Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hole detection method, device, equipment and medium

A detection method and hole technology, applied in the field of detection, can solve problems such as poor recognition effect, limited aluminum formwork wall quality, complex environment, etc., and achieve the effect of improving accuracy and reducing the influence of external light.

Pending Publication Date: 2020-04-28
GUANGDONG BOZHILIN ROBOT CO LTD
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The site environment is complex, and the light on different walls and different positions on the same wall is not uniform. After the aluminum formwork is removed, mud traces will remain on the periphery of the hole, making the edge of the hole not obvious
The end of the robot drives the camera to collect images from different angles. The images inside the holes may be transparent, opaque or slightly transparent, resulting in no uniform features inside the holes. It becomes difficult to extract and locate these defects. very difficult
The recognition effect of hole detection through a single image processing method is poor, and it is very limited by the quality of the aluminum formwork wall, which is greatly affected by the light, and is prone to misidentification and missed identification.

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
  • Hole detection method, device, equipment and medium
  • Hole detection method, device, equipment and medium
  • Hole detection method, device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] figure 1 It is a flow chart of a hole detection method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of wall hole detection. The method can be performed by a hole detection device, and specifically includes the following steps:

[0029] S110. Acquire a color image and a depth image of the wall to be detected, register the color image and the depth image, and generate a point cloud data set, wherein the wall to be detected includes at least one hole.

[0030] Exemplarily, an RGB-D (RGB and Depth, color and depth) camera can be installed on the wall hole sealing robot for shooting holes on the wall to be detected, and the RGB-D camera can simultaneously acquire color images in the environment and depth images. Generally, a depth image is also called a distance image, which refers to an image with the distance (depth) from the image collector to each point in the scene as the pixel value, which directly reflects the geom...

Embodiment 2

[0050] image 3 It is a flow chart of a hole detection method provided by Embodiment 2 of the present invention. This embodiment is further optimized on the basis of the above embodiment. Optionally, the hole detection method further includes: determining the minimum circumscribed area of ​​the hole according to the detection result rectangle, and calculate the pixel point coordinates of the center point of the circumscribed rectangle; determine the position of the hole in the wall image to be detected according to the pixel point coordinates of the center point. The position of the hole in the wall to be detected is determined by calculating the coordinates of the center point of the circumscribed rectangle of the hole, and the location of the hole in the wall image is realized.

[0051] Such as image 3 As shown, it specifically includes the following steps:

[0052] S210. Acquire a color image and a depth image of the wall to be detected, and register the color image and ...

Embodiment 3

[0069] Figure 5 A flow chart of a hole detection method provided by Embodiment 3 of the present invention. This embodiment is further optimized on the basis of the above-mentioned embodiments. The hole detection method also includes: calculating the mortar ejection capacity according to the pixel area of ​​the smallest circumscribed rectangle. The hole is blocked; when the plugging device is used to block the hole, the capacity of the mortar sprayed out each time corresponds to the size of the current hole, which avoids the waste of mortar. Detect the flatness of the plugging of the hole, judge whether the flatness meets the requirements, and if it meets the requirements, proceed to the plugging of the next hole. It is ensured that the hole can be completely blocked, and the quality of plugging is improved.

[0070] Such as Figure 5 As shown, it specifically includes the following steps:

[0071] S310. Acquire a color image and a depth image of the wall to be detected, an...

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 embodiment of the invention discloses a hole detection method and device, equipment and a medium. The method comprises steps that a color image and a depth image of a to-be-detected wall surface are acquired, registration of the color image and the depth image is carried out, a point cloud data set is generated, and the to-be-detected wall surface comprises at least one hole; a failure pointcloud data set is determined according to the point cloud data set, and a sunken point cloud data set is determined according to the point cloud data set and the failure point cloud data set, the failure point cloud data set is a point cloud data set with a depth value of 0; and the sunken point cloud data set is mapped into a color image to obtain a color image of the sunken point cloud data set,and the hole is determined according to the color image of the sunken point cloud data set. The problems that wall surface hole detection is easily influenced by illumination, and mistaken recognition and missing recognition occur are solved, and the effects of reducing the external illumination influence and improving the hole detection accuracy during hole detection are achieved.

Description

technical field [0001] Embodiments of the present invention relate to detection technology, and in particular to a hole detection method, device, equipment and medium. Background technique [0002] As my country vigorously promotes prefabricated buildings and develops new construction methods, aluminum alloy formwork, as a new type of formwork system, has developed rapidly in the construction industry at home and abroad by virtue of its advantages such as light weight, high strength, and good economic benefits. The current market There are two aluminum molds with two different reinforcement systems, the double-pull screw type and the pull-tab type. After the formwork is removed, many screw round holes or pull-tab holes will be left. These holes are defects on the wall and need to be sealed after the holes are sealed. to complete subsequent construction. [0003] At present, the method of manually sealing holes is mainly used to deal with wall defects. Manual sealing is labor-...

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
IPC IPC(8): G06T7/00G06T7/33
CPCG06T7/0004G06T7/33G06T2207/10004G06T2207/10024G06T2207/10028G06T2207/30132Y02P90/30
Inventor 廖伟杨
Owner GUANGDONG BOZHILIN ROBOT CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products