Showing papers on "Homography (computer vision) published in 2005"

Synthetic Aperture Focusing using a Shear-Warp Factorization of the Viewing Transform

Abstract: Synthetic aperture focusing consists of warping and adding together the images in a 4D light field so that objects lying on a specified surface are aligned and thus in focus, while objects lying of this surface are misaligned and hence blurred. This provides the ability to see through partial occluders such as foliage and crowds, making it a potentially powerful tool for surveillance. If the cameras lie on a plane, it has been previously shown that after an initial homography, one can move the focus through a family of planes that are parallel to the camera plane by merely shifting and adding the images. In this paper, we analyze the warps required for tilted focal planes and arbitrary camera configurations. We characterize the warps using a new rank- 1 constraint that lets us focus on any plane, without having to perform a metric calibration of the cameras. We also show that there are camera configurations and families of tilted focal planes for which the warps can be factorized into an initial homography followed by shifts. This shear-warp factorization permits these tilted focal planes to be synthesized as efficiently as frontoparallel planes. Being able to vary the focus by simply shifting and adding images is relatively simple to implement in hardware and facilitates a real-time implementation. We demonstrate this using an array of 30 videoresolution cameras; initial homographies and shifts are performed on per-camera FPGAs, and additions and a final warp are performed on 3 PCs.

Two-view geometry estimation unaffected by a dominant plane

Abstract: A RANSAC-based algorithm for robust estimation of epipolar geometry from point correspondences in the possible presence of a dominant scene plane is presented. The algorithm handles scenes with (i) all points in a single plane, (ii) majority of points in a single plane and the rest off the plane, (iii) no dominant plane. It is not required to know a priori which of the cases (i)-(iii) occurs. The algorithm exploits a theorem we proved, that if five or more of seven correspondences are related by a homography then there is an epipolar geometry consistent with the seven-tuple as well as with all correspondences related by the homography. This means that a seven point sample consisting of two outliers and five inliers lying in a dominant plane produces an epipolar geometry which is wrong and yet consistent with a high number of correspondences. The theorem explains why RANSAC often fails to estimate epipolar geometry in the presence of a dominant plane. Rather surprisingly, the theorem also implies that RANSAC-based homography estimation is faster when drawing nonminimal samples of seven correspondences than minimal samples of four correspondences.

Homography-based visual servo regulation of mobile robots

Abstract: A monocular camera-based vision system attached to a mobile robot (i.e., the camera-in-hand configuration) is considered in this paper. By comparing corresponding target points of an object from two different camera images, geometric relationships are exploited to derive a transformation that relates the actual position and orientation of the mobile robot to a reference position and orientation. This transformation is used to synthesize a rotation and translation error system from the current position and orientation to the fixed reference position and orientation. Lyapunov-based techniques are used to construct an adaptive estimate to compensate for a constant, unmeasurable depth parameter, and to prove asymptotic regulation of the mobile robot. The contribution of this paper is that Lyapunov techniques are exploited to craft an adaptive controller that enables mobile robot position and orientation regulation despite the lack of an object model and the lack of depth information. Experimental results are provided to illustrate the performance of the controller.

Automatic Multiscale Image Acquisition from a Steerable Camera

Abstract: A system for automatically acquiring high-resolution images by steering a pan-tilt-zoom camera at targets detected in a fixed camera view is provided. The system uses automatic or manual calibration between multiple cameras. Using automatic calibration, the homography between the cameras in a home position is estimated together with the effects of pan and tilt controls and the expected height of a person in the image. These calibrations are chained together to steer a slave camera. The manual calibration scheme steers a camera to the desired region of interest and calculates the pan, tile and zoom parameters accordingly.

Vehicle segmentation and tracking from a low-angle off-axis camera

Abstract: We present a novel method for visually monitoring a highway when the camera is relatively low to the ground and on the side of the road. In such a case, occlusion and the perspective effects due to the heights of the vehicles cannot be ignored. Features are detected and tracked throughout the image sequence, and then grouped together using a multilevel homography, which is an extension of the standard homography to the low-angle situation. We derive a concept called the relative height constraint that makes it possible to estimate the 3D height of feature points on the vehicles from a single camera, a key part of the technique. Experimental results on several different highways demonstrate the system's ability to successfully segment and track vehicles at low angles, even in the presence of severe occlusion and significant perspective changes.

