Strawberry plant wetness detection using computer vision and deep learning

Patel, Arth; Lee, Won Suk; Peres, Natália A.; Fraisse, Clyde W.

doi:10.1016/j.atech.2021.100013

Cited by 10 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SAS’s GCREC weather station uses calibrated leaf wetness sensors to detect leaf wetness, and this station was located approximately 5 m away from the system used in this study. A comparison between the leaf wetness sensor method and the imaging-based method was made in [ 11 ], which explains the differences in the results.…”

Section: Discussionmentioning

confidence: 99%

“…A CNN usually performs better in image classification problems when a large amount of data are available. In addition, previous studies [ 11 , 13 ] have tried image processing and other approaches using color and thermal images, but those techniques had limitations and did not yield promising results. Hence, a CNN was a preferred choice for our task.…”

Section: Methodsmentioning

confidence: 99%

“…A feasibility study was carried out to detect leaf wetness using an imaging-based device [ 11 ]. This study concluded that a device could be made that takes images of a reference surface, and using a pre-trained convolutional neural network model, the images can be classified into wet/dry categories.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry

Patel

Lee

Peres

2022

Sensors

Self Cite

View full text Add to dashboard Cite

The Strawberry Advisory System (SAS) is a tool developed to help Florida strawberry growers determine the risk of common fungal diseases and the need for fungicide applications. Leaf wetness duration (LWD) is one of the important parameters in SAS disease risk modeling. By accurately measuring the LWD, disease risk can be better assessed, leading to less fungicide use and more economic benefits to the farmers. This research aimed to develop and test a more accurate leaf wetness detection system than traditional leaf wetness sensors. In this research, a leaf wetness detection system was developed and tested using color imaging of a reference surface and a convolutional neural network (CNN), which is one of the artificial-intelligence-based learning methods. The system was placed at two separate field locations during the 2021–2022 strawberry-growing season. The results from the developed system were compared against manual observation to determine the accuracy of the system. It was found that the AI- and imaging-based system had high accuracy in detecting wetness on a reference surface. The developed system can be used in SAS for determining accurate disease risks and fungicide recommendations for strawberry production and allows the expansion of the system to multiple locations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry

Patel

Lee

Peres

2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Correct disease identification is essential to applying correct products and thus the reduction or elimination of the disease or pest in the plantation, sometimes requiring specialized professionals or previous knowledge from the farmer. In addition, some identification processes must take samples and send them to the laboratory for analysis, consuming more time, leaving the farm unprotected, and allowing disease to spread across other parts [ 6 ]. Alternatively, researchers have begun investigating new methods based on Artificial Intelligence and mobile devices, seeking to develop accurate and reliable methods for disease detection.…”

Section: Introductionmentioning

confidence: 99%

“…Disease identification tasks use Deep Neural Networks, and several applications have been developed to improve the detection and correctness of the disease on the plantation. In addition, thermal cameras to detect the humidity and prediction of disease on leaves [ 6 ], classification of soil conditions [ 23 ], and automatic irrigation of the plantation [ 24 ] already were proposed.…”

Section: Introductionmentioning

confidence: 99%

Smart Strawberry Farming Using Edge Computing and IoT

Cruz

Mafra

Teixeira

et al. 2022

Sensors

View full text Add to dashboard Cite

Strawberries are sensitive fruits that are afflicted by various pests and diseases. Therefore, there is an intense use of agrochemicals and pesticides during production. Due to their sensitivity, temperatures or humidity at extreme levels can cause various damages to the plantation and to the quality of the fruit. To mitigate the problem, this study developed an edge technology capable of handling the collection, analysis, prediction, and detection of heterogeneous data in strawberry farming. The proposed IoT platform integrates various monitoring services into one common platform for digital farming. The system connects and manages Internet of Things (IoT) devices to analyze environmental and crop information. In addition, a computer vision model using Yolo v5 architecture searches for seven of the most common strawberry diseases in real time. This model supports efficient disease detection with 92% accuracy. Moreover, the system supports LoRa communication for transmitting data between the nodes at long distances. In addition, the IoT platform integrates machine learning capabilities for capturing outliers in collected data, ensuring reliable information for the user. All these technologies are unified to mitigate the disease problem and the environmental damage on the plantation. The proposed system is verified through implementation and tested on a strawberry farm, where the capabilities were analyzed and assessed.

show abstract