Abstract
The extraction of road centreline from a remote sensing image is an important part of obtaining and updating basic geographic information data. In view of the shortcomings of traditional road centreline extraction algorithm, such as the presence of burrs, lengthy time consumption and ineffective extraction of the centreline around intersections, we propose an algorithm based on an improved beamlet transform combined with K-means clustering to extract the road centreline of high-resolution remote sensing images. The proposed method includes the following steps. Firstly, K-means clustering is used to identify the road area. Secondly, the improved beamlet transform algorithm is utilised to extract the road centreline. Reducing the beamlet base and simplifying the beamlet dictionary reduces the algorithm complexity. By adding energy threshold and direction constraint, each binary block is guaranteed to contain only one optimal base that avoids the overlapping and missing of the beamlet base. Lastly, a connection algorithm is designed to connect the breaks of some road centrelines. Experimental results show that the proposed algorithm can accurately extract the road centreline, effectively form high-resolution remote sensing images and had good anti-noise ability. Compared with traditional beamlet transform, the proposed beamlet transform achieves better results.
Similar content being viewed by others
References
Cheng, J.H.; Gao, G.; Ku, X.S.: Review of road network extraction from SAR images. J. Image Graph. 18, 11–23 (2013)
Cheng, G.L.; Wang, Y.; Xu, S.B.; Wang, H.; Xiang, S.; Pan, C.: Automatic road detection and centreline extraction via cascaded end-to-end convolutional neural network. IEEE Trans. Geosci. Remote. 55: 3322–3337 (2017) https://doi.org/10.1109/TGRS.2017.2669341
Song, F.L.; Liu, R.: Road extraction from remotely sensed image: review and prospects. Water Conserv. Sci. Technol. Econ. 11, 636–638 (2005)
Poullis, C.; You, S.Y.: Delineation and geometric modeling of road networks. Isprs J. Photogramm. 65: 165–181 (2010). https://doi.org/10.1016/j.isprsjprs.2009.10.004
Shi, W.; Miao, Z.; Debayle, J.: An integrated method for urban main-road centreline extraction from optical remotely sensed imagery. Ieee T Geosci Remote. 52, 3359–3372 (2013). https://doi.org/10.1109/TGRS.2013.2272593
Zhao, W.Z.; Luo, L.Q.; Guo, Z.; Yue, J.; Yu, X.Y.; Liu, H.; Wei, J.: Road Extraction in Remote Sensing Images Based on Spectral and Edge Analysis. Spectrosc Spect Anal. 35, 2814–2819 (2015). https://doi.org/10.3964/j.issn.1000-0593(2015)10-2814-06
Shanmugam, L.; Kaliaperumal, V.: Junction-aware water flow approach for urban road network extraction. IET Image Process 10(3), 227–234 (2016). https://doi.org/10.1049/iet-ipr.2015.0263
Gaetano, R.; Zerubia, J.; Scarpa, G.; Poggi.: Morphological road segmentation in urban areas from high resolution satellite images. In: Proceedings Inter Conference on Digital Signal Processing, pp. 1–8 (2011). https://doi.org/10.1109/icdsp.2011.6005015
Li, M.; Stein, A.; Bijker, W.: Zhan, Q.: Region- based urban road extraction from VHR satellite images using Binary Partition Tree. Int J Appl Earth Obs Geoinf, 44:217–225 (2016). https://doi.org/10.1016/j.jag.2015.09.005
Das, S.; Mirnalinee, T.T.; Varghese, K.: Use of Salient features for the design of a multistage framework to extract roads from high-resolution multispectral satellite images. IEEE Trans. Geosci. Remote Sens. 49(10), 3906–3931 (2011). https://doi.org/10.1109/tgrs.2011.2136381
