Machine Learning Approaches for Rice Seedling Growth Stages Detection

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.

Method for inspection of atmospheric discharge protection systems: Grain storage plants

“…Several studies have been developed on the use of RPAS in transmission line inspections, with a focus on the development and application of techniques for optimal route identification and autonomous insulator inspection, which provides greater agility to the process (Ma et al, 2021;Ahmed et al, 2022;Yin et al, 2022); b) Civil construction -there are several reports, among them the application of deep learning methods associated with image capture techniques in the automation of defect evaluation due to moisture in structures, models for detecting and evaluating cracks in tanks, an inspection of pathological manifestations, and cracks in facades with ceramic cladding and investigation procedures for traditional wood structures (Jeong et al, 2020;Liu et al, 2020;Martinez et al, 2020;Wu et al, 2020); c) Agriculture and other areas -in the agricultural sector, the use of RPAS has been gaining space in the performance of several activities, such as geomapping, pest control, and soil analysis, among other applications, mainly due to its operating characteristics, which allow the development of non-destructive analysis of the terrain in a shorter time. Tan et al (2022) addressed in their research the combination of UAV (Unmanned Aerial Vehicle) technologies and machine learning algorithms to explore efficient ways to detect the three main growth stages of rice seedlings.…”

An Overview of Machine Learning Applications on Plant Phenotyping, with a Focus on Sunflower

“…As shown in Figure 8, an automated ML was employed for binary classification "lodged" or "nonlodged" (image classification) and prediction of lodging score (image regression) [165,166]. CNN performance far exceeds that of traditional ML approaches, e.g., SVM, and it was demonstrated, for example, in rice seedling growth stage recognition [167].…”

Progress in the Application of CNN-Based Image Classification and Recognition in Whole Crop Growth Cycles

“…Another study utilized a GL-CNN model to classify red phoenix vegetables based on leaf images during the growth period [69]. Tan et al [70] achieved the automatic detection of rice seedlings at different varieties, seedling densities, and sowing dates using EfficientnetB4, with an accuracy of 99.47%.…”