First prototypes of standard plenoptic cameras (SPCs) were based on arrays of pinhole cameras. Despite the array nature, viewpoint pinhole arrays are not intrinsically provided by current SPC calibration tools. In this work, we start by detailing the mapping between the SPC model and a camera array of viewpoints. Then, the mapping is used to propose a calibration procedure for the SPC based on a grid of corners. Calibration involves two steps, first a linear solution and then a nonlinear optimization minimizing the ray re-projection error. The proposed calibration methodology compares favourably with state of the art calibrations and the linear solution proposed for the initial stage of the calibration outperforms the state of the art.

This article presents for the first time a global method for registering 3D curves with 3D surfaces without requiring an initialization. The algorithm works with 2-tuples point+vector that consist in pairs of points augmented with the information of their tangents or normals. A closed-form solution for determining the alignment transformation from a pair of matching 2-tuples is proposed. In addition, the set of necessary conditions for two 2-tuples to match is derived. This allows fast search of correspondences that are used in an hypothesise-and-test framework for accomplishing global registration. Comparative experiments demonstrate that the proposed algorithm is the first effective solution for curve vs surface registration, with the method achieving accurate alignment in situations of small overlap and large percentage of outliers in a fraction of a second. The proposed framework is extended to the cases of curve vs curve and surface vs surface registration, with the former being particularly relevant since it is also a largely unsolved problem.

The article describes a pipeline that receives as input a sequence of stereo images, and outputs the camera motion and a Piecewise-Planar Reconstruction (PPR) of the scene. The pipeline, named Piecewise-Planar StereoScan (PPSS), works as follows: the planes in the scene are detected for each stereo view using semi-dense depth estimation; the relative pose is computed by a new closed-form minimal algorithm that only uses point correspondences whenever plane detections do not fully constrain the motion; the camera motion and the PPR are jointly refined by alternating between discrete optimization and continuous bundle adjustment; and, finally, the detected 3D planes are segmented in images using a new framework that handles low texture and visibility issues. PPSS is extensively validated in indoor and outdoor datasets, and benchmarked against two popular point-based SfM pipelines. The experiments confirm that plane-based visual odometry is resilient to situations of small image overlap, poor texture, specularity, and perceptual aliasing where the fast LIBVISO2 [1] pipeline fails. The comparison against VisualSfM+CMVS/PMVS [2] , [3] shows that, for a similar computational complexity, PPSS is more accurate and provides much more compelling and visually pleasant 3D models. These results strongly suggest that plane primitives are an advantageous alternative to point correspondences for applications of SfM and 3D reconstruction in man-made environments.

We propose a new method to add an uncalibrated node into a network of calibrated cameras using only pairwise point correspondences. While previous methods perform this task using triple correspondences, these are often difficult to establish when there is limited overlap between different views. In such challenging cases we must rely on pairwise correspondences and our solution becomes more advantageous. Our method includes an 11-point minimal solution for the intrinsic and extrinsic calibration of a camera from pairwise correspondences with other two calibrated cameras, and a new inlier selection framework that extends the traditional RANSAC family of algorithms to sampling across multiple datasets. Our method is validated on different application scenarios where a lack of triple correspondences might occur: addition of a new node to a camera network; calibration and motion estimation of a moving camera inside a camera network; and addition of views with limited overlap to a Structure-from-Motion model.

The article concerns the automatic calibration of a camera with radial distortion from a single image. It is known that, under the mild assumption of square pixels and zero skew, lines in the scene project into circles in the image, and three lines suffice to calibrate the camera up to an ambiguity between focal length and radial distortion. The calibration results highly depend on accurate circle estimation, which is hard to accomplish because lines tend to project into short circular arcs. To overcome this problem, we show that, given a short circular arc edge, it is possible to robustly determine a line that goes through the center of the corresponding circle. These lines, henceforth called Lines of Circle Centres (LCCs), are used in a new method that detects sets of parallel lines and estimates the calibration parameters, including the center and amount of distortion, focal length, and camera orientation with respect to the Manhattan frame. Extensive experiments in both semi-synthetic and real images show that our algorithm outperforms state-of-the-art approaches in unsupervised calibration from a single image, while providing more information.

Global 3D point cloud registration has been solved by finding putative matches between the point clouds for establishing alignment hypotheses. A naive approach would try to perform exhaustive search of triplets with a cubic runtime complexity in the number of data points. Super4PCS reduces this complexity to linear by making use of sets of 4 coplanar points. This paper proposes 2-Point-Normal Sets (2PNS), a new global 3D registration approach that advances Super4PCS by using 2 points and their normals for generating alignment hypotheses. The dramatic improvement in the complexity of 2PNS when compared to Super4PCS is demonstrated by the experiments that show speed-ups of two orders of magnitude in noise-free datasets and up to 5.2× in Kinect scans, while improving robustness and alignment accuracy, even in datasets with overlaps as low as 5%.