Zang, Y.; Wang, C.; Yu, Y.; Luo, L.; Yang, K.; Li, J.: Joint enhancing filtering for road network extraction. IEEE Trans. Geosci. Remote Sens. 55(3), 1511–1525 (2017). https://doi.org/10.1109/tgrs.2016.2626378
Hu, J.G.; Zhang, X.; Shen, X.; Zhang, C.: A method of road extraction in high-resolution remote sensing imagery based on object-oriented image analysis. Remote Sens. Technol. Appl. 21, 184–188 (2006). https://doi.org/10.1007/s11769-006-0026-1
Cao, F.Z.; Zhu, S.; Zhu, B.; Li, R.; Meng, W.: Tracking road centrelines from remotely sensed imagery using mean shift and Kalman filtering. Acta Geodaetica et Cartographica Sinica. 45, 205–212 (2016). https://doi.org/10.11947/j.AGCS.2016.20140610
Wang, Q.; Gao, J.; Yuan, Y.: Embedding structured contour and location prior in siamesed fully convolutional networks for road detection. IEEE Trans. Intell. Transp. Syst. 19(1):230–241,(2017). https://doi.org/10.1109/tits.2017.2749964
Mohan, R.: Deep deconvolutional networks for scene parsing. Comput. Sci. 1, 1–8 (2014)
Alshehhi, R.; Marpu, P.R.; Woon, W.L.; Dalla Mura, M.: Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. Isprs J. Photogramm.130, 139–149 (2017). https://doi.org/10.1016/j.isprsjprs.2017.05.002
Rezaee, M.; Zhang, Y.: Road detection using deep neural network in high spatial resolution images. In: Proceedings of 2017 Joint Urban Remote Sensing Event (JURSE); pp. 1–4. https://doi.org/10.1109/JURSE.2017.7924619
Li, M.; Stein, A.; Bijker, W.; Zhan, Q.: Region-based urban road extraction from VHR satellite images using binary partition tree. Int. J. Appl. Earth Obs. 44, 217–225 (2016). https://doi.org/10.1016/j.jag.2015.09.005
Alshehhi, R.; Marpu, P.R.: Hierarchical graph-based segmentation for extracting road networks from high-resolution satellite images. Isprs J Photogramm. 126, 245–260 (2017). https://doi.org/10.1016/j.isprsjprs.2017.02.008
Amo, M.; Martínez, F.; Torre, M.: Road extraction from aerial images using a region competition algorithm. IEEE Trans. Image Process. 15, 1192–1201 (2006). https://doi.org/10.1109/tip.2005.864232
Xiao, Y.; Tien, D.; Jia, X.: Region-based perceptual grouping for road extraction from high-resolution images. Int. J. Intell. Syst. Technol. Appl. 9, 208–217 (2010). https://doi.org/10.1504/ijista.2010.036576
Shi, W.; Miao, Z.; Wang, Q.; Zhang, H.: Spectral–spatial classification and shape features for urban road centreline extraction. Ieee Geosci Remote S. 11, 788–792 (2013). https://doi.org/10.1109/LGRS.2013.2279034
Zhang, Q.; Couloigner, I.: Accurate centreline detection and line width estimation of thick lines using the radon transform. IEEE Trans. Image Process. 16, 310–316 (2007). https://doi.org/10.1109/tip.2006.887731
Soille, P.: Morphological Image Analysis: Principles and Applications. Springer, Berlin (2013)
Liu, R.; Song, J.; Miao, Q.; Xu, P.; Xue, Q.: Road centrelines extraction from high resolution images based on an improved directional segmentation and road probability. Neurocomputing. 212, 88–95 (2016). https://doi.org/10.1016/j.neucom.2016.03.095
Donoho, D.L.; Huo, X.: Beamlet pyramids: A new form of multiresolution analysis, suited for extracting lines, curves, and objects from very noisy image data. Proc. SPIE. 4119(1): 434–444 (2000). https://doi.org/10.1117/12.408630
Donoho, D.L.; Huo, X.: Beamlets and multiscale image analysis. In: Multiscale and multiresolution methods, Springer. pp. 149–196 (2002)
