東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Machine Vision Technologies for Eval...

Yang, Xiao,

Linked to FindBook

Google Book

Amazon

博客來

Machine Vision Technologies for Evaluating Key Production and Welfare Indicators of Cage-Free Layers /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Machine Vision Technologies for Evaluating Key Production and Welfare Indicators of Cage-Free Layers // Xiao Yang.
Author:	Yang, Xiao,
Description:	1 electronic resource (294 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-07, Section: B.
Contained By:	Dissertations Abstracts International86-07B.
Subject:	Agricultural engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31632090
ISBN:	9798302131461

Machine Vision Technologies for Evaluating Key Production and Welfare Indicators of Cage-Free Layers /
Yang, Xiao,

Machine Vision Technologies for Evaluating Key Production and Welfare Indicators of Cage-Free Layers /Xiao Yang. - 1 electronic resource (294 pages)

Source: Dissertations Abstracts International, Volume: 86-07, Section: B.

With rising consumer concerns about animal welfare, the United States (USA) egg industry is shifting towards cage-free farming practices. This shift introduces challenges in poultry management, sustainable egg production, and automation in poultry farming. In response, this study investigates updated computer vision techniques, thermal cameras, and robotics to monitor poultry floor distribution, predict bird body weight, manage floor eggs, and detect behaviors and welfare conditions. The objective of this dissertation was to evaluate the performance of traditional convolutional neural network (CNN) models (e.g., YOLO series, EfficientNetV2, SegFormer, and SETR) and large vision models (LVM) (e.g., Segment Anything Model and Track Anything Model) in assessing key production and welfare indicators of cage-free layers. Furthermore, the research explored advanced robotic systems for detecting floor eggs and dead chickens. For this study, 800 hens were raised in four cage-free research rooms under different experimental designs based on specific research objectives. The results demonstrated that CNN models can effectively track chickens' spatial distribution (90.0% precision), detect floor eggs (94.8% accuracy), and classify six behaviors (i.e., feeding, drinking, walking, perching, dust bathing, and nesting) with 95.3% accuracy. LVMs, combined with thermal cameras, predicted chicken body weight (R² = 0.90) and tracked individual hens (RMSE = 0.02 m/s). Moreover, integrating CNN models with intelligent bionic quadruped robots allowed for the detection of floor eggs in dimly lit areas, such as beneath feeders and in corner spaces, as well as the identification of dead chickens within the flock. In conclusion, this dissertation highlights the cutting-edge techniques of precision farming technologies in advancing automated poultry management in cage-free systems. By integrating CNN, LVM, and robotic technologies, this research offers an interdisciplinary approach to addressing the challenges of modern cage-free farming, advancing the poultry industry with more ethical, efficient, automated, and sustainable production practices.

English

ISBN: 9798302131461Subjects--Topical Terms:

3168406
Agricultural engineering.
Subjects--Index Terms:

Cage-free farming

Machine Vision Technologies for Evaluating Key Production and Welfare Indicators of Cage-Free Layers /
LDR:03625nmm a22004213i 4500 001 2428620
005 20250414021915.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798302131461
035 $a (MiAaPQD)AAI31632090
035 $a AAI31632090
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Yang, Xiao, $e author. $3 3815955
245 1 0 $a Machine Vision Technologies for Evaluating Key Production and Welfare Indicators of Cage-Free Layers / $c Xiao Yang.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (294 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-07, Section: B.
500 $a Advisors: Chai, Lilong Committee members: Applegate, Todd; Ritz, Casey W.; Kim, Woo K.; Regmi, Prafulla; Liu, Tianming.
502 $b Ph.D. $c University of Georgia $d 2024.
520 $a With rising consumer concerns about animal welfare, the United States (USA) egg industry is shifting towards cage-free farming practices. This shift introduces challenges in poultry management, sustainable egg production, and automation in poultry farming. In response, this study investigates updated computer vision techniques, thermal cameras, and robotics to monitor poultry floor distribution, predict bird body weight, manage floor eggs, and detect behaviors and welfare conditions. The objective of this dissertation was to evaluate the performance of traditional convolutional neural network (CNN) models (e.g., YOLO series, EfficientNetV2, SegFormer, and SETR) and large vision models (LVM) (e.g., Segment Anything Model and Track Anything Model) in assessing key production and welfare indicators of cage-free layers. Furthermore, the research explored advanced robotic systems for detecting floor eggs and dead chickens. For this study, 800 hens were raised in four cage-free research rooms under different experimental designs based on specific research objectives. The results demonstrated that CNN models can effectively track chickens' spatial distribution (90.0% precision), detect floor eggs (94.8% accuracy), and classify six behaviors (i.e., feeding, drinking, walking, perching, dust bathing, and nesting) with 95.3% accuracy. LVMs, combined with thermal cameras, predicted chicken body weight (R² = 0.90) and tracked individual hens (RMSE = 0.02 m/s). Moreover, integrating CNN models with intelligent bionic quadruped robots allowed for the detection of floor eggs in dimly lit areas, such as beneath feeders and in corner spaces, as well as the identification of dead chickens within the flock. In conclusion, this dissertation highlights the cutting-edge techniques of precision farming technologies in advancing automated poultry management in cage-free systems. By integrating CNN, LVM, and robotic technologies, this research offers an interdisciplinary approach to addressing the challenges of modern cage-free farming, advancing the poultry industry with more ethical, efficient, automated, and sustainable production practices.
546 $a English
590 $a School code: 0077
650 4 $a Agricultural engineering. $3 3168406
650 4 $a Animal sciences. $3 3174829
653 $a Cage-free farming
653 $a Computer vision
653 $a Large vision models
653 $a Precision poultry management
690 $a 0539
690 $a 0475
690 $a 0778
710 2 $a University of Georgia. $b Poultry Science - PHD. $e degree granting institution. $3 3815956
720 1 $a Chai, Lilong $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-07B.
790 $a 0077
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31632090