Abstract

In recent years, algorithms have been developed to decompose images into structural and textural components. Radar images, known for all-weather capabilities, prove increasingly valuable in equatorial regions with quasi-permanent cloud cover. As the African population undergoes rapid demographic growth, it becomes imperative to establish automatic mapping methods for radar images. This facilitates timely urban evolution studies within territorial jurisdictions. This paper presented an approach to delineate urban boundaries in synthetic aperture radar (SAR) images from European Remote Sensing Satellite (ERS)-1, focusing on Douala, Cameroon. Our method emphasizes detecting key features, including road networks, urban structures, inhabited areas, and wetlands, considering the unique granularity of SAR imagery. The decomposition technique was applied to road network detection in aerial or satellite imagery. The algorithmic chain employs a combination of textural image analysis and mathematical morphology, utilizing set theory for road network extraction from radar images and aerial photography. Additionally, linear structures are detected through mathematical morphology, followed by the refinement of extracted roads using statistical active contours. Applying wavelet transforms, filtering by rectangularity measure, histogram analysis, Canny contour detection, morphological operators, and watershed transformation demonstrated precise road detection, effectively distinguishing them from other objects. The algorithm proves efficient across urban, rural, and peri-urban contexts. For inhabited areas and wetlands, the algorithm adapts to higher gray levels associated with rooftops and accurately detects extremely low gray levels indicative of water bodies.

Keyword

Linear structures, Watershed lines, Mathematical morphology, Segmentation, Urban area, First order histogram, Wavelet filtering.

Cite this article

Nkomba FE, Kombe T, Ele P

Refference

[1][1]Gitas IZ, Polychronaki A, Katagis T, Mallinis G. Contribution of remote sensing to disaster management activities: a case study of the large fires in the Peloponnese, Greece. International Journal of Remote Sensing. 2008; 29(6):1847-53.

[2][2]Rodriguez H, Quarantelli EL, Dynes RR, Thomas DS, Ertugay K, Kemec¸ S. The role of geographic information systems/remote sensing in disaster management. Handbook of Disaster Research. 2007:83-96.

[3][3]Mohammadzadeh A, Tavakoli A, Valadan ZMJ. Road extraction based on fuzzy logic and mathematical morphology from pan‐sharpened IKONOS images. The Photogrammetric Record. 2006; 21(113):44-60.

[4][4]Chaudhuri D, Kushwaha NK, Samal A. Semi-automated road detection from high resolution satellite images by directional morphological enhancement and segmentation techniques. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2012; 5(5):1538-44.

[5][5]Jinxin C, Qixin S, Liguang S. A methodology for automatic detection and extraction of road edges from high resolution remote sensing images. In international conference on industrial technology 2006 (pp. 69-74). IEEE.

[6][6]Sun J, Mao S. River detection algorithm in SAR images based on edge extraction and ridge tracing techniques. International Journal of Remote Sensing. 2011; 32(12):3485-94.

[7][7]Mena JB, Malpica JA. An automatic method for road extraction in rural and semi-urban areas starting from high resolution satellite imagery. Pattern Recognition Letters. 2005; 26(9):1201-20.

[8][8]Zhang R, Lin X. Automatic road extraction based on local histogram and support vector data description classifier from very high resolution digital aerial. In international geoscience and remote sensing symposium 2010 (pp. 441-4). IEEE.

[9][9]Zhu H, Li C, Zhang L, Shen J. River channel extraction from SAR images by combining gray and morphological features. Circuits, Systems, and Signal Processing. 2015; 34:2271-86.

[10][10]Herumurti D, Uchimura K, Koutaki G, Uemura T. Urban road extraction based on hough transform and region growing. In the 19th korea-japan joint workshop on frontiers of computer vision 2013 (pp. 220-4). IEEE.

[11][11]Wei QR, Feng DZ. Extracting line features in SAR images through image edge fields. IEEE Geoscience and Remote Sensing Letters. 2016; 13(4):540-4.

[12][12]Shackelford AK, Davis CH. Urban road network extraction from high-resolution multispectral data. In 2nd GRSS/ISPRS joint workshop on remote sensing and data fusion over urban areas 2003 (pp. 142-6). IEEE.

[13][13]Naouai M, Hamouda A, Akkari A, Weber C. New approach for road extraction from high resolution remotely sensed images using the quaternionic wavelet. In pattern recognition and image analysis: 5th Iberian conference, Ib PRIA, las palmas de gran canaria, spain 2011 (pp. 452-9). Springer Berlin Heidelberg.

[14][14]Begni G, Escafadal R, Fontannaz D, Hong-nga NAT. Remote sensing: a tool for monitoring and assessing desertification, CSFD, 2005; 1-48.

[15][15]Emran A. Landsat global data on Africa, an example: tracking the spatio-temporal evolution of the city of Rabat in Morocco. In seminars of the United Nations program on space applications. United Nations, New York, 2006 (pp. 15-24). NASA Astrophysics Data System.

