• Home
  • Search
  • Enhancing Green Fraction Estimation in Rice and Wheat Crops: A Self-Supervised Deep Learning Semantic Segmentation Approach.
  • Cite Icon30
  • https://doi.org/10.34133/plantphenomics.0064Copy DOI Icon

Enhancing Green Fraction Estimation in Rice and Wheat Crops: A Self-Supervised Deep Learning Semantic Segmentation Approach.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The green fraction (GF), which is the fraction of green vegetation in a given viewing direction, is closely related to the light interception ability of the crop canopy. Monitoring the dynamics of GF is therefore of great interest for breeders to identify genotypes with high radiation use efficiency. The accuracy of GF estimation depends heavily on the quality of the segmentation dataset and the accuracy of the image segmentation method. To enhance segmentation accuracy while reducing annotation costs, we developed a self-supervised strategy for deep learning semantic segmentation of rice and wheat field images with very contrasting field backgrounds. First, the Digital Plant Phenotyping Platform was used to generate large, perfectly labeled simulated field images for wheat and rice crops, considering diverse canopy structures and a wide range of environmental conditions (sim dataset). We then used the domain adaptation model cycle-consistent generative adversarial network (CycleGAN) to bridge the reality gap between the simulated and real images (real dataset), producing simulation-to-reality images (sim2real dataset). Finally, 3 different semantic segmentation models (U-Net, DeepLabV3+, and SegFormer) were trained using 3 datasets (real, sim, and sim2real datasets). The performance of the 9 training strategies was assessed using real images captured from various sites. The results showed that SegFormer trained using the sim2real dataset achieved the best segmentation performance for both rice and wheat crops (rice: Accuracy=0.940, F1-score=0.937; wheat: Accuracy=0.952, F1-score=0.935). Likewise, favorable GF estimation results were obtained using the above strategy (rice: R2=0.967, RMSE=0.048; wheat: R2=0.984, RMSE=0.028). Compared with SegFormer trained using a real dataset, the optimal strategy demonstrated greater superiority for wheat images than for rice images. This discrepancy can be partially attributed to the differences in the backgrounds of the rice and wheat fields. The uncertainty analysis indicated that our strategy could be disrupted by the inhomogeneity of pixel brightness and the presence of senescent elements in the images. In summary, our self-supervised strategy addresses the issues of high cost and uncertain annotation accuracy during dataset creation, ultimately enhancing GF estimation accuracy for rice and wheat field images. The best weights we trained in wheat and rice are available: https://github.com/PheniX-Lab/sim2real-seg.

Similar Papers
  • Research Article
  • Citations19

Exopolysaccharides of Xanthomonas pathovar strains that infect rice and wheat crops.

  • Jun 01, 2001
  • Applied microbiology and biotechnology
  • R Sunish Kumar +1
  • Research Article
  • Citations42

Estimation of root zone soil moisture using passive microwave remote sensing: A case study for rice and wheat crops for three states in the Indo-Gangetic basin

  • Jan 04, 2019
  • Journal of Environmental Management
  • Anudeep Sure +1
  • Research Article

Rates and Methods of Rice Straw Application to Wheat and Rice Crops and the Implications on Crop Productivity as Well as some Soil Properties

  • Mar 30, 2014
  • Egyptian Journal of Soil Science
  • Ashraf Mohamed Gouda Taha Oweis
  • PDF
  • Research Article
  • Citations1

Relevancy between Objects Based on Common Sense for Semantic Segmentation

  • Dec 11, 2022
  • Applied Sciences
  • Jun Zhou +2
  • Research Article
  • Citations7

Research on defect pattern recognition of Light Guide Plate based on Deep Learning semantic Segmentation

  • Apr 01, 2021
  • Journal of Physics: Conference Series
  • Linlin Liu +2
  • Conference Article
  • Citations3

Real-time semantic segmentation on edge devices: A performance comparison of segmentation models

  • Oct 19, 2022
  • Myeongseok Lee +2
  • Research Article
  • Citations3

Self-supervised semantic segmentation of retinal pigment epithelium cells in flatmount fluorescent microscopy images

  • Apr 03, 2023
  • Bioinformatics
  • Hanyi Yu +6
  • Supplementary Content
  • Citations36

Rice and Wheat Crop Productivity in the Indo-Gangetic Plains of India: Changing Pattern of Growth and Future Strategies

  • Jan 01, 2012
  • Indian journal of agricultural economics
  • I Sekar +1
  • Research Article
  • Citations17

Management of Insect, Disease, and Nematode Pests of Rice and Wheat in the Indo-Gangetic Plains

  • Mar 01, 2001
  • Journal of Crop Production
  • M Sehgal +2
  • Research Article
  • Citations14

Derivation of human health risk-based thresholds for lead in soils promote the production of safer wheat and rice

  • Dec 28, 2021
  • Ecotoxicology and Environmental Safety
  • Yang Yang +5
  • Research Article
  • Citations53

Differential allelopathic potential of sunflower (Helianthus annuus L.) genotypes on weeds and wheat (Triticum aestivum L.) crop

  • Oct 01, 2012
  • Archives of Agronomy and Soil Science
  • Ibrahim S Alsaadawi +2
  • Research Article
  • Citations48

PeriorbitAI: Artificial Intelligence Automation of Eyelid and Periorbital Measurements

  • May 16, 2021
  • American Journal of Ophthalmology
  • Alexandra Van Brummen +10
  • Conference Article
  • Citations1

The Effect of Input Size in Deep Learning Semantic Segmentation

  • Oct 11, 2022
  • Esther Parra-Mora +2
  • Preprint Article

Deep Learning-Based Semantic Segmentation in Autonomous Driving

  • Feb 22, 2024
  • Hrag-Harout Jebamikyous
  • Conference Article
  • Citations3

Improvements of numerical weather predictions using a new AVHRR green vegetation fraction dataset

  • Aug 28, 2008
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Yuhong Tian +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.