Land cover mapping via crowdsourced multi-directional views: The more directional views, the better
In the last decades, a number of crowdsourced land cover datasets have been developed, owning to their great potential to provide human-centric ground observations. In this study, we investigated the GLOBE Observer Land Cover program by assessing the efficacy of its multi-directional data-collecting...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-08-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223002066 |
| _version_ | 1827861431549165568 |
|---|---|
| author | Xiao Huang Di Yang Yaqian He Peder Nelson Russanne Low Shawna McBride Jessica Mitchell Michael Guarraia |
| author_facet | Xiao Huang Di Yang Yaqian He Peder Nelson Russanne Low Shawna McBride Jessica Mitchell Michael Guarraia |
| author_sort | Xiao Huang |
| collection | DOAJ |
| description | In the last decades, a number of crowdsourced land cover datasets have been developed, owning to their great potential to provide human-centric ground observations. In this study, we investigated the GLOBE Observer Land Cover program by assessing the efficacy of its multi-directional data-collecting protocol. Specifically, we explored data characteristics by presenting its unique data sampling protocol, data sample distributions, and similarity across multi-directional views. We developed an end-to-end classification framework that links user-uploaded multi-directional views with their user-provided land cover labels and investigated classification performance with different levels of viewing involvement, using various popular deep learning architectures, under different image fusion strategies. Our study provides empirical evidence that multi-directional views benefit land cover classification. We observe that classification performance improved across four selected deep learning architectures when more directional views were involved. The classification scenario with EfficentNet, the involvement of quadruple views, and the late fusion strategy led to an improvement of 0.084 in the weighted F1 score (from 0.628 to 0.712) compared to the one with single view. We encourage crowdsourced observing and monitoring programs to adopt multi-directional view sampling protocols and call for the development of robust information on fusion strategies that harness the potential of multi-directional views. |
| first_indexed | 2024-03-12T13:37:45Z |
| format | Article |
| id | doaj.art-da75a2cdbae9434c949e757ed3ee7ef7 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-12T13:37:45Z |
| publishDate | 2023-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-da75a2cdbae9434c949e757ed3ee7ef72023-08-24T04:34:06ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-08-01122103382Land cover mapping via crowdsourced multi-directional views: The more directional views, the betterXiao Huang0Di Yang1Yaqian He2Peder Nelson3Russanne Low4Shawna McBride5Jessica Mitchell6Michael Guarraia7Department of Geosciences, University of Arkansas, Fayetteville, AR 72701, USA; Department of Environmental Sciences, Emory University, Atlanta, GA 30322, USAWyoming Geographic Information Science Center, School of Computing, University of Wyoming, Laramie, WY 82071, USA; Corresponding author.Department of Geography, University of Central Arkansas, Conway, AR 72034, USACollege of Earth, Ocean, and Atmospheric Science, Oregon State University, Corvallis, OR 97331, USAInstitute for Global Environmental Strategies, Arlington, VA 22202, USAWyoming NASA Space Grant and EPSCoR, University of Wyoming, Laramie, WY 82071, USASpatial Analysis Lab, University of Montana, Missoula, MT 59812, USAProject Lead The Way, Indianapolis, IN 46240, USAIn the last decades, a number of crowdsourced land cover datasets have been developed, owning to their great potential to provide human-centric ground observations. In this study, we investigated the GLOBE Observer Land Cover program by assessing the efficacy of its multi-directional data-collecting protocol. Specifically, we explored data characteristics by presenting its unique data sampling protocol, data sample distributions, and similarity across multi-directional views. We developed an end-to-end classification framework that links user-uploaded multi-directional views with their user-provided land cover labels and investigated classification performance with different levels of viewing involvement, using various popular deep learning architectures, under different image fusion strategies. Our study provides empirical evidence that multi-directional views benefit land cover classification. We observe that classification performance improved across four selected deep learning architectures when more directional views were involved. The classification scenario with EfficentNet, the involvement of quadruple views, and the late fusion strategy led to an improvement of 0.084 in the weighted F1 score (from 0.628 to 0.712) compared to the one with single view. We encourage crowdsourced observing and monitoring programs to adopt multi-directional view sampling protocols and call for the development of robust information on fusion strategies that harness the potential of multi-directional views.http://www.sciencedirect.com/science/article/pii/S1569843223002066CrowdsourcingLand cover mappingCitizen scienceInformation fusion |
| spellingShingle | Xiao Huang Di Yang Yaqian He Peder Nelson Russanne Low Shawna McBride Jessica Mitchell Michael Guarraia Land cover mapping via crowdsourced multi-directional views: The more directional views, the better International Journal of Applied Earth Observations and Geoinformation Crowdsourcing Land cover mapping Citizen science Information fusion |
| title | Land cover mapping via crowdsourced multi-directional views: The more directional views, the better |
| title_full | Land cover mapping via crowdsourced multi-directional views: The more directional views, the better |
| title_fullStr | Land cover mapping via crowdsourced multi-directional views: The more directional views, the better |
| title_full_unstemmed | Land cover mapping via crowdsourced multi-directional views: The more directional views, the better |
| title_short | Land cover mapping via crowdsourced multi-directional views: The more directional views, the better |
| title_sort | land cover mapping via crowdsourced multi directional views the more directional views the better |
| topic | Crowdsourcing Land cover mapping Citizen science Information fusion |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223002066 |
| work_keys_str_mv | AT xiaohuang landcovermappingviacrowdsourcedmultidirectionalviewsthemoredirectionalviewsthebetter AT diyang landcovermappingviacrowdsourcedmultidirectionalviewsthemoredirectionalviewsthebetter AT yaqianhe landcovermappingviacrowdsourcedmultidirectionalviewsthemoredirectionalviewsthebetter AT pedernelson landcovermappingviacrowdsourcedmultidirectionalviewsthemoredirectionalviewsthebetter AT russannelow landcovermappingviacrowdsourcedmultidirectionalviewsthemoredirectionalviewsthebetter AT shawnamcbride landcovermappingviacrowdsourcedmultidirectionalviewsthemoredirectionalviewsthebetter AT jessicamitchell landcovermappingviacrowdsourcedmultidirectionalviewsthemoredirectionalviewsthebetter AT michaelguarraia landcovermappingviacrowdsourcedmultidirectionalviewsthemoredirectionalviewsthebetter |