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

Site-Specific Weed Management Using ...

Upadhyay, Arjun,

Linked to FindBook

Google Book

Amazon

博客來

Site-Specific Weed Management Using Ground Robotic Platforms /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Site-Specific Weed Management Using Ground Robotic Platforms // Arjun Upadhyay.
Author:	Upadhyay, Arjun,
Description:	1 electronic resource (252 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
Contained By:	Dissertations Abstracts International86-12B.
Subject:	Engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31939394
ISBN:	9798280735477

Site-Specific Weed Management Using Ground Robotic Platforms /
Upadhyay, Arjun,

Site-Specific Weed Management Using Ground Robotic Platforms /Arjun Upadhyay. - 1 electronic resource (252 pages)

Source: Dissertations Abstracts International, Volume: 86-12, Section: B.

The advancement of robotic technologies in agriculture shows promising improvement in weed management strategies. Weeding robots can utilize machine vision and artificial intelligence techniques for accurate identification and localization of weed and crops, which enables real-time site-specific weed management. However, there is challenge to integrate all these technologies together in a single unit for designing a intelligent weeding robot. This dissertation focuses on research studies directed towards the design of intelligent robotic platforms for smart weed management.The first chapter includes literature review to identify different types of robotic technologies used so far for smart weed management. The three fundamental components for robotic weed control are taken into considerations, which includes: path navigation, weed identification and localization, and weeding techniques. The technological advancements in these three components were highlighted and compared the performance in terms of weed control efficacy. The second chapter includes the design and development of machine vision based smart sprayer robotic platform. The robotic platform utilized FLIR camera for image acquisition and deep learning algorithms for weed identification. The performance of robotic weeding platform was evaluated in both indoor and field conditions. The third chapter includes the formation of an open-source RGB dataset for weed crop identification. The dataset includes eight different species of crop and five species of weeds. The fourth chapter involves integrating the YOLO models with edge device and testing the performance of each model based on inference time, and utilizing the best model to evaluate the performance of smart spraying robotic platform. The fifth chapter includes the development of multi-species weed identification models using different YOLO variants. Different versions of YOLO were tested for inference time and number of parameters, and the best model was suggested to be utilized with edge computing device for real-time application. The sixth chapter involves designing the mechanical structure and electrical circuits for the delta arm robotic platform to operate in real-time for intelligent mechanical weeding. In conclusion, the deep learning models for weed identification and the design of smart robotic platform for weeding shows promise in contributing to the future of sustainable weed management practices.

English

ISBN: 9798280735477Subjects--Topical Terms:

586835
Engineering.
Subjects--Index Terms:

Deep learning

Site-Specific Weed Management Using Ground Robotic Platforms /
LDR:03892nmm a22004333i 4500 001 2434232
005 20250912100622.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798280735477
035 $a (MiAaPQD)AAI31939394
035 $a AAI31939394
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Upadhyay, Arjun, $e author. $0 (orcid)0009-0008-5633-6271 $3 3824143
245 1 0 $a Site-Specific Weed Management Using Ground Robotic Platforms / $c Arjun Upadhyay.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (252 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: 86-12, Section: B.
500 $a Advisors: Sun, Xin Rex Committee members: Selekwa, Majura; Howatt, Kirk; Koparan, Cengiz.
502 $b Ph.D. $c North Dakota State University $d 2025.
520 $a The advancement of robotic technologies in agriculture shows promising improvement in weed management strategies. Weeding robots can utilize machine vision and artificial intelligence techniques for accurate identification and localization of weed and crops, which enables real-time site-specific weed management. However, there is challenge to integrate all these technologies together in a single unit for designing a intelligent weeding robot. This dissertation focuses on research studies directed towards the design of intelligent robotic platforms for smart weed management.The first chapter includes literature review to identify different types of robotic technologies used so far for smart weed management. The three fundamental components for robotic weed control are taken into considerations, which includes: path navigation, weed identification and localization, and weeding techniques. The technological advancements in these three components were highlighted and compared the performance in terms of weed control efficacy. The second chapter includes the design and development of machine vision based smart sprayer robotic platform. The robotic platform utilized FLIR camera for image acquisition and deep learning algorithms for weed identification. The performance of robotic weeding platform was evaluated in both indoor and field conditions. The third chapter includes the formation of an open-source RGB dataset for weed crop identification. The dataset includes eight different species of crop and five species of weeds. The fourth chapter involves integrating the YOLO models with edge device and testing the performance of each model based on inference time, and utilizing the best model to evaluate the performance of smart spraying robotic platform. The fifth chapter includes the development of multi-species weed identification models using different YOLO variants. Different versions of YOLO were tested for inference time and number of parameters, and the best model was suggested to be utilized with edge computing device for real-time application. The sixth chapter involves designing the mechanical structure and electrical circuits for the delta arm robotic platform to operate in real-time for intelligent mechanical weeding. In conclusion, the deep learning models for weed identification and the design of smart robotic platform for weeding shows promise in contributing to the future of sustainable weed management practices.
546 $a English
590 $a School code: 0157
650 4 $a Engineering. $3 586835
650 4 $a Agricultural engineering. $3 3168406
650 4 $a Robotics. $3 519753
653 $a Deep learning
653 $a Weed management strategies
653 $a Robotic technologies
653 $a Weeding techniques
690 $a 0539
690 $a 0537
690 $a 0800
690 $a 0771
710 2 $a North Dakota State University. $b Agricultural and Biosystems Engineering. $e degree granting institution. $3 3824144
720 1 $a Sun, Xin Rex $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-12B.
790 $a 0157
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31939394