Showing papers on "Homography (computer vision) published in 1999"

Automatic line matching and 3d reconstruction of buildings from multiple views

Abstract: This paper describes two developments in the automatic reconstruction of buildings from aerial images. The first is an algorithm for automatically matching line segments over multiple images. The algorithm employs geometric constraints based on the multi-view geometry together with photometric constraints derived from the line neighbourhood, and achieves a performance of better than 95% correct matches over three views. The second development is a method for automatically computing a piecewise planar reconstruction based on the matched lines. The novelty here is that a planar facet hypothesis can be generated from a single 3D line, using an inter-image homography applied to the line neighbourhood. The algorithm has successfully generated near complete roof reconstructions from multiple images. This work has been carried out as part of the EC IMPACT project. A summary of the project is included.

Calibrating a Structured Light Stripe System: A Novel Approach

Abstract: The problem associated with calibrating a structured light stripe system is that known world points on the calibration target do not normally fall onto every light stripe plane illuminated from the projector. We present in this paper a novel calibration method that employs the invariance of the cross ratio to overcome this problem. Using 4 known non-coplanar sets of 3 collinear world points and with no prior knowledge of the perspective projection matrix of the camera, we show that world points lying on each light stripe plane can be computed. Furthermore, by incorporating the homography between the light stripe and image planes, the 4 × 3 image-to-world transformation matrix for each stripe plane can also be recovered. The experiments conducted suggest that this novel calibration method is robust, economical, and is applicable to many dense shape reconstruction tasks.

Method and system for calibrating digital cameras

Abstract: A digital camera is calibrated by establishing the coordinates of at least four feature points of a pattern mounted on a planar surface. At least two, and preferably three or more, images of the planar pattern are captured at different, non-parallel orientations using the digital camera. The image coordinates of the pattern's feature points are then identified in the captured images. A closed form solution can be employed to derive all the intrinsic and extrinsic parameters needed to provide the camera calibration. Essentially, the known pattern coordinates and corresponding image coordinates are used to compute a homography for each image. Then, a process is employed that estimates the intrinsic camera parameters by analyzing the homographies associated with each image. Finally, the extrinsic parameters for each image are computed from the intrinsic parameters and the homographies. However, the images can be effected by various noise sources which could affect the accuracy of the closed form solution process. If higher accuracy is called for, a maximum likelihood inference process can be employed to either provide a more accurate first estimate, or to refine the estimates derived from the closed form solution. If radial distortion caused by the lens of the camera is also a concern, the camera parameters can be further refined by taking into account this distortion.

Image interpolation by joint view triangulation

Abstract: Creating novel views by interpolating prestored images or view morphing has many applications in visual simulation. We present in this paper a new method of automatically interpolating two images which tackles two most difficult problems of morphing due to the lack of depth informational pixel matching and visibility handling. We first describe a quasi-dense matching algorithm based on region growing with the best first strategy for match propagation. Then, we describe a robust construction of matched planar patches using local geometric constraints encoded by a homography. After that we introduce a novel representation, joint view triangulation, for visible and half-occluded patches in two images to handle their visibility during the creation of new view. Finally we demonstrate these techniques on real image pairs.

Scene augmentation via the fusion of industrial drawings and uncalibrated images with a view to marker-less calibration

Abstract: The application presented augments uncalibrated images of factories with industrial drawings. Industrial drawings are among the most important documents used during the lifetime of industrial environments. They are the only common documents used during design, installation, monitoring and control, maintenance, update and finally dismantling of industrial units. Leading traditional industries towards the full use of virtual and augmented reality technology is impossible unless industrial drawings are integrated into our systems. We provide the missing link between industrial drawings and digital images of industrial sites. On one hand, this could enable us to calibrate cameras and build a 3D model of the scene without using any calibration markers. On the other hand it brings industrial drawings, floor map, images and 3D models into one unified framework. This provides a solid foundation for building efficient enhanced virtual industrial environments. The augmented scene is obtained by perspective warping of an industrial drawing of the factory onto its floor, wherever the floor is visible. The visibility of the floor is determined using probabilistic reasoning over a set of clues including (1) floor color/intensity (2) image warping and differencing between an uncalibrated stereoscopic image pair using the ground plane homography. Experimental results illustrate the approach.

Accuracy bounds and optimal computation of homography for image mosaicing applications

Abstract: We describe a theoretically optimal algorithm for computing the homography between two images in relation to image mosaicing applications. First, we derive a theoretical accuracy bound based on a mathematical model of image noise and do simulation to confirm that our renormalization technique effectively attains that bound; our algorithm is optimal in that sense. Then, we apply our technique to mosaicing of images with small overlaps. By using real images, we show how our algorithm reduces the instability of the image mapping.

