Boundary Regularization of Urban Buildings using Mask Region Convolutional Neural Networks
Keywords:
Convolutional Neural Network, Mask R-CNN, High-Resolution Satellite Imagery, Boundary Regularization, Semantic SegmentationAbstract
Knowing the shape patterns can be highly helpful for building extraction in very high-resolution satellite (VHRS) images, which is among the most fascinating and difficult topics. For a variety of purposes, including land-cover mapping, managing urban resources, keeping track of natural disasters, and locating illegal structures. Deep-learning-based semantic segmentation networks have significantly improved building footprint generation performance when compared to more traditional processes. Some of the existing methods like CLP-CNN, and RegGAN have disadvantages that are unavoidably impacted by a number of circumstances, such as unpredictable backgrounds, blurry buildings in the background, obstructions, etc. These methods can utilize local texture and context data, but they are unable to record patterns of building shapes. A solution based on deep learning is suggested to regularize building borders in order to overcome this problem. The Mask R-CNN technique is employed for detection and Masking. For boundary regularization of buildings Guided filter is used to refine the output masks. These refined masks of two images at different timelines are used to perform change detection. This method has given the regularized building footprints as the output in the form of masks with the changes detected. The performance of the proposed system is measured and obtained an accuracy of 0.92, F1-score of 0.95, precision score of 0.93 and recall score of 0.98. By incorporating guided filters for boundary regularization and change detection, the proposed method achieves high precision in detecting building changes and offers a versatile, non-intrusive solution for various applications, including land-cover mapping and urban resource management
Downloads
References
. Phung, Van Hiep, and Eun Joo Rhee. 2019. "A High-Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets" Applied Sciences 9, no. 21: 4500. https://doi.org/10.3390/app9214500
. He, K., Gkioxari, G., Dollár, P., &Girshick, R. (2017)," Mask R-CNN", ArXiv, https://doi.org/10.48550/arXiv.1703.06870
. Jiayao Chen, Mingliang Zhou, Dongming Zhang, Hongwei Huang, Fengshou Zhang,"Quantification of water inflow in rock tunnel faces via convolutional neural network approach",Automation in Construction,Volume 123,2021,103526, https://doi.org/10.1016/j.autcon.2020.103526
. Reda K ,Kedzierski M,” Detection, Classification and Boundary Regularization of Buildings in Satellite Imagery Using Faster Edge Region Convolutional Neural Networks”, Remote Sens. 2020, 12, 2240. https://doi.org/10.3390/rs12142240
. Li Qingyu, Stefano Zorzi, Yilei Shi, Friedrich Fraundorfer, and Xiao Xiang Zhu,” RegGAN: An End-to-End Network for Building Footprint Generation with Boundary Regularization” ,Remote Sensing.2022,14, no. 8: 1835, https://doi.org/10.3390/rs14081835.
. L. Ding, H. Tang, Y. Liu, Y. Shi, X. X. Zhu and L. Bruzzone, ”Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images”, in IEEE Transactions on Image Processing, vol. 31, pp. 678-690, 2022, doi: 10.1109/TIP.2021.3134455.
. Z. Liu, H. Tang and W. Huang, ”Building Outline Delineation From VHR Remote Sensing Images Using the Convolutional Recurrent Neural Network Embedded With Line Segment Information”, in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-13, 2022, Art no. 4705713,doi: 10.1109/TGRS.2022.3154046. .
. S. Wei, T. Zhang and S. Ji,”A Concentric Loop Convolutional Neural Network for Manual Delineation-Level Building Boundary Segmentation From Remote-Sensing Images”, in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-11, 2022, Art no. 4407511, doi: 10.1109/TGRS.2021.3126704.
. X. Yan, L. Shen, J. Wang, Y. Wang, Z. Li and Z. Xu,”PANet: Pixelwise Affinity Network for Weakly Supervised Building Extraction From High-Resolution Remote 37 Sensing Images”, in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 6515905, doi: 10.1109/LGRS.2022.3205309.
