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

Underwater netting system damage detection method based on machine vision

A technology of damage detection and machine vision, which is applied in the detection of the damage state of net clothing, has the function of non-contact and accurate detection of damage degree and position, and can solve the problems of cage net damage detection lag, cumbersome process, economic loss, etc. Achieve the effect of improving the detection efficiency of net clothing, ensuring personal safety, and simplifying the calculation process

Active Publication Date: 2020-04-21
DALIAN UNIV OF TECH
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The most critical component is the underwater netting system. Once damaged, if it is not discovered in time, it will cause a large number of fish to escape, causing serious economic losses and ecological pollution.
However, the damage detection of cage net clothing has been lagging behind in technology
At present, in the breeding process, for the inspection of net clothes, regular net changes or professional divers are often employed to conduct underwater mesh inspections. The process is relatively cumbersome, and there are not only operational efficiency problems, but also the safety of the staff cannot be guaranteed.

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
  • Underwater netting system damage detection method based on machine vision
  • Underwater netting system damage detection method based on machine vision
  • Underwater netting system damage detection method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Embodiment 1. The present invention proposes a machine vision-based detection method for underwater netting damage in cages, including the steps of mesh information identification and mesh abnormality detection.

[0035] Cell information identification steps, such as figure 1 shown, including:

[0036] S1, utilize underwater robot (ROV) to carry out video collection to underwater net clothing, obtain the local image of cage net clothing;

[0037] S2. Carry out net clothing image preprocessing, including:

[0038] S2.1, input the net clothing video into the computer, convert it into a single frame image, set the main analysis area (ROI) of the net clothing image, ignore the image edge area, to improve the computer calculation speed and accuracy;

[0039] S2.2. Perform a double-sided band filtering operation on the mesh pixel matrix in the ROI area, and remove other noises while retaining the edges of the mesh;

[0040] S2.3, gray-scale processing is carried out to the...

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 belongs to the technical field of ocean engineering and information technology fusion, and provides an underwater netting system damage detection method based on machine vision, which comprises mesh information identification and mesh anomaly detection. According to the net cage underwater netting damage detection method based on machine vision, the original video image of the netting is acquired through the ROV underwater robot, underwater noise is removed based on a traditional image processing technology, and then the netting image is simplified into a binary image. The area of each mesh is obtained through connected domain segmentation, a netting characteristic gradient curve is formed, a netting damage judgment formula is determined, the netting damage condition is judged according to a self-adaptive netting abnormal threshold value, the netting damage position in the original image is accurately returned, and the netting damage area is automatically framed. According to the method, automatic detection and analysis are carried out in the whole netting damage detection process, labor consumption in netting damage detection can be effectively reduced while nettingdetection efficiency is improved, and personal safety of workers is guaranteed.

Description

technical field [0001] The invention belongs to the technical field of integration of marine engineering and information technology, and relates to a method for detecting the damaged state of net clothing, in particular to a method with the function of non-contact and accurate detection of the degree of damage and its position. Background technique [0002] Fishery is an important part of my country's agriculture and national economy. In order to achieve the sustainable development of fishery and maintain the balance of marine ecology, marine fishing operations have gradually developed from traditional rough fishing to intermittent fishing and intensive marine cage culture. status quo. With the continuous increase of the demand gap for seafood and the increasingly harsh offshore aquaculture environment, deep-sea cage culture has become the main development direction of marine fish farming in my country. As a high-tech farming method, deep-sea cage culture is a high-input, Hig...

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): G06T7/00G06T7/11G06T7/136G06T7/187G06K9/32G06K9/34G06K9/38G01N21/88
CPCG06T7/0002G06T7/11G06T7/136G06T7/187G01N21/8851G06T2207/10016G01N2021/8887G01N2021/8883G06V10/255G06V10/28G06V10/267Y02A40/81
Inventor 赵云鹏杜海毕春伟牛丽娟
Owner DALIAN UNIV OF TECH
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