{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T15:14:00Z","timestamp":1781363640378,"version":"3.54.1"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T00:00:00Z","timestamp":1736812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Accurate building segmentation has become critical in various fields such as urban management, urban planning, mapping, and navigation. With the increasing diversity in the number, size, and shape of buildings, convolutional neural networks have been used to segment and extract buildings from such images, resulting in increased efficiency and utilization of image features. We propose a building semantic segmentation method to improve the traditional Unet convolutional neural network by integrating attention mechanism and boundary detection. The attention mechanism module combines attention in the channel and spatial dimensions. The module captures image feature information in the channel dimension using a one-dimensional convolutional cross-channel method and automatically adjusts the cross-channel dimension using adaptive convolutional kernel size. Additionally, a weighted boundary loss function is designed to replace the traditional semantic segmentation cross-entropy loss to detect the boundary of a building. The loss function optimizes the extraction of building boundaries in backpropagation, ensuring the integrity of building boundary extraction in the shadow part. Experimental results show that the proposed model AMBDNet achieves high-performance metrics, including a recall rate of 0.9046, an IoU of 0.7797, and a pixel accuracy of 0.9140 on high-resolution remote sensing images, demonstrating its robustness and effectiveness in precise building segmentation. Experimental results further indicate that AMBDNet improves the single-class recall of buildings by 0.0322 and the single-class pixel accuracy by 0.0169 in the high-resolution remote sensing image recognition task.<\/jats:p>","DOI":"10.3389\/fnbot.2024.1482051","type":"journal-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T06:11:59Z","timestamp":1736835119000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Integrating attention mechanism and boundary detection for building segmentation from remote sensing images"],"prefix":"10.3389","volume":"18","author":[{"given":"Ping","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangtian","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hesong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinru","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhichuan","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shufeng","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,14]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"2152","DOI":"10.1080\/01431161.2011.606852","article-title":"Unsupervised building detection in complex urban environments from multispectral satellite imagery","volume":"33","author":"Aytek\u0131n","year":"2012","journal-title":"Int. J. Remote Sens."},{"key":"ref2","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1109\/JSTARS.2023.3238720","article-title":"ResAt-UNet: a U-shaped network using ResNet and attention module for image segmentation of urban buildings","volume":"16","author":"Fan","year":"2023","journal-title":"IEEE J. Top. Appl. Earth Observat. Remote Sens."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"457","DOI":"10.11947\/j.AGCS.2022.20200601","article-title":"The cavity convolution E-Unet algorithm for building extraction from high-resolution remote sensing image","volume":"51","author":"He","year":"2022","journal-title":"J. Surv. Map."},{"key":"ref5","first-page":"472","volume-title":"Automatic building detection in aerial images using a hierarchical feature based image segmentation.2010 20th international conference on pattern recognition","author":"Izadi","year":"2010"},{"key":"ref6","first-page":"285","article-title":"Boundary loss for highly unbalanced segmentation","author":"Kervadec","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"Computer Science"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1006\/cviu.1998.0724","article-title":"Building detection and description from a single intensity image","volume":"72","author":"Lin","year":"1998","journal-title":"Comput. Vis. Image Underst."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"306","DOI":"10.3788\/AOS201636.0428001","article-title":"Research on high resolution remote sensing image classification based on deep learning","volume":"36","author":"Liu","year":"2016","journal-title":"J. Opt."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2849","DOI":"10.3390\/rs12172849","article-title":"Building extraction from airborne LiDAR data based on min-cut and improved post-processing","volume":"12","author":"Liu","year":"2020","journal-title":"Remote Sens."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"4257","DOI":"10.1007\/s11063-021-10592-w","article-title":"CT-UNet: context-transfer-UNet for building segmentation in remote sensing images","volume":"53","author":"Liu","year":"2021","journal-title":"Neural. Process. Lett."},{"key":"ref12","first-page":"640","article-title":"Fully convolutional networks for semantic segmentation","volume":"39","author":"Long","year":"2015","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit."},{"key":"ref13","first-page":"3226","article-title":"Can semantic labeling methods generalize to any city? The inria aerial image labeling benchmark","author":"Maggiori","year":"2017"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/9781119682042.ch1","article-title":"Land-use classification with integrated data","volume-title":"Machine vision inspection systems: image processing, concepts, methodologies and applications","author":"Meedeniya","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"3258","DOI":"10.1049\/ipr2.12558","article-title":"Weakly supervised building semantic segmentation via superpixel-CRF with initial deep seeds guiding","volume":"16","author":"Moghalles","year":"2022","journal-title":"IET Image Process."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.26.1.011016","article-title":"Architectural style classification of mexican historical buildings using deep convolutional neural networks and sparse features","volume":"26","author":"Obeso","year":"2017","journal-title":"J Electron Imaging"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2023.3243609","article-title":"Building extraction from very high-resolution remote sensing images using refine-UNet","volume":"20","author":"Qiu","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref18","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention\u2013MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.cmpb.2019.07.005","article-title":"Efficient skin lesion segmentation using separable-Unet with stochastic weight averaging","volume":"178","author":"Tang","year":"2019","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"207","DOI":"10.26599\/TST.2018.9010044","article-title":"CasNet: a cascade coarse-to-fine network for semantic segmentation","volume":"24","author":"Wang","year":"2018","journal-title":"Tsinghua Sci. Technol."},{"key":"ref21","first-page":"100","article-title":"FPB-UNet++: semantic segmentation for remote sensing images of reservoir area via improved UNet++ with FPN","author":"Wang","year":"2022"},{"key":"ref22","first-page":"11534","article-title":"ECA-net: efficient channel attention for deep convolutional neural networks","author":"Wang","year":"2020"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1109\/JURSE.2011.5764756","volume-title":"Segment-based building detection with conditional random fields.2011 joint urban remote sensing event","author":"Wegne","year":"2011"},{"key":"ref24","first-page":"3","article-title":"Cbam: convolutional block attention module","author":"Woo","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2932","DOI":"10.3390\/s22082932","article-title":"AGs-Unet: building extraction model for high resolution remote sensing images based on attention gates U network","volume":"22","author":"Yu","year":"2022","journal-title":"Sensors"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"5175","DOI":"10.3390\/rs14205175","article-title":"Building extraction and floor area estimation at the village level in rural China via a comprehensive method integrating UAV photogrammetry and the novel EDSANet","volume":"14","author":"Zhou","year":"2022","journal-title":"Remote Sens."}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1482051\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T06:12:05Z","timestamp":1736835125000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1482051\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,14]]},"references-count":26,"alternative-id":["10.3389\/fnbot.2024.1482051"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1482051","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,14]]},"article-number":"1482051"}}