{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T11:57:05Z","timestamp":1762084625565,"version":"build-2065373602"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"This research was supported by the Shanxi Graduate Education Innovation Project of China","award":["Grant No. 2019SY126.","Grant No. 2019SY126."],"award-info":[{"award-number":["Grant No. 2019SY126.","Grant No. 2019SY126."]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cloud Comp"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In recent ages, the use of deep learning approaches to extract ground object information from remote sensing high-resolution images has attracted extensive attention in many fields. Nevertheless, due to the high similarity of features between roads, prevailing deep learning semantic segmentation networks commonly demonstrate reduced continuity in road segmentation. Besides this, the role of advanced computing technologies including cloud and edge infrastructures has also become very important due to large number of images and their storage requirements. In order to better study the road details in images related to remote sensing, this paper suggests a road extraction technique which is basically founded on Dimensional U-Net (DU-Net) network. At the deepening level of the U-Net network, a parallel attention mechanism, known as ProCBAM, is added and implemented to the feature transmission step of the classical U-Net network. Moreover, we use and implement the edge-cloud architecture to develop and construct a unique remote sensing image service system that integrates several datacenters and their related edge infrastructure. In the proposed system, the edge network is primarily used for caching and distributing the processed remote sensing images, while the remote datacenter serves as the cloud platform and is responsible for the storage and processing of original remote sensing images. The results show that the proposed cloud enabled DU-Net model has achieved good performance in road segmentation. We observed that it can achieve improved road segmentation and resolve the issue of reduced continuity of road segmentation when compared with other state-of-the-art learning networks. Moreover, our empirical evaluations suggest that the proposed system not only distributes the workload of processing tasks across the edges but also achieves data efficiency among them, which enhances image processing efficiency and reduces data transmission costs.<\/jats:p>","DOI":"10.1186\/s13677-023-00403-z","type":"journal-article","created":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T08:03:36Z","timestamp":1677485016000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["DU-Net-Cloud: a smart cloud-edge application with an attention mechanism and U-Net for remote sensing images and processing"],"prefix":"10.1186","volume":"12","author":[{"given":"Jiayuan","family":"Kong","sequence":"first","affiliation":[]},{"given":"Yanjun","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"403_CR1","doi-asserted-by":"publisher","first-page":"3906","DOI":"10.1109\/TGRS.2011.2136381","volume":"49","author":"S Das","year":"2011","unstructured":"Das S, Mirnalinee TT, Varghese K (2011) Use of salient features for the design of a multistage framework to extract roads from high-resolution multispectral satellite images. IEEE Trans Geosci Remote Sens 49:3906\u20133931","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"403_CR2","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1080\/01431161.2018.1513666","volume":"40","author":"X Lv","year":"2019","unstructured":"Lv X, Ming D, Chen YY, Wang M (2019) Very high resolution remote sensing image classification with SEEDS-CNN and scale effect analysis for superpixel CNN classification. Int J Remote Sens 40:506\u2013531","journal-title":"Int J Remote Sens"},{"key":"403_CR3","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.3390\/rs10121946","volume":"10","author":"X Lv","year":"2018","unstructured":"Lv X, Ming D, Lu T, Zhou K, Wang M, Bao H (2018) A new method for region-based majority voting CNNs for very high resolution image classification. Remote Sens 10:1946","journal-title":"Remote Sens"},{"issue":"3","key":"403_CR4","first-page":"339","volume":"22","author":"QZ Luo","year":"2007","unstructured":"Luo QZ, Yin Q, Kuang DB (2007) Research on extracting road based on its spectral feature and shape feature. Remote Sens Technol Appl 22(3):339\u2013344","journal-title":"Remote Sens Technol Appl"},{"issue":"3","key":"403_CR5","first-page":"293","volume":"34","author":"XG Lin","year":"2009","unstructured":"Lin XG, Zhang JX, Li HT et al (2009) Semi-automatic extraction of ribbon road from high resolution remotely sensed imagery by a T-shaped template matching. Geomat Inf Sci Wuhan Univ 34(3):293\u2013296","journal-title":"Geomat Inf Sci Wuhan Univ"},{"issue":"2","key":"403_CR6","first-page":"17","volume":"35","author":"LF Chen","year":"2015","unstructured":"Chen LF, Wen J, Xiao HG et al (2015) Road extraction algorithm for high resolution SAR image by fusion of MRF segmentation and mathematical morphology. Chin Space Sci Technol 35(2):17\u201324","journal-title":"Chin Space Sci Technol"},{"issue":"10","key":"403_CR7","first-page":"1231","volume":"45","author":"YG Cao","year":"2016","unstructured":"Cao YG, Wang ZP, Shen L et al (2016) Fusion of pixel-based and object-based features for road centerline extraction from high-resolution satellite imagery. Acta Geod Cartogr Sin 45(10):1231\u20131240","journal-title":"Acta Geod Cartogr Sin"},{"key":"403_CR8","doi-asserted-by":"publisher","first-page":"66","DOI":"10.3390\/rs12010066","volume":"12","author":"S Zhang","year":"2020","unstructured":"Zhang S, Li C, Qiu S, Gao C, Zhang F, Du Z, Liu R (2020) EMMCNN: an ETPS-based multi-scale and multi-feature method using CNN for high spatial resolution image land-cover classification. Remote Sens 12:66","journal-title":"Remote Sens"},{"issue":"6","key":"403_CR9","doi-asserted-by":"publisher","first-page":"3322","DOI":"10.1109\/TGRS.2017.2669341","volume":"55","author":"G Cheng","year":"2017","unstructured":"Cheng G, Wang Y, Xu S et al (2017) Automatic road detection and centerline extraction via cascaded end-to-end convolutional neural network. IEEE Trans Geosci Remote Sens 55(6):3322\u20133337","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"403_CR10","first-page":"1377","volume-title":"Proceedings of IEEE International Conference on Computer Vision (ICCV)","author":"Z Liu","year":"2015","unstructured":"Liu Z, Li X, Luo P et al (2015) Semantic image segmentation via deep parsing network. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp 1377\u20131385"},{"key":"403_CR11","doi-asserted-by":"publisher","first-page":"60344","DOI":"10.1109\/ACCESS.2020.2983202","volume":"8","author":"M Jeong","year":"2020","unstructured":"Jeong M, Nam J, Ko BC (2020) Lightweight multilayer random forests for monitoring driver emotional status. IEEE Access 8:60344\u201360354","journal-title":"IEEE Access"},{"key":"403_CR12","first-page":"234","volume-title":"Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5\u20139 October 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5\u20139 October 2015. Springer, Cham, pp 234\u2013241"},{"key":"403_CR13","first-page":"1","volume":"4","author":"W Yuan","year":"2021","unstructured":"Yuan W, Xu WB, Zhou T (2021) A loss function of road segmentation in remote sensing image by deep learning. Chinese Space Sci Technol 4:1\u201310","journal-title":"Chinese Space Sci Technol"},{"issue":"4","key":"403_CR14","first-page":"377","volume":"36","author":"F Jin","year":"2019","unstructured":"Jin F, Wang LF, Liu Z et al (2019) Double U-net remote sensing image road extraction method. J Geomat Sci Technol 36(4):377\u2013387","journal-title":"J Geomat Sci Technol"},{"issue":"4","key":"403_CR15","first-page":"741","volume":"35","author":"Z Wang","year":"2020","unstructured":"Wang Z, Yan HW, Lu XM et al (2020) High-resolution remote sensing image road extraction method for improving U-Net. Remote Sens Technol Appl 35(4):741\u2013748","journal-title":"Remote Sens Technol Appl"},{"key":"403_CR16","first-page":"102685","volume":"107","author":"D John","year":"2022","unstructured":"John D, Zhang C (2022) An attention-based U-Net for detecting deforestation within satellite sensor imagery. Int J Appl Earth Obs Geoinf 107:102685","journal-title":"Int J Appl Earth Obs Geoinf"},{"key":"403_CR17","doi-asserted-by":"publisher","first-page":"2357","DOI":"10.1109\/JSTARS.2022.3157648","volume":"15","author":"T Chen","year":"2022","unstructured":"Chen T et al (2022) A Siamese network based U-Net for change detection in high resolution remote sensing images. IEEE J Sel Top Appl Earth Obs Remote Sens 15:2357\u20132369","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"key":"403_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2020.3042202","volume":"60","author":"Q Zhao","year":"2021","unstructured":"Zhao Q et al (2021) Semantic segmentation with attention mechanism for remote sensing images. IEEE Trans Geosci Remote Sens 60:1\u201313","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"403_CR19","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, et al (2018) CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV). pp. 3-19","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"403_CR20","doi-asserted-by":"publisher","first-page":"107194","DOI":"10.1016\/j.compeleceng.2021.107194","volume":"93","author":"K-K Tseng","year":"2021","unstructured":"Tseng K-K et al (2021) A fast instance segmentation with one-stage multi-task deep neural network for autonomous driving. Comput Electr Eng 93:107194","journal-title":"Comput Electr Eng"},{"key":"403_CR21","doi-asserted-by":"crossref","unstructured":"Kong J, Gao Y, Zhang Y, et al (2021)Improved attention mechanism and residual network for remote sensing image scene classification, IEEE Access 9:134800-134808.","DOI":"10.1109\/ACCESS.2021.3116968"},{"issue":"2","key":"403_CR22","doi-asserted-by":"publisher","first-page":"026516","DOI":"10.1117\/1.JRS.16.026516","volume":"16","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Kong J, Long S et al (2022) Convolutional block attention module U-Net: a method to improve attention mechanism and U-Net for remote sensing images. J Appl Remote Sens 16(2):026516","journal-title":"J Appl Remote Sens"},{"key":"403_CR23","first-page":"1","volume":"60","author":"H Huang","year":"2021","unstructured":"Huang H, Chen Y, Wang R (2021) A lightweight network for building extraction from remote sensing images. IEEE Trans Geosci Remote Sens 60:1\u201312","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"403_CR24","volume-title":"IEEE Transactions on Network Science and Engineering","author":"Y Wu","year":"2022","unstructured":"Wu Y et al (2022) Edge computing driven low-light image dynamic enhancement for object detection. In: IEEE Transactions on Network Science and Engineering"},{"key":"403_CR25","doi-asserted-by":"publisher","first-page":"101972","DOI":"10.1109\/ACCESS.2021.3097630","volume":"9","author":"L Xu","year":"2021","unstructured":"Xu L et al (2021) HA U-Net: improved model for building extraction from high resolution remote sensing imagery. IEEE Access 9:101972\u2013101984","journal-title":"IEEE Access"}],"container-title":["Journal of Cloud Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13677-023-00403-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13677-023-00403-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13677-023-00403-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T08:06:21Z","timestamp":1677485181000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofcloudcomputing.springeropen.com\/articles\/10.1186\/s13677-023-00403-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["403"],"URL":"https:\/\/doi.org\/10.1186\/s13677-023-00403-z","relation":{},"ISSN":["2192-113X"],"issn-type":[{"type":"electronic","value":"2192-113X"}],"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"9 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25"}}