This paper addresses the problem of image based localization. The goal is to find quickly and accurately the relative pose from a query taken from a stereo camera and a map obtained using visual SLAM which contains poses and 3D points associated to descriptors. In this paper we introduce a new method that leverages the stereo vision by adding geometric information to visual descriptors. This method can be used when the vertical direction of the camera is known (for example on a wheeled robot). This new geometric visual descriptor can be used with several image based localization algorithms based on visual words. We test the approach with different datasets (indoor, outdoor) and we show experimentally that the new geometric-visual descriptor improves standard image based localization approaches.

In this paper, we propose to calibrate a vehicle equipped with several 2D-LIDARs and cameras. Our goal is to offer a method which is easy to use with very little manual intervention and which doesn't need a special calibration target. Sensor data is recorded while the vehicle is driven along a trajectory in a man made environment with vertical walls. The first step is a classical autocalibration approach based on visual SLAM and bundle adjustment is used to recover the cameras internal and external parameters. The second step which is the main contribution of the paper, is a novel optimisation algorithm to compute the external parameters of the LIDAR. We present the methodology in its entirety because the user has to do a single data acquisition for camera and LIDAR calibration. Our approach is validated by real experimental results.

This paper presents a hybrid structure/trajectory constraint, that uses output camera poses of a model-based tracker, for object localization with SLAM algorithm. This constraint takes into account the structure information given by a CAD model while relying on the formalism of trajectory constraints. It has the advantages to be compact in memory and to accelerate the SLAM optimization process. The accuracy and robustness of the resulting localization as well as the memory and time gains are evaluated on synthetic and real data. Videos are available as supplementary material.

In this paper we propose to improve the localization and the 3D mapping provided by an RGBD SLAM algorithm, using a prior knowledge of the 3D model of the environment. The proposed solution relies on an feature-based RGBD SLAM algorithm to localize the camera and update the 3D map of the scene. To improve the accuracy and the robustness of the localization, we propose to combine in a local bundle adjustment process, geometric information provided by a prior coarse 3D model of the scene (e.g. generated from the 2D plan of the building) with RGBD data. The proposed approach is evaluated on a public benchmark dataset as well as on a real scene acquired by a Kinect sensor.

This paper addresses the challenging issue of real-time camera localization relative to any object that have texture or not, sharp edges or occluding contours. 3D contour points, dynamically extracted from a CAD model by Analysis-by-Synthesis on the graphics hardware, are combined with a keyframe-based SLAM algorithm to estimate camera poses. Our tracking solution is accurate, robust to sudden motions and to occlusions, as demonstrated on synthetic and real data. This solution is also easy to deploy since it only uses an RGB camera and a CAD model of the object of interest, requires no manual intervention on this model and runs on a consumer tablet at a frequency of 40Hz on a HD video-stream. Videos are available as supplemental material.

We improve in this paper the localization accuracy of visual SLAM (VSLAM) / GPS fusion in dense urban area by using 3D building models provided by Geographic Information System (GIS). GPS inaccuracies are corrected by comparison of the reconstruction resulting from the VSLAM / GPS fusion with 3D building models. These corrected GPS data are thereafter re-injected in the fusion process. Experimental results demonstrate the accuracy improvements achieved through our proposed solution.

Vehicle geo-localization based on monocular visual Simultaneous Localization And Mapping (SLAM) remains a challenging issue mainly due to the accumulation errors and scale factor drift. To tackle these limitations, a common solution is to introduce geo-referenced information into the visual SLAM algorithm. In this paper, we propose two different bundle adjustment processes that merge both GPS measurements and “Digital Elevation Model” (DEM) data. Proposed solutions are devoted to ensure an accurate and robust geo-localization in both rural and urban environment. Experiments on synthetic and large scale real sequences show that, in addition to the real-time (i.e. about 30 Hz) performances, we obtain an accurate 6DoF localization.

