PROPOSED SYSTEM for CONVERT SATELLITE SURFACE IMAGE to GEOMETRIC REPRESENTATION (MESH STRUCTURE)

raed Abd Alreda Shekan

doi:10.30572/2018/KJE/170202

Authors

raed Abd Alreda Shekan Department of Computer Science, College of Computer Science & Information Technology, University of Babylon, Iraq

DOI:

https://doi.org/10.30572/2018/KJE/170202

Keywords:

Images of Satellite, Canny Algorithm, Smart Detector, Sift, Delaunay Translation Technology, Mesh Image, Mesh Generation

Abstract

Satellite images provide a wealth of information that is used in various applications such as urban planning, environmental monitoring and terrain analysis. However, converting raw satellite data into a grid image suitable for these applications remains a challenge. this study proposes a three-stage methodology that integrates advanced image processing techniques to transform satellite image surfaces into a mesh image to enhance the utility in e geometric topology. The first phase involves applying intelligent detectors technology to identifying the edges of objects within the satellite image. By detecting high-density change points which are characteristic points at edge intersections especially at corners or angular features formed by objects. In the second stage, these features are processed using SIFT which ensures that scale-invariant features are extracted across different images. The final stage utilizes Delaunay triangulation to create the mesh, effectively converting the satellite image surfaces into a mesh representation. This mesh representation is a type of graph consisting of nodes (representing extracted features) and edges (connecting these nodes). Such a representation opens up new possibilities for analysis and study and providing an organized and detailed depiction of the Earth's surface. The mesh image produced through this methodology can be applied to numerous scientific and practical applications, bridging the gap between raw satellite data and its practical utilization in various fields. The satellite images used in this study are high-resolution raster optical images, commonly employed in applications such as urban mapping, environmental monitoring, and geographic analysis. These types of images are typically captured by satellites like Landsat. Such raster optical imagery provides detailed visual information that is essential for analyzing surface features and patterns. The results demonstrate the effectiveness of the proposed system, achieving a Ki metric value of (104.46) compared to (78.51) in previous approaches, indicating superior mesh quality

Downloads

Download data is not yet available.

References

Bern, M., Eppstein, D. and Gilbert, J., 1994. Provably good mesh generation. Journal of Computer and System Sciences, 48(3), pp.384-409.

Botsch, M., Kobbelt, L., Pauly, M., Alliez, P. and Lévy, B., 2010. Polygon mesh processing. CRC Press.

Botsch, M., Pauly, M., Kobbelt, L., Alliez, P., Lévy, B., Bischoff, S. and Röossl, C., 2007. Geometric modeling based on polygonal meshes.

Canny, J., 1986. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, pp.679-698.

Cazals, F. and Giesen, J., 2006. Delaunay triangulation-based surface reconstruction. In: Effective computational geometry for curves and surfaces. Berlin, Heidelberg: Springer, pp.231-276.

Chen, R., Yin, X., Yang, Y. and Tong, C., 2023. Multi-view Pixel2Mesh++: 3D reconstruction via Pixel2Mesh with more images. The Visual Computer, 39(10), pp.5153-5166.

Chen, S., Yin, S. and Zhao, Y., 2023. An improved Hibbard interpolation algorithm based on edge gradient feature detection using Sobel operator. Applied and Computational Engineering, 4, pp.786-794.

Cheng, K. and Idesawa, M., 1986. A simplified interpolation and conversion method of contour surface model to mesh surface model. Journal of Robotic Systems, 3(3), pp.237-247.

Da Silva, E.S., Santos, A. and Pedrini, H., 2018. Metrics for image surface approximation based on triangular meshes. Image Analysis and Stereology, 37(1), pp.71-82.

Dai, C., Wang, Z., Dong, L., Chen, Y. and Qiu, J., 2020. Surface mesh generation in parametric space using a Riemannian surface definition. International Journal of Fluid Machinery and Systems, 13(2), pp.476-484.

Dey, T.K., 2007. Delaunay mesh generation of three-dimensional domains. In: Tessellations in the sciences: virtues, techniques, and applications of geometric tilings.

Foteinos, P. and Chrisochoides, N., 2013. High-quality real-time image-to-mesh conversion for finite element simulations. In: Proceedings of the 27th International ACM Conference on International Conference on Supercomputing, pp.233-242.

Gavrilova, M.L., ed., 2008. Generalized Voronoi diagram: a geometry-based approach to computational intelligence. Vol. 158. Springer Science & Business Media.

Gbash, E.K. and Saleh, S.M., 2017. Scale-invariant feature transform algorithm with fast approximate nearest neighbor. Baghdad Science Journal, 14(3), pp.651-651.

Han, S. and Vasconcelos, N., 2008. Object-based regions of interest for image compression. In: Data Compression Conference (DCC 2008), pp.132-141. IEEE.

Lo, S.H., 2002. Finite element mesh generation and adaptive meshing. Progress in Structural Engineering and Materials, 4(4), pp.381-399.

Lowe, D.G., 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60, pp.91-110.

Mount, D.M., 2021. CMSC 754: Lecture 11 Delaunay triangulations: General properties. Department of Computer Science, University of Maryland. Available at: https://www.cs.umd.edu/class/fall2021/cmsc754/Lects/lect11-delaun-prop.pdf [Accessed 12 Jan. 2025].

Papari, G. and Petkov, N., 2011. Edge and line-oriented contour detection: State of the art. Image and Vision Computing, 29(2-3), pp.79-103.

Pontes, J.K., Kong, C., Sridharan, S., Lucey, S., Eriksson, A. and Fookes, C., 2019. Image2mesh: A learning framework for single image 3D reconstruction. In: Computer Vision–ACCV 2018, pp.365-381. Springer.

Shin, H.C., et al., 2016. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics, and transfer learning. IEEE Transactions on Medical Imaging, 35(5), pp.1285-1298.

Stillwell, J., 1995. Geometry of surfaces. Springer Science & Business Media.

Szendrei, R., Elek, I. and Márton, M., 2011. A knowledge-based approach to raster-vector conversion of large-scale topographic maps. Acta Cybernetica, 20(1), pp.145-165.

Tang, J., Han, X., Tan, M., Tong, X. and Jia, K., 2021. SkeletonNet: A topology-preserving solution for learning mesh reconstruction of object surfaces from RGB images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10), pp.6454-6471.

Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W. and Jiang, Y.G., 2018. Pixel2mesh: Generating 3D mesh models from single RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp.52-67.

Welch, W. and Witkin, A., 1994. Free-form shape design using triangulated surfaces. In: Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, pp.247-256.

Young, P.G., et al., 2008. An efficient approach to converting three-dimensional image data into highly accurate computational models. Philosophical Transactions of the Royal Society A, 366(1878), pp.3155-3173.

Zhao, B., Zhang, S., Xu, C., Sun, Y. and Deng, C., 2021. Deep fake geography? When geospatial data encounter artificial intelligence. Cartography and Geographic Information Science, 48(4), pp.338-352.

Zheng, Y., Lewis, R.W. and Gethin, D.T., 1996. Three-dimensional unstructured mesh generation: Part 1. Fundamental aspects of triangulation and point creation. Computer Methods in Applied Mechanics and Engineering, 134(3-4), pp.249-268.