A review of machine learning techniques for identifying weeds in corn

Venkataraju, Akhil; Arumugam, Dharanidharan; Stepan, Calvin; Kiran, Ravi; Peters, Thomas

doi:10.1016/j.atech.2022.100102

Cited by 26 publications

(9 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They trained an SVM model to differentiate the monocotyledon weeds, Ageratum conyzoides, and Amaranthus palmeri weeds from other weeds for selective spraying. Many other studies have also utilized the different versions of SVMs and discussed their advantages [60,61].…”

Section: Support Vector Classificationmentioning

confidence: 99%

Image-to-Image Translation-Based Data Augmentation for Improving Crop/Weed Classification Models for Precision Agriculture Applications

et al. 2022

View full text Add to dashboard Cite

Applications of deep-learning models in machine visions for crop/weed identification have remarkably upgraded the authenticity of precise weed management. However, compelling data are required to obtain the desired result from this highly data-driven operation. This study aims to curtail the effort needed to prepare very large image datasets by creating artificial images of maize (Zea mays) and four common weeds (i.e., Charlock, Fat Hen, Shepherd’s Purse, and small-flowered Cranesbill) through conditional Generative Adversarial Networks (cGANs). The fidelity of these synthetic images was tested through t-distributed stochastic neighbor embedding (t-SNE) visualization plots of real and artificial images of each class. The reliability of this method as a data augmentation technique was validated through classification results based on the transfer learning of a pre-defined convolutional neural network (CNN) architecture—the AlexNet; the feature extraction method came from the deepest pooling layer of the same network. Machine learning models based on a support vector machine (SVM) and linear discriminant analysis (LDA) were trained using these feature vectors. The F1 scores of the transfer learning model increased from 0.97 to 0.99, when additionally supported by an artificial dataset. Similarly, in the case of the feature extraction technique, the classification F1-scores increased from 0.93 to 0.96 for SVM and from 0.94 to 0.96 for the LDA model. The results show that image augmentation using generative adversarial networks (GANs) can improve the performance of crop/weed classification models with the added advantage of reduced time and manpower. Furthermore, it has demonstrated that generative networks could be a great tool for deep-learning applications in agriculture.

show abstract

Section: Support Vector Classificationmentioning

confidence: 99%

Image-to-Image Translation-Based Data Augmentation for Improving Crop/Weed Classification Models for Precision Agriculture Applications

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Different from the approach in previous work [ 40 ], this research does not focus on developing a novel classification algorithm, which is why the well-established U-Net architecture was employed for weed segmentation. The U-Net’s strong feature learning capabilities and automatic feature extraction allow for easy scaling to new datasets, making it highly suitable for real-world applications [ 10 , 22 , 41 ]. The pixel-based classifications generated by this dense semantic segmentation framework serve as a valuable data source for autonomous weed control based on precise localization information.…”

Section: Introductionmentioning

confidence: 99%

Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors

Seiche,

Wittstruck,

Jarmer

2024

Sensors

View full text Add to dashboard Cite

In order to meet the increasing demand for crops under challenging climate conditions, efficient and sustainable cultivation strategies are becoming essential in agriculture. Targeted herbicide use reduces environmental pollution and effectively controls weeds as a major cause of yield reduction. The key requirement is a reliable weed detection system that is accessible to a wide range of end users. This research paper introduces a self-built, low-cost, multispectral camera system and evaluates it against the high-end MicaSense Altum system. Pixel-based weed and crop classification was performed on UAV datasets collected with both sensors in maize using a U-Net. The training and testing data were generated via an index-based thresholding approach followed by annotation. As a result, the F1-score for the weed class reached 82% on the Altum system and 76% on the low-cost system, with recall values of 75% and 68%, respectively. Misclassifications occurred on the low-cost system images for small weeds and overlaps, with minor oversegmentation. However, with a precision of 90%, the results show great potential for application in automated weed control. The proposed system thereby enables sustainable precision farming for the general public. In future research, its spectral properties, as well as its use on different crops with real-time on-board processing, should be further investigated.

show abstract

“…Ruiz, Trasviña, Rojas. Detección de enfermedades en cultivos de maíz mediante imágenes con visión artificial: un caso práctico Para generar entornos de diagnóstico con IA se ha generado investigación continuamente como lo expuesto por (Venkataraju, et al, 2023) quienes plantean el estudio de las investigaciones existentes con uso de modelos de aprendizaje automático para identificar tipos de maleza en los cultivos. Los autores buscaron aquellas aplicaciones que realizan una correcta clasificación e intervención de crecimientos de hierba invasora.…”

Section: Introductionunclassified

Detección de enfermedades en cultivos de maíz mediante imágenes con visión artificial: un caso práctico

José Ruiz,

Jazmín Trasviña,

Erick Rojas

2024

Rev.Cienc.Tecnol.

View full text Add to dashboard Cite

En México y el mundo, el maíz es una de las plantas más susceptible a padecimientos graves que afectan su desarrollo y el rendimiento de la semilla. Factores como el cambio climático y la llegada poco común de insectos vectores en la actualidad han propiciado que los patógenos que afectan este tipo de cultivos se vuelvan más resistentes. Tener la certeza del tipo de enfermedad que afecta a las plantas es importante en la agricultura ya que genera una mejor toma de decisiones sobre la actuación previa a afectaciones graves. En la actualidad se estima que el 65% del sector agrícola no cuenta con tecnología aplicada a la sanidad vegetal. Se ha trabajado constantemente en el desarrollo de herramientas de visión artificial, procesamiento digital de imágenes y aprendizaje automático para realizar diagnósticos de enfermedades en cultivos. El presente estudio brinda una perspectiva reciente de los avances tecnológicos en la detección de enfermedades en cultivos, su eficiencia y la relación con la búsqueda de la construcción de un sector agrícola productivo y sustentable. Se muestra además un caso de aplicación de detección de enfermedades comunes en cultivos del centro de México, donde se logró un error de identificación mínimo

show abstract

A review of machine learning techniques for identifying weeds in corn

Cited by 26 publications

References 57 publications

Image-to-Image Translation-Based Data Augmentation for Improving Crop/Weed Classification Models for Precision Agriculture Applications

Image-to-Image Translation-Based Data Augmentation for Improving Crop/Weed Classification Models for Precision Agriculture Applications

Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors

Detección de enfermedades en cultivos de maíz mediante imágenes con visión artificial: un caso práctico

Contact Info

Product

Resources

About