{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T18:09:53Z","timestamp":1778868593134,"version":"3.51.4"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Precise extraction of buildings from high-resolution remote sensing images is essential for urban analysis and land management. However, accurately extracting buildings as a region of interest (ROI) from remote sensing (RS) images remains challenging. This difficulty arises from the spectral similarity of other objects, such as roads, cars, or trees, along with limited information on building boundaries and small buildings. Traditional image segmentation methods often rely on a fixed threshold value, making optimisation difficult in cases of over-segmented regions. As a result, region merging is subsequently performed on the region adjacency graph (RAG). Consequently, building segmentation in RS images becomes problematic and can lead to inaccurate boundary delineation or region classification. To overcome these limitations, we propose a novel segmentation approach that incorporates an adaptive thresholding optimisation technique and a merging criterion (MC) based on deep features extracted via a convolutional neural network (CNN)-based AttentionU-Net architecture. This ensures that merging decisions are guided by intrinsic region-level characteristics and refined through deep feature representations. Beginning with initial segmentation generated by the simple linear iterative clustering (SLIC) algorithm, the AttentionU-Net architecture is applied to high-resolution RS images to extract deep features, respectively. As a result, our approach combines both low and high-level feature information, reducing misalignment during merging and enhancing traditional region merging strategies. To validate this approach, the WHU buildings\u2019 RS images dataset was utilised. Experimental results demonstrate that our approach achieves superior segmentation accuracy in building delineation while eliminating the need for rigid thresholds. Finally, the results were compared with those obtained using the multiresolution segmentation (MRS) algorithm implemented in eCognition software on the same WHU buildings RS images, where our approach performs better. Specifically, the proposed approach attained a higher segmentation accuracy, with an F-measure of 0. 91 and a goodness of segmentation score G\n                    <jats:sub>s<\/jats:sub>\n                    of 0.92, compared to 0.52 and 0.83, respectively, achieved by the MRS algorithm.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0348364","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T17:25:57Z","timestamp":1778865957000},"page":"e0348364","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning\u2013based region merging with adaptive threshold optimization for building segmentation in remote sensing images"],"prefix":"10.1371","volume":"21","author":[{"given":"Asim","family":"Shoaib","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Waqas","family":"Nadeem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nohaidda","family":"Sariff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syeda Tehreem","family":"Haider","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fasee","family":"Ullah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ateeq Ur","family":"Rehman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sadiq","family":"Muhammad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7622-9632","authenticated-orcid":true,"given":"Rab","family":"Nawaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Adnan","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,5,15]]},"reference":[{"key":"pone.0348364.ref001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2025.3544549","article-title":"Deep Merge: Deep-Learning-Based Region Merging for Remote Sensing Image Segmentation","volume":"63","author":"X Lv","year":"2025","journal-title":"IEEE Trans Geosci Remote Sensing"},{"issue":"1","key":"pone.0348364.ref002","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1080\/22797254.2017.1416676","article-title":"Automatic building footprint extraction from high-resolution satellite image using mathematical morphology","volume":"51","author":"NL Gavankar","year":"2017","journal-title":"European J Remote Sensing"},{"issue":"3","key":"pone.0348364.ref003","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1109\/34.49050","article-title":"Integrating region growing and edge detection","volume":"12","author":"T Pavlidis","year":"1990","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"pone.0348364.ref004","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.isprsjprs.2019.02.009","article-title":"Segmentation