Wheat ear detection based on one-stage object detector

Jing Zhan

doi:10.1117/12.3006000

10 October 2023 Wheat ear detection based on one-stage object detector

Jing Zhan

Proceedings Volume 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023); 127995R (2023) https://doi.org/10.1117/12.3006000
Event: 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 2023, Kuala Lumpur, Malaysia

Abstract

This study aims to achieve precise detection of wheat ears using the YOLOv3 object detector. By using a large-scale wheat ear dataset for training and evaluation, we demonstrated the superior performance of YOLOv3 in wheat ear detection tasks. YOLOv3 is an efficient and accurate object detection algorithm based on deep learning. This algorithm divides the image into grid units and predicts the position and category of wheat ears on each unit, achieving the goal of quickly detecting wheat ears in wheat fields. At the same time, YOLOv3 adopts multi-layer Convolutional neural network and feature pyramid structure, which can accurately locate the bounding box of wheat ears, and can achieve good results even under different scales and occlusion. The experimental results show that using YOLOv3 for wheat ear detection can effectively detect and locate wheat ears in wheat fields, with a detection accuracy of 86.6%.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jing Zhan "Wheat ear detection based on one-stage object detector", Proc. SPIE 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 127995R (10 October 2023); https://doi.org/10.1117/12.3006000

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available