A Weakly Supervised Semantic Segmentation Model of Maize Seedlings and Weed Images Based on Scrawl Labels
Sensors · 2023
DOI: 10.3390/s23249846 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Lulu Zhao und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China. Hauptthemen laut MEDLINE: Seedlings, Zea mays. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Sub-project of the Fourteenth-Five Year National Key R&D Plan, Sub-project of National Key R&D Plan.
Abstract (Originalsprache)
The task of semantic segmentation of maize and weed images using fully supervised deep learning models requires a large number of pixel-level mask labels, and the complex morphology of the maize and weeds themselves can further increase the cost of image annotation. To solve this problem, we proposed a Scrawl Label-based Weakly Supervised Semantic Segmentation Network (SL-Net). SL-Net consists of a pseudo label generation module, encoder, and decoder. The pseudo label generation module converts scrawl labels into pseudo labels that replace manual labels that are involved in network training, improving the backbone network for feature extraction based on the DeepLab-V3+ model and using a migration learning strategy to optimize the training process. The results show that the intersection over union of the pseudo labels that are generated by the pseudo label module with the ground truth is 83.32%, and the cosine similarity is 93.55%. In the semantic segmentation testing of SL-Net for image seedling of maize plants and weeds, the mean intersection over union and average precision reached 87.30% and 94.06%, which is higher than the semantic segmentation accuracy of DeepLab-V3+ and PSPNet under weakly and fully supervised learning conditions. We conduct experiments to demonstrate the effectiveness of the proposed method.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China.
- Liaoning Agricultural Informatization Engineering Technology Research Center, Shenyang 110866, China.
Förderung
- National Natural Science Foundation of China
- Sub-project of the Fourteenth-Five Year National Key R&D Plan
- Sub-project of National Key R&D Plan
- Liaoning Province Innovation Capability Enhancement Joint Fund Project
- Sub-project of the Fourteenth-Five Year National Key R&D Plan
- Sub-project of National Key R&D Plan
Zitieren
APA
Zhao, L., Zhao, Y., Liu, T., & Deng, H. (2023). A Weakly Supervised Semantic Segmentation Model of Maize Seedlings and Weed Images Based on Scrawl Labels. Sensors. https://doi.org/10.3390/s23249846
Vancouver
Zhao L, Zhao Y, Liu T, Deng H. A Weakly Supervised Semantic Segmentation Model of Maize Seedlings and Weed Images Based on Scrawl Labels. Sensors. 2023. doi:10.3390/s23249846
BibTeX
@article{Zhao2023,
author = {Zhao, Lulu and Zhao, Yanan and Liu, Ting and Deng, Hanbing},
title = {A Weakly Supervised Semantic Segmentation Model of Maize Seedlings and Weed Images Based on Scrawl Labels},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23249846}
}
EUVIMED