Affine Correspondences (ACs) are more informative than Point Correspondences (PCs) that are used as input in mainstream algorithms for Structure-from-Motion (SfM). Since ACs enable to estimate models from fewer correspondences, its use can dramatically reduce the number of combinations during the iterative step of sample-and-test that exists in most SfM pipelines. However, using ACs instead of PCs as input for SfM passes by fully understanding the relations between ACs and multi-view geometry, as well as by establishing practical, effective AC-based algorithms. This article is a step forward into this direction, by providing a clear account about how ACs constrain the two-view geometry, and by proposing new algorithms for plane segmentation and visual odometry that compare favourably with respect to methods relying in PCs.

The camera response function (CRF) relates quantised image pixel values with physical incoming light. This paper describes a method to estimate the CRF from a single image of a general two-coloured surface for which the albedo ratio between the coloured regions is known a priori. While other radiometric calibration methods either use multiple frames or require the light to be infinitely distant, the algorithm herein proposed makes no assumptions about lighting conditions and can handle cameras with strong vignetting. Although the approach is generic, in the sense that can be applied to any camera system, the method is particularly well suited for determining the CRF of near-lighting endoscopes in the operating room. This is a very pertinent problem for which no practical, effective solutions have been proposed. The robustness, repeatability, and accuracy of the algorithm is experimentally validated in real images acquired with different endoscopic set-ups.

Instead of measuring photo-similarity, SymStereo is a stereo vision algorithm that uses new cost functions to measure symmetry differences between pairs of images. In this paper we propose the acceleration of a complete signal processing pipeline for generating 3D volumes based on dense SymStereo. The outputs here generated achieve superior reconstruction quality namely for slant based scenarios, so typical in autonomous systems, that have to capture pairs of images and perform moving decisions in real-time. In particular, we analyse several parallelization strategies for the compute-intensive aggregation procedure using different parameters and evaluate a trade-off between processing time, and higher precision of the calculated depths and quality of the final reconstructed 3D volume. The developed parallel pipeline allows to process more than 4.5 volumes per second for high resolution images using commodity GPUs, which conveniently suits its application in a variety of robotics systems.

SymStereo is a new algorithm used for stereo estimation. Instead of measuring photo-similarity, it proposes novel cost functions that measure symmetry for evaluating the likelihood of two pixels being a match. In this work we propose a parallel approach of the LogN matching cost variant of SymStereo capable of processing pairs of images in real-time for depth estimation. The power of the graphics processing units utilized allows exploring more efficiently the bank of log-Gabor wavelets developed to analyze symmetry, in the spectral domain. We analyze tradeoffs and propose different parameter-izations of the signal processing algorithm to accommodate image size, dimension of the filter bank, number of wavelets and also the number of disparities that controls the space density of the estimation, and still process up to 53 frames per second (fps) for images with size 288 × 384 and up to 3 fps for 768 × 1024 images.

The article describes a new algorithm for calibrating a Kinect sensor that achieves high accuracy using only 6 to 10 image-disparity pairs of a planar checkerboard pattern. The method estimates the projection parameters for both color and depth cameras, the relative pose between them, and the function that converts kinect disparity units (kdu) into metric depth. We build on the recent work of Herrera et. al [8] that uses a large number of input frames and multiple iterative minimization steps for obtaining very accurate calibration results. We propose several modifications to this estimation pipeline that dramatically improve stability, usability, and runtime. The modifications consist in: (i) initializing the relative pose using a new minimal, optimal solution for registering 3D planes across different reference frames, (ii) including a metric constraint during the iterative refinement to avoid a drift in the disparity to depth conversion, and (iii) estimating the parameters of the depth distortion model in an open-loop post-processing step. Comparative experiments show that our pipeline can achieve a calibration accuracy similar to [8] while using less than 1/6 of the input frames and running in 1/30 of the time.

