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

Method and system for recognizing cattle and sheep based on remote sensing images

A remote sensing image, cattle and sheep technology, applied in the field of image recognition, can solve the problems of small quantity, difficult to distinguish, and unable to measure the parameters of sheep body size, etc., to achieve the effect of fast speed, no line of sight occlusion, and low cost

Active Publication Date: 2020-06-26
INST OF BOTANY CHINESE ACAD OF SCI
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the existing methods of deep learning to identify wild animals deal with creatures with small individual size and high population density, such as flocks, it is difficult to distinguish each sheep, resulting in the final calculated flock The number of middle sheep is less than the actual number, and it is impossible to measure the body size parameters of the sheep

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
  • Method and system for recognizing cattle and sheep based on remote sensing images
  • Method and system for recognizing cattle and sheep based on remote sensing images
  • Method and system for recognizing cattle and sheep based on remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] This embodiment discloses a method for identifying cattle and sheep based on remote sensing images, including the following steps:

[0032] S1 is based on the remote sensing image set, and the recognition model is obtained through the deep learning target recognition algorithm;

[0033] S2 identifies the individual cattle in the remote sensing images through the recognition model, and counts the number of cattle;

[0034] S3 combines the threshold method to identify individual sheep in remote sensing images, and counts the number of sheep;

[0035] S4 judges the body size of cattle and sheep through the identified cattle and sheep.

[0036] This embodiment uses the method of combining the deep learning target recognition algorithm and the threshold method to automatically identify grassland cattle and sheep and invert their quantity and body size, which solves the problem that it is difficult to automatically identify the individual and quantity of cattle and sheep in ...

Embodiment 2

[0054] Based on the same inventive concept, this embodiment discloses a system for identifying cattle and sheep based on remote sensing images, including: an identification model generation module for training identification models through deep learning target identification algorithms based on remote sensing image sets; a cattle identification module for The training model is used to identify individual cattle in remote sensing images and count the number of cattle; the sheep identification module is used to identify individual sheep in remote sensing images by combining the threshold method and count the number of sheep; the cattle / sheep body size calculation module uses It is used to judge the body size of cattle and sheep by identifying individual cattle and sheep.

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 image recognition, and relates to a method and system for recognizing cattle and sheep based on remote sensing images, and the method comprises the following steps: S1, training a recognition model through a deep learning target recognition algorithm based on a remote sensing image set; S2, recognizing cattle individuals in the remote sensing image through a training model, and counting the number of cattle; S3, identifying sheep individuals in the remote sensing image in combination with a threshold method, and counting the number of sheep; andS4, judging the body sizes of the cattle and the sheep according to the identified cattle individuals and sheep individuals. The sheep flock range is determined by utilizing a YOLO V3 algorithm recognition result for sheep flocks which are densely distributed, and sheep individuals in the region are further distinguished and recognized by combining a threshold method and counting the total number;the body lengths of different cattle and sheep in the image are calculated through the recognition result, the proportional relation between the body lengths and other body sizes such as the body height and the chest circumference is obtained through the existing measured data, and the inversion of other body sizes of cattle and sheep in the image is carried out.

Description

technical field [0001] The invention relates to a method and system for identifying cattle and sheep based on remote sensing images, and belongs to the technical field of image identification. Background technique [0002] In field ecological surveys, it is a routine task to evaluate the development of animal husbandry, and the number and body size of cattle and sheep are commonly used evaluation parameters. With the continuous increase in the number of cattle and sheep raised by herdsmen, a method for quickly counting the number and body size of cattle and sheep is needed. The more conventional method in the prior art is to use drones to shoot remote sensing images within a certain range, and then count the number of cattle and sheep in the remote sensing images based on visual interpretation. However, the human and time costs of visual interpretation are still high in the statistical process, and the body measurements of cattle and sheep cannot be obtained more accurately...

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): G06K9/00G06K9/38G06T7/00G06T7/62G06N3/04G06N3/08
CPCG06T7/0002G06T7/62G06N3/08G06T2207/10032G06T2207/30242G06V20/13G06V10/28G06N3/045Y02A40/70
Inventor 白永飞陈文贺赵玉金鲁小名王扬
Owner INST OF BOTANY CHINESE ACAD OF SCI
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