Plant Stress Detection Using a Three-Dimensional Analysis from a Single RGB Image
Authors:
- Madaín Pérez-PatricioMPMadaín Pérez-Patricio
- J. A. de Jesús Osuna-CoutiñoJOJ. A. de Jesús Osuna-Coutiño
- German Ríos-ToledoGRGerman Ríos-Toledo
- Abiel Aguilar-GonzálezAAAbiel Aguilar-González
- J. L. Camas-AnzuetoJCJ. L. Camas-Anzueto
- N. A. Morales-NavarroNMN. A. Morales-Navarro
- J. Renán Velázquez-GonzálezJVJ. Renán Velázquez-González
- Luis Ángel Cundapí-LópezLCLuis Ángel Cundapí-López
Open Access
Abstract
Plant stress detection involves the process of Identification, Classification, Quantification, and Prediction (ICQP) in crop stress. Numerous approaches exist for plant stress identification; however, a majority rely on expert personnel or invasive techniques. While expert employees demonstrate proficiency across various plants, this approach demands a substantial workforce to ensure the quality of crops. Conversely, invasive techniques entail leaf dismemberment. To overcome these challenges, an alternative is to employ image processing to interpret areas where plant geometry is observable, eliminating the dependency on skilled labor or the need for crop dismemberment. However, this alternative introduces the challenge of accurately interpreting ambiguous image features. Motivated by the latter, we propose a methodology for plant stress detection using 3D reconstruction and deep learning from a single RGB image. For that, our methodology has three steps. First, the plant recognition step provides the segmentation, location, and delimitation of the crop. Second, we propose a leaf detection analysis to classify and locate the boundaries between the different leaves. Finally, we use a Deep Neural Network (DNN) and the 3D reconstruction for plant stress detection. Experimental results are encouraging, showing that our approach has high performance under real-world scenarios. Also, the proposed methodology has 22.86% higher precision, 24.05% higher recall, and 23.45% higher F1-score than the 2D classification method.Keywords
Funding Information
- Consejo Nacional de Humanidades, Ciencias y Tecnologías (CONAHCyT)
This publication has 52 references indexed in Scilit:
- Plant Stress Recognition Using Deep Learning and 3D Reconstruction2023
- Identification of olive leaf disease through optimized deep learning approachAlexandria Engineering Journal, 2023
- Recent advances in agricultural disease image recognition technologies: A reviewConcurrency and Computation: Practice and Experience, 2023
- Reliable and Accurate Plant Leaf Disease Detection with Treatment Suggestions Using Enhanced Deep Learning TechniquesSN Computer Science, 2023
- Optimized classification model for plant diseases using generative adversarial networksInnovations in Systems and Software Engineering, 2022
- Nanotechnology as a tool for abiotic stress mitigation in horticultural cropsBiologia, 2022
- Bioanalytical approaches for the detection, characterization, and risk assessment of micro/nanoplastics in agriculture and food systemsAnalytical and Bioanalytical Chemistry, 2022
- Volumetric structure extraction in a single imageThe Visual Computer, 2021
- A New Performance Evaluation Metric for Classifiers: Polygon Area MetricJournal of Classification, 2020
- The adoption of automated phenotyping by plant breedersEuphytica, 2018