A Structural Analysis of Complex Aerial Photographs

It is most appropriate that the first volume to appear in the series "Advanced Applications in Pattern Recognition" should be this monograph by Nagao and Matsuyama. The work described here is a deep unification and synthesis of the two fundamental approaches to pat­ tern recognition: numerical (also known as "statistical") and struc­ tural ("linguistic," "syntactic"). The power and unity of the meth­ odology flow from the apparently effortless and natural use of the knowledge-base framework illuminated by the best results of artificial intelligence research. An integral part of the work is the algorithmic solution of many hitherto incompletely or clumsily treated problems. It was on the occasion of a laboratory visit in connection with the 4th IJCPR (of ~hich Professor Nagao was the very able Program Chairman) that I saw in operation the system described here. On the spot I expressed the desire to see the work described for the inter­ national technical audience in this series and the authors were kind enough to agree to contribute to a new and unknown series. With the publication of this monograph on the eve of the 5th ICPR my wish is fu1fi11~d. I want to thank here the authors and Plenum Publishing Corporation for making this volume and the series a reality.

1. Introduction.- 1.1 Preliminary Remarks.- 1.2 Statistical Classification Methods.- 1.3 Target Detection.- 1.4 Image Understanding Applied to Aerial Photographs.- 1.5 Structural Analysis of Complex Aerial Photographs.- 2. Overview of the System.- 2.1 Specifications of the Aerial Photographs Under Analysis.- 2.2 Processing Sequence in the System.- 2.3 Production System as the Software Architecture.- 2.4 Focusing Mechanism of the System.- 3. Some Basic Techniques in Picture Processing and Feature Extraction.- 3.1 Edge-Preserving Smoothing.- 3.2 A Measure of Elongatedness of a Region.- 3.3 A Structural Description of Regularly Arranged Patterns.- 4. Structuring of Picture Data.- 4.1. Low-Level Processing in Image Understanding.- 4.2. Edge-Preserving Smoothing.- 4.3. Segmentation.- 4.4. Calculation of Basic Properties of Elementary Regions.- 5. Extraction of Characteristic Regions.- 5.1. Large Homogeneous Regions.- 5.2. Elongated Regions.- 5.3. Shadow Regions and Shadow-Making Regions.- 5.4. Vegetation Regions.- 5.5. Water Regions.- 5.6. High-Contrast Texture Areas.- 6. Object Recognition.- 6.1. Crop Field.- 6.2. Forest and Grassland.- 6.3. Road and River.- 6.4. Car.- 6.5. House and Building.- 7. Control Structure of the System.- 7.1. Structure of the Blackboard.- 7.2. Conflict Resolution.- 7.3. Correction of Segmentation Errors 162 "Bottle-neck" detection algorithm.- 8. Performance Evaluation.- 8.1. Some Examples of the Analysis.- 8.2. Processing Time Evaluation.- 9. Conclusion.- 9.1. Summary.- 9.2. Areas for Future Work.- Overview of the Authors' Laboratory.- Computer Facilities.