國立虎尾科技大學 |

Rice Panicles Detection From Drone Images Using Deep Learning

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Rice Panicles Detection From Drone Images Using Deep Learning/ Mansi Piyush Vaghasiya.
作者:	Vaghasiya, Mansi Piyush,
面頁冊數:	1 electronic resource (48 pages)
附註:	Source: Masters Abstracts International, Volume: 86-11.
Contained By:	Masters Abstracts International86-11.
標題:	Computer engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32038310
ISBN:	9798315721864

Rice Panicles Detection From Drone Images Using Deep Learning
Vaghasiya, Mansi Piyush,

Rice Panicles Detection From Drone Images Using Deep Learning [electronic resource] /Mansi Piyush Vaghasiya. - 1 electronic resource (48 pages)

Source: Masters Abstracts International, Volume: 86-11.

This thesis presents an advanced deep-learning architecture to automate the detection of rice panicles from high-resolution drone images, with goal of improving yield prediction accuracy and efficiency. By integrating drone technology with a customized deep learning architecture, the model is trained on images collected using drone at different growth stages and environmental conditions, meticulously annotated by rice specialists to ensure precise detection. In this thesis, transfer learning is used to test additional images for better visual representation. Built upon the YOLOv11 framework, the architecture is specifically tailored for rice panicle detection, addressing challenges such as detecting small panicles, handling occlusions by leaves or adjacent panicles, and preventing feature loss in noisy backgrounds. Performance evaluation was conducted using images captured at varying environmental conditions and growth stages, incorporating data augmentation techniques. This approach ensures that the model performs effectively across a variety of real-world scenarios, overcoming the limitations of traditional phenotyping methods.

English

ISBN: 9798315721864Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Deep-learning architecture

Rice Panicles Detection From Drone Images Using Deep Learning
LDR:02589nam a22004213i 4500 001 1172924
005 20260622113225.5
006 m o d
007 cr|nu||||||||
008 260803s2025 miu||||||m |||||||eng d
020 $a 9798315721864
035 $a (MiAaPQD)AAI32038310
035 $a AAI32038310
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Vaghasiya, Mansi Piyush, $e author. $3 1503568
245 1 0 $a Rice Panicles Detection From Drone Images Using Deep Learning $c Mansi Piyush Vaghasiya. $h [electronic resource] /
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (48 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: Masters Abstracts International, Volume: 86-11.
500 $a Advisors: Zhang, Jing Committee members: Sun, Bo; Wang, Sujing.
502 $b M.S. $c Lamar University - Beaumont $d 2025.
520 # $a This thesis presents an advanced deep-learning architecture to automate the detection of rice panicles from high-resolution drone images, with goal of improving yield prediction accuracy and efficiency. By integrating drone technology with a customized deep learning architecture, the model is trained on images collected using drone at different growth stages and environmental conditions, meticulously annotated by rice specialists to ensure precise detection. In this thesis, transfer learning is used to test additional images for better visual representation. Built upon the YOLOv11 framework, the architecture is specifically tailored for rice panicle detection, addressing challenges such as detecting small panicles, handling occlusions by leaves or adjacent panicles, and preventing feature loss in noisy backgrounds. Performance evaluation was conducted using images captured at varying environmental conditions and growth stages, incorporating data augmentation techniques. This approach ensures that the model performs effectively across a variety of real-world scenarios, overcoming the limitations of traditional phenotyping methods.
546 $a English
590 $a School code: 0424
650 # 4 $a Computer engineering. $3 569006
650 # 4 $a Computer science. $3 573171
653 # # $a Deep-learning architecture
653 # # $a Phenotyping methods
653 # # $a Environmental conditions
653 # # $a Accuracy
653 # # $a Data augmentation techniques
690 $a 0984
690 $a 0464
710 2 # $a Lamar University - Beaumont. $b Computer Science. $3 1148598
720 1 $a Zhang, Jing $e degree supervisor.
773 0 # $t Masters Abstracts International $g 86-11.
790 $a 0424
791 $a M.S.
792 $a 2025
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32038310