{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T11:14:12Z","timestamp":1770549252814,"version":"3.49.0"},"reference-count":49,"publisher":"Emerald","issue":"1","license":[{"start":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T00:00:00Z","timestamp":1691020800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJICC"],"published-print":{"date-parts":[[2024,2,29]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>High-resolution remote sensing images possess a wealth of semantic information. However, these images often contain objects of different sizes and distributions, which make the semantic segmentation task challenging. In this paper, a bidirectional feature fusion network (BFFNet) is designed to address this challenge, which aims at increasing the accurate recognition of surface objects in order to effectively classify special features.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>There are two main crucial elements in BFFNet. Firstly, the mean-weighted module (MWM) is used to obtain the key features in the main network. Secondly, the proposed polarization enhanced branch network performs feature extraction simultaneously with the main network to obtain different feature information. The authors then fuse these two features in both directions while applying a cross-entropy loss function to monitor the network training process. Finally, BFFNet is validated on two publicly available datasets, Potsdam and Vaihingen.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>In this paper, a quantitative analysis method is used to illustrate that the proposed network achieves superior performance of 2\u20136%, respectively, compared to other mainstream segmentation networks from experimental results on two datasets. Complete ablation experiments are also conducted to demonstrate the effectiveness of the elements in the network. In summary, BFFNet has proven to be effective in achieving accurate identification of small objects and in reducing the effect of shadows on the segmentation process.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>The originality of the paper is the proposal of a BFFNet based on multi-scale and multi-attention strategies to improve the ability to accurately segment high-resolution and complex remote sensing images, especially for small objects and shadow-obscured objects.<\/jats:p><\/jats:sec>","DOI":"10.1108\/ijicc-03-2023-0053","type":"journal-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T03:50:42Z","timestamp":1690948242000},"page":"20-37","source":"Crossref","is-referenced-by-count":14,"title":["BFFNet: a bidirectional feature fusion network for semantic segmentation of remote sensing objects"],"prefix":"10.1108","volume":"17","author":[{"given":"Yandong","family":"Hou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1967-9626","authenticated-orcid":false,"given":"Zhengbo","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xinghua","family":"Ren","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9882-140X","authenticated-orcid":false,"given":"Kaiwen","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4164-1157","authenticated-orcid":false,"given":"Zhengquan","family":"Chen","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2023,8,3]]},"reference":[{"issue":"12","key":"key2024022811223637300_ref001","first-page":"2481","article-title":"SegNet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling","volume":"39","year":"2015"},{"key":"key2024022811223637300_ref002","first-page":"357","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","volume":"4","year":"2014"},{"key":"key2024022811223637300_ref003","first-page":"834","article-title":"DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"key2024022811223637300_ref004","doi-asserted-by":"publisher","article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","DOI":"10.48550\/arXiv.1706.05587"},{"key":"key2024022811223637300_ref005","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","year":"2018"},{"issue":"1","key":"key2024022811223637300_ref006","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1109\/TGRS.2020.2994150","article-title":"LANet: local attention embedding to improve the semantic segmentation of remote sensing images","volume":"59","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"key2024022811223637300_ref007","article-title":"Using remote sensing to identify soil types based on multiscale image texture features","volume":"187","year":"2021","journal-title":"Computers and Electronics in Agriculture"},{"key":"key2024022811223637300_ref008","first-page":"3141","article-title":"Dual attention network for scene segmentation","year":"2018"},{"issue":"6","key":"key2024022811223637300_ref009","doi-asserted-by":"publisher","first-page":"2987","DOI":"10.1109\/tgrs.2014.2367129","article-title":"Marker-controlled watershed-based segmentation of multiresolution remote sensing images","volume":"53","year":"2015","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"1","key":"key2024022811223637300_ref010","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.16.014515","article-title":"SRANet: semantic relation aware network for semantic segmentation of remote sensing images","volume":"16","year":"2022","journal-title":"Journal of Applied Remote Sensing"},{"issue":"2","key":"key2024022811223637300_ref011","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s13735-017-0141-z","article-title":"A review of