Muutke küpsiste eelistusi

Stereo Scene Flow for 3D Motion Analysis 2011 ed. [Kõva köide]

,
  • Formaat: Hardback, 128 pages, kõrgus x laius: 235x155 mm, kaal: 383 g, 60 Illustrations, color; 14 Illustrations, black and white; IX, 128 p. 74 illus., 60 illus. in color., 1 Hardback
  • Ilmumisaeg: 17-Aug-2011
  • Kirjastus: Springer London Ltd
  • ISBN-10: 0857299646
  • ISBN-13: 9780857299642
Teised raamatud teemal:
  • Kõva köide
  • Hind: 95,02 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 111,79 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Stereo Scene Flow for 3D Motion Analysis 2011 ed.Suurem pilt
  • Formaat: Hardback, 128 pages, kõrgus x laius: 235x155 mm, kaal: 383 g, 60 Illustrations, color; 14 Illustrations, black and white; IX, 128 p. 74 illus., 60 illus. in color., 1 Hardback
  • Ilmumisaeg: 17-Aug-2011
  • Kirjastus: Springer London Ltd
  • ISBN-10: 0857299646
  • ISBN-13: 9780857299642
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780857299642.html
Märksõnad:

Presenting methods for estimating optical flow and scene flow motion with high accuracy, this logically structured book focuses on the practical application of these methods in camera-based driver assistance systems.



This book presents methods for estimating optical flow and scene flow motion with high accuracy, focusing on the practical application of these methods in camera-based driver assistance systems. Clearly and logically structured, the book builds from basic themes to more advanced concepts, culminating in the development of a novel, accurate and robust optic flow method. Features: reviews the major advances in motion estimation and motion analysis, and the latest progress of dense optical flow algorithms; investigates the use of residual images for optical flow; examines methods for deriving motion from stereo image sequences; analyses the error characteristics for motion variables, and derives scene flow metrics for movement likelihood and velocity; introduces a framework for scene flow-based moving object detection and segmentation; includes Appendices on data terms and quadratic optimization, and scene flow implementation using Euler-Lagrange equations, in addition to a helpful Glossary.
1 Machine Vision Systems
1(4)
2 Optical Flow Estimation
5(30)
2.1 Optical Flow and Optical Aperture
5(2)
2.2 Feature-Based Optical Flow Approaches
7(4)
2.2.1 Census Based Optical Flow
8(2)
2.2.2 The Optical Flow Constraint
10(1)
2.2.3 Lucas-Kanade Method
10(1)
2.3 Variational Methods
11(6)
2.3.1 Total Variation Optical Flow
13(1)
2.3.2 Quadratic Relaxation
14(1)
2.3.3 Large Displacement Flow: Novel Algorithmic Approaches
15(2)
2.3.4 Other Optical Flow Approaches
17(1)
2.4 The Flow Refinement Framework
17(18)
2.4.1 Data Term Optimization
18(6)
2.4.2 Smoothness Term Evaluation
24(6)
2.4.3 Implementation Details
30(5)
3 Residual Images and Optical Flow Results
35(16)
3.1 Increasing Robustness to Illumination Changes
35(3)
3.2 Quantitative Evaluation of the Refinement Optical Flow
38(7)
3.2.1 Performance
38(4)
3.2.2 Smoothness
42(2)
3.2.3 Accuracy
44(1)
3.3 Results for Traffic Scenes
45(3)
3.4 Conclusion
48(3)
4 Scene Flow
51(14)
4.1 Visual Kinesthesia
51(4)
4.1.1 Related Work
53(1)
4.1.2 A Decoupled Approach for Scene Flow
53(2)
4.2 Formulation and Solving of the Constraint Equations
55(6)
4.2.1 Stereo Computation
55(2)
4.2.2 Scene Flow Motion Constraints
57(2)
4.2.3 Solving the Scene Flow Equations
59(1)
4.2.4 Evaluation with Different Stereo Inputs
59(2)
4.3 From Image Scene Flow to 3D World Scene Flow
61(4)
5 Motion Metrics for Scene Flow
65(16)
5.1 Ground Truth vs. Reality
65(1)
5.2 Derivation of a Pixel-Wise Accuracy Measure
66(9)
5.2.1 A Quality Measure for the Disparity
67(6)
5.2.2 A Quality Measure for the Scene Flow
73(1)
5.2.3 Estimating Scene Flow Standard Deviations
74(1)
5.3 Residual Motion Likelihood
75(2)
5.4 Speed Likelihood
77(4)
6 Extensions of Scene Flow
81(18)
6.1 Flow Cut-Moving Object Segmentation
81(11)
6.6.1 Segmentation Algorithm
83(2)
6.1.2 Deriving the Motion Likelihoods
85(3)
6.1.3 Experimental Results and Discussion
88(4)
6.2 Kalman Filters for Scene Flow Vectors
92(7)
6.2.1 Filtered Flow and Stereo: 6D-Vision
92(2)
6.2.2 Filtered Dense Optical Flow and Stereo: Dense-6D
94(1)
6.2.3 Filtered Variational Scene Flow: Variational-6D
95(1)
6.2.4 Evaluation with Ground Truth Information
96(2)
6.2.5 Real-World Results
98(1)
7 Conclusion and Outlook
99(2)
8 Appendix: Data Terms and Quadratic Optimization
101(10)
8.1 Optical Flow Constraint Data Term
101(1)
8.2 Adaptive Fundamental Matrix Constraint
101(2)
8.3 Quadratic Optimization via Thresholding
103(8)
8.3.1 Karush-Kuhn-Tucker (KKT) Conditions
103(1)
8.3.2 Single Data Term
104(2)
8.3.3 Two Data Terms
106(5)
9 Appendix: Scene Flow Implementation Using Euler-Lagrange Equations
111(8)
9.1 Minimization of the Scene Flow Energy
111(2)
9.2 Implementation of Scene Flow
113(6)
Glossary 119(2)
References 121(6)
Index 127