Unlock instant, AI-driven research and patent intelligence for your innovation.

Working pavement anomaly detection and path optimization method based on computer vision

A computer vision and anomaly detection technology, applied in the field of computer vision, can solve the problems of AGV car bumping, economic loss, and the falling of goods from the car, so as to improve the calculation speed, avoid obstacles in time, and avoid economic losses.

Active Publication Date: 2022-07-29
QIDONG CHUANGLYU GREENING ENG CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] During the operation of the AGV trolley, the AGV trolley will be bumped due to abnormal bumps on the road surface or the presence of foreign objects, causing the cargo on the trolley to fall, resulting in economic losses

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
  • Working pavement anomaly detection and path optimization method based on computer vision
  • Working pavement anomaly detection and path optimization method based on computer vision
  • Working pavement anomaly detection and path optimization method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] The embodiment of the present invention provides a method for abnormal detection and path optimization of working road surface based on computer vision, such as figure 1 shown, including:

[0051] The specific scenario for this embodiment is: an AGV trolley automated transportation factory.

[0052] 101. Collect real-time working pavement images, and perform image preprocessing to obtain preprocessed working pavement images.

[0053] The real-time working road image is collected by the camera that comes with the AGV car; image preprocessing is performed on the collected real-time working road image, including: performing Gamma correction and histogram equalization on the image to increase the color difference between the images. contrast and the overall image contrast effect.

[0054] Then, the image is denoised, and the black and white light and dark spot noises generated from the image sensor, channel transmission and decoding processing are processed by median filter...

Embodiment 2

[0083] The embodiment of the present invention provides a method for abnormal detection and path optimization of working road surface based on computer vision, such as figure 2 shown, including:

[0084] 201. Collect a real-time working pavement image, and perform image preprocessing to obtain a preprocessed working pavement image.

[0085] The real-time working road image is collected by the camera that comes with the AGV car; image preprocessing is performed on the collected real-time working road image, including: performing Gamma correction and histogram equalization on the image to increase the color difference between the images. contrast and the overall image contrast effect.

[0086] Then, the image is denoised, and the black and white light and dark spot noises generated from the image sensor, channel transmission and decoding processing are processed by median filtering to obtain the preprocessed image.

[0087] 202. Perform region segmentation on the preprocessed...

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 discloses a working pavement anomaly detection and path optimization method based on computer vision, which is mainly used for AGV working pavement bulge detection, relates to the field of computer vision, and comprises the following steps: collecting a real-time working pavement image and carrying out image preprocessing; performing region segmentation on the preprocessed road surface image to obtain an ROI region image of the working road surface; obtaining a farthest end edge region in the ROI region image, and calculating a gray gradient value of the farthest end edge region; comparing the gray gradient value with a preset threshold value, and determining whether the working pavement image is abnormal or not; when the gray scale gradient value is greater than a preset threshold value, determining that the working pavement image is abnormal; obtaining a road surface abnormal edge area of the abnormal road surface image; judging the abnormal type; the working pavement is evaluated according to the abnormal type; and optimizing the working path according to the evaluation result. According to the technical means provided by the invention, the condition of the front road surface can be quickly detected, and meanwhile, the path is optimized according to the abnormal condition, so that the AGV can avoid obstacles in time.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for abnormal detection and path optimization of a working road surface based on computer vision. Background technique [0002] With the continuous development of intelligent technology, it has brought great changes to logistics, manufacturing and other industries. For example, the emergence of AGV cars can help enterprises to be more convenient and efficient in the production process. AGV trolley has the characteristics of heavy load bearing, fast transportation and high safety, which makes it more and more widely used in China. [0003] During the operation of the AGV trolley, the AGV trolley will be bumped due to abnormal bumps on the road surface or the presence of foreign objects, causing the trolley goods to fall and causing economic losses. In the vision-guided AGV car, the road surface image is used to detect abnormal bumps on the road surface, ensuring that the AG...

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 & Authority Applications(China)
IPC IPC(8): G06V20/56G06V10/25G06Q10/04
CPCG06V20/588G06V10/25G06Q10/047Y02T10/40
Inventor 韩玉盼李姗姗
Owner QIDONG CHUANGLYU GREENING ENG CO LTD