IJMTES – EXTRACTION OF VEHICLES FROM REMOTE SENSING IMAGES USING OBJECT BASED IMAGE ANALYSIS

Journal Title : International Journal of Modern Trends in Engineering and Science

Author’s Name : Sarigha V  unnamed

Volume 03 Issue 09 2016

ISSN no:  2348-3121

Page no: 32-35

Abstract – In modern vast encounter to perfectly identify and trace geospatial objects with consistent of small object outlines from Remote Sensing (RS) images such as vehicles. In this paper, obtainable on Object Based Image Analysis (OBIA) is defined to address the encounter. It signifies the extraction and segmentation for small objects like vehicles from the earth’s surface. Hence it delivers object oriented image methodology, the information is segmented on the base of significant image objects rather than the conventional pixel based approach. The application of this technique can be identifying vehicles with different shapes, color and its ability is found to be excessive addition to the existing pixel based image technology. This proposed method which is used to segment and extract image object more efficient than previous methods. In this methodology, to meet color, shape and texture property from the large-scale high-resolution RS images. The results show that OBIA improves the accuracy of vehicles extraction by using Multi-Resolution segmentation and the performance efficiency reaches high level. 

Keywords— Geographical information system, geospatial feature, object-based image analysis (OBIA), remote sensing (RS), high-resolution 

Reference

  1. C. B. Jones, Geographical Information Systems and Computer Cartography.Evanston,IL, USA:Routledge, 2014.
  2. R. R. Vatsavai, A. Cheriyadat, and S.Gleason, “Unsupervised semantic labeling framework for identification of complex facilities in high-resolution remote sensing images,” in Proc.IEEE ICDMW, 2010, pp.273–280.
  3. O.Benarchidetal., “Building extraction using object-based classification and shadow information in very high resolution multi spectral images, a case study: Tetuan, Morocco,” Can.J.Image Process. Comput. Vis., vol.4, no.1, pp.1–8, Jan.2013.
  4. J.Wang,J.Qian,andR.Ma,“Urban road information extraction from high resolution remotely sensed image based on semantic model,” presented at the IEEE 21st Int. Conf. GEOINFORMATICS, 2013.
  5. C.Chenetal.,“Extraction of bridges overwater from high-resolution optical remote-sensing images based on mathematical morphology,” Int. J.Remote Sens.,vol.35,no.10,pp.3664–3682, May2014.
  6. ENVI, “Feature Extraction with Rule Based Classification Tutorial,” Tech. Online Rep.,Accessed by May2014. [Online]. Available: http:// www.exelisvis.com/portals/0/pdfs/envi/FXRuleBasedTutorial.pdf
  7. P.Zhao,T.Foerster,and P.Yue, “The geoprocessing web, ”Comput. Geosci.,vol.47, pp.3–12, Oct.2012.
  8. P. Liang, G. Teodoro, H. Ling, E. Blasch, G. Chen, and L. Bai, “Multiple Kernel Learning for vehicle detection in wide area motion imagery,” in Proc. 15th Int. Conf. Inf. Fusion, 2012, pp. 1629–1636.
  9. K. Ali, F. Fleuret, D. Hasler, and P. Fua, “A real-time deformable detector,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 2, pp. 225–239, Feb. 2012.
  10. J. Leitloff, S. Hinz, and U. Stilla, “Vehicle detection in very high resolution satellite images of city areas,” IEEE Trans. Geosci. Remote Sens.,vol. 48, no. 7, pp. 2795–2806, Jul. 2010.
  11. H. Sun, X. Sun, H. Wang, Y. Li, and X. Li, “Automatic target detection in high-resolution remote sensing images using spatial sparse coding bagof-words model,” IEEE Geosci. Remote Sens. Lett., vol. 9, no. 1, pp. 109–113, Jan. 2012.
  12. X. Sun, H. Wang, and K. Fu, “Automatic detection of geospatial objects using taxonomic semantics,” IEEE Geosci. Remote Sens. Lett., vol. 7,no. 1, pp. 23–26, Jan. 2010.
  13. D. C. Ciresan, U. Meier, and J. Schmidhuber, “Multi-column deep neural networks for image classification,” in Proc. IEEE Comput. Vis. Pattern Recognit., Jun. 2012, pp. 3642–3649.