To provide high quality augmented reality service in a car navigation system, accurate 6DoF localization is required. To ensure such accuracy, most of current vision-based solutions rely on an off-line large scale modeling of the environment. Nevertheless, while existing solutions require expensive equipments and/or a prohibitive computation time, we propose in this paper a complete framework that automatically builds an accurate city scale database using only a standard camera, a GPS and Geographic Information System (GIS). As illustrated in the experiments, only few minutes are required to model large scale environments. The resulting databases can then be used during a localization algorithm for high quality Augmented Reality experiences.

We address the challenging issue of camera localization in a partially known environment, i.e. for which a geometric 3D model that covers only a part of the observed scene is available. When this scene is static, both known and unknown parts of the environment provide constraints on the camera motion. This paper proposes a nonlinear refinement process of an initial SfM reconstruction that takes advantage of these two types of constraints. Compare to those that exploit only the model constraints i.e. the known part of the scene, including the unknown part of the environment in the optimization process yields a faster, more accurate and robust refinement. It also presents a much larger convergence basin. This paper will demonstrate these statements on varied synthetic and real sequences for both 3D object tracking and outdoor localization applications.

This article deals with a simple and flexible extrinsic calibration method, for non-overlapping camera rig. The cameras do not see the same area at the same time. They are rigidly linked and can be moved. The most representative application is the mobile robotics domain. The calibration procedure consists in maneuvering the system while each camera observes a static scene. A linear solution derived from hand eye calibration scheme is proposed to compute an initial estimate of the extrinsic parameters. The main contribution is a specific bundle adjustment which refines both the scene geometry and the extrinsic parameters. Finally, an efficient implementation of the specific bundle adjustment step is defined for online calibration purpose. The proposed approach is validated with both synthetic and real data.

Local Bundle Adjustments were recently introduced for visual SLAM (Simultaneous Localization and Mapping). In Monocular Visual SLAM, the scale factor is not observable and the reconstruction scale drifts as time goes by. On long trajectory, this problem makes absolute localisation not usable. To overcome this major problem, data fusion is a possible solution. In this paper, we describe Weighted Local Bundle Adjustment(WLBA) for monocular visual SLAM purposes. We show that W-LBA used with local covariance gives better results than Local Bundle Adjustment especially on the scale propagation. Moreover W-LBA is well designed for sensor fusion. Since odometer is a common sensor and is reliable to obtain a scale information, we apply W-LBA to fuse visual SLAM with odometry data. The method performance is shown on a large scale sequence.

Multi-camera systems are more and more used in vision-based robotics. An accurate extrinsic calibration is usually required. In most of cases, this task is done by matching features through different views of the same scene. However, if the cameras fields of view do not overlap, such a matching procedure is not feasible anymore. This article deals with a simple and flexible extrinsic calibration method, for nonoverlapping camera rig. The aim is the calibration of non-overlapping cameras embedded on a vehicle, for visual navigation purpose in urban environment. The cameras do not see the same area at the same time. The calibration procedure consists in manoeuvring the vehicle while each camera observes a static scene. The main contributions are a study of the singular motions and a specific bundle adjustment which both reconstructs the scene and calibrates the cameras. Solutions to handle the singular configurations, such as planar motions, are exposed. The proposed approach has been validated with synthetic and real data.

In this system paper, we propose a real-time car localisation process in dense urban areas by using a single perspective camera and a priori on the environment. To tackle this problem, it is necessary to solve two well-known monocular SLAM limitations: scale factor drift and error accumulation. The proposed idea is to combine a monocular SLAM process based on bundle adjustment with simple knowledge, i.e. the position and orientation of the camera with regard to the road and a coarse 3D model of the environment, as those provided by GIS database. First, we show that, thanks to specific SLAM-based constraints, the road homography can be expressed only with respect to the scale factor parameter. This allows the scale factor to be robustly and frequently estimated. Then, we propose to use the global information brought by 3D city models in order to correct the monocular SLAM error accumulation. Even with coarse 3D models, turnings give enough geometrical constraints to allow fitting the reconstructed 3D point cloud with the 3D model. Experiments on large-scale sequences (several kilometres) show that the entire process permits the real-time localisation of a car in city centre, even in real traffic condition.

