Description
Springer An Invitation to 3-D Vision From Images to Geometric Models by Yi Ma, Stefano Soatto, Jana Kosecka, S. Shankar Sastry
This book introduces the geometry of 3-D vision, that is, the reconstruction of 3-D models of objects from a collection of 2-D images. It details the classic theory of two view geometry and shows that a more proper tool for studying the geometry of multiple views is the so-called rank consideration of the multiple view matrix. It also develops practical reconstruction algorithms and discusses possible extensions of the theory._x000D_ Table of contents :- _x000D_
Preface_x000D_
1 Introduction_x000D_
1.1 Visual perception: from 2-D images to 3-D models_x000D_
1.2 A mathematical approach_x000D_
1.3 A historical perspective_x000D_
I Introductory material_x000D_
2 Representation of a three-dimensional moving scene_x000D_
2.1 Three-dimensional Euclidean space_x000D_
2.2 Rigid body motion_x000D_
2.3 Rotational motion and its representations_x000D_
2.4 Rigid body motion and its representations_x000D_
2.5 Coordinate and velocity transformations_x000D_
2.6 Summary_x000D_
2.7 Exercises_x000D_
2.A Quaternions and Euler angles for rotations_x000D_
3 Image formation_x000D_
3.1 Representation of images_x000D_
3.2 Lenses, light, and basic photometry_x000D_
3.3 A geometric model of image formation_x000D_
3.4 Summary_x000D_
3.5 Exercises_x000D_
3.A Basic photometry with light sources and surfaces_x000D_
3.B Image formation in the language of projective geometry_x000D_
4 Image primitives and correspondence_x000D_
4.1 Correspondence of geometric features_x000D_
4.2 Local deformation models_x000D_
4.3 Matching point features_x000D_
4.4 Tracking line features_x000D_
4.5 Summary_x000D_
4.6 Exercises_x000D_
4.A Computing image gradients_x000D_
II Geometry of two views_x000D_
5 Reconstruction from two calibrated views_x000D_
5.1 Epipolar geometry_x000D_
5.2 Basic reconstruction algorithms_x000D_
5.3 Planar scenes and homography_x000D_
5.4 Continuous motion case_x000D_
5.5 Summary_x000D_
5.6 Exercises_x000D_
5.A Optimization subject to epipolar constraint_x000D_
6 Reconstruction from two uncalibrated views_x000D_
6.1 Uncalibrated camera or distorted space?_x000D_
6.2 Uncalibrated epipolar geometry_x000D_
6.3 Ambiguities and constraints in image formation_x000D_
6.4 Stratified reconstruction_x000D_
6.5 Calibration with scene knowledge_x000D_
6.6 Dinner with Kruppa_x000D_
6.7 Summary_x000D_
6.8 Exercises_x000D_
6.A From images to Fundamental matrices_x000D_
6.B Properties of Kruppa's equations_x000D_
7 Segmentation of multiple moving objects from two views_x000D_
7.1 Multibody epipolar constraint and Fundamental matrix_x000D_
7.2 A rank condition for the number of motions_x000D_
7.3 Geometric properties of the multibody Fundamental matrix_x000D_
7.4 Multibody motion estimation and segmentation_x000D_
7.5 Multibody structure from motion_x000D_