Showing papers by "Andrew Zisserman published in 1995"

3D motion recovery via affine epipolar geometry

Abstract: Algorithms to perform point-based motion estimation under orthographic and scaled orthographic projection abound in the literature. A key limitation of many existing algorithms is that they operate on the minimum amount of data required, often requiring the selection of a suitable minimal set from the available data to serve as a “local coordinate frame”. Such approaches are extremely sensitive to errors and noise in the minimal set, and forfeit the advantages of using the full data set. Furthermore, attention is seldom paid to the statistical performance of the algorithms.

Planar object recognition using projective shape representation

Abstract: We describe a model based recognition system, called LEWIS, for the identification of planar objects based on a projectively invariant representation of shape. The advantages of this shape description include simple model acquisition (direct from images), no need for camera calibration or object pose computation, and the use of index functions. We describe the feature construction and recognition algorithms in detail and provide an analysis of the combinatorial advantages of using index functions. Index functions are used to select models from a model base and are constructed from projective invariants based on algebraic curves and a canonical projective coordinate frame. Examples are given of object recognition from images of real scenes, with extensive object libraries. Successful recognition is demonstrated despite partial occlusion by unmodelled objects, and realistic lighting conditions.

Metric calibration of a stereo rig

Abstract: Describes a method to determine affine and metric calibration for a stereo rig. The method does not involve the use of calibration objects or special motions, but simply a single general motion of the rig with fixed parameters (i.e. camera parameters and relative orientation of the camera pair). The novel aspects of this work are: first, relating the distinguished objects of Euclidean geometry to fixed entities of a Euclidean transformation matrix; second, showing that these fixed entities are accessible from the conjugate Euclidean transformation arising from the projective transformation of the structure under a motion of the fixed stereo rig; and third, a robust and automatic implementation of the method. Results are included of affine and metric calibration and structure recovery using images of real scenes.

Robust detection of degenerate configurations for the fundamental matrix

Abstract: New methods are reported for the detection of multiple solutions (degeneracy) when estimating the fundamental matrix, with specific emphasis on robustness in the presence of data contamination (outliers). The fundamental matrix can be used as a first step in the recovery of structure from motion. If the set of correspondences is degenerate then this structure cannot be accurately recovered and many solutions will explain the data equally well. It is essential that we are alerted to such eventualities. However, current feature matchers are very prone to mismatching, giving a high rate of contamination within the data. Such contamination can make a degenerate data set appear non degenerate, thus the need for robust methods becomes apparent. The paper presents such methods with a particular emphasis on providing a method that will work on real imagery and with an automated (non perfect) feature detector and matcher. It is demonstrated that proper modelling of degeneracy in the presence of outliers enables the detection of outliers which would otherwise be missed. Results using real image sequences are presented. All processing, point matching, degeneracy detection and outlier detection is automatic. >

Shape from Symmetry: Detecting and Exploiting Symmetry in Affine Images

Abstract: We investigate the constraints placed on the image projection of a planar object having local reflectional symmetry. Under the affine approximation to projection, we demonstrate an efficient (low-complexity) algorithm for detecting and verifying symmetries despite the distorting effects of image skewing. The symmetries are utilized for three distinct tasks: first, determining image back-projection up to a similarity transformation ambiguity; second, determining the object plane orientation (slant and tilt); and third, as a test for non-coplanarity amongst a collection of objects. These results are illustrated throughout with examples from images of real scenes.

