Animal target counting method based on dual-light camera

A target quantity and animal technology, applied in the field of breeding, can solve problems such as missed or misjudgment, and the influence of the accuracy of the number of animals counted in the pen

Pending Publication Date: 2021-11-30
NEW HOPE LIUHE +4
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are many problems. For example, the track needs to be planned and laid in advance when the pig farm is built, which poses a huge challenge to the reconstruction plan of the built farm; The accuracy of counting the number of animals in the pens has a great influence, and the inaccurate statistics of the number of animals will directly relate to the final economic benefits

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 target counting method based on dual-light camera
  • Animal target counting method based on dual-light camera
  • Animal target counting method based on dual-light camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] An embodiment of the present invention provides a method for counting animal targets based on a dual-light camera, which specifically includes the following steps:

[0037] Step S1: Obtain animal stall images to build a sample library, take the stall images with animal faces or heads as positive samples, and take the stall images without animal faces as negative samples; the acquired sample library includes two The sample libraries are respectively the visible light image sample library and the thermal imaging image sample library.

[0038] Step S2: Build a counting model, the counting model includes two neural network models for animal recognition, which are used to recognize visible light images and thermal imaging images respectively, and the two neural network structure models can be preferentially YOLOv4 neural networks; in addition , the counting model also includes a correction model connected to the back end of the two neural network models, and the correction m...

Embodiment 2

[0050] On the basis of Example 1, the visible light image sample library and thermal imaging image sample library, as well as the visible light image group and thermal imaging image group to be tested, are respectively obtained by using the visible light camera RealSense D435 and the infrared thermal imaging camera Arrow AT600.

Embodiment 3

[0052] On the basis of embodiment 1 or 2, when step S4 in embodiment 1 acquires the image to be tested of each column, intelligent patrol car (smart patrol car is the prior art, will not be repeated here) can be used as Carrier; and the method / method of patrolling is: advance horizontally from the first column, take an S-shaped route from the starting point to the end point, and control the stopping time of the intelligent patrol car in front of the fence according to the shooting time.

[0053] see figure 1 , a specific scheme is given; figure 1 Among them, the columns are divided into 4 columns, and each column has 100 measuring points (that is, 100 columns). Take at least two visible light images and thermal imaging images of the pigs at each measuring point in a row (that is, one visible light image and one infrared image), and patrol the fence once a day. The intelligent inspection vehicle can control the camera to interact with the pigs every time. The shooting distanc...

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 target counting method based on a dual-light camera. The animal target counting method specifically comprises the following steps: acquiring animal column images to construct a sample library; constructing a counting model, wherein the counting model comprises a neural network model for animal identification; inputting the sample library into the neural network model for training to obtain a trained neural network model; obtaining to-be-detected images of all columns in sequence, each column corresponds to one to-be-detected image group, and each to-be-detected image group comprises n to-be-detected images; and sequentially inputting 2n to-be-detected images corresponding to each field into the constructed counting model to obtain a final recognition result of each field, and counting the final recognition results of all fields to obtain the number of animal targets. The beneficial effects of the method are that the system is especially suitable for a limiting fence feeding environment in a large-scale pig farm, and can achieve the more precise non-contact large-scale in-house pig inventory.

Description

technical field [0001] The invention relates to the technical field of farming, in particular to a method for counting animal targets based on a dual-light camera. Background technique [0002] In the process of pig breeding, as far as pig inventory is concerned, it is necessary to count the number of animals in the pen in real time at all stages from the farrowing room to the gestation house, from nursery to slaughter, so that large-scale farms can track production information and adjust production strategies. However, traditional The operation method is to manually count the number of pigs in the house, which is not only time-consuming and labor-intensive, but also the number of pigs changes every day. There are dead pigs, and there are pigs transferred to houses and pens. Manual recording is prone to errors. [0003] In recent years, with the rise of artificial intelligence technology in the breeding industry, more and more companies have begun to use technologies such 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): G06T7/00G06N3/04G06N3/08
CPCG06T7/0002G06N3/08G06T2207/30242G06N3/045
Inventor 杜晓冬樊士冉梅佳琪刘聪陈麒麟闫雪冬赵铖
Owner NEW HOPE LIUHE
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