Binocular vision intelligent detection method and system

A binocular vision, intelligent detection technology, applied in character and pattern recognition, instruments, computing models, etc., can solve the problems of difficult to achieve individual tracking monitoring and targeted automation measures, single parameters, etc., to achieve precise movement and improve production performance , the effect of effective control

Inactive Publication Date: 2021-12-31
XUZHOU NORMAL UNIVERSITY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a binocular vision intelligent detection method and system, which can solve the problems existing in the prior art, such as visual monitoring behavior or single parameter, difficulty in realizing individual tracking monitoring and targeted automatic measures, etc.

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
  • Binocular vision intelligent detection method and system
  • Binocular vision intelligent detection method and system
  • Binocular vision intelligent detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] This embodiment provides a binocular vision intelligent detection method, such as figure 1 As shown, the method includes the following steps:

[0058] S100. Collecting visible light images and infrared images of the object;

[0059] S200. Identify abnormal behaviors in the visible light image according to machine learning results;

[0060] S300. Perform temperature behavior analysis on the infrared image corresponding to the visible light image of the identified abnormal behavior, and then determine whether the abnormal behavior is a problem behavior.

[0061] As a preferred embodiment, such as figure 2 As shown, before collecting the visible light image and the infrared image of the object, there are the following steps:

[0062] S10. Recognizing multiple objects according to the captured visible light image;

[0063] S20. Read the ID information of the plurality of objects, and retrieve the historical data of the plurality of objects corresponding to the pluralit...

Embodiment 2

[0081] This embodiment also provides a binocular vision intelligent detection system, such as Figure 5 As shown, the system includes:

[0082] The binocular vision module 3 collects visible light images and infrared images of objects;

[0083] Processor 1 identifies abnormal behaviors in visible light images based on machine learning results, and analyzes temperature behaviors of infrared images corresponding to visible light images of identified abnormal behaviors, and then determines whether abnormal behaviors are problematic behaviors.

[0084] The processor 1 also recognizes a plurality of objects according to the captured visible light images, reads the ID information of the plurality of objects, and retrieves the historical data of the plurality of objects corresponding to the plurality of ID information, and according to the historical data and the read The positioning data when multiple object ID information is taken realizes the correspondence of ID information of m...

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 binocular vision intelligent detection method and system. The method comprises the following steps: collecting a visible light image and an infrared image of an object; identifying an abnormal behavior in the visible light image according to a machine learning result; and carrying out temperature behavior analysis on the infrared image corresponding to the visible light image of the identified abnormal behavior so as to obtain whether the abnormal behavior is a problem behavior or not. On one hand, behaviors of breeding objects are monitored, on the other hand, object body temperature monitoring based on the infrared image fusion technology can be achieved, deep image fusion is carried out, and whether physiological data are abnormal or not is judged by combining the behaviors and body temperature data, so that a breeding method and a management technology are scientifically formulated or changed; more suitable environmental conditions are created, and the breeding capacity is improved.

Description

technical field [0001] The invention relates to the field of image monitoring, in particular to a binocular vision intelligent detection method and system. Background technique [0002] In the process of large-scale breeding of pigs, cattle and sheep, in addition to monitoring the breeding environment and animal physiological parameters, daily preventive work such as abnormal animal behavior monitoring, abnormal body temperature monitoring, and disinfection and epidemic prevention of the breeding environment is also the guarantee for the healthy growth of animals. In existing technologies, machine vision is usually used to monitor animal behavior such as water drinking behavior to evaluate the health status of animals. However, it is difficult to determine the health status of animals only by monitoring a single behavior of animals, and usually it can only be determined by a single captured behavior, and cannot Realize continuous tracking and combine with historical data to ...

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): G06K9/00G06N20/00A01K29/00
CPCG06N20/00A01K29/00
Inventor 魏明生仇欣宇贺磊刘加跃
Owner XUZHOU NORMAL UNIVERSITY
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