Version 1
: Received: 20 March 2024 / Approved: 21 March 2024 / Online: 22 March 2024 (08:17:47 CET)
How to cite:
Hu, X.; Jeon, W.; Rhee, S. Research on Weed and Crop Identification System Using Pixel-Wise Segmentation. Preprints2024, 2024031311. https://doi.org/10.20944/preprints202403.1311.v1
Hu, X.; Jeon, W.; Rhee, S. Research on Weed and Crop Identification System Using Pixel-Wise Segmentation. Preprints 2024, 2024031311. https://doi.org/10.20944/preprints202403.1311.v1
Hu, X.; Jeon, W.; Rhee, S. Research on Weed and Crop Identification System Using Pixel-Wise Segmentation. Preprints2024, 2024031311. https://doi.org/10.20944/preprints202403.1311.v1
APA Style
Hu, X., Jeon, W., & Rhee, S. (2024). Research on Weed and Crop Identification System Using Pixel-Wise Segmentation. Preprints. https://doi.org/10.20944/preprints202403.1311.v1
Chicago/Turabian Style
Hu, X., Wang-su Jeon and Sang-Yong Rhee. 2024 "Research on Weed and Crop Identification System Using Pixel-Wise Segmentation" Preprints. https://doi.org/10.20944/preprints202403.1311.v1
Abstract
Deep learning is widely used in image segmentation, effectively identifying crops and weeds and contributing to the reduction of herbicide use. Traditional methods of applying pesticides over large areas are inefficient in dealing with weeds as needed, leading to massive waste of pesticides, high-cost production, and serious environmental pollution. This affects crop yield and quality. Although weed recognition using conventional deep learning methods has evolved over time, there are still challenges in weed extraction, detection, and segmentation. Accurate recognition and detection of weeds are essential prerequisites for implementing variable spraying. This paper proposes a semantic segmentation method based on UNet++ for complex environments where accurate identification of plants and weeds is challenging, targeting weeds in sugar beets, peas, and rice. An attention module is integrated into the upsampling process of UNet++, and UNet++ is used as a backbone network to effectively integrate multi-scale information, efficiently suppressing external noise interference. The UNet++ model with an integrated attention mechanism module achieves higher IOU than the general UNet++ model used in medical image analysis. This method effectively detects crops and weeds in complex backgrounds, providing reference material for the accurate application of robotic herbicides.
Keywords
Semantic Segmentation; Weed Recognition; Deep Learning; Image Recognition; Machine Vision
Subject
Computer Science and Mathematics, Computer Science
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