The Simultaneous Localisation And Mapping (SLAM) for a camera moving in a scene is a long term research problem. Here we improve a recent visual SLAM which applies Local Bundle Adjustments (LBA) on selected key-frames of a video: we show how to correct the scale drift observed in long monocular video sequence using an additional odometry sensor. Our method and results are interesting for several reasons: (1) the pose accuracy is improved on real examples (2) we do not sacrifice the consistency between the reconstructed 3D points and image features to fit odometry data (3) the modification of the original visual SLAM method is not difficult.

Multi-camera systems are used in many domains such as vision-based robotics or video surveillance. An accurate extrinsic calibration is usually required. In most of cases, this task is done by matching features through different views of the same scene. However, if the cameras' fields of view do not overlap, such a matching procedure is not feasible anymore. Despite this constraint, this article deals with a simple and flexible extrinsic calibration method. The main contribution is the use of an unknown geometry scene and a planar mirror to create an overlap between views of the different cameras. Furthermore, the impact of the mirror refraction is also studied. The aim is the calibration of two non-overlapping cameras embedded on a vehicle, for visual navigation purpose in urban environment. The proposed approaches have been validated with both synthetic and real data in a metrological experimental framework.

In the past few years, lots of works were achieved on Simultaneous Localization and Mapping (SLAM). It is now possible to follow in real time the trajectory of a moving camera in an unknown environment. However, current SLAM methods are still prone to drift errors, which prevent their use in large-scale applications. In this paper, we propose a solution to reduce those errors a posteriori. Our solution is based on a postprocessing algorithm that exploits additional geometric constraints, relative to the environment, to correct both the reconstructed geometry and the camera trajectory. These geometric constraints are obtained through a coarse 3D modelisation of the environment, similar to those provided by GIS database. First, we propose an original articulated transformation model in order to roughly align the SLAM reconstruction with this 3D model through a non-rigid ICP step. Then, to refine the reconstruction, we introduce a new bundle adjustment cost function that includes, in a single term, the usual 3D point/ID observation consistency constraint as well as the geometric constraints provided by the 3D model. Results on large-scale synthetic and real sequences show that our method successfully improves SLAM reconstructions. Besides, experiments prove that the resulting reconstruction is accurate enough to be directly used for global relocalization applications.

International audience

In this paper we describe a method that estimates the motion of a calibrated camera (settled on an experimental vehicle) and the tridimensional geometry of the environment. The only data used is a video input. In fact, interest points are tracked and matched between frames at video rate. Robust estimates of the camera motion are computed in real-time, key-frames are selected and permit the features 3D reconstruction. The algorithm is particularly appropriate to the reconstruction of long images sequences thanks to the introduction of a fast and local bundle adjustment method that ensures both good accuracy and consistency of the estimated camera poses along the sequence. It also largely reduces computational complexity compared to a global bundle adjustment. Experiments on real data were carried out to evaluate speed and robustness of the method for a sequence of about one kilometer long. Results are also compared to the ground truth measured with a differential GPS.

This paper introduces an incremental method for "structure from motion" of complex scenes from a video sequence. More precisely, we estimate the 3D positions of the viewed points in images and the camera positions and orientations through the sequence. The method can be seen as a fast but accurate alternative to classical reconstruction methods that use bundle adjustment, and that can become slow and computation time expensive for very long scenes. Our results are compared to the reconstruction obtained by the classical hierarchical bundle adjustment method. They have also been successfully used as a reference sequence for the vision based localization of an autonomous mobile robot

In this paper, a vision-based measuring device is proposed and experimentally demonstrated to be an accurate, flexible, and low-cost tool for the kinematic calibration of parallel mechanisms. The accuracy and ease of use of the proposed vision sensor are outlined, with the suppression of the need for an accurate calibration target, and adequacy to the kinematic calibration process is investigated. In particular, identifiability conditions with the use of such an exteroceptive sensor are derived, considering the calibration with inverse or implicit models. Extensive results are given, with the evaluation of the measuring device and the calibration of an H4 robot. Using the full-pose measurement, an experimental analysis of the optimal calibration model is achieved, with study of the kinematic behavior of the mechanism. The efficiency of the provided method is thus evaluated, and the applicability of vision-based measuring devices to the context of kinematic calibration of parallel mechanisms is discussed.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

In this paper we present a method for computing the localization of a mobile robot with reference to a learning video sequence. The robot is first guided on a path by a human, while the camera records a monocular learning sequence. Then a 3D reconstruction of the path and the environment is computed off line from the learning sequence. The 3D reconstruction is then used for computing the pose of the robot in real time (30 Hz) in autonomous navigation. Results from our localization method are compared to the ground truth measured with a differential GPS.

