{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:55:04Z","timestamp":1778086504475,"version":"3.51.4"},"reference-count":46,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2018,7,18]],"date-time":"2018-07-18T00:00:00Z","timestamp":1531872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Building extraction from remotely sensed imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. Several published contributions dedicated to the applications of deep convolutional neural networks (DCNN) for building extraction using aerial\/satellite imagery exists. However, in all these contributions, high accuracy is always obtained at the price of extremely complex and large network architectures. In this paper, we present an enhanced fully convolutional network (FCN) framework that is designed for building extraction of remotely sensed images by applying conditional random fields (CRFs). The main objective is to propose a methodology selecting a framework that balances high accuracy with low network complexity. A modern activation function, namely, the exponential linear unit (ELU), is applied to improve the performance of the fully convolutional network (FCN), thereby resulting in more accurate building prediction. To further reduce the noise (falsely classified buildings) and to sharpen the boundaries of the buildings, a post-processing conditional random fields (CRFs) is added at the end of the adopted convolutional neural network (CNN) framework. The experiments were conducted on Massachusetts building aerial imagery. The results show that our proposed framework outperformed the fully convolutional network (FCN), which is the existing baseline framework for semantic segmentation, in terms of performance measures such as the F1-score and IoU measure. Additionally, the proposed method outperformed a pre-existing classifier for building extraction using the same dataset in terms of the performance measures and network complexity.<\/jats:p>","DOI":"10.3390\/rs10071135","type":"journal-article","created":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T03:50:43Z","timestamp":1531972243000},"page":"1135","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":101,"title":["Improved Fully Convolutional Network with Conditional Random Fields for Building Extraction"],"prefix":"10.3390","volume":"10","author":[{"given":"Sanjeevan","family":"Shrestha","sequence":"first","affiliation":[{"name":"NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa, Portugal"}]},{"given":"Leonardo","family":"Vanneschi","sequence":"additional","affiliation":[{"name":"NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2018,7,18]]},"reference":[{"key":"ref_1","unstructured":"Planet (2017, December 22). Planet Doubles Sub-1 Meter Imaging Capacity with Successful Launch of 6 Skysats. Available online: https:\/\/www.planet.com\/pulse\/planet-doubles-sub-1-meter-imaging-capacity-with-successful-launch-of-6-skysats\/."},{"key":"ref_2","unstructured":"Digital Globe (2017, November 12). Open Data for Disaster Recovery. Available online: https:\/\/www.digitalglobe.com\/."},{"key":"ref_3","unstructured":"FAA (2017, November 12). UAS Integration Pilot Program, Available online: https:\/\/www.faa.gov\/uas\/programs_partnerships\/uas_integration_pilot_program\/."},{"key":"ref_4","unstructured":"Space News (2017, December 12). U.S. Government Eases Restrictions on DigitalGlobe, Available online: http:\/\/spacenews.com\/40874us-government-eases-restrictions-on-digitalglobe\/."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1006\/cviu.1999.0750","article-title":"Automatic object extraction from aerial imagery\u2014A survey focusing on buildings","volume":"74","author":"Mayer","year":"1999","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_6","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"1","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_7","unstructured":"Shu, Y. (2014). Deep Convolutional Neural Networks for Object Extraction from High Spatial Resolution Remotely Sensed Imagery. [Ph.D. Thesis, University of Waterloo]."},{"key":"ref_8","unstructured":"Yuan, J. (arXiv, 2016). Automatic building extraction in aerial scenes using convolutional networks, arXiv."},{"key":"ref_9","unstructured":"Nielsen, J. (2017, July 22). Participation Inequality: Encouraging More Users to Contribute, Alertbox. Available online: http: \/\/www. useit.com\/alertbox\/participation_inequality fifth."},{"key":"ref_10","unstructured":"Marcu, A., and Leordeanu, M. (arXiv, 2016). Dual local-global contextual pathways for recognition in aerial imagery, arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yuan, J., and Cheriyadat, A.M. (2014, January 4\u20137). Learning to count buildings in diverse aerial scenes. Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Fort Worth, TX, USA.","DOI":"10.1145\/2666310.2666389"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/0734-189X(88)90016-3","article-title":"Detecting buildings in aerial images","volume":"41","author":"Huertas","year":"1998","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1080\/01431160512331326675","article-title":"Model and context\u2014Driven building extraction in dense urban aerial images","volume":"26","author":"Peng","year":"2005","journal-title":"Int. J. Remote Sens."},{"key":"ref_14","unstructured":"Levitt, S., and Aghdasi, F. (1998, January 8). An investigation into the use of wavelets and scaling for the extraction of buildings in aerial images. Proceedings of the IEEE 1998 South African Symposium on Communications and Signal Processing, Rondebosch, South Africa."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.isprsjprs.2007.05.011","article-title":"Automatic recognition of man-made objects in high resolution optical remote sensing images by SVM classification of geometric image features","volume":"62","author":"Inglada","year":"2007","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.compenvurbsys.2013.01.004","article-title":"An adaptive fuzzy-genetic algorithm approach for building detection using high-resolution satellite images","volume":"39","author":"Sumer","year":"2013","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.isprsjprs.2017.05.002","article-title":"Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks","volume":"130","author":"Alshehhi","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_18","unstructured":"Mnih, V. (2013). Machine Learning for Aerial Image Labeling. [Ph.D. Thesis, University of Toronto]."