no industry in the warehouse. [0003] At present, the detection methods for stack shape are not very mature, and most of them are manually unstacked, which is time-consumin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityPatents(China)
IPC IPC(8): G06T7/12G06T7/136G06T7/181G06T7/90
CPCG06T2207/20116G06T7/12G06T7/136G06T7/181G06T7/90
Inventor李天剑刘诗晗金秋黄民
OwnerBEIJING INFORMATION SCI & TECH UNIV