In this paper, a complete system for outdoor robot navigation is presented. It uses only monocular vision. The robot is first guided on a path by a human. During this learning step, the robot records a video sequence. From this sequence, a three dimensional map of the trajectory and the environment is built. When this map has been computed, the robot is able to follow the same trajectory by itself. Experimental results carried out with an urban electric vehicle are shown and compared to the ground truth.

In this paper we present a method for computing the localization of a mobile robot with reference to a learning video sequence. The robot is first guided on a path by a human, while the camera records a monocular learning sequence. Then the computer builds a map of the environment. This is done by first extracting key frames from the learning sequence. Then the epipolar geometry and camera motion are computed between key frames. Additionally a hierarchical bundle adjustment is used to refine the reconstruction. The map stored for the localization include the position of the camera associated with each key frame as well as a set of interest points detected in the images and reconstructed in 3D. Using this map it is possible to compute the localization of the robot in real time during the automatic driving phase. 1

The work presents a method for estimating the inverse Jacobian matrix of a function, without computing the direct Jacobian matrix. The resulting inverse Jacobian matrix is shown to perform much better in modelling a relation /spl theta/ = f/sup -1/ (x) than the classical Moore-Penrose inverse J/sup +//sub f/. Theoretical insight as well as comparisons in the domain of visual servoing are provided to demonstrate this assertion.

We present a supervised approach to recover 3D models of buildings from multiple uncalibrated views. With this method the user matches 3D vertices in the images and defines the 3D model of the building with the help of elementary and intuitive geometric constraints. At the same time, a graph describing relationships between vertices is built. Then, unknown parameters of this graph are estimated non-linearly through a bundle adjustment to recover the building model and the camera parameters. This method asserts that geometric rules are perfectly respected. This approach is used to recover independently 3D parts of the building with suitable images. Then all these independent 3D models are merged to obtain a full multiscale model of the building. An example on real images is given.

In this paper, a new pose selection criterion for the kinematic calibration of parallel mechanisms is proposed. It enables one to take into account the measurement noise amplification that may occur for parallel mechanisms, as well as the variation of amplitude and anisotropy of the measuring device accuracy. This new criterion is applied to vision-based calibration of an Orthoglide mechanism, both in simulation, with comparison to existing criteria, and experimentally.

Bundle adjustment is one of the cornerstone to recover the scene structure from a sequence of images. The main drawback of this technique, due to nonlinear optimisation, is the need of initial conditions for intrinsic and extrinsic camera parameters and for the 3D structure that we want to reconstruct.

All in-text\treferences\tunderlined\tin\tblue\tare\tlinked\tto\tpublications\ton\tResearchGate, letting you\taccess\tand\tread\tthem\timmediately.

International audience

We propose a real time 3D tracking algorithm dedicated to the tracking of human faces in video sequences. A face is represented by a collection of 2D images called reference views. In our approach, a pattern is a region of the image defined in an area of interest and its sampling gives a grey level vector. The tracking technique involves two stages. An off-line learning stage is devoted to the computation of an interaction matrix for every reference view. This matrix relates the grey level difference between the tracked reference pattern and the current pattern sampled inside the area of interest to its "fronto parallel" movement (which do not modify its aspect in the image). The on-line stage consists in using this matrix to track the reference pattern in the current image. During this stage, appearance changes due to movements in roll are managed by switching between the different reference patterns. The reference pattern, after motion correction, giving the smallest grey level difference is supposed to be the new tracked reference pattern. We present experimental results showing the efficiency and the robustness of our approach.

In this article, an evaluation of a vision-based measuring system for parallel machine-tool calibration is performed. Simultaneous measurement of the 6 pose components enables one to perform calibration using the efficient inverse kinematic method. The system is composed of a single camera and a calibration board generated on a LCD monitor. Calibration board size can be adapted to the camera field of view, and specific points of interest can be generated, in order to improve pose measurement. Based on a single industrial camera, the measuring system is low-cost and easy-to-use. An experimental evaluation of the system is performed on a machine-tool axis. Measurement bias and precision are estimated by comparison with laser interferometry, and the influence of focal length and sensor resolution is examined.

Hager and Belhumeur (1998) proposed a general framework for object tracking in video images. It consists of low-order parametric models for the image motion of a target region. These models are used to predict movement and to track the target. The difference in intensity between the pixels belonging to the current region and the pixels of the selected target (learned during an offline stage) allows a straightforward prediction of the region position in the current image. The main aim of the article is to propose an important improvement within this framework, making the convergence faster with the same amount of online computation.

One of the most popular methods to extract useful information from an image sequence is the template matching approach. In this well known method the tracking of a certain feature or target over time is based on the comparison of the content of each image with a sample template. We propose a 3D template matching algorithm that is able to track targets corresponding to the projection of 3D surfaces. With only a few hundred subtractions and multiplications per frame, our algorithm provides, in real time, an estimation of the 3D surface pose. The key idea is to compute the difference between the current image content and the visual aspect of the target under the predicted spatial attitude. This difference image is converted into corrections on the 3D location parameters.

We propose a general framework for object tracking in video images. It consists of low-order parametric models for the image motion of a target region. These models are used to predict the movement and to track the target. The difference of intensity between the pixels belonging to the current region and the pixels of the selected target (learnt during an off-line stage) allows a straightforward prediction of the region position in the current image. The proposed algorithm allows to track in real time (less than 10 ms) any planar textured target under homographic motions. This algorithm is very simple (a few lines of code) and very efficient (less than 10 ms on a 150 MHz hardware).

We present an efficient method for real time tracking of 3D objects. Within this approach, target objects are modeled by sets of 2D patterns including all of the possible object appearances. The tracker is based on two tasks: a 2D tracker estimates the position of the current appearance in the current image; in real time, a second tracker looks for the change of appearance of the object. We experimentally show the efficiency of the algorithm, as well as its ability to resist occultations and changes of brightness.

A strategy combining advantages of view-based and model-based object recognition approaches has been developed. Textured 3D models are used to produce local appearances of object key-points. Correspondences between 3D points and local appearances are also established during this learning stage. The recognition consists first in matching these local appearances and those extracted from the image. A robust 3D pose estimation is then carried out, discarding spurious correspondences. This algorithm is computationally very efficient. It can analyse images including several objects and can also handle partial object occultations as well as important changes of brightness and contrast.

The purpose of this article is the localization of the camera in a textured universe. This environment, described by a database, is composed of a trihedron. The method is structured around three phases. At first, points obtained by the Harris and Stephens operator (1988) are associated between two successive images. This association is based on a light intensity correlation followed by an homography correlation. Secondly, the camera is localized by minimizing a double criteria. The first part of this criteria illustrates a good projection of the textured model in the image. The second one illustrates the fact that the system composed of the scene and two successive images have to satisfy the epipolar constraint. The minimization criteria is symmetric in relation to time in order to not perturb the localization process by previous localization errors. Indeed, the method calls into question the previous localization, in relation to the new image, to localize at best the new camera attitude. Finally, because of the geometry of the scene, the camera attitude is only localized about a scale factor. So, the last step consists in determining the scale factor by exploiting the "close surrounding" of the trihedron.

Reprocessing cells of nuclear plants are constituted by a great number of specular metallic pipes. When they are illuminated, this kind of pipes generates areas of high light intensity, called highlights. The latter can produce erroneous results, especially in edge detection. The matter of this paper is to suppress and further to exploit the highlight effects. With this aim in view, we propose a system based on the polarization of light, which not only suppresses highlights in the scene but also uses them to extract relevant information like the pipes axes at the video rate.