Odometry consists in using data from a moving sensor to estimate change in position over time. It is a crucial step for several applications in robotics and computer vision. This paper presents a novel approach for estimating the relative motion between suc-cessive RGB-D frames that uses plane-primitives instead of point features. The planes in the scene are extracted and the motion estimation is cast as a plane-to-plane registra-tion problem with a closed-form solution. Point features are only extracted in the cases where the plane surface configuration is insufficient to determine motion with no ambi-guity. The initial estimate is refined in a photo-geometric optimization step that takes full advantage of the plane detection and simultaneous availability of depth and visual appearance cues. Extensive experiments show that our plane-based approach is as accu-rate as state-of-the-art point-based approaches when the camera displacement is small, and significantly outperforms them in case of wide-baseline and/or dynamic foreground. 1

The problem of estimating the relative pose between axial cameras from pairwise point correspondences is still open to improvement. The state-of-the-art solutions are either too specific in its scope, assuming certain types of correspondences; too broad, dealing with all types of generalized cameras and failing to address the specific issues of axial cameras; or non-minimal linear solutions. The aim of this paper is to pursue new insights on axial cameras that can lead to a suitable minimal solution for this problem. We propose a new formulation for modeling the intersection of back-projection rays of axial cameras through a 5×5 essential matrix that enables a better understanding of some particular axial configurations and leads to a new set of polynomial equations that proves to be useful in constraining the motion estimation. These equations enable to compute a solution from 10 correspondences, an improvement over the 16-point algorithm, which is the state-of-the-art solution within our aimed scope. Both synthetic and real experiments show that our algorithm achieves a better performance than the 16-point algorithm in the context of robust optimization with RANSAC.

This article presents a new global approach for detecting vanishing points and groups of mutually orthogonal vanishing directions using lines detected in images of man-made environments. These two multi-model fitting problems are respectively cast as Uncapacited Facility Location (UFL) and Hierarchical Facility Location (HFL) instances that are efficiently solved using a message passing inference algorithm. We also propose new functions for measuring the consistency between an edge and a putative vanishing point, and for computing the vanishing point defined by a subset of edges. Extensive experiments in both synthetic and real images show that our algorithms outperform the state-of-the-art methods while keeping computation tractable. In addition, we show for the first time results in simultaneously detecting multiple Manhattan-world configurations that can either share one vanishing direction (Atlanta world) or be completely independent.

The tradeoff between error-correcting performance and numerical complexity of LDPC decoding algorithms is a well-known problem. In this paper we depict the unseen error-floor performance of the Self-Corrected Min-Sum algorithm for long length DVB-S2 codes. We developed a massively parallel simulation using GPUs which allowed a comprehensive BER characterization either in the waterfall or in the error-floor region. We show that the self-correction technique increases the BER performance by 0.5 and 0.2 dB, in the waterfall and error-floor region, when compared to the Min-Sum algorithm. Furthermore, it reaches within 0.2 dB to the Logarithmic Sum-Product BER performance and it also outperforms the Normalized Min-Sum at high SNR, a low complexity decoding algorithm which yields good BER performance.

Estimating the amount and center of distortion from lines in the scene has been addressed in the literature by the so-called ``plumb-line'' approach. In this paper we propose a new geometric method to estimate not only the distortion parameters but the entire camera calibration (up to an ``angular'' scale factor) using a minimum of 3 lines. We propose a new framework for the unsupervised simultaneous detection of natural image of lines and camera parameters estimation, enabling a robust calibration from a single image. Comparative experiments with existing automatic approaches for the distortion estimation and with ground truth data are presented.

This article addresses the problem of imagebased localization in indoor environments. The localization is achieved by querying a database of omnidirectional images that constitutes a detailed visual map of the building where the robot operates. Omnidirectional cameras have the advantage, when compared to standard perspectives, of capturing in a single frame the entire visual content of a room. This, not only speeds up the process of acquiring data for creating the map, but also favors scalability by significantly decreasing the size of the database. The problem is that omnidirectional images have strong non-linear distortion, which leads to poor retrieval results when the query images are standard perspectives. This paper reports for the first time thorough experiments in using perspectives to index a database of para-catadioptric images for the purpose of robot localization. We propose modifications to the SIFT algorithm that significantly improve point matching between the two types of images with positive impact in the recognition based in visual words. We also compare the classical bags-of-words against the recent framework of visual-phrases, showing that the latter outperforms the former.

