Road network extraction in classified SAR images using genetic algorithm

Abstract

Due to the complicated background of objectives and speckle noise, it is almost impossible to extract roads directly from original synthetic aperture radar (SAR) images. A method is proposed for extraction of road network from high-resolution SAR image. Firstly, fuzzy C means is used to classify the filtered SAR image unsupervisedly, and the road pixels are isolated from the image to simplify the extraction of road network. Secondly, according to the features of roads and the membership of pixels to roads, a road model is constructed, which can reduce the extraction of road network to searching globally optimization continuous curves which pass some seed points. Finally, regarding the curves as individuals and coding a chromosome using integer code of variance relative to coordinates, the genetic operations are used to search global optimization roads. The experimental results show that the algorithm can effectively extract road network from high-resolution SAR images.

Keywords

genetic algorithm / road network extraction / SAR image / fuzzy C means

References

[1] BonnefonR, DhereteP, DesachyJ. Geographic information system updating using remote sensing images [J]. Pattern Recognition Letters, 2002, 23(9): 1 073-1 083

[2] Van CleynenbreugetJ, FierenF, SuetensP, et al.. Delineating road structures on satellite imagery by a GIS-guided technique [J]. Photogrammetric Engineering and Remote Sensing, 1990, 56(6): 893-898

[3] GemanD, JedynakB. An active testing model for tracking roads in satellite images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(1): 1-14

[4] CaoWu-feng, QinQi-ming. A knowledge-based research for road extraction from digital satellite images [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 1998, 34(2–3): 254-263(in Chinese)

[5] MerletN, ZerubiaJ. New prospects in line detection by dynamic programming [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(4): 426-431

[6] SamadaniR, VeseckyJ F. Finding curvilinear features in speckled images [J]. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(7): 669-6673

[7] HuberR, LangK. Road extraction from high-resolution airborne SAR using operator fusion [A]. International Geoscience and Remote Sensing Symposium (IGARSS) [C]. Sydney Institute of Electrical and Electronics Engineers Inc., 2001, 6: 2 813-2 815

[8] LiSu-dan, ZhangCui, WangZheng-zhi. A study of road network detection method for SAR images [J]. Journal of Astronautics, 2002, 23(1): 17-24(in Chinese)

[9] JeonB K, JangJ H, HongK S. Road detection in space borne SAR images based on ridge extraction [A]. IEEE International Conference on Image Processing [C], 1999, Kobe, Institute of Electrical and Electronics Engineers Computer Society: 735-739

[10] TupinF, ManginJ F, NicolasJ M, et al.. Detection of linear features in SAR images: application to road network extraction [J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(2): 434-453

[11] ShiWen-zhong, ZhuChang-qing. The line segment match for extracting road network from high-resolution satellite images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(2): 511-514

[12] Dell’AcquaF, GambaP. Detection of urban structures in SAR images by robust fuzzy clustering algorithm: the example of street tracking [J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(10): 2 287-2 296

[13] DoucetteP, AgourisP, StefanidisA, et al.. Self-organised clustering for road extraction in classified imagery [J]. Photogammetry and Remote Sensing, 2001, 55(5–6): 347-358

[14] JeonB K, JangJ H, HongK S. Road detection in spaceborne SAR images using a genetic algorithm [J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(1): 22-29

[15] JeonB K, JangJ H, HongK S. Road detection in SAR images using genetic algorithm with region growing concept [A]. IEEE International Conference on Image Processing [C], 2000, Vancouver, Institute of Electrical and Electronics Engineers Computer Society: 688-691