Net cage netting damage monitoring method and system based on monocular space-time continuous images

A continuous image and reference image technology, applied in the field of image processing, can solve the problems of high cost and low accuracy of damage monitoring, and achieve the effects of low cost, reduced manpower consumption, and simple hardware configuration

Pending Publication Date: 2019-10-15
QINGDAO UNIV OF SCI & TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the technical problem of using underwater robots to inspect the damage of net cages in the prior art, which is costly and is easily blocked by fish, resulting in low damage monitoring accuracy, and proposes a cage based on monocular spatiotemporal continuous images Net damage monitoring method can solve the above problems

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
  • Net cage netting damage monitoring method and system based on monocular space-time continuous images
  • Net cage netting damage monitoring method and system based on monocular space-time continuous images
  • Net cage netting damage monitoring method and system based on monocular space-time continuous images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Embodiment 1, the present invention proposes a method for monitoring cage net damage based on monocular space-time continuous images, including an unsupervised learning network model training step and a net clothing image processing step, wherein the unsupervised learning network model training step, Used for training to obtain an unsupervised learning network model;

[0061] Net clothing image processing steps, such as figure 1 shown, including:

[0062] S1. Use a monocular camera to scan the net clothing to obtain multiple spatially continuous net clothing partial images; figure 2 As shown, it is a netting model, assuming that the netting is a standard cylinder, and the monocular camera scans and takes pictures along the surface of the netting;

[0063] S2. Input the net partial image into the unsupervised learning network model to obtain the depth of field with different semantics in each net partial image, separate the pixels whose semantic meaning is net, remove...

Embodiment 2

[0124] Embodiment 2, this embodiment proposes a cage net clothing damage monitoring system based on monocular space-time continuous images, such as Figure 9 shown, including:

[0125] Central axis 11, it is arranged on the center of net clothing 12 along vertical direction;

[0126] a beam 13, which is arranged horizontally and is rotatably connected with the central shaft 11;

[0127] A first driving mechanism (not shown in the figure), which accepts the control of the control module, is used to drive the beam 13 to rotate around the central axis 11;

[0128] Telescopic arm 14, one end of which is fixed on crossbeam 13 near one end of net clothing 12, and the length can be stretched along the vertical direction;

[0129] Monocular camera 15, which is fixed on the free end of telescopic arm 14, is used for shooting net clothing 14;

[0130] The control module 16 receives the image information sent by the monocular camera 15, and monitors the damage of the net clothing acco...

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 net cage netting damage monitoring method and system based on monocular space-time continuous images. The method comprises an unsupervised learning network model training step; a netting image processing step, comprising the following steps: (1) scanning a netting by using a monocular camera to obtain a plurality of spatially continuous netting local images; (2) inputtingthe local image of the netting into an unsupervised learning network model to obtain a preliminary image of the netting; (3) repairing and splicing the shielded area in the preliminary image of the netting to obtain an overall image of the netting; and (4) carrying out damage detection on the whole image of the netting. According to the netting damage monitoring method, the whole process is automatically detected and analyzed, manpower consumption in netting damage detection can be effectively reduced, and the netting damage condition can be monitored in real time with high precision. And compared with an underwater robot, hardware configuration required by the method is simpler, and the cost is low.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method and system for monitoring damage to cage netting based on monocular space-time continuous images. Background technique [0002] Fishery is an important part of my country's agriculture and national economy. With the growth of population and the improvement of national living standards, the demand for fishery products is also increasing, especially the demand for high-quality marine aquatic products is growing rapidly. Fish cage culture has developed rapidly, especially the scale of deep-water cages has gradually increased. Large-scale and large-scale production of deep-water cage culture is an inevitable trend. However, it is difficult to find out in time when the deep-sea net cage is damaged, which will easily cause a large number of cultured fish to escape, causing huge losses to the farmers. Therefore, net clothing safety monitoring has become a ...

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): G06T7/00G06T7/11G06T7/593G06T5/00G06T5/50G06T3/40G06Q50/02
CPCG06T7/0002G06T7/11G06T7/593G06T5/005G06T5/50G06T3/4038G06Q50/02G06T2207/30232G06T2207/20081G06T2207/10004G06T2207/10012G06T2207/20221
Inventor 王景景李嘉恒王传旭施威闫正强杜子俊李爽张海霞
Owner QINGDAO UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap