Gérard Rives

Determination of the attitude of 3D objects from a single perspective view

A method for finding analytical solutions to the problem of determining the attitude of a 3D object in space from a single perspective image is presented. Its principle is based on the interpretation of a triplet of any image lines as the perspective projection of a triplet of linear ridges of the object model, and on the search for the model attitude consistent with these projections. The geometrical transformations to be applied to the model to bring it into the corresponding location are obtained by the resolution of an eight-degree equation in the general case. Using simple logical rules, it is shown on examples related to polyhedra that this approach leads to results useful for both location and recognition of 3D objects because few admissible hypotheses are retained from the interpolation of the three line segments. Line matching by the prediction-verification procedure is thus less complex. >

Modeling an object of revolution by zooming

This paper presents a system for modeling solids of revolution from a set of images taken with a zoom-lens. Using a zoom in monocular vision has interesting optical properties. The displacement of the optical center along the optical axis, when the focal length is modified, permits one to implement a triangulation process. Modeling a solid of revolution requires the estimation of the 3D location of its revolution axis. First, the authors describe an original method, using zoom properties, to compute the 3D pose of the revolution axis. It requires the detection in each image of the object axis projection. Then, the modeling algorithm is presented. It is based on the resolution of the inverse perspective problem for points detected in the images. An experimental result of reconstruction, from a real images set is finally given. >

The inverse perspective problem from a single view for polyhedra location

A method to find the analytical solutions of the inverse perspective problem for the determination of the 3-D object attitude in space from a single perspective image is presented. Its principle is based on the interpretation of a triplet of any image lines as the perspective projection of triplet of linear ridges of the object model. The geometrical transformations to apply to the model to bring it into the corresponding location are obtained by the resolution of an eighth-degree equation. The number of admissible solutions can still be reduced, using simple pruning rules. This approach leads to very strong results useful for both location and recognition of 3D objects. Because few admissible hypotheses are retained, the line-matching procedure by prediction-verification is less complex.<<ETX>>

MODEL-BASED RECOGNITION AND LOCATION OF LOCAL PATTERNS IN POLYGONAL CONTOURS VIA HYPOTHESIS ACCUMULATION

For industrial scene analysis, structural pattern recognition is a necessary way when the objects can be partially viewed. Recognition and location of local patterns are then the first steps to achieve and for that a new method is proposed. It is based on the use of a model of the piecewise linear segmented contour of these local patterns, and on a hypothesis accumulation procedure analogous to the generalized Hough transform. This method is applied to scenes of overlapping industrial pieces with local patterns having quite different shapes.

Sequential piecewise-linear segmentation of binary contours

An algorithm for the segmentation of binary contours into linear segments is presented, which sequentially processes the lines of a digital image.

Detection of patterns in images from piecewise linear contours

Structural pattern recognition for image understanding is based on the detection of elementary patterns which compose the structural description of the objects to be recognized and located in scenes. Detection of these elementary patterns in piecewise linear contours is the first step in the recognition task for which a new algorithm is presented in this paper. The representation of a pattern model is the set of the linear segments obtained during the learning phase from the segmentation of its contour. The detection of the occurrences of a pattern in a scene is made according to a hypothesis-accumulation procedure followed by a peak picking search in a two dimensional array. Experimental results of pattern detection are also given.

An algorithm for isolated object location in digital images

For real-time location, a new algorithm is proposed which uses a simple but efficient description of the image of any isolated object. This description is a small set of points, one being the barycenter of the contour of the image object, and the others being the intersection points of the contour and of a circle centered at the barycenter. Two characteristic vectors are calculated and used for the determination of the object orientation and of the face of a flat object. Several methods are given to obtain the intersection points. Some details of the implementation of the algorithm and real-time experimental results are also mentioned.