for Object-Based Image Analysis (OBIA): A review of algorithms and challenges from remote sensing perspective","volume":"150","author":"MD Hossain","year":"2019","journal-title":"ISPRS J Photogrammetry and Remote Sensing"},{"key":"pone.0348364.ref005","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1007\/3-540-47977-5_27","article-title":"Yet Another Survey on Image Segmentation: Region and Boundary Information Integration","author":"J Freixenet","year":"2002","journal-title":"Lecture Notes in Computer Science"},{"key":"pone.0348364.ref006","doi-asserted-by":"crossref","unstructured":"Bhargava N, Trivedi P, Toshniwal A, Swarnkar H. Iterative Region Merging and Object Retrieval Method Using Mean Shift Segmentation and Flood Fill Algorithm. In: 2013 Third International Conference on Advances in Computing and Communications. 2013;157\u201360. https:\/\/doi.org\/10.1109\/icacc.2013.100","DOI":"10.1109\/ICACC.2013.100"},{"issue":"13","key":"pone.0348364.ref007","doi-asserted-by":"crossref","first-page":"15105","DOI":"10.1007\/s11042-017-4558-4","article-title":"Multi-scale segmentation of very high resolution remote sensing image based on gravitational field and optimized region merging","volume":"76","author":"AZ Zhang","year":"2017","journal-title":"Multimed Tools Appl"},{"key":"pone.0348364.ref008","doi-asserted-by":"crossref","first-page":"6721","DOI":"10.1109\/JSTARS.2024.3373385","article-title":"Evaluation of Global-Scale and Local-Scale Optimized Segmentation Algorithms in GEOBIA With SAM on Land Use and Land Cover","volume":"17","author":"T He","year":"2024","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"},{"issue":"4","key":"pone.0348364.ref009","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1080\/01431161003743173","article-title":"Assessing object-based classification: advantages and limitations","volume":"1","author":"D Liu","year":"2010","journal-title":"Remote Sensing Letters"},{"key":"pone.0348364.ref010","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.isprsjprs.2014.09.011","article-title":"Hybrid region merging method for segmentation of high-resolution remote sensing images","volume":"98","author":"X Zhang","year":"2014","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0348364.ref011","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.isprsjprs.2020.07.017","article-title":"Machine learning-assisted region merging for remote sensing image segmentation","volume":"168","author":"T Su","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0348364.ref012","unstructured":"Building dataset. GPCV WHU. http:\/\/gpcv.whu.edu.cn\/data\/building_dataset.html. Accessed 2025 January 10."},{"issue":"5","key":"pone.0348364.ref013","doi-asserted-by":"crossref","first-page":"781","DOI":"10.3390\/rs10050781","article-title":"Region Merging Considering Within- and Between-Segment Heterogeneity: An Improved Hybrid Remote-Sensing Image Segmentation Method","volume":"10","author":"Y Wang","year":"2018","journal-title":"Remote Sensing"},{"issue":"14","key":"pone.0348364.ref014","doi-asserted-by":"crossref","first-page":"2782","DOI":"10.3390\/rs13142782","article-title":"Improvement of Region-Merging Image Segmentation Accuracy Using Multiple Merging Criteria","volume":"13","author":"H Wang","year":"2021","journal-title":"Remote Sensing"},{"key":"pone.0348364.ref015","doi-asserted-by":"crossref","first-page":"103871","DOI":"10.1016\/j.imavis.2020.103871","article-title":"Bottom-up unsupervised image segmentation using FC-Dense u-net based deep representation clustering and multidimensional feature fusion based region merging","volume":"94","author":"Z Khan","year":"2020","journal-title":"Image and Vision Computing"},{"key":"pone.0348364.ref016","author":"X Lv","year":"2023"},{"key":"pone.0348364.ref017","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.isprsjprs.2013.01.002","article-title":"Boundary-constrained multi-scale segmentation method for remote sensing images","volume":"78","author":"X Zhang","year":"2013","journal-title":"ISPRS J Photogrammetry and Remote Sensing"},{"issue":"2","key":"pone.0348364.ref018","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","article-title":"Efficient Graph-Based Image Segmentation","volume":"59","author":"PF Felzenszwalb","year":"2004","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"pone.0348364.ref019","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/TIT.1975.1055330","article-title":"The estimation of the gradient of a density function, with applications in pattern recognition","volume":"21","author":"K