Multi-Sensor Fusion: Fundamentals and Applications With Software

TLDR: A comparison with Existing Approaches, a New Method for Cloud Removal, and Experimental Results of the Exhaustive Search Algorithm: Designing Optimal Sensor Systems within Dependability Bounds.

Abstract: I. INTRODUCTION TO SENSOR FUSION. 1. Introduction. Importance. Sensor Processes. Applications. Summary. Problem Set 1. II. FOUNDATIONS OF SENSOR FUSION. 2. Sensors. Mathematical Description. Use of Multiple Sensors. Construction of Reliable Abstract Sensors From Simple Abstract Sensors. Static and Dynamic Networks. Conclusion. Problem Set 2. 3. Mathematical Tools Used. Algorithms. Linear Algebra. Coordinate Transformations. Rigid Body Motion. Probability. Dependability and Markov Chains. Gaussian Noise. Meta-Heuristics. Summary. Problem Set 3. 4. High-Performance Data Structures: CAD Based. Boundary Representations. Sweep Presentation. CSG - Constructive Solid Geometry. Wire-Frame Models and the Wing-Edge Data Structure. Surface Patches and Contours. Generalized Cylinders. Summary. Problem Set 4. 5. High-Performance Data Structures: Tessellated. Sparse Arrays. Simplex Grids of Non-Uniform Sizes. Grayscale and Color Arrays. Occupancy Grids and HIMM Histogram Maps. Summary. Problem Set 5. 6. High-Performance Data Structures: Trees, and Graphs. 2n Trees. Forest of Quadtrees. Translation Invariant Data Structure. Multi-Dimensional Trees. Graphs of Free Space. Description Trees of Polygons. Range and Interval Trees. Summary. Problem Set 6. 7. High-Performance Data Structures: Functions. Interpolation. Least Squares Estimation. Splines. Bezier Curves and Bi-Cubic Patches. Fourier Transform, Cepstrum and Wavelets. Modal Representation. Summary. Problem Set 7. 8. Representing Ranges and Uncertainty in Data Structures. Explicit Accuracy Bounds. Probability and Dempster-Shafer Methods. Statistics. Fuzzy Sets. Summary. Problem Set 8. III. APPLICATIONS TO SENSOR FUSION. 9. Image Registration for Sensor Fusion. Image Registration Techniques. Problem Statement. Fitness Function. Tabu Search. Genetic Algorithms. Simulated Annealing. Results. Summary. 10. Designing Optimal Sensor Systems within Dependability Bounds. Applications. Dependability Measures. Optimization Model. Exhaustive Search on the Multidimensional Surface. Experimental Results of the Exhaustive Search Algorithm. Heuristic Methods. Summary. 11. Sensor Fusion and Approximate Agreement. Byzantine Generals Problem. Approximate Byzantine Matching. Fusion of Contradictory Sensor Information. Performance Comparison. Hybrid Algorithm. Example 1. Example 2. Summary. 12. Kalman Filtering Applied to a Sensor Fusion Problem. Background. A New Method. A New Technique for Cloud Removal. A Prototype System. Kalman Filter for Scenario 1. Discussion of Results. Summary. 13. Optimal Sensor Fusion Using Range Trees Recursively. Sensors. Redundancy and Associated Errors. Faulty Sensor Averaging Problem. Interval Trees. Algorithm to Find the Optimal Region. Algorithm Complexity. Comparison with Known Methods. Summary. 14. Distributed Dynamic Sensor Fusion. Problem Description. New Paradigm for Distributed Dynamic Sensor Fusion. Robust Agreement Using the Optimal Region. A Comparison with Existing Approaches. Experimental Results. Summary. IV. CASE STUDIES AND CONCLUSION. 15. Sensor Fusion Case Studies. Levels of Sensor Fusion. Types of Sensors Available. Research Trends. Case Studies. Summary. 16. Conclusion. Review. Conclusion. Appendix A. Program Source Code. References. Index483.