Active visual navigation using non-metric structure

Abstract: Demonstrates a method of using nonmetric visual information derived from an uncalibrated active vision system to navigate an autonomous vehicle through free-space regions detected in a cluttered environment. The structure of 3-space is recovered modulo an affine transformation using an uncalibrated active stereo head carried by the vehicle. The plane at infinity, necessary for recovering affine structure from projective structure, is found in a novel manner by making controlled rotations of the head. The structure is composed of 3D points obtained by detecting and matching image corners through the stereo image sequence. Considerable care has been taken to ensure that the processing is reliable, robust and automatic. Driveable regions are determined from the projection of the affine structure onto a plane parallel to the ground determined using projective constructs. Two methods of negotiating the regions are explored. The first introduces metric information to allow control of a Euclidean vehicle. The second uses visual servoing of the active head to navigate in the affinely described free-space regions. >

Class-based grouping in perspective images

Abstract: In any object recognition system a major and primary task is to associate those image features, within an image of a complex scene, that arise from an individual object. The key idea here is that a geometric class defined in 3D induces relationships in the image which must hold between points on the image outline (the perspective projection of the object). The resulting image constraints enable both identification and grouping of image features belonging to objects of that class. The classes include surfaces of revolution, canal surfaces (pipes) and polyhedra. Recognition proceeds by first recognising an object as belonging to one of the classes (for example a surface of revolution) and subsequently identifying the object (for example as a particular vase). This differs from conventional object recognition systems where recognition is generally targetted at particular objects. These classes also support the computation of 3D invariant descriptions including symmetry axes, canonical coordinate frames and projective signatures. The constraints and grouping methods are viewpoint invariant, and proceed with no information on object pose. We demonstrate the effectiveness of this class-based grouping on real, cluttered scenes using grouping algorithms developed for rotationally symmetric surfaces, canal-surfaces and polyhedra. >

Detection and tracking of independent motion

Abstract: We describe an efficient method of using a translating camera to detect and track independently translating objects and assess the likelihood of a collision. By analysing the underlying geometry, it is shown that the tracking is reduced to two independent linear searches for a single feature in the image plane. Results are presented for both an off-line and a real time implementation using no special hardware. The method is completely automatic and shown to be accurate and robust.

Uncalibrated x-ray stereo reconstruction

Abstract: We describe a novel application of uncalibrated stereo reconstruction to Roentgen Stereophotogrammetry Analysis (RSA). In RSA, stereo X-ray images are taken of a bone containing a prosthesis (e.g. a replacement knee) and a number of metal markers. The aim is to recover the relative position of the prosthesis and markers in 3D. Accuracy in previous RSA methods has been limited by two factors: manual feature selection and an assumption that camera calibration parameters are known to high precision - this is not the case in practice. Furthermore, the manual processing is slow and tedious. We report progress towards developing a fully automatic RSA system. New algorithms are described for automatically localising marker points in X-ray images to sub-pixel accuracy, and using them to reconstruct accurate 3D positions using robust statistical methods. Preliminary experiments give excellent results.

MORSE: An Architecture for 3D Object Recognition Based on Invariants

Abstract: Over the past few years, there has been considerable interest in the application of geometric invariance to the problem of object recognition[2, 3, 4, 5, 6]. While most work has focused on the problem of discovering and characterizing new geometric invariants, several recognition systems, based on invariants have been implemented. A key example is the LEWIS[7] system. LEWIS exploits projective invariants of planar objects to enable object indexing and classification. Experience with LEWIS and its limitations, motivated the MORSE 6 The MORSE project, started in January 1994, has the goal of providing a Cq-+ environment for the implementation of a system for recognizing 3D objects based on invariant class descriptions. MORSE embodies invariant representations for geometric classes of 3D objects such as: rotational symmetry, translational symmetry and polyhedra. The architecture is designed to support image segmentation, classbased grouping, model library management and scene reasoning. The LEWIS system has also been re-implemented using the MORSE infrastructure to provide for recognition of planar objects. To motivate the architectural design, it will prove useful to review and contrust the key steps in object recognition for two geometric classes: rotational symmetry and structures repeated by translation. Then we will describe how these steps are mapped onto the implemented architecture. Both classes require the segmentation of image features from regions of interest. In MORSE, edgel segmentation is carried out using a modified Canny edge detector and connected edgel chains are linked topologically to form a connected network of boundary segments. The two classes have different feature grouping stages, as follows.