Animal lairage track extraction method and device, animal lairage statistical model construction method and device, and animal lairage statistical method and device

A trajectory extraction and animal technology, applied in computing, image analysis, image enhancement and other directions, can solve the problems of complex trajectory tracking process of animals entering the circle, not taking into account the environmental characteristics of farming and pastoral areas, and not having real-time performance, reducing computing power. quantity, improve efficiency, and improve the effect of accuracy

Active Publication Date: 2019-09-24
TIBET UNIVERSITY FOR NATIONALITIES
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an animal encirclement trajectory extraction, statistical model construction, statistical method and device, to solve the problem that the prior art does not take into account the environmental characteristics of agricultural and pastoral areas, resulting in complex and inefficient tracking of animal encirclement trajectories and does not have real-time problems

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 lairage track extraction method and device, animal lairage statistical model construction method and device, and animal lairage statistical method and device
  • Animal lairage track extraction method and device, animal lairage statistical model construction method and device, and animal lairage statistical method and device
  • Animal lairage track extraction method and device, animal lairage statistical model construction method and device, and animal lairage statistical method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] In this embodiment, a method for extracting the trajectory of animals entering a circle in an agricultural and pastoral area is provided to obtain the trajectory of each animal entering the circle.

[0075] In this embodiment, the yak statistics of herdsmen in Tibet are taken as an example to obtain the trajectory of the yak entering the circle.

[0076] The method described is executed in the following steps:

[0077] Step 1. Set up a pair of animal entry detection surfaces in the space, one of the animal entry detection surfaces coincides with the surface where the trap door is located, and the other animal entry detection surface is parallel to the surface where the trap door is located and is located outside the ring door;

[0078] In this step, the space is the space where the actual detection area is located, that is, the circle gate in the farming and pastoral area and the space outside the circle gate. In this step, in order to realize the detection of animals entering t...

Embodiment 2

[0151] A method for constructing a statistical model of animals entering a pen in a farming and pastoral area is executed according to the following steps:

[0152] Step 1. Use the method of step 1-2 in the first embodiment to obtain videos of animals entering the circle and a pair of animals entering the circle detection surface to obtain a sample video sequence. The sample video sequence includes a variety of animals, and each animal corresponds to An animal name tag;

[0153] In this step, the animal species can be animals of the same kind but different sizes of big yak and small yak, or different kinds of animals such as sheep, yaks, and horses.

[0154] In this embodiment, in order to count the yaks in Tibetan homes, the specific statistics are the total number of yaks, the number of big yaks, and the number of small yaks. Therefore, the animal name tags are designed as big yaks and small yaks.

[0155] Step II: Use the sample video sequence as a video sequence to be processed, a...

Embodiment 3

[0160] A statistical method for animals entering the circle in the farming and pastoral area is implemented by using the method from step A to step D to obtain statistical results:

[0161] Step A: Use the method of step 1-2 in the first embodiment to obtain videos of animals entering the circle and a pair of animals entering the circle detection surface, to obtain a video sequence to be counted;

[0162] Step B: Use the video sequence to be counted as a video sequence to be processed, and perform trajectory extraction on the video sequence to be processed using steps 3 to 5 in the first embodiment to obtain a trajectory set;

[0163] Step C: After inputting the trajectory set into the statistical model of animal entering the circle obtained in Example 2, the animal name label corresponding to the trajectory of each animal entering the circle is obtained;

[0164] Step D: Perform statistics on all animal name tags obtained in Step C, and obtain statistical results. The statistical resu...

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 lairage track extraction method and device, an animal lairage statistical model construction method and device, and an animal lairage statistical method and device, in a farming and pasturing area, capable of performing classification and statistics on the tracks by using a trained SVM classifier after obtaining the tracks of lairage animals by processing the video of animal lairage after obtaining animal lairage and the video of a pair of animal lairage detection surfaces by using a calibrated camera. The animal lairage statistical model construction and the animal lairage statistical method in a farming and pasturing area can count the number of animals and also can count the types of the animals by setting multiple animal tags, thus solving the problem of low efficiency of traditional manual counting; and secondly, the statistical method provided by the invention can ensure that safe lairage of all yaks after the grazing is finished, and can also provide technical support for the development of intelligent pasture in the future.

Description

Technical field [0001] The invention relates to a statistical method for animals entering a circle, in particular to an animal entering a circle trajectory extraction, statistical model construction, statistical method and device. Background technique [0002] For ordinary people in agricultural and pastoral areas, most families have hundreds of animals, such as yaks and sheep. The area of ​​grassland in agricultural and pastoral areas is very large. How to efficiently and accurately count the number of yaks that have ended grazing is one Problems that must be solved very much for herders. [0003] In the prior art, image-based counting methods for animals in agricultural and pastoral areas are relatively rare. The basic idea is to extract the trajectory of the animals entering the circle to obtain the trajectory of the animals entering the circle for further processing and counting; however, in the prior art , The trajectory tracking method used for extracting the trajectory of a...

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): G06T7/187G06T7/20G06T3/40
CPCG06T7/187G06T7/20G06T3/4038G06T2207/30242G06T2207/10016G06T2207/20081Y02A40/70
Inventor 王菽裕李春国宋俊芳薛茹张春玉
Owner TIBET UNIVERSITY FOR NATIONALITIES
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