Fukunaga","year":"1975","journal-title":"IEEE Trans Inform Theory"},{"key":"pone.0348364.ref020","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1007\/978-3-540-88693-8_52","article-title":"Quick Shift and Kernel Methods for Mode Seeking","author":"A Vedaldi","year":"2008","journal-title":"Lecture Notes in Computer Science"},{"issue":"11","key":"pone.0348364.ref021","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","article-title":"SLIC superpixels compared to state-of-the-art superpixel methods","volume":"34","author":"R Achanta","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0348364.ref022","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.isprsjprs.2021.01.020","article-title":"Remote sensing image segmentation advances: A meta-analysis","volume":"173","author":"I Kotaridis","year":"2021","journal-title":"ISPRS J Photogrammetry and Remote Sensing"},{"key":"pone.0348364.ref023","doi-asserted-by":"crossref","first-page":"187","DOI":"10.3233\/FI-2000-411207","article-title":"The Watershed Transform: Definitions, Algorithms and Parallelization Strategies","volume":"41","author":"JBTM Roerdink","year":"2000","journal-title":"Fundamenta Informaticae"},{"key":"pone.0348364.ref024","doi-asserted-by":"crossref","unstructured":"Neubert P, Protzel P. Compact Watershed and Preemptive SLIC: On Improving Trade-offs of Superpixel Segmentation Algorithms. In: 2014 22nd International Conference on Pattern Recognition. 2014;996\u20131001. https:\/\/doi.org\/10.1109\/icpr.2014.181","DOI":"10.1109\/ICPR.2014.181"},{"issue":"11","key":"pone.0348364.ref025","doi-asserted-by":"crossref","first-page":"1768","DOI":"10.1109\/TPAMI.2006.233","article-title":"Random walks for image segmentation","volume":"28","author":"L Grady","year":"2006","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0348364.ref026","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.46300\/9106.2022.16.131","article-title":"Effects of Different Superpixel Algorithms on Interactive Segmentations","volume":"16","author":"KL Goh","year":"2022","journal-title":"Int J Circuits Syst Signal Processing"},{"key":"pone.0348364.ref027","doi-asserted-by":"crossref","unstructured":"Martins J, Sant\u2019Ana DA, Junior JM, Pistori H, Goncalves WN. Aerial Image Segmentation In Urban Environment For Vegetation Monitoring. In: 2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS). 2020. 375\u20139. https:\/\/doi.org\/10.1109\/lagirs48042.2020.9165618","DOI":"10.1109\/LAGIRS48042.2020.9165618"},{"key":"pone.0348364.ref028","doi-asserted-by":"crossref","unstructured":"Patel S, Kadhiwala B. Comparative Analysis of Cluster Based Superpixel Segmentation Techniques. In: 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI). 2018;1454\u20139. https:\/\/doi.org\/10.1109\/icoei.2018.8553834","DOI":"10.1109\/ICOEI.2018.8553834"},{"key":"pone.0348364.ref029","doi-asserted-by":"crossref","unstructured":"Moore AP, Prince SJD, Warrell J, Mohammed U, Jones G. Superpixel lattices. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition. 2008;1\u20138. https:\/\/doi.org\/10.1109\/cvpr.2008.4587471","DOI":"10.1109\/CVPR.2008.4587471"},{"key":"pone.0348364.ref030","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.isprsjprs.2019.01.007","article-title":"Another look on region merging procedure from seed region shift for high-resolution remote sensing image segmentation","volume":"148","author":"X Zhang","year":"2019","journal-title":"ISPRS J Photogrammetry and Remote Sensing"},{"key":"pone.0348364.ref031","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.rse.2016.12.011","article-title":"Region merging using local spectral angle thresholds: A more accurate method for hybrid segmentation of remote sensing images","volume":"190","author":"J Yang","year":"2017","journal-title":"Remote Sensing of Environment"},{"key":"pone.0348364.ref032","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.isprsjprs.2018.12.003","article-title":"Scale-variable region-merging for high resolution remote sensing image segmentation","volume":"147","author":"T Su","year":"2019","journal-title":"ISPRS J Photogrammetry and Remote Sensing"},{"key":"pone.0348364.ref033","doi-asserted-by":"crossref","first-page":"81492","DOI":"10.1109\/ACCESS.2022.3194047","article-title":"Local Scale-Guided Hierarchical Region Merging and Further Over- and Under-Segmentation Processing for Hybrid Remote Sensing Image Segmentation","volume":"10","author":"Y Wang","year":"2022","journal-title":"IEEE Access"},{"issue":"3","key":"pone.0348364.ref034","article-title":"Robust Segmentation of Remote Sensing Images Using Optimized Region Merging Algorithm","volume":"12","author":"DrI