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

Animal three-dimensional parameter extraction method and system based on unmanned aerial vehicle, and electronic equipment

A technology of parameter extraction and unmanned aerial vehicles, which is applied in 3D object recognition, image data processing, computer parts, etc., can solve the problems of low accuracy of 3D parameters of animals and the inability to accurately obtain the height of each head/animal, etc. Achieve the effect of improving recognition accuracy and rapid extraction

Active Publication Date: 2020-09-15
INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS +1
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The applicant and his team have also carried out surveys of large herbivores such as yaks, Tibetan sheep, Tibetan wild donkeys, blue sheep and other large herbivores based on drone aerial photography in Maduo County, Qinghai Province. The height of each head / animal cannot be accurately obtained in the plane image, which leads to the low accuracy of the three-dimensional parameters of the recognized animals

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 three-dimensional parameter extraction method and system based on unmanned aerial vehicle, and electronic equipment
  • Animal three-dimensional parameter extraction method and system based on unmanned aerial vehicle, and electronic equipment
  • Animal three-dimensional parameter extraction method and system based on unmanned aerial vehicle, and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Such as figure 1 As shown, an animal three-dimensional parameter extraction method according to an embodiment of the present invention includes the following steps:

[0050] S1. Integrate a high-resolution camera and a lidar sensor into the same drone with a high-precision POS system, and obtain high-resolution images and lidar point clouds of the drone simultaneously. The relative error of human-machine high-resolution images is better than 0.2m;

[0051] S2. Recognize the high-resolution image of the UAV through the image animal recognition model to obtain the type of each animal / animal and the mask polygon corresponding to the outline of each animal / animal;

[0052] S3. Supervise and classify the lidar point cloud to obtain an animal point and the smallest convex hull polygon of each animal / animal corresponding point;

[0053] S4. Obtain the three-dimensional parameters of each animal / animal according to the mask polygon obtained in the high-resolution image of the UAV and i...

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 an animal three-dimensional parameter extraction method and system based on an unmanned aerial vehicle, and electronic equipment. The animal three-dimensional parameter extraction method comprises the following steps: firstly, identifying an image through an image animal identification model to obtain the type of each animal and a mask polygon corresponding to the outlineof each animal, and obtaining animal points according to laser radar point cloud; then, by obtaining the animal point corresponding to each mask polygon, accurately obtaining the position matching relationship of the animal in the image and the laser radar point cloud; and finally, obtaining the height of each animal from the laser radar point cloud, and calculating parameters such as the body length and the body area of the animal from the high-resolution image of the unmanned aerial vehicle. By fusing the high-resolution images of the unmanned aerial vehicle and the laser radar point cloud,the animal three-dimensional parameter extraction method can improve the animal recognition precision, can achieve rapid extraction of three-dimensional parameters, can quantitatively estimate the weight of large herbivorous animals and sheep units, and has important significance in animal husbandry development and wild animal protection.

Description

Technical field [0001] The invention relates to the technical field of animal surveys, and in particular to a method, system and electronic equipment for extracting three-dimensional parameters of animals based on drones. Background technique [0002] Three-dimensional parameters such as the height, body length and body area of ​​large herbivores are important indicators for estimating animal weight and food intake. They are essential for accurate verification of grass-livestock balance, development of precision breeding and grass husbandry. Traditional animal surveys mainly use ground surveys Method, using infrared trigger photography, environmental DNA monitors, rangefinders, telescopes, sound and position recorders and other sensors to investigate the number, behavior, structure and other information of animals. However, in some areas, the ground is difficult for people to reach, and there are problems such as obstruction of sight, low survey efficiency, high cost, and insuffi...

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): G06K9/00G06K9/62G06N3/04G06T7/62
CPCG06T7/62G06T2207/10028G06V20/64G06V20/10G06N3/045G06F18/24G06F18/214Y02T10/40
Inventor 王东亮岳焕印彭金榜廖小罕叶虎平谭翔
Owner INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS
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