About the self-calibration of a rotating and zooming camera: Theory and practice

Abstract: This paper deals with the uniqueness of the self-calibration of a rotating and zooming camera theoretically. We assume that the principal point and the aspect ratio are fixed but the focal length changes as the camera moves. In this case, at least one inter-image homography is required in order to compute the internal calibration parameters as well as the rotation. We analyze the effects of the deviation of the principal point on the estimation of the focal length and the rotation. The more the camera changes its zoom, the larger the effects are, and the larger the rotation angle is, the smaller the effects are. Thus, we may take the image center as the principal point in practical applications. Experiments using real images are given.

Multi-view subspace constraints on homographies

Abstract: The motion of a planar surface between two camera views induces a homography. The homography depends on the camera intrinsic and extrinsic parameters, as well as on the 3D plane parameters. While camera parameters vary across different views, the plane geometry remains the same. Based on this fact, the paper derives linear subspace constraints on the relative motion of multiple (/spl ges/2) planes across multiple views. The paper has three main contributions. It shows that the collection of all relative homographies of a pair of planes (homologies) across multiple views, spans a 4-dimensional linear subspace. It shows how this constraint can be extended to the case of multiple planes across multiple views. It suggests two potential application areas which can benefit from these constraints: the accuracy of homography estimation can be improved by enforcing the multi-view subspace constraints; and violations of these multi-view constraints can be used as a cue for moving object detection. All the results derived in this paper are true for uncalibrated cameras.

Subspace Methods and Equilibration in Computer Vision

Abstract: Many computer vision problems (e.g. the estimation of the fundamental matrix, pure parameters or camera calibration as well as the factorization method) belong to the class of subspace problems which are well-known in signal processing. They essentially consist in dividing a vector space into a lower dimensional data space and an orthogonal error space, based on the information available from a set of measurement vectors. This can be formulated as a rank reduction problem on a perturbed measurement matrix. Considering explicitly the ‘subspace estimation’ nature of a given problem is very often the first step to obtain much better estimates of the sought entities (lower variance, reduced or eliminated bias, ...) and often a direct (non-iterative) solution is possible. Besides that, it is crucial to consider the structure of the noise in the given measurements in detail. This dictates the correct error metric which is one of the most important characteristics of the optimization problem to be solved. We begin this paper by examining the error structure of the point correspondences used for two-view motion analysis. Then we introduce the method of equilibration which ensures that this error structure is considered correctly for performing a subspace analysis. Subsequently, we describe the application of subspace methods to four different computer vision problems in order to show their potential for designing better algorithms. With the theoretical background given in this paper, it becomes obvious that the discussed problems must be considered as subspace problems in order to obtain reliable and precise results. While the problems of fundamental matrix estimation, camera calibration and factorization are regarded on a more global scale, the estimation of the pure parameters or plane homography in two-view analysis is examined in more detail. These results are related to a paper recently presented on a workshop [MUE99b] specially devoted to statistical techniques in image analysis. The motivation for presenting these mathematical tools is given by the conviction that practically useful vision algorithms can only be designed on the basis of a full comprehension of the algebraic and statistical nature of the given problem. The authors hope that the present report constitutes an advancement towards this goal.

View synthesis and 3D reconstruction of piecewise planar scenes using intersection lines between the planes

Abstract: A linear algorithm for synthesizing new views of piecewise planar objects without making an explicit 3D reconstruction is proposed, together with a simple algorithm for 3D reconstruction of the scene. It is shown how this can be done using only one image and information about the projection of the intersection lines between the object planes. These could either be estimated manually or more automatically using at least one more image. No calibration information is needed. A main idea in the paper is to work with textured planes. A patch in one image, corresponding to a planar surface in the scene, is transformed to a patch in another image by a homography. The generalized eigenvectors and eigenvalues of the homographies have geometrical interpretations that are used in the algorithms. To generate a new image, we calculate the homographies for each plane to the new image. The textures can then easily be mapped to the new image. The reconstruction is given as the equation of each plane in the corresponding homography to a certain image.

