Natural scene recognition using locus search

Abstract This paper describes an image understanding system that can recognize photographs of the city of Pittsburgh. It uses an effective and efficient artificial intelligence search technique called Locus. The system builds a three-dimensional model of the city and uses information from hypothesized two-dimensional views to label images. It currently achieves less than 20% error when labeling photographs, given a knowledge base of over fifty objects. In addition, the system can determine the angle of view around the city with approximately 40° of error. The paper formulates image understanding as a problem of search; shows how Locus search can be used to label images; describes the many sources of knowledge used in the interpretation; explores extensions to the use of knowledge; and presents some experimental results. New issues presented here include the multidimensionality of Locus search and techniques for automatically acquiring scene knowledge.

[1]  William A. Woods,et al.  Computational Linguistics Transition Network Grammars for Natural Language Analysis , 2022 .

[2]  Nils J. Nilsson,et al.  Problem-solving methods in artificial intelligence , 1971, McGraw-Hill computer science series.

[3]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[4]  King-Sun Fu,et al.  Syntactic Methods in Pattern Recognition , 1974, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .

[6]  J. Baker,et al.  The DRAGON system--An overview , 1975 .

[7]  Dana H. Ballard,et al.  An Approach to Knowledge-Directed Image Analysis , 1977, IJCAI.

[8]  Victor R. Lesser,et al.  A Multi-Level Organization For Problem Solving Using Many, Diverse, Cooperating Sources Of Knowledge , 1975, IJCAI.

[9]  R. Kettig,et al.  Classification of Multispectral Image Data by Extraction and Classification of Homogeneous Objects , 1976, IEEE Transactions on Geoscience Electronics.

[10]  Bruce L. Bullock,et al.  Real world scene analysis in perspective , 1975, ACM '75.

[11]  David L. Waltz,et al.  Understanding Line drawings of Scenes with Shadows , 1975 .

[12]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[13]  Harry G. Barrow,et al.  Experiments in Interpretation-Guided Segmentation , 1977, Artificial Intelligence.

[14]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[15]  Kiyoo Takeyasu,et al.  An Intelligent Robot with Cognition and Decision-Making Ability , 1971, IJCAI.

[16]  Charles A. Harlow.  Image analysis and graphs , 1973, Comput. Graph. Image Process..

[17]  Alfred V. Aho,et al.  The Theory of Parsing, Translation, and Compiling , 1972 .

[18]  Keith Price,et al.  Picture Segmentation Using a Recursive Region Splitting Method , 1998 .

[19]  Ramakant Nevatia,et al.  Description and Recognition of Curved Objects , 1977, Artif. Intell..

[20]  Martin A. Fischler,et al.  The Representation and Matching of Pictorial Structures , 1973, IEEE Transactions on Computers.

[21]  Jerome A. Feldman,et al.  Decision Theory and Artificial Intelligence: I. A Semantics-Based Region Analyzer , 1974, Artif. Intell..

[22]  Stuart E. Dreyfus,et al.  Applied Dynamic Programming , 1965 .

[23]  Ömer Akin,et al.  Knowledge Acquisition for Image Understanding Research , 1977 .

[24]  D R Reddy,et al.  Representation of Three-Dimensional Objects. , 1978 .

[25]  R. Narasimhan,et al.  Syntax-directed interpretation of classes of pictures , 1966, CACM.

[26]  Raj Reddy,et al.  Matching Segments of Images , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  W. A. Perkins.  Model-Based Vision System for Scenes Containing Multiple Parts , 1977, IJCAI.