Range image registration by neural network

• Autorzy: Wu X. , Li D.
• Języki publikacji: EN

Abstrakty

EN

Range image contain 3D coordinates of points on the object surface which are sampled by range sensors. In general, a sensor can capture only parts of the object of occlusion and sensing limitations. A 3D model needs to be registered using multiple range images to integrate a complete one. Instead of registering range datasets with the traditional iterative closest point (ICP) method, we use a new algorithm combined with image processing and artificial neural network (ANN). Experimental results show the validity and efficiency of our method.

Słowa kluczowe

EN

artificial neural network; iterative closest points; registration of range images

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2003
• Tom: Vol. 12, No. 2
• Strony: 257--266
• Opis fizyczny: Bibliogr. 20 poz., rys.

Twórcy

autor

Wu X.

• Institute of Pattern Recognition and Artificial Intelligence, the State Key Lab. for Image Processing & Intelligent Control, Huazhong Univ. of Sci. & Tech Wuhan, 430074, China

autor

Li D.

• Institute of Pattern Recognition and Artificial Intelligence, the State Key Lab. for Image Processing & Intelligent Control, Huazhong Univ. of Sci. & Tech Wuhan, 430074, China

Bibliografia

• [1] Faugeras O., Hebert M.: The representation, recognition, and location of 3D objects. IJPR, 5(3). 1986.
• [2] Ketharnavaz N., Mohan S.: A framework for estimation of motion parametersfrom range images. CVGIP, 45, 88-105. 1989.
• [3] Besl P.J., McKay N.D.: A method for registration of 3D shapes. IEEE Trans. on PAMI, 14(2), 239-256. 1992.
• [4] Yang Chen, Medioni G.: Object modelling by registration of multiple range images. Image and Vision Computing, 10(3), April, 145-155. 1992.
• [5] Stein.F, Medioni.G.: Structural indexing: efficient 3D object recognition. PAMI, 14(2), 125-145. 1992.
• [6] Tabbone S., Ziou D.: Subpixel positioning of edges for first and second order operators. ICPR92, 655-658. 1992.
• [7] Tabbone S.: Detecting junctions using properties of the Laplacian of Gaussian detector. ICPR94, (A:52-56). 1994.
• [8] Turk G., Levoy M.: Zippered polygon meshes from range images. Proc. of SIGGRAPH'94, Orlando, Florida, July 24-29, 311-318. 1994.
• [9] Zhang Z.Y.: Iterative point matching for registration of free-form curves and surfaces. IJCV, 13(2), Oct., 119-152. 1994.
• [10] Bergevin R., Laurendeau D., Poussart D.: Registering range views of multpart objects. CVIU, 61(1), 1-16. 1995.
• [11] Takeshi Masuda, Naokazu Yokoya: A robust method for registration and segmentation of multiple range images. CVIU, 61(3), 295-307. 1995.
• [12] Feldmar J., Ayache N.: Rigid, afine and locall affine registration of free-form surfaces. Int. J. Computer Vision, 18(2), 99-199. 1996.
• [13] Dorai C., Weng J., Jain A.: Optimal registration of object views using range data. Trans. PAMI, 19(10), 1131-1138. 1997.
• [14] Johnson A., Kang S.: Registration and integration of textured 3D data. Proc. 3D. 1997.
• [15 Pedersini F., Sarti A., Tubaro S.: Estimation and compensation of subpixel edge localization error. Trans. PAMI, 19(11) , 1278-1284. 1997.
• [16] Pulli K.: Surface Reconstruction and Display from Range and ColorD ata", Ph. D. Dissertation, University of Washington. 1997.
• [17] Rioux M., Godin G., Blais F., Baribeau R.: High resolution digital 3D imaging of large structure. Proc of SPIE, 3Dimensional Image Capture, 3303, 109-118. 1997.
• [18] Eggert D. W., Fitzgibbon A.W., Fisher R.B.: Simultaneous registration of multiple range views for use in reverse engineering of CAD models CVIU, 69(3), 253-272. 1998.
• [19] Schütz C., Jost T., Hügli H.: Semi-automatic 3D object digitizing system using range images. Proc. of Asian Conf. on Computer Vision, Jan. 1998.
• [20] Pulli K.: Multiview registration for large data sets. Proc. 3DIM. 1999.