Computer Interpretation of a Dynamic Image from a Moving Vehicle.

Abstract : The goal of this thesis is the design and implementation of a computer program that constructs an interpretation of images of a natural scene, in particular one imaged while the camera is in a moving automobile. The succession of images is to be interpreted in terms of surfaces and objects in three-dimensional space. The agreement between image dynamics and an internal surface model of the environment is measured by comparing a pair of temporally disparate images (two movie frames). Using the model, an image taken at one location can be transformed into a synthetic image of the scene as it would be viewed from another location. This synthesis accounts for point displacements and occlusion effects as predicted by the internal model. Differences between the real and the synthetic images are then used as an error measure in a search that refines the model. Once the model is refined, unresolved errors are used to correct the initial surface model by resegmenting the image into a better approximation of the surfaces in the environment.

[1]  Raj Reddy,et al.  Change Detection and Analysis in Multispectral Images , 1977, IJCAI.

[2]  Allen R. Hanson,et al.  Model-Building in the Visions System , 1977, IJCAI.

[3]  Allen R. Hanson,et al.  The Design of a Semantically Directed Vision Processor (Revised and Updated). , 1975 .

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

[5]  David L Milgram.  Region Tracking using Dynamic Programming , 1977 .

[6]  Jerome A. Feldman,et al.  A Semantics-Based Decision Theory Region Analyser , 1973, IJCAI.

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

[8]  Marsha Jo Hannah,et al.  Computer matching of areas in stereo images. , 1974 .

[9]  Lawrence G. Roberts,et al.  Machine Perception of Three-Dimensional Solids , 1963, Outstanding Dissertations in the Computer Sciences.

[10]  David L. Waltz,et al.  Generating Semantic Descriptions From Drawings of Scenes With Shadows , 1972 .

[11]  T. Garvey.  Perceptual strategies for purposive vision , 1975 .

[12]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[13]  Yoshiaki Shirai,et al.  A Context Sensitive Line Finder for Recognition of Polyhedra , 1973, Artif. Intell..

[14]  Richard O. Duda,et al.  Use of Range and Reflectance Data to Find Planar Surface Regions , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Gary Grant Hendrix,et al.  Partitioned networks for the mathematical modeling of natural language semantics. , 1975 .

[16]  W. B. Thompson,et al.  Combining motion and contrast for segmentation , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Jake K. Aggarwal,et al.  Computer Tracking of Objects Moving in Space , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Bruce L Bullock.  Unstructured Control and Communication Processes in Real World Scene Analysis. , 1977 .

[19]  W F Clocksin,et al.  Perception of Surface Slant and Edge Labels from Optical Flow: A Computational Approach , 1980, Perception.

[20]  Ronald Bert Ohlander,et al.  Analysis of natural scenes. , 1975 .

[21]  Allen R. Hanson,et al.  Experiments in Schema-Driven Interpretation of a Natural Scene , 1981 .

[22]  Berthold K. P. Horn.  SHAPE FROM SHADING: A METHOD FOR OBTAINING THE SHAPE OF A SMOOTH OPAQUE OBJECT FROM ONE VIEW , 1970 .