Automated Agave Detection and Counting Using a Convolutional Neural Network and Unmanned Aerial Systems

Flores, Donovan; González-Hernández, I.; Lozano, Rogelio; Vazquez-Nicolas, J. M.; Toral, Jorge Luis Hernandez

doi:10.3390/drones5010004

Cited by 17 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Estimation of the agave area also improved with the deep learning algorithms; the estimation error was less than 40 m² when compared with the estimate obtained in the field (Table 1). The algorithm with the best overall precision and the lowest error in estimating agave area was OBIA, with an overall precision of 0.96, which is slightly better than that reported by Calvario et al (2020) andFlores et al (2021) for the detection of blue agave. The deep learning algorithms used in this study have the advantage that during the classification process they start from a distribution-free assumption; that is, no underlying model is assumed for the multivariate distribution of class-specific data in the feature space.…”

Section: Resultsmentioning

confidence: 67%

“…They found that the estimate of the number of plants identified automatically in the images had an overall precision between 0.830 and 0.980. Another recent study, also carried out with blue agave, was Flores et al (2021). They applied a convolutional neural network (CNN), in which patterns and textures are learned, and used to carry out automated counts in images taken from UAVs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison Of Algorithms For Agave Detection On Unmanned Aerial Vehicle Images

Escobar-Flores

Sandoval

Gámiz-Romero

2021

Preprint

View full text Add to dashboard Cite

In this study, six supervised classification algorithms were compared. The algorithms were based on cluster analysis, distance, deep learning and object-based image analysis. Our objective was to determine which of these algorithms has the highest overall accuracy in both detection and automated estimation of agave cover in a given area to help growers manage their plantations. An orthomosaic with a spatial resolution of 2.5 cm was derived from 300 images obtained with a DJI Inspire 1 unmanned aerial system. Two training classes were defined: 1) sites where the presence of agaves was identified, 2) “absence”; where there were no agaves but other plants were present. The object-oriented algorithm was found to have the highest overall accuracy (0.963), followed by the support-vector machine with 0.928 accuracy and the neural network with 0.914. The algorithms with statistical criteria for classification were the least accurate; Mahalanobis distance = 0.752 accuracy and minimum distance = 0.421. We recommend that agave plantation managers use drones for their efficiency and speed. We further recommend that the object-oriented algorithm be used, because in addition to having the highest overall accuracy for the image segmentation process, it yields parameters that are useful for estimating the coverage area, size, and shapes, which can aid in better selection of agave individuals for harvest.

show abstract

Section: Resultsmentioning

confidence: 67%

Section: Introductionmentioning

confidence: 99%

Comparison Of Algorithms For Agave Detection On Unmanned Aerial Vehicle Images

Escobar-Flores

Sandoval

Gámiz-Romero

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recent FCN applications are the classification of tree species based on high resolution UAV images with less than 1.6 cm ground sampling distance (GSD) [11]. For specific tasks such as the detection and counting of agave trees in plantations, CNN are able to reach F1-scores of 96% [12]. These tasks are also accomplished by directly segmenting 3D-point clouds with 3D-CNN [13].…”

Section: Related Researchmentioning

confidence: 99%

Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks

et al. 2021

View full text Add to dashboard Cite

The increasing number of severe storm events is threatening European forests. Besides the primary damages directly caused by storms, there are secondary damages such as bark beetle outbreaks and tertiary damages due to negative effects on the market. These subsequent damages can be minimized if a detailed overview of the affected area and the amount of damaged wood can be obtained quickly and included in the planning of clearance measures. The present work utilizes UAV-orthophotos and an adaptation of the U-Net architecture for the semantic segmentation and localization of windthrown stems. The network was pre-trained with generic datasets, randomly combining stems and background samples in a copy–paste augmentation, and afterwards trained with a specific dataset of a particular windthrow. The models pre-trained with generic datasets containing 10, 50 and 100 augmentations per annotated windthrown stems achieved F1-scores of 73.9% (S1Mod10), 74.3% (S1Mod50) and 75.6% (S1Mod100), outperforming the baseline model (F1-score 72.6%), which was not pre-trained. These results emphasize the applicability of the method to correctly identify windthrown trees and suggest the collection of training samples from other tree species and windthrow areas to improve the ability to generalize. Further enhancements of the network architecture are considered to improve the classification performance and to minimize the calculative costs.

show abstract

“…They observed that the accuracy of the algorithm was affected by variability in plant size in the field and lighting conditions, obtaining a range of accuracy from 83 to 98 %. Furthermore, Flores et al (2021) created a database of agave plant images and performed automatic plant detection and counting using a CNN applied to RGB images captured by RPAS at an altitude of 50 m, achieving an accuracy of 96 %, but with a high computational cost. According to the review, the trend to implement DL techniques on sets of images acquired by RPAS in agriculture is reaffirmed.…”

Section: Introductionmentioning

confidence: 99%

Agave Plant Density Using Convolutional Neural Networks on Aerial Imagery

Espinoza-Hernández,

López-Canteñs,

López-Cruz

et al. 2023

agro

View full text Add to dashboard Cite

Agave plants (Agave tequilana Weber) are an indispensable element in the tequila production chain. Traditionally, plantation monitoring has been done manually; however, having accurate information on agave inventories is crucial for planning and estimating production volume. In this context, it was proposed that deep learning algorithms can achieve high detection rates of agave plants, improving the management and control of plantations. For this purpose, YOLOv4 and YOLOv4-tiny convolutional algorithms were implemented and evaluated using high-resolution RGB aerial images captured by a remotely piloted aircraft system for the determination of agave plant density. Three flight plans were planned and carried out, with ground sampling distances of 1.10, 1.64, and 2.19 cm pixel-1, respectively. The database was created, and the algorithms were evaluated for a confidence level of 0.25 and an intersection threshold over the junction of 0.50. The results showed an average mean accuracy of 0.99 for both algorithms and an F1 score of 0.95 for YOLOv4 and 0.96 for YOLOv4-tiny. Furthermore, a high detection rate (Rc) of 99 % and precision values (Pr) between 90 and 92 % were obtained. A decrease in the performance of the algorithms was observed when detecting agave tillers in images with a spatial resolution of 2.19 cm pixel-1. The implemented YOLO convolutional algorithms proved to be highly robust and able to generalize agave plant characteristics at different phenological stages, allowing accurate detections. In addition, the coordinates of the detected plants were used to estimate the distance between them, with a maximum error of 20 cm.

show abstract

Automated Agave Detection and Counting Using a Convolutional Neural Network and Unmanned Aerial Systems

Cited by 17 publications

References 32 publications

Comparison Of Algorithms For Agave Detection On Unmanned Aerial Vehicle Images

Comparison Of Algorithms For Agave Detection On Unmanned Aerial Vehicle Images

Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks

Agave Plant Density Using Convolutional Neural Networks on Aerial Imagery

Contact Info

Product

Resources

About