Page 10 - Dynamic Vision for Perception and Control of Motion
P. 10

Contents      xi




            4 Application Domains, Missions, and Situations .........111
               4.1 Structuring of Application Domains....................................................... 111
               4.2 Goals and Their Relations to Capabilities .............................................. 117
               4.3 Situations as Precise Decision Scenarios................................................ 118
                   4.3.1 Environmental Background........................................................ 118

                   4.3.2 Objects/Subjects of Relevance................................................... 119
                   4.3.3 Rule Systems for Decision-Making ........................................... 120
               4.4 List of Mission Elements........................................................................ 121



            5 Extraction of Visual Features  ......................................123
               5.1 Visual Features...................................................................................... 125
                   5.1.1 Introduction to Feature Extraction ............................................. 126

                   5.1.2 Fields of View, Multifocal Vision, and Scales........................... 128
               5.2 Efficient Extraction of Oriented Edge Features .................................... 131
                   5.2.1 Generic Types of Edge Extraction Templates............................ 132
                   5.2.2 Search Paths and Subpixel Accuracy......................................... 137
                   5.2.3 Edge Candidate Selection .......................................................... 140

                   5.2.4 Template Scaling as a Function of the Overall Gestalt .............. 141
               5.3 The Unified Blob-edge-corner Method (UBM) .................................... 144
                   5.3.1 Segmentation of Stripes Through Corners, Edges, and Blobs  ..144
                   5.3.2 Fitting an Intensity Plane in a Mask Region ..............................151
                   5.3.3 The Corner Detection Algorithm ...............................................167
                   5.3.4 Examples of Road Scenes  .........................................................171

               5.4 Statistics of Photometric Properties of Images .....................................174
                   5.4.1 Intensity Corrections for Image Pairs ........................................176
                   5.4.2 Finding Corresponding Features ...............................................177
                   5.4.3 Grouping of Edge Features to Extended Edges .........................178

               5.5 Visual Features Characteristic of General Outdoor Situations..............181
   5   6   7   8   9   10   11   12   13   14   15