The radial trifocal tensor: a tool for calibrating the radial distortion of wide-angle cameras

Abstract: We present a technique to linearly estimate the radial distortion of a wide-angle lens given three views of a real-world plane. The approach can also be used with pure rotation as in this case all points appear as lying on a plane. The three views can even be recorded using three different cameras as long as the deviation from the pin-hole model for each camera is distortion along radial lines. We introduce the 1D radial camera which projects scene points onto radial lines and the radial trifocal tensor which encodes the multi-view relations between radial lines. Given at least seven triplets of corresponding points the radial trifocal tensor can be computed linearly. This allows recovery of the radial cameras and the projective reconstruction of the plane up to a two fold ambiguity. This 2D reconstruction is unaffected by radial distortion and can be used in different ways to compute the radial distortion parameters. We propose to use the division model as in this case we obtain a linear algorithm that computes the radial distortion coefficients and the 3 remaining degrees of freedom of the homography relating the reconstructed 2D plane to the undistorted image. Each feature point that has at least one corresponding point yields one linear constraint on those unknowns. Our method is validated on real-world images. We successfully calibrate several wide-angle cameras.

Acquiring Multi-Scale Images by Pan-Tilt-Zoom Control and Automatic Multi-Camera Calibration

Abstract: This paper describes a system for automatically acquiring high-resolution images by steering a pan-tilt-zoom camera at targets detected in a fixed camera view. The system uses a novel method to automatically calibrate between multiple cameras, estimating the homography between the cameras in a home position, together with the effects of pan and tilt controls and the expected height of a person in the image. These calibrations are chained together to steer a slave camera. In addition we describe a simple manual calibration scheme

Adaptive homography-based visual servo tracking for a fixed camera configuration with a camera-in-hand extension

Abstract: In this brief, a homography-based adaptive visual servo controller is developed to enable a robot end-effector to track a desired Euclidean trajectory as determined by a sequence of images for both the camera-in-hand and fixed-camera configurations. To achieve the objectives, a Lyapunov-based adaptive control strategy is employed to actively compensate for the lack of unknown depth measurements and the lack of an object model. The error systems are constructed as a hybrid of pixel information and reconstructed Euclidean variables obtained by comparing the images and decomposing a homographic relationship. Simulation results are provided to demonstrate the performance of the developed controller for the fixed camera configuration.

Real-Time Detection of Independent Motion using Stereo

Abstract: We describe a system that detects independently moving objects from a mobile platform in real time using a calibrated stereo camera. Interest points are first detected and tracked through the images. These tracks are used to obtain the motion of the platform by using an efficient three-point algorithm in a RANSAC framework for outlier detection. We use a formulation based on disparity space for our inlier computation. In the disparity space, two disparity images of a rigid object are related by a homography that depends on the object's euclidean rigid motion. We use the homography obtained from the camera motion to detect the independently moving objects from the disparity maps obtained by an efficient stereo algorithm. Our system is able to reliably detect the independently moving objects at 16 Hz for a 320 x 240 stereo image sequence using a standard laptop computer.

Using vanishing points to correct camera rotation in images

Abstract: Vanishing points provide valuable information regarding the camera model used to capture an image. To explore the relationship between classes of camera models and the location of vanishing points, typical consumer photographic behavior is considered. Based on these findings, an algorithm is presented that can automatically remove the tilted appearance of an image captured with a camera rotated about the principal axis. The algorithm includes detecting vanishing points in an image, determining if any vanishing points are associated with vertical lines in the scene, computing the angle of rotation, and rotating the image. Results of the algorithm are shown for a set of images. The algorithm performs well and produces pleasing images from original images that contain undesirable levels of tilt.

Camera calibration method and camera calibration device

Abstract: Planar calibration indices (c 1 ) including coordinate information of at least four points are placed on a first plane (S 1 ), and an image plane of the camera image including the calibration indices is input as a second plane (S 2 ). Points (c 2 ) existing on the second plane and corresponding to predetermined portions of the calibration indices are specified, and homography between the first plane and the second plane is computed, on the basis of the corresponding relationship of the at least four points included commonly in the first plane and the second plane, so that the camera image is calibrated. For example, a device is mounted on a vehicle, and four points, whose arrangement on a plane in 3D space is known, are used as calibration indices, and corresponding four points on the camera image, which correspond to them respectively, is achieved automatically.

Autocalibration of a projector-camera system

Abstract: This paper presents a method for calibrating a projector-camera system that consists of multiple projectors (or multiple poses of a single projector), a camera, and a planar screen. We consider the problem of estimating the homography between the screen and the image plane of the camera or the screen-camera homography, in the case where there is no prior knowledge regarding the screen surface that enables the direct computation of the homography. It is assumed that the pose of each projector is unknown while its internal geometry is known. Subsequently, it is shown that the screen-camera homography can be determined from only the images projected by the projectors and then obtained by the camera, up to a transformation with four degrees of freedom. This transformation corresponds to arbitrariness in choosing a two-dimensional coordinate system on the screen surface and when this coordinate system is chosen in some manner, the screen-camera homography as well as the unknown poses of the projectors can be uniquely determined. A noniterative algorithm is presented, which computes the homography from three or more images. Several experimental results on synthetic as well as real images are shown to demonstrate the effectiveness of the method.