[16][16]Pouyllau M. Remote sensing and the third world Methodologies, practices, new fields and new issues. CNRS editions, Paris; 1991.

[17][17]Tonyé E, Akono A, Nyoungui AN, Assako RJ. Extraction of the road network on an ERS-2 SAR image and on an HRV (XS) SPOT image by texture analysis and mathematical morphology: application to the city of Yaoundé (Cameroon). Remote sensing in the French-speaking world: critical analysis and perspectives. Ed. AUPELF UREF. 2000:95-103.

[18][18]Coster M, Chermant JL. Précis danalyse d images. Presses du CNRS, Paris; 1989.

[19][19]Schmitt M, Mattioli J. Morphologie mathématique. Presses des MINES; 2013.

[20][20]Najman L, Talbot H. Mathematical morphology: from theory to applications. John Wiley & Sons; 2013.

[21][21]Kombe T, Assako RJ. Mathematical morphology applied to rso images for the differentiation of urban fabrics: case of the city of Douala (Cameroon). Remote Sensing Review. 2007; 7(1-2):3-4.

[22][22]Nicolas G, Denis L, Tupin F. Detection of line structures in synthetic aperture radar images by generalized likelihood ratio test. In CAP-RFIAP. 2020:1-7.

[23][23]Tupin F, Gouinaud C, Maitre H, Cretez JP. Detection of the road network on ERS 1 radar images. RFIA AFCET 96 (Rennes). 1996; 43:52.

[24][24]MaIrte H. A panorama of the hough transform. Signal Processing. 1985; 2(4).

[25][25]Poncelet N, Cornet Y. Hough transform and lineament detection on satellite images and digital terrain models. Bulletin of the Geographical Society of Liège. 2010; 145-56.

[26][26]Tupin F, Trouve E, Descombes X, Nicolas JM, Maitre H. Improving IFSAR phase unwrapping by early detection of noninterferometric features. In microwave sensing and synthetic aperture radar 1996 (pp. 250-61). SPIE.

[27][27]Kombe T, Assato RA. Mathematical morphology applied to SAR images for the detection of urban areas: the case study of the city of Douala. Revue Télédétection. 2007; 7(1-2):3-4.

[28][28]Lacoste C. Extraction de reseaux lineiques a partir dimages satellitaires et aeriennes par processus ponctuels marques (Doctoral dissertation, Universite Nice Sophia Antipolis). 2004.

[29][29]Zhang X, Ma W, Li C, Wu J, Tang X, Jiao L. Fully convolutional network-based ensemble method for road extraction from aerial images. IEEE Geoscience and Remote Sensing Letters. 2019; 17(10):1777-81.

[30][30]Li P, He X, Qiao M, Cheng X, Li Z, Luo H, et al. Robust deep neural networks for road extraction from remote sensing images. IEEE Transactions on Geoscience and Remote Sensing. 2020; 59(7):6182-97.

[31][31]Li P, He X, Qiao M, Cheng X, Li J, Guo X, et al. Exploring label probability sequence to robustly learn deep convolutional neural networks for road extraction with noisy datasets. IEEE Transactions on Geoscience and Remote Sensing. 2021; 60:1-8.

[32][32]Yang K, Yi J, Chen A, Liu J, Chen W. ConDinet++: full-scale fusion network based on conditional dilated convolution to extract roads from remote sensing images. IEEE Geoscience and Remote Sensing Letters. 2021; 19:1-5.

[33][33]Tan X, Xiao Z, Wan Q, Shao W. Scale sensitive neural network for road segmentation in high-resolution remote sensing images. IEEE Geoscience and Remote Sensing Letters. 2020; 18(3):533-7.

[34][34]Zhu Q, Zhang Y, Wang L, Zhong Y, Guan Q, Lu X, et al. A global context-aware and batch-independent network for road extraction from VHR satellite imagery. ISPRS Journal of Photogrammetry and Remote Sensing. 2021; 175:353-65.

[35][35]Wu Q, Luo F, Wu P, Wang B, Yang H, Wu Y. Automatic road extraction from high-resolution remote sensing images using a method based on densely connected spatial feature-enhanced pyramid. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2020; 14:3-17.

[36][36]Zhou M, Sui H, Chen S, Wang J, Chen X. BT-RoadNet: a boundary and topologically-aware neural network for road extraction from high-resolution remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing. 2020; 168:288-306.

[37][37]Wu Z, Zhang J, Zhang L, Liu X, Qiao H. Bi-HRNet: a road extraction framework from satellite imagery based on node heatmap and bidirectional connectivity. Remote Sensing. 2022; 14(7):1732.

[38][38]Yang Z, Zhou D, Yang Y, Zhang J, Chen Z. TransRoadNet: a novel road extraction method for remote sensing images via combining high-level semantic feature and context. IEEE Geoscience and Remote Sensing Letters. 2022; 19:1-5.

