Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland

Simple item page
dc.contributor.authorPashaei, Mohammad
dc.contributor.authorKamangir, Hamid
dc.contributor.authorStarek, Michael J.
dc.contributor.authorTissot, Philippe
dc.contributor.authorPashaei, Mohammad
dc.contributor.authorKamangir, Hamid
dc.contributor.authorStarek, Michael J.
dc.contributor.authorTissot, Philippe
dc.creator.orcidhttps://orcid.org/0000-0002-1427-6265
dc.creator.orcidhttps://orcid.org/0000-0001-9718-7518
dc.creator.orcidhttps://orcid.org/0000-0002-7996-0594
dc.creator.orcidhttps://orcid.org/0000-0002-2954-2378
dc.creator.orcidhttps://orcid.org/0000-0002-1427-6265
dc.creator.orcidhttps://orcid.org/0000-0001-9718-7518
dc.creator.orcidhttps://orcid.org/0000-0002-7996-0594
dc.creator.orcidhttps://orcid.org/0000-0002-2954-2378
dc.date.accessioned2020-04-30T21:35:56Z
dc.date.accessioned2020-04-30T21:35:56Z
dc.date.available2020-04-30T21:35:56Z
dc.date.available2020-04-30T21:35:56Z
dc.date.issued2020-01-24
dc.date.issued2020-01-242020-01-24
dc.date.issued2020-01-24
dc.description.abstractDeep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional sensor and platform for acquiring high spatial and high temporal resolution data with high operational flexibility. Coastal wetlands are among some of the most challenging and complex ecosystems for land cover prediction and mapping tasks because land cover targets often show high intra-class and low inter-class variances. In recent years, several deep convolutional neural network (CNN) architectures have been proposed for pixel-wise image labeling, commonly called semantic image segmentation. In this paper, some of the more recent deep CNN architectures proposed for semantic image segmentation are reviewed, and each model’s training efficiency and classification performance are evaluated by training it on a limited labeled image set. Training samples are provided using the hyper-spatial resolution UAS imagery over a wetland area and the required ground truth images are prepared by manual image labeling. Experimental results demonstrate that deep CNNs have a great potential for accurate land cover prediction task using UAS hyper-spatial resolution images. Some simple deep learning architectures perform comparable or even better than complex and very deep architectures with remarkably fewer training epochs. This performance is especially valuable when limited training samples are available, which is a common case in most RS applications.en_US
dc.description.abstractDeep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional sensor and platform for acquiring high spatial and high temporal resolution data with high operational flexibility. Coastal wetlands are among some of the most challenging and complex ecosystems for land cover prediction and mapping tasks because land cover targets often show high intra-class and low inter-class variances. In recent years, several deep convolutional neural network (CNN) architectures have been proposed for pixel-wise image labeling, commonly called semantic image segmentation. In this paper, some of the more recent deep CNN architectures proposed for semantic image segmentation are reviewed, and each model’s training efficiency and classification performance are evaluated by training it on a limited labeled image set. Training samples are provided using the hyper-spatial resolution UAS imagery over a wetland area and the required ground truth images are prepared by manual image labeling. Experimental results demonstrate that deep CNNs have a great potential for accurate land cover prediction task using UAS hyper-spatial resolution images. Some simple deep learning architectures perform comparable or even better than complex and very deep architectures with remarkably fewer training epochs. This performance is especially valuable when limited training samples are available, which is a common case in most RS applications.
dc.identifier.citationPashaei, M.; Kamangir, H.; Starek, M.J.; Tissot, P. Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland. Remote Sens. 2020, 12, 959.en_US
dc.identifier.citationPashaei, M.; Kamangir, H.; Starek, M.J.; Tissot, P. Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland. Remote Sens. 2020, 12, 959.
dc.identifier.doi10.3390/rs12060959
dc.identifier.doi10.3390/rs1206095910.3390/rs12060959
dc.identifier.doi10.3390/rs12060959
dc.identifier.urihttps://hdl.handle.net/1969.6/87837
dc.identifier.urihttps://hdl.handle.net/1969.6/87837https://hdl.handle.net/1969.6/87837
dc.identifier.urihttps://hdl.handle.net/1969.6/87837
dc.language.isoen_USen_US
dc.language.isoen_US
dc.publisherRemote Sensingen_US
dc.publisherRemote Sensing
dc.rightsAttribution 3.0 United States*
dc.rightsAttribution 3.0 United States
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/us/*
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/us/
dc.subjectcoastal wetlanden_US
dc.subjectland cover mappingen_US
dc.subjectsemantic image segmentationen_US
dc.subjectmachine learningen_US
dc.subjectdeep-learningen_US
dc.subjectconvolutional neural networksen_US
dc.subjecttransfer learningen_US
dc.subjectunmanned aircraft systemsen_US
dc.subjectcoastal wetland
dc.subjectland cover mapping
dc.subjectsemantic image segmentation
dc.subjectmachine learning
dc.subjectdeep-learning
dc.subjectconvolutional neural networks
dc.subjecttransfer learning
dc.subjectunmanned aircraft systems
dc.titleReview and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetlanden_US
dc.titleReview and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland
dc.typeArticleen_US
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Pashaei_Mohammad_ReviewandEvaluation.pdf
Size:
10.9 MB
Format:
Adobe Portable Document Format
Description:
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