Recent progress in monocular localization of modelled objects allow to design a robot command based on pose from visual information. The computing time of such algorithms was was once too great for them to be used in real-time closed-loop control, but this is no longer so. The principle of this command is to control the camera location relative to the pose of a target object: this approach is not only straightforward, but moreover it is fairly general in the fact that it does not depend on the visual information which is treated but only of the localization delivered by these treatments. This command has been implemented on a camera-equipped robotic system, a Cartesian robot arm, to track volumic objects.

Deals with the hand-eye calibration problem. The question is to find the relative position and orientation between a camera rigidly mounted on the robot's last joint and the gripper. Hand-eye calibration is useful in many cases as for example, grasping objects or reconstructing 3D scenes. Almost all existing solutions lead to solving for homogeneous transformation equations of the form AX=XB. We propose a new formulation. Our method determines simultaneously the hand-eye transformation and the location of a calibration object with respect to the robot world coordinate system. The main advantage is that the number of unknowns remains constant and the solution is constrained to be consistent with the whole set of calibration data. Results of simulation experiments and comparisons with classical techniques are reported and analysed. Real experiments with a Cartesian robot are described and the results accuracy discussed.

We describe and compare two approaches to achieve segments matching between two images from a sequence, without any knowledge on the viewed object and/or on the motion of the camera between the different images. The first method uses an Hopfield neural network with several local constraints like correlation and distance between segments of consecutive images. The second algorithm is an iterative optimization of a criterion. We model the primitives displacement between the images by an homographic transform. Then we search, with a Levenberg-Marquardt method, the homography matrix giving the best match between the segments of the two images. The two algorithms are validated and compared on sequences of real images.

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.>

Our paper proposes a new model based approach to locate and track an object in a multi-cameras system: this method does not involve triangulation. If the calibration and the mutual geometry of the acquisition systems are known, it is possible to express the whole set of equations pertaining to each monocular system, in an unique reference system. In this way it is possible to show that based model methods are not restricted to monocular vision and that some techniques generally viewed as purely monocular can be readily extended and integrated to a multi-cameras system. We prove by experiments on sequences of real images that this approach leads to results better than the monocular ones in two directions: better accuracy as many different view points are used; better robustness as the system is able to deal gracefully with the loss of some of the captors.>

The paper presents a new technique to infer 3D information using a static camera provided with a zoom lens. The modelling process is straightforward and does not involve the computation of intrinsic camera parameters. The approach is based on the exploitation of images of accurate regular grids. The main idea is to compute a transformation which allows to obtain a relationship between the real grids (without distortion) located in front of the camera and their distorted images on the CCD matrix. This relationship takes automatically all the distortion phenomena into account. Previous work in reconstruction by zooming involved high quality optical systems. The principal aim of the present work is to generalize this kind of reconstruction in the case of a standard zoom lens.>

Presents a method for estimating the radial distortion generated by the lenses of an optical system. This method is based on the properties of a projective invariant: the cross ratio of four collinear points. It provides an iterative correction algorithm which computes images of planar grids. The calculated distortion curve is modeled by a cubic B-spline. Experiments with both synthetic and real data prove the validity of the approach. Furthermore, to show the effect of the radial distortion correction, results of different localization processes applied to corrected and uncorrected images are reported and compared.>

This paper presents a new method that permits to solve the problem of determination of a modelled 3D-object spatial attitude from a single perspective image and to compute the covariance matrix associated to the attitude parameters. Its principle is based on the interpretation of at least three segments as the perspective projection of linear ridges of the object model and on the iterative search ( using Kalman filtering) of the model attitude consistent with these projections. The knowledge of the attitude and of the associated covariances enables to use a higher level Kalman filter to track an object along an image sequence. In the tracking process this Kalman filter is used to predict the attitude of the object and the error matrices are used to make robust automatic matches between the image segments and the model ridges. Tracking experiments have been made that proves the validity of this approach.

