A lightweight and scalable greenhouse mapping method based on remote sensing imagery
Seeking a low-cost, high-efficiency greenhouse mapping technology has immense significance. While greenhouse extraction methods using deep learning have been proposed, the challenge of extracting dense small objects remains an unresolved problem. The inherent downscaling strategy in general-purpose...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223003771 |
| _version_ | 1827582870048210944 |
|---|---|
| author | Wei Chen Qingpeng Wang Dongliang Wang Yameng Xu Yingxuan He Lan Yang Hongzhao Tang |
| author_facet | Wei Chen Qingpeng Wang Dongliang Wang Yameng Xu Yingxuan He Lan Yang Hongzhao Tang |
| author_sort | Wei Chen |
| collection | DOAJ |
| description | Seeking a low-cost, high-efficiency greenhouse mapping technology has immense significance. While greenhouse extraction methods using deep learning have been proposed, the challenge of extracting dense small objects remains an unresolved problem. The inherent downscaling strategy in general-purpose semantic segmentation (SS) models renders them unsuitable for such tasks. In contrast, the dramatically increasing computational complexity associated with this problem may result in an unaffordable cost for consumer-level applications. To address the aforementioned challenges, this study presents a novel greenhouse mapping model based on remote sensing (RS) images, which not only exhibits high precision and robust generalization capabilities but also offers significant lightweight advantages. To meet broader needs, we also provide corresponding customizable and scalable rules that allow for a trade-off between accuracy and speed. To evaluate the performance of our model, we select several representative works to conduct benchmark experiments on a self-annotated dataset. The results demonstrate that our method can provide more powerful visual representations for greenhouse segmentation with minimal cost. Compared to the control group, the proposed method achieves an mIoU improvement of 1.116 %-10.77 % using only 3.282 M parameters, while maintaining a considerable inference speed. Code will be available at: https://github.com/W-qp/EGENet.git |
| first_indexed | 2024-03-08T22:57:48Z |
| format | Article |
| id | doaj.art-af6dc04739b849c19beda6fdcda348d9 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-08T22:57:48Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-af6dc04739b849c19beda6fdcda348d92023-12-16T06:06:26ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-12-01125103553A lightweight and scalable greenhouse mapping method based on remote sensing imageryWei Chen0Qingpeng Wang1Dongliang Wang2Yameng Xu3Yingxuan He4Lan Yang5Hongzhao Tang6College of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, ChinaInstitute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China; Corresponding author.College of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, ChinaCollege of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, ChinaLand Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100048, ChinaSeeking a low-cost, high-efficiency greenhouse mapping technology has immense significance. While greenhouse extraction methods using deep learning have been proposed, the challenge of extracting dense small objects remains an unresolved problem. The inherent downscaling strategy in general-purpose semantic segmentation (SS) models renders them unsuitable for such tasks. In contrast, the dramatically increasing computational complexity associated with this problem may result in an unaffordable cost for consumer-level applications. To address the aforementioned challenges, this study presents a novel greenhouse mapping model based on remote sensing (RS) images, which not only exhibits high precision and robust generalization capabilities but also offers significant lightweight advantages. To meet broader needs, we also provide corresponding customizable and scalable rules that allow for a trade-off between accuracy and speed. To evaluate the performance of our model, we select several representative works to conduct benchmark experiments on a self-annotated dataset. The results demonstrate that our method can provide more powerful visual representations for greenhouse segmentation with minimal cost. Compared to the control group, the proposed method achieves an mIoU improvement of 1.116 %-10.77 % using only 3.282 M parameters, while maintaining a considerable inference speed. Code will be available at: https://github.com/W-qp/EGENet.githttp://www.sciencedirect.com/science/article/pii/S1569843223003771GreenhousesDeep learningSemantic segmentationRemote sensing imageryLow-cost |
| spellingShingle | Wei Chen Qingpeng Wang Dongliang Wang Yameng Xu Yingxuan He Lan Yang Hongzhao Tang A lightweight and scalable greenhouse mapping method based on remote sensing imagery International Journal of Applied Earth Observations and Geoinformation Greenhouses Deep learning Semantic segmentation Remote sensing imagery Low-cost |
| title | A lightweight and scalable greenhouse mapping method based on remote sensing imagery |
| title_full | A lightweight and scalable greenhouse mapping method based on remote sensing imagery |
| title_fullStr | A lightweight and scalable greenhouse mapping method based on remote sensing imagery |
| title_full_unstemmed | A lightweight and scalable greenhouse mapping method based on remote sensing imagery |
| title_short | A lightweight and scalable greenhouse mapping method based on remote sensing imagery |
| title_sort | lightweight and scalable greenhouse mapping method based on remote sensing imagery |
| topic | Greenhouses Deep learning Semantic segmentation Remote sensing imagery Low-cost |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223003771 |
| work_keys_str_mv | AT weichen alightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT qingpengwang alightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT dongliangwang alightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT yamengxu alightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT yingxuanhe alightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT lanyang alightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT hongzhaotang alightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT weichen lightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT qingpengwang lightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT dongliangwang lightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT yamengxu lightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT yingxuanhe lightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT lanyang lightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery AT hongzhaotang lightweightandscalablegreenhousemappingmethodbasedonremotesensingimagery |