Many robotic systems combine cameras with Laser Rangefinders (LRF) for simultaneously achieving multi-purpose visual sensing and accurate depth recovery. Employing a single sensor modality for accomplishing both goals is an appealing proposition because it enables substantial savings in equipment, and tends to decrease the overall complexity of the system. This article explores the possibility of replacing LRF by passive stereo vision for reconstructing the scene along a 2D scan plane. We present a new stereo algorithm that is specifically tailored for the purpose. The algorithm recovers the depth along the scan plane using a symmetry-based matching cost (SymStereo), and refines the raw estimates by applying dynamic programming, followed by a Markov Random Field (MRF) that decides if the reconstructed contour is a line or not. We report for the first time comparative experiments between Stereo Rangefinding (SRF) and LRF. The results are encouraging by showing that SRF can be a plausible alternative to LRF in several application scenarios. Moreover, since SRF also enables independent depth estimates along multiple scan planes with arbitrary orientation, being the only constraint that the scan plane intersects the stereo baseline, it is an important benefit that can be decisive for many robotic applications.

This paper presents a new algorithm for the extrinsic calibration of a perspective camera and an invisible 2D laser-rangefinder (LRF). The calibration is achieved by freely moving a checkerboard pattern in order to obtain plane poses in camera coordinates and depth readings in the LRF reference frame. The problem of estimating the rigid displacement between the two sensors is formulated as one of registering a set of planes and lines in the 3D space. It is proven for the first time that the alignment of three plane-line correspondences has at most eight solutions that can be determined by solving a standard p3p problem and a linear system of equations. This leads to a minimal closed-form solution for the extrinsic calibration that can be used as hypothesis generator in a RANSAC paradigm. Our calibration approach is validated through simulation and real experiments that show the superiority with respect to the current state-of-the-art method requiring a minimum of five input planes.

Keypoint detection and matching is of fundamental importance for many applications in computer and robot vision. The association of points across different views is problematic because image features can undergo significant changes in appearance. Unfortunately, state-of-the-art methods, like the scale-invariant feature transform (SIFT), are not resilient to the radial distortion that often arises in images acquired by cameras with microlenses and/or wide field-of-view. This paper proposes modifications to the SIFT algorithm that substantially improve the repeatability of detection and effectiveness of matching under radial distortion, while preserving the original invariance to scale and rotation. The scale-space representation of the image is obtained using adaptive filtering that compensates the local distortion, and the keypoint description is carried after implicit image gradient correction. Unlike competing methods, our approach avoids image resampling (the processing is carried out in the original image plane), it does not require accurate camera calibration (an approximate modeling of the distortion is sufficient), and it adds minimal computational overhead. Extensive experiments show the advantages of our method in establishing point correspondence across images with radial distortion.

Rigid motion estimation from image point correspondences is an overconstrained problem that can be solved by minimizing an adequate cost function. Given the unreliable nature of image point correspondences, they must be divided into two categories: inliers and outliers. Finding the correct camera motion and discarding the outliers is a coupled problem usually solved by a random search of the solution space. This article proposes adaptive and hybrid genetic approaches to improve the efficiency of this search. We build on top of the GASAC algorithm that has been recently presented for solving problems in geometric computer vision. GASAC is modified to address the specific issues of camera motion estimation such as outlier ratios above 50% due to wide-baseline image acquisition and an adequate choice of a fitness function. In order to avoid local minima, we propose three adaptive strategies: varying the mutation probability, resampling the lowest ranked individuals, and using a hybrid approach that combines GASAC with simulated annealing. Results are validated on publicly available benchmark images, and it is shown that the proposed genetic approaches outperform the standard RANSAC search used among computer vision practitioners.

Image keypoints are broadly used in robotics for different purposes, ranging from recognition to 3D reconstruction, passing by SLAM and visual servoing. Robust keypoint matching across different views is problematic because of the relative motion between camera and scene that causes significant changes in feature appearance. The problem can be partially overcome by using state-of-the-art methods for keypoint detection and matching, that are resilient to common affine transformations such as changes in scale and rotation. Unfortunately, these approaches are not invariant to the radial distortion present in images acquired by cameras with wide field-of-view. This article proposes modifications to the Scale Invariant Feature Transform (SIFT), that improve the repeatability of detection and effectiveness of matching in the presence of distortion, while preserving the characteristics of invariance to scale and rotation. These modifications require an approximate modeling of the image distortion, and consist in using adaptative gaussian filtering for detection and implicit gradient correction for description. Extensive experiments, with both synthetic and real images, show that our method outperforms explicit distortion correction using image rectification.

Endoscopic camera for surgical navigation and 3D visualization requires precise and stable estimates of the calibration parameters. The estimation of the hand-eye transform between the camera frame and the opto-tracked body of the endoscope is an important issue of the calibration. This paper presents a new stable method for the hand-eye calibration problem. The most popular method estimates the transform directly in the special euclidean group SE(3) by computing separately the rotation and the translation. The second famous approach formulates the problem in the dual quaternion space and estimates jointly the rotation and the translation. In a first glance, the simultaneous estimation seems to be always advantageous. However, and according to the experiments, this is not the case for the rotation estimation that is affected by the noise in translation. Our approach takes advantage of the both methods and uses the dual quaternion to estimate separately the rotation and the translation. We show experimentally that our algorithm is more stable with minimal number and small amplitude of motions.