A modular multi-camera framework for team sports tracking

Abstract: This article presents a modular architecture for multicamera tracking in the context of sports broadcasting. For each video stream, a geometrical module continuously performs the image-to-model homography estimation. A local-feature based tracking module tracks the players in each view. A supervisor module collects, associates and fuses the data provided by the tracking modules. The originality of the proposed system is three-fold. First, it allows to localize the targets on the ground with rotating and zooming cameras; second, it does not use background modeling techniques; and third, the local tracking can cope with severe occlusions. We present experimental results on raw TV-camera footage of a soccer game.

Consistent labeling for multi-camera object tracking

Abstract: In this paper, we present a new approach to multi-camera object tracking based on the consistent labeling. An automatic and reliable procedure allows to obtain the homographic transformation between two overlapped views, without any manual calibration of the cameras. Object's positions are matched by using the homography when the object is firstly detected in one of the two views. The approach has been tested also in the case of simultaneous transitions and in the case in which people are detected as a group during the transition. Promising results are reported over a real setup of overlapped cameras.

A system and method for calibrating multiple cameras without employing a pattern by inter-image homography

Abstract: Interactive multi-view video presents new types of video capture systems, video formats, video compression algorithms, and services. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos are compressed in control PCs and are sent to a server in real-time. Users can subscribe to a new type of service that allows users to connect to the servers and receive multi-view videos interactively. In one embodiment of the invention, an automatic pattern-free calibration tool is employed to calibrate the multiple cameras. In contrast with a pattern-based method which uses the correspondences between image points and pattern points, the pattern-free calibration method is based on the correspondences between image points from different views.

System and method for mechanically adjusting projector pose with six degrees of freedom for image alignment

Abstract: A method adjusts a pose of a projector with respect to a display surface. A homography HD,P is determined between a display surface and a projector. The homography HD,P is decomposed into rotation and translation parameters expressing a pose MP of the projector. An ideal pose M0 of the projector corresponding to an ideal homography H0 is determined. A pose adjustment MA is determined according to MA=M0(MP)−1. The pose adjustment MA is decomposed into rotation and translation adjustment parameters. Then, the projector is adjusted mechanically to the ideal pose M0 according to the rotation and translation adjustment parameters.

2 1/2 D visual servoing with central catadioptric cameras

Abstract: In this paper, we present how the 2 1/2 D visual servoing scheme can be used with omnidirectional cameras. Motivated by the growing interest for omnidirectional sensors on robotic applications and particularly on vision-based control, we extend this framework to the entire class of central catadioptric systems. Indeed, conventional cameras suffer from restricted field of view. Central catadioptric systems have larger fields of view thus overcoming the visibility problem encountered when using conventional cameras. The 2 1/2 D visual servoing is based on the estimation of the partial camera displacement between two views, given by the current and desired images. Geometrical relationships are exploited to enable a partial Euclidean reconstruction by decoupling the interaction between translation and rotation components of a homography matrix. First we describe how to obtain a generic homography matrix for central catadioptric cameras from the projection model of an entire class of camera. Then the information obtained from the homography is used to develop a 2 1/2 D visual servoing scheme.

Direct homography computation by local linearization

Abstract: A method and apparatus for determining a homography between an image and an expected image is described. The homography accounts for differences in perspective of a camera viewing an objective plane of the image, in some examples, a paper with information on it.

Camera calibration with spheres: linear approaches

Abstract: This paper addresses the problem of camera calibration from spheres. By studying the relationship between the dual images of spheres and that of the absolute conic, a linear solution has been derived from a recently proposed non-linear semi-definite approach. However, experiments show that this approach is quite sensitive to noise. In order to overcome this problem, a second approach has been proposed, where the orthogonal calibration relationship is obtained by regarding any two spheres as a surface of revolution. This allows a camera to be fully calibrated from an image of three spheres. Besides, a conic homography is derived from the imaged spheres, and from its eigenvectors the orthogonal invariants can be computed directly. Experiments on synthetic and real data show the practicality of such an approach.