. H. Jung, H. -S. Choi and M. Kang, ”Boundary Enhancement Semantic Segmentation for Building Extraction From Remote Sensed Image”, in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-12, 2022, Art no. 5215512, doi 10.1109/TGRS.2021.3108781.
. Y chen, Wei Yao, “Extraction of Orthogonal Building Boundary from Airborne Lidar Data Based on Feature Dimension Reduction”, DOI:10.5194/isprs-annals-V2-2022-351-2022
. Ji, Shunping, Yanyun Shen, Meng Lu, and Yongjun Zhang. 2019. "Building Instance Change Detection from Large-Scale Aerial Images using Convolutional Neural Networks and Simulated Samples" Remote Sensing 11, no. 11: 1343. https://doi.org/10.3390/rs11111343
. AkramEftekhari, Farhad Samadzadegan, FarzanehDadrassJavan,“Building change detection using the parallel spatial-channel attention block and edge-guided deep network” International Journal of Applied Earth Observation and Geoinformation, Volume 117,2023, 103180,ISSN 1569-8432. https://doi.org/10.1016/j.jag.2023.103180.
. Diego Alonso Javier Quispe and Jose Sulla-Torres, “Automatic Building Change Detection on Aerial Images using Convolutional Neural Networks and Handcrafted Features” International Journal of Advanced Computer Science and Applications(IJACSA), 11(6), 2020. http://dx.doi.org/10.14569/IJACSA.2020.0110683
. Luis Rodriguez-Benitez, Carlos C ordoba Ruiz, Luis Caba nero G omez, Ram on Herv as, Luis Jimenez-Linares,An Internet of Agents Architecture for Training and Deploymentof Deep Convolutional Models,Journal of Signal Processing Systems (2022) 94:283– 291,https://doi.org/10.1007/s11265-020-01602-6
. Xu, Yongyang, Liang Wu, Zhong Xie, and Zhanlong Chen. 2018. ”Building Extraction in Very High Resolution Remote Sensing Imagery Using Deep Learning and Guided Filters” Remote Sensing 10, no. 1: 144. https://doi.org/10.3390/rs10010144
. K. Wu, W. Dong, Y. Cao, X. Wang and Q. Zhao, ”An Improved Method of Median Filtering Forensics for Enhanced Image Security Detection,” 2021 International Conference on Networking and Network Applications (NaNA), 2021, pp. 308-312, doi: 10.1109/NaNA53684.2021.00060.
. M. A. Badamchizadeh and A. Aghagolzadeh, ”Comparative study of unsharp masking methods for image enhancement,” Third International Conference on Image and Graphics (ICIG’04), 2004, pp. 27-30, doi: 10.1109/ICIG.2004.50.
. K. He, G. Gkioxari, P. Doll´ar and R. Girshick, ”Mask R-CNN,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 386-397, 2020, doi:10.1109/TPAMI.2018.2844175.
. K. He, J. Sun and X. Tang, ”Guided Image Filtering,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1397-1409, 2013, doi: 10.1109/TPAMI.2012.213.
. Keiron O’Shea1 and Ryan Nash, An Introduction to Convolutional Neural Networks, arXiv:1511.08458, pp:1-11, 2015, https://doi.org/10.48550/arXiv.1511.08458
. A. Mohammad, O. S. Gullapalli, S. Vasavi and S. Jayanthi, "Updating of GIS maps with Change Detection of Buildings using Deep Learning techniques," 2022 International Conference on Futuristic Technologies (INCOFT), 2022, pp. 1-6, doi: 10.1109/INCOFT55651.2022.10094545.
. K. He, G. Gkioxari, P. Dollár and R. Girshick, "Mask R-CNN," 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980-2988, doi: 10.1109/ICCV.2017.322.
. Canny, J., A Computational Approach To Edge Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6):679–698, 1986.
. Liu, Dongju (2009). "Otsu method and K-means". Ninth International Conference on Hybrid Intelligent Systems IEEE. 1: 344–349.
. J. Long, E. Shelhamer and T. Darrell, ”Fully convolutional networks for semantic segmentation,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431-3440, doi: 10.1109/CVPR.2015.7298965
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