semantic segmentation using deep neural networks","volume":"7","year":"2018","journal-title":"International Journal of Multimedia Information Retrieval"},{"issue":"8","key":"key2024022811223637300_ref012","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","article-title":"Squeeze-and-Excitation networks","volume":"42","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"key2024022811223637300_ref013","doi-asserted-by":"publisher","first-page":"6896","DOI":"10.1109\/TPAMI.2020.3007032","article-title":"CCNet: criss-cross attention for semantic segmentation","volume":"45","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"key2024022811223637300_ref014","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1109\/icvrv.2015.35","article-title":"Remote sensing image classification method based on superpixel segmentation and adaptive weighting K-means","year":"2015"},{"issue":"5","key":"key2024022811223637300_ref015","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1109\/LGRS.2020.2988294","article-title":"SCAttNet: semantic segmentation network with spatial and channel attention mechanism for high-resolution remote sensing images","volume":"18","year":"2021","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"key2024022811223637300_ref016","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3093977","article-title":"Multiattention network for semantic segmentation of fine-resolution remote sensing images","volume":"60","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"key2024022811223637300_ref017","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2021.102449","article-title":"MHIBS-Net: multiscale hierarchical network for indoor building structure point clouds semantic segmentation","volume":"102","year":"2021","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"key2024022811223637300_ref018","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2022.110231","article-title":"Intelligent classification model of land resource use using deep learning in remote sensing images","volume":"475","year":"2023","journal-title":"Ecological Modelling"},{"key":"key2024022811223637300_ref019","doi-asserted-by":"publisher","article-title":"SAN: scale-aware network for semantic segmentation of high-resolution aerial images","year":"2019","DOI":"10.48550\/arXiv.1907.03089"},{"issue":"2","key":"key2024022811223637300_ref020","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/s13042-020-01175-7","article-title":"Cross-domain sentiment aware word embeddings for review sentiment analysis","volume":"12","year":"2020","journal-title":"International Journal of Machine Learning and Cybernetics"},{"key":"key2024022811223637300_ref021","doi-asserted-by":"publisher","article-title":"Polarized self-attention: towards high-quality pixel-wise regression","year":"2021","DOI":"10.48550\/arXiv.2107.00782"},{"key":"key2024022811223637300_ref022","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119110","article-title":"Aliasing black box adversarial attack with joint self-attention distribution and confidence probability","volume":"214","year":"2023","journal-title":"Expert Systems with Applications"},{"issue":"12","key":"key2024022811223637300_ref023","doi-asserted-by":"publisher","first-page":"8555","DOI":"10.1109\/tgrs.2020.2988782","article-title":"RSVQA: visual question answering for remote sensing data","volume":"58","year":"2020","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"key2024022811223637300_ref024","doi-asserted-by":"publisher","first-page":"3431","DOI":"10.1109\/CVPR.2015.7298965","article-title":"Fully convolutional networks for semantic segmentation","year":"2015"},{"key":"key2024022811223637300_ref025","doi-asserted-by":"publisher","article-title":"Boundary guided context aggregation for semantic segmentation","year":"2021","DOI":"10.48550\/arXiv.2110.14587"},{"issue":"1","key":"key2024022811223637300_ref026","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.aci.2018.07.004","article-title":"Segmentation based traversing-agent approach for road width extraction from satellite images using volunteered geographic information","volume":"17","year":"2021","journal-title":"Applied Computing and Informatics"},{"key":"key2024022811223637300_ref027","doi-asserted-by":"publisher","article-title":"ResAttUNet: detecting marine debris using an attention activated residual UNet","year":"2022","DOI":"10.48550\/arXiv.2210.08506"},{"key":"key2024022811223637300_ref028","doi-asserted-by":"publisher","article-title":"Classification of high-resolution images based on MRF fusion and multiscale segmentation","year":"2008","DOI":"10.1109\/igarss.2008.4778981"},{"key":"key2024022811223637300_ref029","doi-asserted-by":"publisher","first-page":"2082","DOI":"10.1109\/igarss.2016.7729537","article-title":"The acquisition modes of COSMO-Skymed di Seconda Generazione: a new combined approach based on SAR and platform agility","year":"2016"},{"key":"key2024022811223637300_ref030","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","year":"2015"},{"issue":"4","key":"key2024022811223637300_ref031","first-page":"280","article-title":"Segmentation of high-resolution remotely sensed data-concepts, applications and problems","volume":"34","year":"2002","journal-title":"International Archives of Photogrammetry and Remote Sensing"},{"issue":"6","key":"key2024022811223637300_ref032","doi-asserted-by":"publisher","DOI":"10.3390\/rs12061050","article-title":"BRRNet: a