Navigation function based visual servo control

Abstract: In this paper, the mapping between the desired camera feature vector and the desired camera pose (i.e., the position and orientation) is investigated to develop a measurable image Jacobian-like matrix. An image-space path planner is then proposed to generate a desired image trajectory based on this measurable image Jacobian-like matrix and an image space navigation function (NF) (i.e., a special potential field function) while satisfying rigid body constraints. An adaptive, homography-based visual servo tracking controller is then developed to navigate the position and orientation of a camera held by the end-effector of a robot manipulator to a goal position and orientation along the desired image-space trajectory while ensuring the target points remain visible (i.e., the target points avoid self-occlusion and remain in the field-of-view (FOV)) under certain technical restrictions. Due to the inherent nonlinear nature of the problem and the lack of depth information from a monocular system, a Lyapunov-based analysis is used to analyze, the path planner and the adaptive controller.

The Smart Bookshelf: A Study of Camera Projector Scene Augmentation of an Everyday Environment

Abstract: Recent research in projector-camera systems has overcome many of the obstacles to deploying and using intelligent displays for a wide range of applications. In parallel with these developments, projector costs continue to decline with corresponding increase in resolution, brightness and contrast ratio. In light of this trend, we are exploring the unique capabilities that camera-projector systems can offer to intelligent environments and ubiqutous computing. Our initial step towards environments that are intelligently augmented by projector-camera devices, is a smart bookshelf application. The system utilizes a camera pair and a projector to monitor the state of a real world library shelf. As books are added to the shelf a foreground detection algorithm which takes into account the projected information yields new pixels in each view that are then verified using a planar parallax constraint across both cameras to yield the book spine. Using a simple calibration scheme, the homography induced by the world plane in which book spines approximately lie is estimated. Users are then able to query for the presence of a book through a user interface and book spines are highlighted by transforming image pixels to their corresponding points in the projector's frame via the known homography. The system also can display the state of the bookshelf at any time in the past. Projected information can also be used to enhance the image-processing tasks at hand and we briefly explore this in this work.

3D-Connected components analysis for traffic monitoring in image sequences acquired from a helicopter

Abstract: The aim of the study was to develop methods for moving vehicle tracking in aerial image sequences taken over urban areas. The first image of the sequence was manually registered to a map. Corner points were extracted semi-automatically, then tracked along the sequence, to enable video stabilisation by homography estimation. Moving objects were detected by means of adaptive background subtraction. The vehicles were identified among many stabilisation artifacts and tracked, with a simple tracker based on spatiotemporal connected components analysis. While the techniques used were basic, the results turned out to be encouraging, and several improvements are under scrutiny.

Learning the Semantic Landscape: embedding scene knowledge in object tracking

Abstract: The accuracy of object tracking methodologies can be significantly improved by utilizing knowledge about the monitored scene. Such scene knowledge includes the homography between the camera and ground planes and the occlusion landscape identifying the depth map associated with the static occlusions in the scene. Using the ground plane, a simple method of relating the projected height and width of people objects to image location is used to constrain the dimensions of appearance models. Moreover, trajectory modeling can be greatly improved by performing tracking on the ground-plane tracking using global real-world noise models for the observation and dynamic processes. Finally, the occlusion landscape allows the tracker to predict the complete or partial occlusion of object observations. To facilitate plug and play functionality, this scene knowledge must be automatically learnt. The paper demonstrates how, over a sufficient length of time, observations from the monitored scene itself can be used to parameterize the semantic landscape.

Camera calibrating method and camera calibrating device

Abstract: Planar calibration indices (c1) including coordinate information of at least four points are placed on a first plane (S1), and an image plane of the camera image including the calibration indices is input as a second plane (S2). Points (c2) existing on the second plane and corresponding to predetermined portions of the calibration indices are specified, and homography between the first plane and the second plane is computed, on the basis of the corresponding relationship of the at least four points included commonly in the first plane and the second plane, so that the camera image is calibrated. For example, a device is mounted on a vehicle, and four points, whose arrangement on a plane in 3D space is known, are used as calibration indices, and corresponding four points on the camera image, which correspond to them respectively, is achieved automatically.

Planar homography: accuracy analysis and applications

Abstract: Projective homography sits at the heart of many problems in image registration. In addition to many methods for estimating the homography parameters (R.I. Hartley and A. Zisserman, 2000), analytical expressions to assess the accuracy of the transformation parameters have been proposed (A. Criminisi et al., 1999). We show that these expressions provide less accurate bounds than those based on the earlier results of Weng et al. (1989). The discrepancy becomes more critical in applications involving the integration of frame-to-frame homographies and their uncertainties, as in the reconstruction of terrain mosaics and the camera trajectory from flyover imagery. We demonstrate these issues through selected examples.