Supercharge Your Innovation With Domain-Expert AI Agents!

Animal contour segmentation method, system and device based on Unet neural network, and storage medium

A neural network and contour technology, applied in neural learning methods, biological neural network models, image analysis, etc., can solve problems such as low measurement accuracy, and achieve the effects of high data stability, high efficiency, and shortened time.

Inactive Publication Date: 2021-09-10
HARBIN UNIV OF SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem of low accuracy of existing traditional animal body measurement, and propose a method, system, device and storage medium for animal contour segmentation based on Unet neural network

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
  • Animal contour segmentation method, system and device based on Unet neural network, and storage medium
  • Animal contour segmentation method, system and device based on Unet neural network, and storage medium
  • Animal contour segmentation method, system and device based on Unet neural network, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0046] A kind of animal contour segmentation method based on Unet neural network of the present embodiment, such as figure 1 As shown, the method is realized through the following steps:

[0047] Steps to collect samples and make datasets;

[0048] Afterwards, the steps of preprocessing and labeling the produced data set; the labeling results are as follows figure 2 shown;

[0049] Then, a step of forming the marked data into an executable file of a computer program;

[0050] Then design the steps to build the segmentation model, including:

[0051] First, Unet neural networks with different depths are used to form an improved Unet neural network, and the jumper of the encoder with the same resolution densely connected is designed, and the various feature maps and decoder feature maps carried in the jumper are determined through the aggregation layer. The fusion method realizes flexible feature fusion in the decoder; through dense connections, each node in the decoder is ...

specific Embodiment approach 2

[0059] Different from the specific embodiment one, in the present embodiment, a Unet neural network-based animal contour segmentation method, the described steps of collecting samples and making a data set include:

[0060] Collect images and form a data set through data enhancement to complete the collection of samples; among them, forming a data set is 3-4 times the number of collected images.

specific Embodiment approach 3

[0062] Different from the specific embodiment one, a kind of animal contour segmentation method based on the Unet neural network of the present embodiment, the described steps of preprocessing and labeling the produced data set include:

[0063] The outline of the target object in each collected image is marked by the labelme method.

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 an animal contour segmentation method, system and device based on a Unet neural network, and a storage medium, and belongs to the field of image segmentation. An existing traditional animal body ruler is low in measurement accuracy. According to the animal contour segmentation method, system and device based on a Unet neural network, and a storage medium, firstly samples are collected, a data set is manufactured, then the made data set is preprocessed and labelled, then a computer program executable file is prepared from the labeled data, then contour segmentation of a target animal in a picture is carried out according to an improved Unet neural network segmentation method, and animal contour segmentation is carried out in real time by using the segmentation model. According to the invention, a basic basis is provided for intelligent animal body size measurement, and the improved Unet neural network segmentation method is designed, so that the measurement result is more accurate.

Description

technical field [0001] The invention relates to a Unet neural network-based animal contour segmentation method, system, equipment and storage medium. Background technique [0002] With the rapid development of image processing technology, the continuous decline of computer hardware costs and the continuous improvement of computer computing speed, computer vision technology has become an important application technology of modern animal husbandry. In recent years, more and more intelligent livestock management solutions have been proposed to help the government achieve scientific management and help herdsmen achieve better grazing management. The application research of "smart ranch" has become the focus of attention, and the management of the ranch is gradually developing in the direction of informatization and intelligence. The ranch managers can improve the information level of the ranch through the smart ranch management platform. The application of the intelligent past...

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): G06T7/12G06N3/08
CPCG06T7/12G06N3/08G06T2207/20081G06T2207/20084
Inventor 房国志贾春秀
Owner HARBIN UNIV OF SCI & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com