Search

Understanding how the shape of a three dimensional object may be recovered fromshading in a two-dimensional image of the object is one of the most important - and still unresolved- problems in machine vision. Although this important subfield is now in its second decade, thisbook is the first to provide a comprehensive review of shape from shading. It brings together all ofthe seminal papers on the subject, shows how recent work relates to more traditional approaches, andprovides a comprehensive annotated bibliography.The book's 17 chapters cover: Surface Descriptionsfrom Stereo and Shading. Shape and Source from Shading. The Eikonal Equation: some ResultsApplicable to Computer Vision. A Method for Enforcing Integrability in Shape from ShadingAlgorithms. Obtaining Shape from Shading Information. The Variational Approach to Shape fromShading. Calculating the Reflectance Map. Numerical Shape from Shading and Occluding Boundaries.Photometric Invariants Related to Solid Shape. Improved Methods of Estimating Shape from ShadingUsing the Light Source Coordinate System. A Provably Convergent Algorithm for Shape from Shading.Recovering Three Dimensional Shape from a Single Image of Curved Objects. Perception of Solid Shapefrom Shading. Local Shading Analysis Pentland. Radarclinometry for the Venus Radar Mapper.Photometric Method for Determining Surface Orientation from Multiple Images.Berthold K. P. Horn isProfessor of Electrical Engineering and Computer Science at MIT. He has presided over the field ofmachine vision for more than a decade and is the author of Robot Vision. Michael Brooks is Reader inComputer Science at The Flinders University of South Australia. Shape from Shading is included inthe Artificial Intelligence series, edited by Michael Brady, Daniel Bobrow, and RandallDavis.