Horse body ruler measurement method based on deep learning and image processing

An image processing and deep learning technology, applied in the field of image processing, can solve the problems of inaccurate measurement of horse body measurements, large errors, inclusion of pasture backgrounds, houses, other buildings and even breeding personnel.

Active Publication Date: 2020-02-11
XINJIANG AGRI UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most of the horse breeding methods in large horse farms are free-range breeding. When collecting the image information of the horse body, it is inevitable to include the background of the pasture, houses, other

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
  • Horse body ruler measurement method based on deep learning and image processing
  • Horse body ruler measurement method based on deep learning and image processing
  • Horse body ruler measurement method based on deep learning and image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0053] Such as figure 1 As shown, YOLACT decomposes the segmentation problem into two parallel processes, using the fully connected fc layer that is good at generating semantic vectors and the convolutional conv layer that is good at generating spatially coherent masks to generate "mask coefficients" and "prototype masks" respectively , the mask and the predicted corresponding coefficients are linearly combined, and cut out by the predicted b-box to realize mask synthesis, and the calculation is realized by a single matrix multiplication; thus, the instance segmentation method maintains in the horse body feature space It ensures the spatial consistency and meets the fast segmentation requirements of horse target detection; taking the image segmentation of Yili horse as an example, the YOLACT method is used to complete the horse target detection and background segmentation on the trained MS-COCO data set. figure 2 shown.

[0054]In the front-end network of YOLACT target detec...

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 the technical field of image processing, in particular to a horse body ruler measuring method based on deep learning and image processing, which comprises the following steps:segmenting YOLACT, preprocessing horse body segmented images, calibrating horse body ruler measuring points and measuring a horse body ruler. Based on a YOLACT example segmentation technology, rapidand high-performance segmentation of a horse body and a background is completed; a measuring point calibration method of the dynamic grid is provided, and data calibration of horse body ruler featurepoints is completed; a Regression multiple linear regression mode is adopted, data fitting and three-dimensional prediction of the chest circumference and the tube circumference in horse body size data are completed, and a body size measurement result is quantitatively obtained by taking two Ili horse body images with the pixel of 640 * 480 as an example; results show that based on deep learning and image measurement technologies, automatic measurement of the body size of the illite horse can be effectively carried out, the error of the body size of the illite horse is controlled within a small range, and the research has example reference significance for the body size measurement technology of large animals.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a horse body measurement method based on deep learning and image processing. Background technique [0002] Horse body size data is an important basis for measuring the growth and development of horses and for scientific feeding and breeding. The horse body measurement technology based on deep learning focuses on the effective segmentation of the horse body and the background. YOLACT is a relatively simple method for fully convolutional network to achieve instance segmentation. This method is suitable for different instance segmentation scenarios due to its technical advantages such as fastness, easy generalization, and high-quality mask generation. The target detection and background segmentation process of the horse body adopts this method. Firstly, its segmentation performance of about 30mAP on the MS-COCO data set is taken into account. Secondly, the target detection...

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): G06T7/12G06T7/62
CPCG06T7/12G06T7/62G06T2207/20081G06T2207/20084Y02P90/30
Inventor 张婧婧张靓靓李勇伟达新民赵新苗徐静
Owner XINJIANG AGRI UNIV
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