Nadher","year":"2020","journal-title":"JARDCS"},{"key":"pone.0348364.ref035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2021.3121419","article-title":"A Hierarchical Region-Merging Algorithm for 3-D Segmentation of Individual Trees Using UAV-LiDAR Point Clouds","volume":"60","author":"Y Hao","year":"2022","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0348364.ref036","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/978-3-030-58539-6_11","article-title":"Object-Contextual Representations for Semantic Segmentation","author":"Y Yuan","year":"2020","journal-title":"Lecture Notes in Computer Science"},{"key":"pone.0348364.ref037","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers.","volume-title":"Advances in Neural Information Processing Systems","author":"E Xie","year":"2021"},{"issue":"1","key":"pone.0348364.ref038","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TGRS.2018.2858817","article-title":"Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set","volume":"57","author":"S Ji","year":"2019","journal-title":"IEEE Trans Geosci Remote Sensing"},{"issue":"10","key":"pone.0348364.ref039","doi-asserted-by":"crossref","DOI":"10.1007\/s12517-016-2585-5","article-title":"Research and application of roadway backfill coal mining technology in western coal mining area","volume":"9","author":"J Zhang","year":"2016","journal-title":"Arab J Geosci"},{"key":"pone.0348364.ref040","doi-asserted-by":"crossref","first-page":"01048","DOI":"10.1051\/itmconf\/20246701048","article-title":"Comparative Studies of Region-Based Segmentation Algorithms on Natural and Remote Sensing Images","volume":"67","author":"A Shoaib","year":"2024","journal-title":"ITM Web Conf"},{"key":"pone.0348364.ref041","first-page":"199","author":"A Shoaib","year":"2023"},{"key":"pone.0348364.ref042","doi-asserted-by":"crossref","unstructured":"Chen H, Lu S. Building Extraction from Remote Sensing Images Using SegNet. In: 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC). 2019;227\u201330. https:\/\/doi.org\/10.1109\/icivc47709.2019.8981046","DOI":"10.1109\/ICIVC47709.2019.8981046"},{"key":"pone.0348364.ref043","doi-asserted-by":"crossref","first-page":"179424","DOI":"10.1109\/ACCESS.2020.3026658","article-title":"VNet: an end-to-end fully convolutional neural network for road extraction from high-resolution remote sensing data","volume":"8","author":"A Abdollahi","year":"2020","journal-title":"IEEE Access"},{"issue":"5","key":"pone.0348364.ref044","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","article-title":"Road Extraction by Deep Residual U-Net","volume":"15","author":"Z Zhang","year":"2018","journal-title":"IEEE Geosci Remote Sensing Lett"},{"key":"pone.0348364.ref045","doi-asserted-by":"crossref","first-page":"103530","DOI":"10.1016\/j.bspc.2022.103530","article-title":"Detection and classification of COVID-19 disease from X-ray images using convolutional neural networks and histogram of oriented gradients","volume":"74","author":"AM Ayalew","year":"2022","journal-title":"Biomed Signal Process Control"},{"key":"pone.0348364.ref046","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.isprsjprs.2022.08.024","article-title":"A hybrid image segmentation method for building extraction from high-resolution RGB images","volume":"192","author":"MD Hossain","year":"2022","journal-title":"ISPRS J Photogrammetry and Remote Sensing"},{"key":"pone.0348364.ref047","first-page":"12","article-title":"Multiresolution segmentation: An optimization approach for high quality multi-scale image segmentation.","volume-title":"Angewandte Geographische Informationsverarbeitung XII","author":"M Baatz","year":"2000"},{"key":"pone.0348364.ref048","doi-asserted-by":"crossref","first-page":"186424","DOI":"10.1109\/ACCESS.2025.3608800","article-title":"Multi-Resolution Region Merging (MRRM): A Novel Post-Processing Framework to Mitigate Fragmentation in SAM-Based Geospatial Segmentation of Rural Buildings","volume":"13","author":"M Ihsan","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0348364.ref049","article-title":"A review of remote sensing image segmentation by deep learning methods","volume":"17","author":"J Li","year":"2024","journal-title":"International Journal of Digital Earth"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T17:26:05Z","timestamp":1778865965000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348364"}},"subtitle":[],"editor":[{"given":"Claudionor Ribeiro da","family":"Silva","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":49,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348364","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,15]]}}}