Embedded-based method for monitoring the number of livestock populations in a natural environment

A natural environment, embedded technology, applied in the direction of character and pattern recognition, instruments, computer components, etc., can solve the problems of low precision, achieve the effect of improving efficiency, solving unmatchable, and improving adaptability

Inactive Publication Date: 2016-06-22
JILIN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional methods such as corner point matching can deal with this kind of problem, but under natural conditions, the group of livestock may be very dense, and the traditional method is not very accurate in this case

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
  • Embedded-based method for monitoring the number of livestock populations in a natural environment
  • Embedded-based method for monitoring the number of livestock populations in a natural environment
  • Embedded-based method for monitoring the number of livestock populations in a natural environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Take the common sheep counting process in livestock as an example. figure 1 The figure on the left is the edge image of part (010) after step C011 to step C015 edge extraction. Before obtaining this edge image, the color image or_img is first obtained through the camera, and then processed in grayscale, smoothing, binarization, and edge extraction. exist figure 1 It can be seen that in addition to the sheep's back edge, there are many short and fragmented false edges. False edges will show intermittent characteristics, and their connectivity is not high, so this feature can be used to filter out false edges. By setting a connected threshold, the connected components smaller than the connected threshold are set as background pixels. The setting of the threshold is very important to the result, and the threshold is set to 6 in the implementation of this algorithm. Traverse the entire image, find each unmarked non-zero p...

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 a method for detecting the number of individuals in a livestock group under a natural environment based on an embedded platform. Under the condition that the livestock group is relatively concentrated and livestock shield one another, satisfied precision degree can be obtained. The method can be widely used for estimating the number of individuals in the livestock group under the natural environment, and summing the livestock, people and articles which are in a monitoring video. For example, the number of cattle and sheep which are grazeed in a large area can be monitored in real time by the method. The method can be operated on the embedded platform and can be conveniently combined with terminal equipment, the requirements on environment and equipment are low, and the application field is expanded.

Description

technical field [0001] The method of the present invention relates to a method for detecting the number of individuals in a livestock group in a natural environment based on an embedded platform. Satisfactory accuracy can also be obtained when the livestock group is concentrated and mutual occlusion is serious. degree; this method can be widely used in the estimation of the number of livestock groups in the natural environment, and the statistical problems of livestock, people and objects in the surveillance video, such as: real-time monitoring of the number of cattle and sheep in large-scale grazing, etc.; at the same time, this method can Running on an embedded platform, it can be easily combined with terminal equipment, has very low requirements on the environment and equipment, and broadens the application occasions. Background technique [0002] In recent years, image processing technology has become more and more mature, and the effect of various denoising algorithms i...

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 Patents(China)
IPC IPC(8): G06K9/54
Inventor 李文辉傅博王莹李慧盈倪洪印刘培勋胡玉龙陈存祺
Owner JILIN 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