Copyright © 2006 The Institute of Electronics, Information and Communication Engineers
Regular Section -- Letters -- Pattern Recognition |
Depth Perception from a 2D Natural Scene Using Scale Variation of Texture Patterns
1 The authors are with the Imaging Science and Engineering Laboratory, Tokyo Institute of Technology, Yokohama-shi, 226–8503 Japan. E-mail: yskang{at}isl.titech.ac.jp, 2 The author had been supported by the Postdoctoral Fellowships for Foreign Researchers of the Japan Society for the Promotion of Science.
In this paper, we introduce a new method for depth perception from a 2D natural scene using scale variation of patterns. As the surface from a 2D scene gets farther away from us, the texture appears finer and smoother. Texture gradient is one of the monocular depth cues which can be represented by gradual scale variations of textured patterns. To extract feature vectors from textured patterns, higher order local autocorrelation functions are utilized at each scale step. The hierarchical linear discriminant analysis is employed to classify the scale rate of the feature vector which can be divided into subspaces by recursively grouping the overlapped classes. In the experiment, relative depth perception of 2D natural scenes is performed on the proposed method and it is expected to play an important role in natural scene analysis.
Key Words: depth perception, texture gradient, hierarchical discriminant analysis, autocorrelation functions
Manuscript received October 12, 2005.