000 04270nam a22005175i 4500
001 978-3-319-48493-8
003 DE-He213
005 20200421111704.0
007 cr nn 008mamaa
008 161209s2016 gw | s |||| 0|eng d
020 _a9783319484938
_9978-3-319-48493-8
024 7 _a10.1007/978-3-319-48493-8
_2doi
050 4 _aTA1637-1638
050 4 _aTA1634
072 7 _aUYT
_2bicssc
072 7 _aUYQV
_2bicssc
072 7 _aCOM012000
_2bisacsh
072 7 _aCOM016000
_2bisacsh
082 0 4 _a006.6
_223
082 0 4 _a006.37
_223
100 1 _aKanatani, Kenichi.
_eauthor.
245 1 0 _aGuide to 3D Vision Computation
_h[electronic resource] :
_bGeometric Analysis and Implementation /
_cby Kenichi Kanatani, Yasuyuki Sugaya, Yasushi Kanazawa.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2016.
300 _aXI, 321 p. 54 illus., 10 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aAdvances in Computer Vision and Pattern Recognition,
_x2191-6586
505 0 _aIntroduction -- Part I: Fundamental Algorithms for Computer Vision -- Ellipse Fitting -- Fundamental Matrix Computation -- Triangulation -- 3D Reconstruction from Two Views -- Homography Computation -- Planar Triangulation -- 3D Reconstruction of a Plane -- Ellipse Analysis and 3D Computation of Circles -- Part II: Multiview 3D Reconstruction -- Multiview Triangulation -- Bundle Adjustment -- Self-calibration of Affine Cameras -- Self-calibration of Perspective Cameras -- Part III: Mathematical Foundation of Geometric Estimation -- Accuracy of Geometric Estimation -- Maximum Likelihood and Geometric Estimation -- Theoretical Accuracy Limit -- Solutions.
520 _aThis classroom-tested and easy-to-understand textbook/reference describes the state of the art in 3D reconstruction from multiple images, taking into consideration all aspects of programming and implementation. Unlike other textbooks on computer vision, this Guide to 3D Vision Computation takes a unique approach in which the initial focus is on practical application and the procedures necessary to actually build a computer vision system. The theoretical background is then briefly explained afterwards, highlighting how one can quickly and simply obtain the desired result without knowing the derivation of the mathematical detail. Topics and features: Reviews the fundamental algorithms underlying computer vision, and their implementation Describes the latest techniques for 3D reconstruction from multiple images Summarizes the mathematical theory behind statistical error analysis for general geometric estimation problems Offers examples of experimental results, enabling the reader to get a feeling of what can be done using each procedure Presents derivations and justifications as problems at the end of each chapter, with solutions supplied at the end of the book Explains the historical background for each topic in the supplemental notes at the end of each chapter Provides additional material at an associated website, include sample code for typical procedures to help readers implement the algorithms described in the book This accessible work will be of great value to students on introductory computer vision courses. Serving as both as a practical programming guidebook and a useful reference on mathematics for computer vision, it is suitable for practitioners seeking to implement computer vision algorithms as well as for theoreticians wishing to know the underlying mathematical detail.
650 0 _aComputer science.
650 0 _aImage processing.
650 1 4 _aComputer Science.
650 2 4 _aImage Processing and Computer Vision.
700 1 _aSugaya, Yasuyuki.
_eauthor.
700 1 _aKanazawa, Yasushi.
_eauthor.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9783319484921
830 0 _aAdvances in Computer Vision and Pattern Recognition,
_x2191-6586
856 4 0 _uhttp://dx.doi.org/10.1007/978-3-319-48493-8
912 _aZDB-2-SCS
942 _cEBK
999 _c55185
_d55185