Huo, X.; Chen, J.: JBEAM: multiscale curve coding via beamlets. IEEE Trans. Image Process. 14: 1665–1677 (2005). https://doi.org/10.1109/tip.2005.857273
Jing, Z.H.; Zhang, S.H.; Li, Q.: Fault identification and linear feature extraction based on beamlet transform. Geophys. Geochem. Explor. 32 (2013). https://doi.org/10.11720/j.issn.1000-8918.2013.3.31
Ying, L.; Salari, E.: Beamlet transform based technique for pavement image processing and classification. In: Proceedings of 2009 IEEE International Conference on Electro/Information Technology; pp. 141–145 (2009). https://doi.org/10.1109/EIT.2009.5189598
Mei, X. M.; Zhang, L. P.; Li, P. X.: Linear features extraction from remote sensing image with Beamlet transform. Appl. Res. Comput. 5 (2008). https://doi.org/10.1142/S0217595908001626
MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of Proceedings of the fifth Berkeley Symposium on Mathematical Statistics and Probability, pp. 281–297 (1967)
Hua, C.; Shuhai, C.; Ping, Z.; Weidong, Y.: Application of K-means classification in remote sensing. Infrared Laser Eng. 2, 10 (2000)
Maurya, R.; Gupta, P.; Shukla, A.S.: Road extraction using k-means clustering and morphological operations. In: Proceedings of 2011 International Conference on Image Information Processing; pp. 1–6. https://doi.org/10.1109/ICIIP.2011.6108839
Yang, X.; Wanli, M.: Road region segmentation of remote sensing images based on K-means and PCNN. In: Proceedings of Proceedings of the 3rd International Conference on Multimedia and Image Processing, pp. 36–40
Chen, T.; Ai, T.: Automatic extraction of skeleton and center of area feature. Geom. Inf. Sci. 29: 443–446 (2004). https://doi.org/10.13203/j.whugis2004.05.015
Lin, Z.; Yan, J.; Yuan, Y.: Target detection for SAR images based on beamlet transform. Multimedia Tools Appl. 75: 2189–2202 (2016). https://doi.org/10.1007/s11042-014-2401-8
Xu, Z.G.; Zhao, X.; Yang, L.; Wei, N.; Zhang, L.: Quick and precise road marking segmentation algorithm based on Beamlet. Chang’an Daxue Xuebao (Ziran Kexue Ban)/J. Chang’an Univ.(Natural Sci. Ed.). 33, 101–108 (2013). https://doi.org/10.19721/j.cnki.1671-8879.2013.05.018
Zeng, J.X.; Zhou, L.L.: Complex image line feature extraction based on improved Beamlet transform and the Canny operator. J. Image Gr. 7 (2012)
Wiedemann, C.; Heipke, C.; Mayer, H.; Jamet, O.: Empirical evaluation of automatically extracted road axes. In: Empirical evaluation techniques in computer vision, Citeseer: Vol. 12, pp. 172–187 (1998)
Wessel, B.; Wiedemann, C.: Analysis of automatic road extraction results from airborne SAR imagery. Int. Archiv. Photogram. Remote Sens. Spatial Inf. Sci. 34, 105–112 (2003). https://doi.org/10.1016/j.applthermaleng.2014.06.068
Acknowledgements
Thanks to the supported of the National Natural Science Foundation of China (Grant No. 41701537) and the CAS Strategic Priority Research Program (Grant No. XDA19030402). The authors acknowledge all the valuable ideas and suggestions provided by the teachers involved in this work.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Rights and permissions
About this article
Cite this article
Fu, H., Deng, F., Shao, Y. et al. Road Centreline Extraction of High-Resolution Remote Sensing Image with Improved Beamlet Transform and K-Means Clustering. Arab J Sci Eng 46, 4153–4162 (2021). https://doi.org/10.1007/s13369-021-05412-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-021-05412-1