Abstract- This paper presents a new method that permits to estimate, in the viewer coordinate system, the spatial attitude of an articulated object from a single perspective image. Its principle is based on the interpretation of some image lines as the perspective projection of linear ridges of the object model, and on an iterative search of the model attitude consistent with these projections. The presented method doesn't locate separately the different parts of the object by using for each of them a technics devoted to the localization of rigid object but computes a global attitude which respects the mechanical articulations of the objet. In fact, the geometrical transformations applied to the model to bring it into the correct attitude are obtained in two steps. The first one is devoted to the estimation of the attitude parameters corresponding to a rotation and involves an iterative process. The second step permits by the resolution of a linear system to estimate the translation parameters. The presented experiments correspond to the localization of robot arms from synthetical and real images. The former case permits to appreciate the accuracy of the method since the final result of the pose estimation can be compared with the attitude parameters used to create the synthetical image. The latter case presents an experiment made in an industrial environment and involves the estimation of twelve paramaters since the observed robot arm owns six inner degrees of freedom. The presented method can be useful in some operation driven by remote control. 1

It is shown that it is possible to infer 3-D information from a set of images taken with a zoom lens. A precise study of the optical properties of such a lens gives two major results: The intersection between the optical axis and the image plane can be independently and accurately determined, and the pin-hole model cannot be used directly for the approximation of such a complex lens system. To explain the optical phenomena occurring during a zoom-lens focal-length change, it is shown that a thick optical model must be considered. Experimental reconstruction results for a set of real images, are given.>

An algorithm for recovering the scaling function of a straight homogeneous generalized cylinder (SHGC) from an image contour is presented. Both location and reference cross section are supposed known. Perspective view assumption and geometric properties of SHGCs are used to derive the method. No additional constraints have been imposed on the object shape. The method has been tested on synthetic image, with promising results.>

A system is presented for modelling solids of revolution from a set of a few monocular images. The reconstruction is obtained by assuming only that the viewed object belongs to this particular class of objects. The knowledge of the camera displacement between each image is not required. The modeling is based on the resolution of the inverse perspective problem for the contour points detected in the different images.>

The localization of some kinds of modeled generalized cylinders from a single brightness perspective image is addressed. It is shown how the zero-curvature points of their contours can be used to solve the inverse perspective problem. Three key theorems about the perspective projection of space curves and of the limbs of a straight homogeneous generalized cylinder whose scaling function has at least one zero-curvature point are discussed. In view of the localization of homogeneous generalized cylinders, an algorithm previously developed by the authors which estimates the pose of a line-triplet is adapted. A new theoretical result about the inverse perspective projection of cones of revolution useful for the localization of objects of revolution is presented. The corresponding algorithms have been implemented, and results of experiments demonstrate the feasibility of the proposed localization methods.>

The authors proposed the localization of some kinds of generalized cylinders from their brightness image by solving the inverse perspective transform of their contours. Geometrical properties of perspective projection of zero-curvature points of space or planar curves are used for that. The main geometrical properties are exploited in two experiments. These experiments involve straight homogeneous cylinder and objects of revolution with a scaling function having at least one zero-curvature point. Knowing the model of these objects, it is shown that their spatial attitude can be recovered from their perspective image.>

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.>

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.>

A new method is presented for the recognition of polyhedra in range data. The method is based on a hypothesis accumulation scheme which allows parallel implementations. The different objects to be recognized are modeled by a set of local geometrical patterns. Local patterns of the same nature are extracted from the scene. For the recognition of an object, local scene and model patterns having the same geometrical characteristics are matched. For each of the possible matches, the geometric transformations (i.e., rotations and translations) are computed, which allows the overlapping of the model elements with those from the scene. This transformation permits the establishment of a hypothesis on the location of the object in the scene and the determination of a point in the transformation space. The presence of an object similar to a model involves the generation of several compatible hypotheses and creates a compact cluster in the transformation space. The recognition of the object is based on the detection of this cluster. The cluster coordinates give the values of the rotations and the translations to be applied to the model such that it corresponds to the object in the scene. The exact location of this object is given by the transformed model.