Kazuhide Sugimoto

Conversion system of monocular image sequence to stereo using motion parallax

A three-dimensional reconstruction system -- the 3DR system -- has been developed. The main feature of the 3DR system is that it converts monocular image sequences to stereoscopic ones. This provides the following advantages: (1) Stereoscopic images can be reproduced even from films taken in the past. (2) A compact 3D-scene capturing system using a monocular camera is realized. The key 3DR technology is depth sensing based on motion parallax. A novel technique for motion analysis is proposed where, according to classification of motion vectors using the stability and colinearity, an iterative operation is performed to obtain an accurate solution. Preliminary evaluations have shown that not only was the motion parallax analyzed very accurately but also stereoscopic images of high quality were generated.

Boundary segmentation by detection of corner, inflection and transition points

For future intelligent man-machine systems with vision, it is necessary to visualize the results of shape and motion and analysis of observed objects in the images. As for object recognition, there are at least three steps. The first is to detect edges which correspond to the boundaries of objects (edge detection). The second is to segment each boundary into simple fine or curve segments (image segmentation). The third is to match those features between the data and the model (feature extraction). The paper presents a new method for the second step: boundary segmentation. It can detect not only corners but inflection points on which the sign of the curvature changes and transitional points on which a line and a curve connect smoothly without any delicate threshold. It also calculates the curvature and the normal vector at each point on the boundary with good accuracy. The features extracted by the proposed method are useful for both machine vision and visualization.<<ETX>>

Scene interpretation based on boundary representations of stereo images

The problem of detecting occluding and ridge edges is solved for objects with planar surfaces, using stereo vision that is based on directional boundary segments of regions in a pair of stereo images. Methods are proposed to detect occlusions in which occluding edges are explicitly identified: to classify the other unidentified edges as either occluding or ridge edges, using the explicitly occluding edges to classify ridge edges further as convex, concave, or flat (paint or shadow) edges, based on the surface normals of both sides of the edges; and to classify the space of the scene into free, occupied, or uninterpretable real surfaces.<<ETX>>

Detection of skewed-symmetrical shape

There is a new approach to define objects qualitatively and hierarchically by generic shapes (we call them primitives) arranged by generic relations so that a class of objects has the same description and to recognize them in a parallel and bottom-up way in the image. This paper presents a method to find a skewed symmetrical pattern in the image as a higher-order primitive which is defined by lower-order primitives such as line segments, curved segments, or the pairs of segments arranged by the relation skewed symmetry since a bilaterally symmetrical figure on an arbitrarily oriented plane viewed under orthographic projection yields a skewed symmetrical figure whose axes of symmetry and skew constrain the orientation of the underlying plane. The proposed method can detect the accurate skewed symmetrical axes of not only polygonal patterns but also curved patterns in a complex image even if some parts of the patterns are occluded.<<ETX>>

Integration and interpretation of incomplete stereo scene data

The authors extend the algorithm for stereo vision on a mobile robot in a unstructured environment to generate the 3-D b-rep of the large environment by incrementally integrating local and incomplete stereo data. The stereo vision is based on the 2-D b-reps of stereo images. The 2-D b-rep is a 2-D version of the 3-D b-rep to describe an image; the image is represented in a hierarchy of regions, boundaries, and line-segments. The b-rep is obtained for each of stereo images and the two images are matched on this data structure. The direct output of stereo is 3-D wireframes, a set of 3-D loops (boundaries) composed of 3-D line-segments, of the scene. A unique surface is then defined for each loop to make the 3-D b-rep, the consistent geometrical model, of the scene. It is necessary for the mobile robot to change views of the scene to make uninterpretable loops interpretable by finding missing segments, and thus make the complete b-rep of the scene.<<ETX>>