Machine Learning Approaches for Rice Seedling Growth Stages Detection

Suiyan Tan, Jingbin Liu, Henghui Lu, Maoyang Lan, Jie Yu, Guanzhong Liao, Yuwei Wang, Zehua Li, Long Qi, Xu MaFrontiers in Plant Science 2022 · DOI

Abstract

Recognizing rice seedling growth stages to timely do field operations, such as temperature control, fertilizer, irrigation, cultivation, and disease control, is of great significance of crop management, provision of standard and well-nourished seedlings for mechanical transplanting, and increase of yield. Conventionally, rice seedling growth stage is performed manually by means of visual inspection, which is not only labor-intensive and time-consuming, but also subjective and inefficient on a large-scale field. The application of machine learning algorithms on UAV images offers a high-throughput and non-invasive alternative to manual observations. This paper presented automatic approaches to detect rice seedling of three critical stages, BBCH11, BBCH12, and BBCH13. Both traditional machine learning algorithms (HOG-SVM) and deep learning algorithms (CNNs) were investigated. EfficientnetB4 achieved the best performance with 99.47% accuracy.

Introduction

In commercial rice farming, seedlings are raised in nursery trays before being transplanted into paddies. The timing of this transplanting is narrow and critical; doing it too early or too late can drastically reduce grain yield. Farmers use the BBCH scale (a decimal system for plant development) to track growth, specifically focusing on stages BBCH11 through BBCH13, which correspond to the unfolding of the first three leaves.

Traditionally, monitoring these stages relies on manual visual inspection. On a large scale, this process is labor-intensive, slow, and prone to human subjectivity. While remote sensing via Unmanned Aerial Vehicles (UAVs) offers a potential solution, the visual similarity between these early growth stages makes automated classification a significant computer vision challenge. This study aims to develop a high-throughput method using drone imagery and machine learning to automatically detect these critical growth stages.

Methodology

The researchers compared two distinct pipelines for image classification: traditional machine learning using Histograms of Oriented Gradients (HOG) with Support Vector Machines (SVM), and modern deep learning using Convolutional Neural Networks (CNNs).

Schematic diagram of the proposed method for rice seedling growth stage detection.

Data Acquisition and Experimental Design

Images were captured using a DJI Phantom 4 RTK drone flying vertically downward at a height of 3 meters. This provided a high ground sampling distance of 0.08 cm/pixel. The study site was located in Zhaoqing, Guangdong Province, China.

Study site location and experimental field design including cultivars and sowing dates.

The dataset was designed to be comprehensive, accounting for various field conditions:

  • Cultivars: Three different rice varieties (Guang8you2156, Huahang No57, and Huahang No51).
  • Densities: Five different nursing seedling densities ranging from 35 to 120 g/tray.
  • Temporal Range: Images were captured across different sowing dates in March 2021 to ensure representation of all three target growth stages.

Classification Models

  1. HOG-SVM: This traditional approach involved extracting texture and shape features using HOG, which counts gradient orientations in localized image portions. These features were then classified using an SVM optimized via grid search for hyperparameters.
  2. Deep Learning (CNNs): The team utilized transfer learning, fine-tuning models pre-trained on ImageNet. Architectures tested included VGG16, ResNet50, DenseNet121, and the EfficientNet family (B0-B7).

Results and Discussion

The experimental results demonstrated a clear superiority of deep learning approaches over traditional machine learning for this specific task.

Model Performance

  • Top Performer: EfficientNetB4 was the most effective model, achieving a near-perfect accuracy of 99.47%, with corresponding high precision (99.53%) and F1 score (99.46%).
  • Traditional ML: The best HOG-SVM model reached an accuracy of 84.9%. While useful, it lacks the reliability required for fully autonomous systems.
  • Architecture Comparison: Within the CNN category, EfficientNetB4 outperformed DenseNet121 (99.06%), ResNet50 (98.97%), and VGG16 (94.84%).

Key Insights

  • The "Adjacent Stage" Difficulty: Distinguishing between BBCH12 and BBCH13 proved to be the most significant challenge. Overlapping leaves and structural similarities made it difficult for HOG features to establish a clear boundary, leading to higher error rates in the SVM model.
  • Resolution Sweet Spot: For HOG-SVM, performance peaked at an input size of 400x400 pixels. Smaller images lacked detail, while larger ones introduced noise that hindered the traditional classifier.
  • Feature Engineering: Deep learning models succeeded because they automatically learn complex, hierarchical features. In contrast, hand-crafted HOG features may miss subtle biological nuances critical for distinguishing early growth stages.

Conclusion

This study confirms that UAV-based imagery combined with deep learning, specifically the EfficientNetB4 architecture, provides a highly accurate and efficient tool for detecting rice seedling growth stages. This high-throughput method offers a non-invasive alternative to manual observations, potentially revolutionizing large-scale crop management. Future work will focus on improving robustness against environmental factors such as varying light conditions and sensor angles.

Summary updated

Abstract

Recognizing rice seedling growth stages to timely do field operations, such as temperature control, fertilizer, irrigation, cultivation, and disease control, is of great significance of crop management, provision of standard and well-nourished seedlings for mechanical transplanting, and increase of yield. Conventionally, rice seedling growth stage is performed manually by means of visual inspection, which is not only labor-intensive and time-consuming, but also subjective and inefficient on a large-scale field. The application of machine learning algorithms on UAV images offers a high-throughput and non-invasive alternative to manual observations and its applications in agriculture and high-throughput phenotyping are increasing. This paper presented automatic approaches to detect rice seedling of three critical stages, BBCH11, BBCH12, and BBCH13. Both traditional machine learning algorithms and deep learning algorithms were investigated the discriminative ability of the three growth stages. UAV images were captured vertically downward at 3-m height from the field. A dataset consisted of images of three growth stages of rice seedlings for three cultivars, five nursing seedling densities, and different sowing dates. In the traditional machine learning algorithm, histograms of oriented gradients (HOGs) were selected as texture features and combined with the support vector machine (SVM) classifier to recognize and classify three growth stages. The best HOG-SVM model obtained the performance with 84.9, 85.9, 84.9, and 85.4% in accuracy, average precision, average recall, and F1 score, respectively. In the deep learning algorithm, the Efficientnet family and other state-of-art CNN models (VGG16, Resnet50, and Densenet121) were adopted and investigated the performance of three growth stage classifications. EfficientnetB4 achieved the best performance among other CNN models, with 99.47, 99.53, 99.39, and 99.46% in accuracy, average precision, average recall, and F1 score, respectively. Thus, the proposed method could be effective and efficient tool to detect rice seedling growth stages.
BibTeX
@inproceedings{tan2022machine,
  author = {Suiyan Tan and Jingbin Liu and Henghui Lu and Maoyang Lan and Jie Yu and Guanzhong Liao and Yuwei Wang and Zehua Li and Long Qi and Xu Ma},
  title = {{Machine Learning Approaches for Rice Seedling Growth Stages Detection}},
  booktitle = {Frontiers in Plant Science},
  year = {2022},
  doi = {10.3389/fpls.2022.914771},
}
Figure