Large-scale farm sign abnormal bird detection system and detection method thereof

A detection method and detection system technology, applied in poultry farming, neural learning methods, radiation pyrometry, etc., can solve the problems of large model adjustment, chickens without combs, and weak robustness, so as to avoid missed detection, Liberate manpower and realize the effect of intelligence

Active Publication Date: 2019-09-06
TIANJIN UNIV
View PDF10 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But from the actual situation, some types of chickens do not have cockscombs, and the use of cockscombs to judge is somewhat accidental
In addition, the above algorithms need to manually extract features, the model adjustment is relatively large in different situations, the model is not robust to different poultry, and the image recognition effect will be greatly weakened in farms with insufficient light

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
  • Large-scale farm sign abnormal bird detection system and detection method thereof
  • Large-scale farm sign abnormal bird detection system and detection method thereof
  • Large-scale farm sign abnormal bird detection system and detection method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A detection system for poultry with abnormal signs in large-scale farms, its structure is as follows: figure 1 As shown, it includes a wheeled robot, a thermal imager, an industrial computer, image processing and recognition software; the wheeled robot is used to carry a thermal imager and an industrial computer; the thermal imager is used to photograph the formation of poultry in a large farm thermal imaging image; the industrial computer is used to process the thermal imaging graphics obtained by shooting, and complete target detection, including image processing and recognition software, which includes a pre-trained detection model; equipped with thermal imaging The wheeled robot of the instrument and the industrial computer performs a fixed trajectory cruise in the farm. The thermal imager transmits the captured data to the industrial computer, and the industrial computer processes the transmitted data. Through image processing and recognition software and its detect...

Embodiment 2

[0041] A method for detecting poultry with abnormal signs in a large-scale farm, which utilizes the poultry detection system with abnormal signs in large-scale farms of the embodiment, and generally includes the following steps:

[0042] S1. Data acquisition preprocessing: Use a thermal imager to collect abnormal poultry data sets in farms; remove images with severe noise pollution from the collected data, then display the temperature according to the thermal imaging image, and manually mark the remaining images. The targets in the data set are divided into two categories, one is abnormal signs, and the other is dead poultry; figure 2 A thermal imaging map with part of the target temperature marked.

[0043] S2, adopt depth residual network (ResNet101) and fully convolutional neural network (FPN) to extract the feature of thermal imaging image, and produce candidate object frame by region recommendation network (RPN);

[0044] S3. Perform pooling and pixel alignment (RoIAlig...

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 large-scale farm sign abnormal bird detection method, which comprises the following steps: pre-processing the collected thermographic images for data annotation, then adopting an instance-based segmentation general framework (Mask RCNN) target detection and instance separation method for feature extraction, pixel alignment, target positioning, classification and mask separation for thermal imaging images, by controlling the target detection number of a single image, improving the detection accuracy rate in each image. The method is an attempt in the field of target detection of current thermal imaging images, breaks the limitations brought by the traditional methods, and uses the superior performance of deep learning in image feature processing to improve the robustness and accuracy of a model. The feasibility of the deep learning method in the field of thermal imaging image detection is verified. At the same time, the method can also be extended to the livestock and other fields, thus improving the level of intelligence in the breeding industry in China.

Description

technical field [0001] The present invention generally relates to the fields of thermal imaging image processing, deep learning technology and target detection, and specifically relates to a detection system and detection method for poultry with abnormal signs in large-scale farms. Background technique [0002] At present, most of the domestic large-scale farms do not have a high level of intelligence, and manual participation is required to check whether there are individuals with abnormal signs in the chicken farm. However, manual inspection is very inefficient and time-consuming, and the general farms are relatively closed, the ventilation is not very good, and there is a lot of toxic gas. If people stay in the farm for a long time, it will have adverse effects on the body. . If the dead chicken is not found in a short period of time, the dead body will cultivate germs and spread continuously. The bird flu spreads rapidly and has a high infection rate, which will cause 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): A61B5/01A61B5/00A01K45/00G01J5/00G06N3/04G06N3/08
CPCG01J5/0025A01K45/00A61B5/0059A61B5/01G06N3/08G01J2005/0077A61B2503/40G06N3/045
Inventor 郑吉星胡清华马锐
Owner TIANJIN 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

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