Affine reconstruction from monocular vision in the presence of a symmetry plane

Abstract: This paper reports a closed-form solution for reconstructing a scene up to an affine transformation from a single image in the presence of a symmetry plane. Unlike scene reconstruction in stereo vision, the affine reconstruction process discussed in this paper does not require any knowledge about camera parameters or camera orientation relative to the scene, so camera self-calibration is totally eliminated. By setting in the scene a plane mirror which creates lateral symmetric world points for an uncalibrated, perspective camera to capture, the linear equations involved in the reconstruction process can be derived from two sets of similar triangles. The affine reconstruction is relative to an arbitrary affine coordinated frame implicitly defined on the mirror plane. Also involved in the process are the estimation of the epipole and recovery of the image-to-mirror plane homography. Implementation on estimating the epipole is detailed. A real experiment is presented to demonstrate the reconstruction.

Homography-Based 3D Scene Analysis of Video Sequences *

Abstract: We propose a framework to recover projectivedepth based on image homography and discuss itsapplication to scene analysis of video sequences.We describe a robust homography algorithmwhich incorporates contrast/brightness adjustmentand robust estimation into image registration. Wepresent a camera motion solver to obtain the ego-motion and the real/virtual plane position fromhomography. We then apply the Levenburg-Marquardt method to generate a dense projectivedepth map. We also discuss temporal integrationover video sequences. Finally we present theresults of applying the homography-based videoanalysis to motion detection. 1 Introduction Temporal information redundancy of videosequences allows us to use efficient, incrementalmethods which perform temporal integration ofinformation for gradual refinement.Approaches handling 3D scene analysis of videosequences with camera motion can be classifiedinto two categories: algorithms which use 2Dtransformation or model fitting, and algorithmswhich use 3D geometry analysis. Video sequencesof our interest are taken from a moving airborneplatform where the ego-motion is complex and thescene is relatively distant but not necessarily flat;

A correlation-symbolic approach to automatic remotely sensed image rectification

Abstract: Remote sensing techniques applied to non-supervised geometric image rectification have to deal with two main issues: control point extraction using matching algorithms and pixel position rectification using the geometric transformation obtained from those control points This paper describes a rectification routine supporting very large scenes and the absence of distinctive features in the image In a first stage, multi-resolution and a region-based algorithm are applied, obtaining an initial registration In the second stage, a correlation method is used to refine the solution, detecting local distortions and using the final set of control points in the geometric correction process

Tag Disambiguation in Italian

Abstract: In this paper we argue in favour of syntactically based tagging by presenting data from a study of a 1,000,000 word corpus of Italian Most papers present approaches on tagging which are statistically based None of the statistically based analyses, however, produce an accuracy level comparable to the one obtained by means of linguistic rules [1] Of course their data are strictly referred to English, with the exception of [2, 3, 4] As to Italian, we argue that purely statistically based approaches are inefficient basically due to great sparsity of tag distribution – 50% only unambiguous tags In addition, the level of homography is also very high: readings per word are 17 compared to 107 computed for English by [2] with a similar tagset In a preliminary experiment we made we obtained 99,97% accuracy in the training set and 99,03% in the test set using syntactic disambiguation: data derived from statistical tagging is well below 95% even when referred to the training set

Recovery of Circular Motion from Profiles of Surfaces

Abstract: This paper addresses the problem of motion recovery from image profiles, in the important case of turntable sequences. No correspondences between points or lines are used. Symmetry properties of surfaces of revolution are exploited to obtain, in a robust and simple way, the image of the rotation axis of the sequence and the homography relating epipolar lines. These, together with geometric constraints for images of rotating objects, are used to obtain epipoles and, consequently, the full epipolar geometry of the camera system. This sequential approach (image of rotation axis -- homography -- epipoles) avoids many of the problems usually found in other algorithms for motion recovery from profiles. In particular, the search for the epipoles, by far the most critical step for the estimation of the epipolar geometry, is carried out as a one-dimensional optimization problem, with a smooth unimodal cost function. The initialization of the parameters is trivial in all three stages of the algorithm. After the estimation of the epipolar geometry, the motion is recovered using the fixed intrinsic parameters of the camera, obtained either from a calibration grid or from self-calibration techniques. Results from real data are presented, demonstrating the efficiency and practicality of the algorithm.

Calibration and 3D structure recovery under varying cameras using known angles

Abstract: We present an algorithm for the calibration of a camera and the recovery of 3D scene structure up to a scale from image sequences using known angles between lines in the scene. The proposed method computes the intrinsic parameters of the camera using the invariance of angles under the similarity transformation. Specifically, we recover the matrix that is the homography between the projective structure and the Euclidean structure using angles. Since this matrix is a unique one in the given set of image sequences, we can easily deal with the problem of varying intrinsic parameters of the camera. Experimental results on the synthetic and real images demonstrate the feasibility of the proposed algorithm.