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

AI video counting method, device, equipment and medium for live pig breeding

A technology for video and live pigs, applied in the computer field, can solve the problems of large errors in manual pig spotting, time-consuming and labor-intensive, and no supervision measures, and achieve the effect of reducing time costs, reducing operational risks, and reducing loan risks.

Inactive Publication Date: 2021-03-23
中国农业银行股份有限公司福建省分行
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The shortcomings of this method are obvious. First, it is time-consuming and labor-intensive. The account manager needs to spare time to go to the pig farms of the farmers, and most of the farms are located in remote rural areas. The whole process takes a long time. After full coverage, the efficiency is extremely low; second, the error of manual pointing pigs is relatively large
Especially in farms with a large number of pigs, the pigs are in a state of motion. During the long-term counting process, the pigs change their positions, which will inevitably dazzle the human eye and cause counting errors.
Third, without effective supervisory measures, it is prone to the operational risk of collusion between account managers and farmers to defraud loans

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
  • AI video counting method, device, equipment and medium for live pig breeding
  • AI video counting method, device, equipment and medium for live pig breeding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, the present embodiment provides an AI video point method for pig breeding, including:

[0041] Step 1, regularly obtain the video of the pig farm, the video is a continuous video;

[0042] Step 2. Analyze the video to obtain the collected video stream of the specified closed area, which includes the active target in the specified closed area; extract the visual features of the video from the video stream, and then cluster the features , and then select a key frame set from the clustered video frames, the key frame set is a group of key image frames used to show the number of pigs, covering the entire pig farm;

[0043]Step 3. For the overlapping parts between the key frames in the key frame set, use the image stitching technology to start from the gray value of the key frame, and calculate the gray value of an area in the key frame and an area of ​​the same size in the reference image. After comparing the difference, judge the similarity of ...

Embodiment 2

[0047] Such as figure 2 As shown, the second aspect is provided in the present embodiment, and the present invention provides a kind of AI video points device for pig breeding, comprising:

[0048] Obtain a video module to regularly obtain the video of the pig farm, and the video is a continuous video;

[0049] The key frame module analyzes the video and obtains the video stream of the designated closed area that has been collected. The video stream includes the moving target in the designated closed area; the visual features of the video are extracted from the video stream, and then the features are aggregated. class, and then select a key frame set from the clustered video frames, the key frame set is a group of key image frames used to show the number of pigs, covering the entire pig farm;

[0050] Stitching module, for the overlapping parts between the key frames in the key frame set, using the image stitching technology, starting from the gray value of the key frame, ca...

Embodiment 3

[0055] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, any implementation manner in Embodiment 1 can be implemented.

[0056] Since the electronic device introduced in this embodiment is the device used to implement the method in Embodiment 1 of this application, based on the method described in Embodiment 1 of this application, those skilled in the art can understand the electronic device of this embodiment. Specific implementation methods and various variations thereof, so how the electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as a person skilled in the art implements the equipment used by the method in the embodiment of the present application, it all belongs to the protection scope of the present application.

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 provides an AI video counting method, device and equipment for pig breeding and a medium, and the method comprises the steps: periodically obtaining a video of a pig farm, wherein the video is a continuous video; analyzing the video, obtaining a collected video stream of a specified closed area, and processing the video stream to obtain a key frame set; splicing the key frames in thekey frame combination by adopting an image splicing technology, and eliminating repeated images to form a complete image containing all live pigs in the pig farm; counting according to the complete image to obtain the number of live pigs; and the counting efficiency and accuracy are improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an AI video point scoring method, device, equipment and medium for pig breeding. Background technique [0002] In recent years, the stable production and supply of live pigs has become a key livelihood project of the government. Governments at all levels, the China Banking and Insurance Regulatory Commission, and provincial and municipal banking and insurance regulatory bureaus have successively issued policy documents to support the development of live pig mortgage loans to better meet the financing needs of the pig industry. [0003] As banks increase their efforts to grant loans to farmers who use pigs as collateral, how to reduce post-loan risks has become a top priority. Pig farming loans use the number of pigs to evaluate farmers’ repayment ability. Therefore, banks need to keep abreast of the current number of pigs raised by farmers, and use the number of pigs as...

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): H04N5/265G06T3/40G06N20/00G06K9/34G06K9/00
CPCH04N5/265G06T3/4038G06N20/00G06V20/41G06V20/46G06V20/53G06V10/267
Inventor 周胜平陈展红陈航吴辉吴雷王艳刘丁巳胡逸生刘进丑陈顶黄泗恩
Owner 中国农业银行股份有限公司福建省分行
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