fully convolutional neural network for automatic building extraction from high-resolution remote sensing images","volume":"12","year":"2020","journal-title":"Remote Sensing"},{"issue":"24","key":"key2024022811223637300_ref033","first-page":"256","article-title":"Remote sensing image semantic segmentation network based on multimodal feature fusion","volume":"58","year":"2022","journal-title":"Computer Engineering and Applications"},{"key":"key2024022811223637300_ref034","first-page":"5228","article-title":"Gated-SCNN: gated shape CNNs for semantic segmentation","year":"2019"},{"key":"key2024022811223637300_ref035","doi-asserted-by":"publisher","article-title":"A survey on deep learning methods for semantic image segmentation in real-time","year":"2020","DOI":"10.48550\/arXiv.2009.12942"},{"issue":"1","key":"key2024022811223637300_ref036","doi-asserted-by":"publisher","first-page":"2032924","DOI":"10.1080\/08839514.2022.2032924","article-title":"A survey on deep learning-based architectures for semantic segmentation on 2d images","volume":"36","year":"2019"},{"key":"key2024022811223637300_ref037","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1109\/igarss.2019.8898332","article-title":"A novel imaging mode for simultaneous single-\/dual- and quad-pol SAR acquisition over swaths of different widths","year":"2019"},{"key":"key2024022811223637300_ref038","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2021.104394","article-title":"Ground object information extraction from hyperspectral remote sensing images using deep learning algorithm","volume":"87","year":"2021","journal-title":"Microprocessors and Microsystems"},{"issue":"4","key":"key2024022811223637300_ref039","first-page":"293","article-title":"A new multi-level threshold segmentation method for ship targets detection in optical remote sensing images","volume":"41","year":"2011","journal-title":"Journal of China University of Science and Technology"},{"key":"key2024022811223637300_ref040","doi-asserted-by":"publisher","first-page":"11531","DOI":"10.1109\/cvpr42600.2020.01155","article-title":"ECA-net: efficient channel attention for deep convolutional neural networks","year":"2020"},{"issue":"4","key":"key2024022811223637300_ref041","first-page":"58","article-title":"Remote sensing image segmentation method using improved PSPNet with ConvCRF","volume":"28","year":"2021","journal-title":"Geomatics World"},{"key":"key2024022811223637300_ref042","doi-asserted-by":"publisher","DOI":"10.1016\/j.earscirev.2022.104110","article-title":"A comprehensive review on deep learning based remote sensing image super-resolution methods","volume":"232","year":"2022","journal-title":"Earth-Science Reviews"},{"key":"key2024022811223637300_ref043","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.isprsjprs.2021.05.004","article-title":"An attention-fused network for semantic segmentation of very-high-resolution remote sensing imagery","volume":"177","year":"2021","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"key2024022811223637300_ref044","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114417","article-title":"A review of deep learning methods for semantic segmentation of remote sensing imagery","volume":"169","year":"2020","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"key2024022811223637300_ref045","doi-asserted-by":"publisher","first-page":"71","DOI":"10.14358\/pers.80.1.71","article-title":"Fast hierarchical segmentation of high-resolution remote sensing image with adaptive edge penalty","volume":"80","year":"2014","journal-title":"Photogrammetric Engineering and Remote Sensing"},{"issue":"4","key":"key2024022811223637300_ref046","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-1505-y","article-title":"Multi-granularity semantic alignment distillation learning for remote sensing image semantic segmentation","volume":"16","year":"2022","journal-title":"Frontiers of Computer Science"},{"key":"key2024022811223637300_ref047","doi-asserted-by":"publisher","first-page":"6230","DOI":"10.1109\/cvpr.2017.660","article-title":"Pyramid scene parsing network","year":"2017"},{"issue":"2","key":"key2024022811223637300_ref048","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.geosus.2023.01.003","article-title":"Assessment of land degradation in Inner Mongolia between 2000 and 2020 based on remote sensing data","volume":"4","year":"2023","journal-title":"Geography and Sustainability"},{"key":"key2024022811223637300_ref049","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1109\/CVPRW.2018.00034","article-title":"D-LinkNet: LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction","year":"2018"}],"container-title":["International Journal of Intelligent Computing and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJICC-03-2023-0053\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJICC-03-2023-0053\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T22:54:12Z","timestamp":1753397652000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ijicc\/article\/17\/1\/20-37\/1236295"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,3]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,8,3]]},"published-print":{"date-parts":[[2024,2,29]]}},"alternative-id":["10.1108\/IJICC-03-2023-0053"],"URL":"https:\/\/doi.org\/10.1108\/ijicc-03-2023-0053","relation":{},"ISSN":["1756-378X"],"issn-type":[{"value":"1756-378X","type":"print"}],"subject":[],"published":{"date-parts":[[2023,8,3]]}}}