[39][39]Chen SB, Ji YX, Tang J, Luo B, Wang WQ, Lv K. DBRANet: road extraction by dual-branch encoder and regional attention decoder. IEEE Geoscience and Remote Sensing Letters. 2021; 19:1-5.

[40][40]Dong S, Chen Z. Block multi-dimensional attention for road segmentation in remote sensing imagery. IEEE Geoscience and Remote Sensing Letters. 2021; 19:1-5.

[41][41]Liu Z, Wang M, Wang F, Ji X. A residual attention and local context-aware network for road extraction from high-resolution remote sensing imagery. Remote Sensing. 2021; 13(24):1-20.

[42][42]Hu A, Chen S, Wu L, Xie Z, Qiu Q, Xu Y. WSGAN: an improved generative adversarial network for remote sensing image road network extraction by weakly supervised processing. Remote Sensing. 2021; 13(13):1-18.

[43][43]Yang C, Wang Z. An ensemble Wasserstein generative adversarial network method for road extraction from high resolution remote sensing images in rural areas. IEEE Access. 2020; 8:174317-24.

[44][44]Abdollahi A, Pradhan B, Sharma G, Maulud KN, Alamri A. Improving road semantic segmentation using generative adversarial network. IEEE Access. 2021; 9:64381-92.

[45][45]Shamsolmoali P, Zareapoor M, Zhou H, Wang R, Yang J. Road segmentation for remote sensing images using adversarial spatial pyramid networks. IEEE Transactions on Geoscience and Remote Sensing. 2020; 59(6):4673-88.

[46][46]Zhang L, Lan M, Zhang J, Tao D. Stagewise unsupervised domain adaptation with adversarial self-training for road segmentation of remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing. 2021; 60:1-3.

[47][47]Wei Y, Ji S. Scribble-based weakly supervised deep learning for road surface extraction from remote sensing images. IEEE Transactions on Geoscience and Remote Sensing. 2021; 60:1-2.

[48][48]Ren Y, Yu Y, Guan H. DA-CapsUNet: a dual-attention capsule U-Net for road extraction from remote sensing imagery. Remote Sensing. 2020; 12(18):1-17.

[49][49]Shao S, Xiao L, Lin L, Ren C, Tian J. Road extraction convolutional neural network with embedded attention mechanism for remote sensing imagery. Remote Sensing. 2022; 14(9):1-18.

[50][50]Li P, He X, Qiao M, Miao D, Cheng X, Song D, et al. Exploring multiple crowdsourced data to learn deep convolutional neural networks for road extraction. International Journal of Applied Earth Observation and Geoinformation. 2021; 104:102544.

[51][51]Lin Y, Wan L, Zhang H, Wei S, Ma P, Li Y, et al. Leveraging optical and SAR data with a UU-Net for large-scale road extraction. International Journal of Applied Earth Observation and Geoinformation. 2021; 103:102498.

[52][52]Zhang J, Hu Q, Li J, Ai M. Learning from GPS trajectories of floating car for CNN-based urban road extraction with high-resolution satellite imagery. IEEE Transactions on Geoscience and Remote Sensing. 2020; 59(3):1836-47.

[53][53]Girard MC, Girard CM. Télédétection appliquée. Zones tempérées intertropicales [Applied remote sensing in intertropical temperate zones]. Partie pédologie. 1989:192-233.

[54][54]Wang L. Un nouvel espace de texture. International Journal of Remote Sensing. 1994; 15(8):1713-23.

[55][55]Cocquerez JP, Philipp S, Bolon P, Chassery JM, Demigny D, Graffigne C, et al. Analyse dimages: filtrage et segmentation. Masson; 1995.

[56][56]Vincent L, Soille P. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis & Machine Intelligence. 1991; 13(06):583-98.

[57][57]Zheng C, Yao H. Segmentation for remote-sensing imagery using the object-based Gaussian-Markov random field model with region coefficients. International Journal of Remote Sensing. 2019; 40(11):4441-72.

[58][58]https://theses-algerie.com/2803423358558140/memoire-de-magister/universite-abou-bekr-belkaid---tlemcen/extraction-de-r%C3%A9seaux-lin%C3%A9iques-%C3%A0-partir-des-images-%C3%A0-hauter%C3%A9solution. Accessed 10 July 2023.

[59][59]Risson V. Application de la morphologie mathématique à lanalyse des conditions déclairage des images couleur (Doctoral dissertation, École Nationale Supérieure des Mines de Paris). 2001.

[60][60]Beucher S. Segmentation dimages et morphologie mathématique (Doctoral dissertation, Ecole Nationale Supérieure des Mines de Paris). 1990.

[61][61]Attia D. Segmentation dimages par combinaison adaptative couleur-texture et classification de pixels.: applications à la caractérisation de lenvironnement de réception de signaux GNSS (Doctoral dissertation, Université de Technologie de Belfort-Montbeliard). 2013.

[62][62]Strauss O, Comby F. Fuzzy morphological operations with variable kernels for omnidirectional single-viewpoint images. Signal Processing. 2005; 22(5):1-23.