Marc Proesmans

Determination of optical flow and its discontinuities using non-linear diffusion

A new method for optical flow computation by means of a coupled set of non-linear diffusion equations is presented. This approach integrates the classical differential approach with the correlation type of motion detectors. A measure of inconsistency within the optical flow field which indicates optical flow boundaries. This information is fed back to the optical flow equations in a non-linear way and allows the flow field to be reconstructed while preserving the discontinuities. The whole scheme is also applicable to stereo matching. The model is applied to a set of synthetic and real image sequences to illustrate the behaviour of the coupled diffusion equations.

Euclidean 3D Reconstruction from Image Sequences with Variable Focal Lenghts

One of the main problems to obtain a Euclidean 3D reconstruction from multiple views is the calibration of the camera. Explicit calibration is not always practical and has to be repeated regularly. Sometimes it is even impossible (i.e. for pictures taken by an unknown camera of an unknown scene). The second possibility is to do auto-calibration. Here the rigidity of the scene is used to obtain constraints on the camera parameters. Existing approaches of this second strand impose that the camera parameters stay exactly the same between different views. This can be very limiting since it excludes changing the focal length to zoom or focus. The paper describes a reconstruction method that allows to vary the focal length. Instead of using one camera one can also use a stereo rig following similar principles, and in which case also reconstruction from a moving rig becomes possible even for pure translation. Synthetic data were used to see how resistant the algorithm is to noise. The results are satisfactory. Also results for a real scene were convincing.

Affine reconstruction from perspective image pairs with a relative object-camera translation in between

A method is described to recover the three-dimensional affine structure of a scene consisting of at least five points identified in two perspective views with a relative object-camera translation in between. When compared to the results for arbitrary stereo views, a more detailed reconstruction is possible using less information. The method presented only assumes that the two images are obtained by identical cameras, but no knowledge about the intrinsic parameters of the camera(s) or about the performed translation is assumed. By the same method, affine 3D reconstruction from a single view can be achieved for parallel structures. In that case, four points suffice for affine reconstruction.

Reading between the lines—a method for extracting dynamic 3D with texture

A method is presented that extracts the 3D shape of objects, together with their surface texture. Both shape and texture are obtained from a single image. The paper sketches the complete system but focuses on the problem of texture extraction. The underlying principle is based on an active technique. A high resolution pattern is projected onto the object and the deformations as observed by a single camera yield the 3rd dimension. The surface texture is extracted from the same image by literally reading between the lines that are used for the shape extraction. This is done using a combination of interpolation and non-linear diffusion techniques. Because the whole procedure is based on a single image, a frame-byframe reconstruction of a video taken with the pattern projected throughout, yields 3D shape dynamics. 1 A paradigm shift in 3D Most methods for three-dimensional shape extraction go via the explicit calculation of the distance between the sensor and the object. The 3D shape of the surface then follows from the variation of this distance. This is what 3D acquisition devices for reverse engineering, shape inspection, and mobile robotics wotild typically do. More recent applications, however, focus on visualization, such as virtual and augmented reality, 3D on the Internet, special effects in movies, etc. These kind of applications come with different priorities: l Extracting the absolute scale of objects usually is not crucial. Objects. will be shown at completely different scales anyway. Permission to make digitalhud copies ofall or pat ofthis material for personal or classroom use is granted without fee provided that the copies are not made or distributed for profit or commercial advantage, the copyright notice, the title of the publication and its date appear, and notice is given that copyright is by pemhsion ofthe ACM, Inc. To copy oh&se, to republish, to post on servers or to redistribute to lists, requires specific permission and/or fee / ACM KWT ‘97 Lausanne Switzerland Copyright 1997 ACM 0-89791-953497/9..

Active acquisition of 3D shape for moving objects

3.50 l The extraction of surface texture becomes a prerequisite. Traditional 3D acquisition systems often lack this ability to align the shape and texture data. l In the top range of visualisation applications such as the movies and virtual worlds 3D dynamics becomes more important. Rather than building a still model and animating it via off-line motion tracking, direct extraction of 3D motion would strongly alleviate such tasks. l Also, with Internet at the fingertips of users in small companies and amateurs at home, 3D acquisition devices should become much cheaper, less bulky and easier to use in order for 3D models to fully pen& trate the Net. The paper proposes a novel, 3D acquisition system that is geared towards these new requirements, i.e. the extraction of 3D models for visualisation. The hardware needed is a simple slide projector, a normal camera, and a computer. Setting up tlie system is easy and requires no exotic calibration objects. It uses special illumination to obtain good geometric precision. From a single image, both 3D shape and surface texture are extracted. This turns the system into a say 4D scanner as it becomes possible to extract dynamic 3D by frame by frame reconstruction of video data. A complete description of the system is outside the scope of this short paper. This paper will mainly focus on the aspect of surface texture extraction (section 3). Nevertheless, section 2 will sketch how the 3D shape is extracted. Results of 3D shapes together with the texture and 3D motions are shown in section 4. That section also shows a preliminary example of how such data can be used for special effects or animation. Section 5 concludes the paper. 2 One-shot 3D acquisition 2.1 Comparison with other methods As passive 3D acquisition systems often lack precision, certainly in untextured areas, we opted for an active ap preach, where a simple square pattern is projected on the

The cascaded Hough transform

An active 3D acquisition system is presented that projects a simple pattern of squares on a scene and views it from a different angle. This paper describes how the observed pattern can be extracted from the image data. The underlying algorithm automatically detects the lines and crossings of the projected pattern in the image. Experiments show that the algorithm is robust and provides accurate three-dimensional (3D) reconstructions. Its one-shot operation principle enables the system to retrieve the shape of moving objects.

One-shot active 3D shape acquisition

When using the original slope-intercept parameterisation for the Hough transform, the resulting parameter space actually corresponds to the dual space. Indeed, lines are transformed into points, and for every point there is also a corresponding line. This paper presents a way of exploiting this special property, by the introduction of the cascaded Hough transform (CHT). This allows to look for the overall structure in an image, such as lines intersecting in a point or intersection points lying on a line. An interesting example is the detection of vanishing points and vanishing lines.

Affine reconstruction from perspective image pairs obtained by a translating camera

An active 3D acquisition system is presented that is based on the projection a simple pattern of squares. Through the observation of the projected pattern, and assuming pseudo-orthographic projection, the 3D shape of the scene can be retrieved up to a single parameter, that can be determined through a particularly simple calibration. An algorithm has been developed to automatically detect the lines and crossings of the projected pattern in the image. Experiments on a variety of scenes show that the algorithm is robust and provides accurate 3D reconstructions. Its one-shot operation enables the system to retrieve the shape of moving objects.

Mirror and point symmetry under perspective skewing

The three-dimensional structure of a scene consisting of at least five points whose images are identified in two perspective views obtained by a translating camera, can be reconstructed up to a 3D affine transformation. Hence, a more detailed reconstruction is possible using less information when compared to the results for arbitrary stereo pairs taken with uncalibrated, perspective cameras.

Planar homologies as a basis for grouping and recognition

Over recent years, symmetry research has shifted from the detection of affinely to perspectively skewed mirror symmetry. Also, links between invariance research and symmetry-specific geometric constraints have been established. The paper aims to contribute to both strands. Several sets of symmetry specific invariants are derived, that can be used in different situations, depending on the a priori assumptions made. It is also argued that all the results directly apply to the case of perspectively skewed point symmetry.