Deep count: Fruit counting based on deep simulated learning

Simple item page
dc.contributor.authorRahnemoonfar, Maryam
dc.contributor.authorSheppard, Clay
dc.date.accessioned2021-10-28T19:14:51Z
dc.date.available2021-10-28T19:14:51Z
dc.date.issued2017-04-20
dc.description.abstractRecent years have witnessed significant advancement in computer vision research based on deep learning. Success of these tasks largely depends on the availability of a large amount of training samples. Labeling the training samples is an expensive process. In this paper, we present a simulated deep convolutional neural network for yield estimation. Knowing the exact number of fruits, flowers, and trees helps farmers to make better decisions on cultivation practices, plant disease prevention, and the size of harvest labor force. The current practice of yield estimation based on the manual counting of fruits or flowers by workers is a very time consuming and expensive process and it is not practical for big fields. Automatic yield estimation based on robotic agriculture provides a viable solution in this regard. Our network is trained entirely on synthetic data and tested on real data. To capture features on multiple scales, we used a modified version of the Inception-ResNet architecture. Our algorithm counts efficiently even if fruits are under shadow, occluded by foliage, branches, or if there is some degree of overlap amongst fruits. Experimental results show a 91% average test accuracy on real images and 93% on synthetic images.en_US
dc.description.abstractRecent years have witnessed significant advancement in computer vision research based on deep learning. Success of these tasks largely depends on the availability of a large amount of training samples. Labeling the training samples is an expensive process. In this paper, we present a simulated deep convolutional neural network for yield estimation. Knowing the exact number of fruits, flowers, and trees helps farmers to make better decisions on cultivation practices, plant disease prevention, and the size of harvest labor force. The current practice of yield estimation based on the manual counting of fruits or flowers by workers is a very time consuming and expensive process and it is not practical for big fields. Automatic yield estimation based on robotic agriculture provides a viable solution in this regard. Our network is trained entirely on synthetic data and tested on real data. To capture features on multiple scales, we used a modified version of the Inception-ResNet architecture. Our algorithm counts efficiently even if fruits are under shadow, occluded by foliage, branches, or if there is some degree of overlap amongst fruits. Experimental results show a 91% average test accuracy on real images and 93% on synthetic images.
dc.identifier.citationRahnemoonfar, M. and Sheppard, C., 2017. Deep count: fruit counting based on deep simulated learning. Sensors, 17(4), p.905.en_US
dc.identifier.citationRahnemoonfar, M. and Sheppard, C., 2017. Deep count: fruit counting based on deep simulated learning. Sensors, 17(4), p.905.
dc.identifier.doihttps://doi.org/10.3390/s17040905
dc.identifier.urihttps://hdl.handle.net/1969.6/89918
dc.language.isoen_USen_US
dc.language.isoen_US
dc.publisherMDPIen_US
dc.publisherMDPI
dc.rightsAttribution 4.0 International*
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectdeep-learningen_US
dc.subjectagricultural sensorsen_US
dc.subjectsimulated learningen_US
dc.subjectyield estimationen_US
dc.subjectdeep-learning
dc.subjectagricultural sensors
dc.subjectsimulated learning
dc.subjectyield estimation
dc.titleDeep count: Fruit counting based on deep simulated learningen_US
dc.titleDeep count: Fruit counting based on deep simulated learning
dc.typeArticleen_US
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Rahnemoonfar_Maryam_sensors.pdf
Size:
18.91 MB
Format:
Adobe Portable Document Format
Description:
Article
Download

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

COE Faculty Works