Page 11 - Dynamic Vision for Perception and Control of Motion

xii Contents

6 Recursive State Estimation ..........................................183
6.1 Introduction to the 4-D Approach for Spatiotemporal Perception......... 184
6.2 Basic Assumptions Underlying the 4-D Approach ............................... 187
6.3 Structural Survey of the 4-D Approach................................................. 190
6.4 Recursive Estimation Techniques for Dynamic Vision......................... 191

6.4.1 Introduction to Recursive Estimation......................................... 191
6.4.2 General Procedure...................................................................... 192
6.4.3 The Stabilized Kalman Filter ..................................................... 196
6.4.4 Remarks on Kalman Filtering .................................................... 196

6.4.5 Kalman Filter with Sequential Innovation ................................. 198
6.4.6 Square Root Filters..................................................................... 199
6.4.7 Conclusion of Recursive Estimation for Dynamic Vision ......... 202

7 Beginnings of Spatiotemporal Road
and Ego-state Recognition ...........................................205
7.1 Road Model........................................................................................... 206
7.2 Simple Lateral Motion Model for Road Vehicles ................................ 208

7.3 Mapping of Planar Road Boundary into an Image................................ 209
7.3.1 Simple Beginnings in the Early 1980s ....................................... 209
7.3.2 Overall Early Model for Spatiotemporal Road Perception ........ 213
7.3.3 Some Experimental Results ....................................................... 214

7.3.4 A Look at Vertical Mapping Conditions.................................... 217
7.4 Multiple Edge Measurements for Road Recognition ............................ 218
7.4.1 Spreading the Discontinuity of the Clothoid Model................... 219
7.4.2 Window Placing and Edge Mapping.......................................... 222
7.4.3 Resulting Measurement Model .................................................. 224
7.4.4 Experimental Results ................................................................. 225

8 Initialization in Dynamic Scene Understanding ............ 227
8.1 Introduction to Visual Integration for Road Recognition...................... 227

8.2 Road Recognition and Hypothesis Generation...................................... 228