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Vakalopoulou, M., Karantzalos, K., Komodakis, N., and Paragios, N. (2015, January 26\u201331). Building detection in very high resolution multispectral data with deep learning features. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Milan, Italy.","DOI":"10.1109\/IGARSS.2015.7326158"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"481","DOI":"10.5194\/isprs-archives-XLII-1-W1-481-2017","article-title":"Building extraction from remote sensing data using fully convolutional networks","volume":"42","author":"Bittner","year":"2017","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_21","unstructured":"Lin, M., Chen, Q., and Yan, S. (arXiv, 2013). Network in network, arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., and Arbor, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, K., Xiangyu, Z., Shaoqing, R., and Jian, S. (2015, January 7\u201313). Delving deep into rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_24","first-page":"3","article-title":"Building and road detection from large aerial imagery","volume":"9405","author":"Saito","year":"2015","journal-title":"SPIE\/IS&T Electron. Imaging"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2352\/ISSN.2470-1173.2016.10.ROBVIS-392","article-title":"Multiple object extraction from aerial imagery with convolutional neural networks","volume":"60","author":"Saito","year":"2016","journal-title":"Electron. Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Huang, Z., Guangliang, C., Hongzhen, W., Haichang, L., Limin, S., and Chunhong, P. (2016, January 10\u201315). Building extraction from multi-source remote sensing images via deep deconvolution neural networks. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.","DOI":"10.1109\/IGARSS.2016.7729471"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1109\/TGRS.2016.2612821","article-title":"Convolutional neural networks for large-scale remote-sensing image classification","volume":"55","author":"Maggiori","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_28","unstructured":"Simonyan, K., and Zisserman, A. (arXiv, 2014). Very deep convolutional networks for large-scale image recognition, arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_30","first-page":"1","article-title":"Deep learning markov random field for semantic segmentation","volume":"40","author":"Liu","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., and Han, B. (2015, January 7\u201313). Learning deconvolution network for semantic segmentation. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref_32","unstructured":"Chen, L., Papandreou, G., Member, S., Kokkinos, I., Murphy, K., and Yuille, A.L. (arXiv, 2016). DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Sun, J., Zhang, X., and Ren, S. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_34","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R., and Member, S. (arXiv, 2015). SegNet: A deep convolutional encoder-decoder architecture for image segmentation, arXiv."},{"key":"ref_35","unstructured":"Clevert, D.-A., Unterthiner, T., and Hochreiter, S. (arXiv, 2015). Fast and accurate deep network learning by exponential linear units (ELUs), arXiv."},{"key":"ref_36","first-page":"109","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","volume":"24","author":"Krahenbuhl","year":"2011","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Fu, G., Liu, C., Zhou, R., Sun, T., and Zhang, Q. (2017). Classification for high resolution remote sensing imagery using a fully convolutional network. Remote Sens., 9.","DOI":"10.3390\/rs9050498"},{"key":"ref_38","unstructured":"Muruganandham, S. (2016). Semantic segmentation of satellite images using deep learning. [Master\u2019s Thesis, Lulea University of Technology]."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"14680","DOI":"10.3390\/rs71114680","article-title":"Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery","volume":"7","author":"Hu","year":"2015","journal-title":"Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.patcog.2016.07.001","article-title":"Towards better exploiting convolutional neural networks for remote sensing scene classification","volume":"61","author":"Nogueira","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s11263-007-0109-1","article-title":"Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context","volume":"81","author":"Shotton","year":"2009","journal-title":"Int. J. Comput. Vis."},{"key":"ref_42","unstructured":"Tensorflow (2017, September 11). An Open-Source Machine Learning Framework for Everyone. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_43","unstructured":"Ruder, S. (arXiv, 2016). An overview of gradient descent optimization algorithms, arXiv."},{"key":"ref_44","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_45","unstructured":"Wiedemann, C., Heipke, C., Mayer, H., and Jamet, O. (1998). Empirical evaluation of automatically extracted road axes. Empirical Evaluation Techniques in Computer Vision, IEEE Computer Society Press."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Yu, H., Yang, W., Xia, G.-S., and Liu, G. (2016). A color-texture-structure descriptor for high-resolution satellite image classification. Remote Sens., 8.","DOI":"10.3390\/rs8030259"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/7\/1135\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:12:50Z","timestamp":1760195570000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/7\/1135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,18]]},"references-count":46,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2018,7]]}},"alternative-id":["rs10071135"],"URL":"https:\/\/doi.org\/10.3390\/rs10071135","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,18]]}}}