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

Prawn culture residual feed counting method based on full convolutional neural network

A convolutional neural network and counting method technology, applied in the field of residual bait counting, can solve problems such as low accuracy, insufficient processing speed, and difficult application, and achieve the effects of high recognition accuracy, fast image processing speed, and accurate counting.

Pending Publication Date: 2020-02-21
NINGBO INST OF TECH ZHEJIANG UNIV ZHEJIANG +2
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] From the existing research, it can be seen that researchers have made some achievements in detecting residual bait, but the accuracy of traditional image processing algorithms is low in actual detection of bait, the processing speed is not fast enough, and the recognition effect is seriously disturbed. It is only in the theoretical research stage. Difficult to apply under actual production conditions

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
  • Prawn culture residual feed counting method based on full convolutional neural network
  • Prawn culture residual feed counting method based on full convolutional neural network
  • Prawn culture residual feed counting method based on full convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below through specific embodiments, but the present invention is not limited to the following specific embodiments.

[0035] Such as figure 1 Shown, the present invention provides a kind of prawn culture residual bait counting method based on fully convolutional neural network (FCN), comprises the following steps:

[0036] Step 1: After sprinkling bait on the feeding platform, put the feeding platform into the water, lift the feeding platform after 30 seconds after the bait is fully consumed, and record the residual bait image at a vertical angle. When capturing pictures in the video, it is necessary to fully consider the interference of bait sticking and fish and shrimp, and save the picture name and number in JPG format.

[0037] Step 1.1: Since the original image file is too large and it is not easy for the computer to capture useful information, the image is divided into small images of 255 pixels*255 pixels.

[0038...

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 residual feed counting method, in particular to a prawn culture residual feed counting method based on a full convolutional neural network. The method comprises the following steps: S1, collecting a test residual bait image; S2, performing calibration; S3, dividing into a test set and a training set according to a proportion; S4, building a model; S5, performing pre-training; S6, training, testing and perfecting; S7, obtaining a binary image; S8, performing iterative corrosion; and S9, counting and summing the connected domains on the extreme corrosion image to obtain the residual bait particle number on the residual bait image. The counting method is high in accuracy.

Description

technical field [0001] The invention relates to a method for counting residual bait, in particular to a method for counting residual bait for shrimp farming based on a fully convolutional neural network. Background technique [0002] Feed waste has always been a serious problem in aquaculture. Because bait accounts for a relatively large proportion of the economic cost of aquaculture, but farmers do not have a clear standard for the amount of feed when feeding, and excessive bait will cause huge economic losses. On the other hand, the residual bait contains nutrients such as fat and vitamins, which will lead to over-nutrition of the breeding waters, deteriorate the breeding environment, and increase the risk of disease of the cultured organisms. Therefore, accurately obtaining the remaining bait is of great practical significance for realizing precise feeding and further understanding of fish and shrimp eating rules. [0003] With the continuous development of deep learnin...

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): G06K9/62G06T5/30G06T7/00G06T7/194G06N3/04G06N3/08
CPCG06T5/30G06T7/0002G06T7/194G06N3/084G06T2207/10004G06T2207/30242G06T2207/20081G06T2207/20084G06N3/045G06F18/214G06F18/241G06F18/2415
Inventor 余心杰王昊李彧王建平
Owner NINGBO INST OF TECH ZHEJIANG UNIV ZHEJIANG
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com