This paper presents a general approach for the simultaneous tracking of multiple moving targets using a generic active stereo setup. The problem is formulated on the plane, where cameras are modeled as “line scan cameras,” and targets are described as points with unconstrained motion. We propose to control the active system parameters in such a manner that the images of the targets in the two views are related by a homography. This homography is specified during the design stage and, thus, can be used to implicitly encode the desired tracking behavior. Such formulation leads to an elegant geometric framework that enables a systematic and thorough analysis of the problem at hand. The benefits of the approach are illustrated by applying the framework to two distinct stereo configurations. In the first case, we assume two pan-tilt-zoom cameras, with rotation and zoom control, which are arbitrarily placed in the working environment. It is proved that such a stereo setup can track up toN= 3 free-moving targets, while assuring that the image location of each target is the same for both views. The second example considers a robot head with neck pan motion and independent eye rotation. For this case, it is shown that it is not possible to track more thanN= 2 targets because of the lack of zoom. The theoretical framework is used to derive the control equations, and the implementation of the tracking behavior is described in detail. The correctness of the results is confirmed through simulations and real tracking experiments.

International audience

This article presents a general approach for the active stereo tracking of multiple moving targets. The problem is formulated on the plane, where cameras are modeled as “line scan cameras” and targets are described as points with unconstrained motion. We propose to control the active system parameters in such a manner that the images of the targets in the two views are related by an homography. This homography is specified during the design stage and implicitly encodes the tracking behavior. It is shown that this formulation leads to an elegant geometric framework that enables to decide about the feasibility of a particular active tracking task. We apply it to prove that two cameras with rotation and zoom control, can track up to three moving targets, while assuring that the image location of each target is the same for both views. In addition, the framework is also useful for devising tracking strategies and deriving the required control equations. This feature is illustrated through a real experiment on tracking two independent targets using a binocular stereo head.

We present a novel calibration technique for all central catadioptric cameras using images of planar grids. We adopted the well-known sphere camera model to describe the catadioptric projection. We show that, using the so-called lifted coordinates, a linear relation mapping the grid points to the corresponding points on the image plane can be written as a 6 × 6 matrix Hcata, which acts like the classical 3 × 3 homography for perspective cameras. We show how to compute the image of the absolute conic (IAC) from at least 3 homographies and how to recover from it the intrinsic parameters of the catadioptric camera. In the case of paracatadioptric cameras one such homography is enough to estimate the IAC, thus allowing the calibration from a single image.

We study the epipolar geometry between views acquired by mixtures of central projection systems including catadioptric sensors and cameras with lens distortion. Since the projection models are in general non-linear, a new representation for the geometry of central images is proposed. This representation is the lifting through Veronese maps of the image plane to the 5D projective space. It is shown that, for most sensor combinations, there is a bilinear form relating the lifted coordinates of corresponding image points. We analyze the properties of the embedding and explicitly construct the lifted fundamental matrices in order to understand their structure. The usefulness of the framework is illustrated by estimating the epipolar geometry between images acquired by a paracatadioptric system and a camera with radial distortion.

When deploying a heterogeneous camera network or when we use cheap zoom cameras like in cell-phones, it is not practical, if not impossible to off-line calibrate the radial distortion of each camera using reference objects. It is rather desirable to have an automatic procedure without strong assumptions about the scene. In this paper, we present a new algorithm for estimating the epipolar geometry of two views where the two views can be radially distorted with different distortion factors. It is the first algorithm in the literature solving the case of different distortion in the left and right view linearly and without assuming the existence of lines in the scene. Points in the projective plane are lifted to a quadric in three-dimensional projective space. A radial distortion of the projective plane results to a matrix transformation in the space of lifted coordinates. The new epipolar constraint depends linearly on a 4 /spl times/ 4 radial fundamental matrix which has 9 degrees of freedom. A complete algorithm is presented and tested on real imagery.

In central catadioptric systems, lines in a scene are projected to conic curves in the image. This work studies the geometry of the central catadioptric projection of lines and its use in calibration. It is shown that the conic curves where the lines are mapped possess several projective invariant properties. From these properties, it follows that any central catadioptric system can be fully calibrated from an image of three or more lines. The image of the absolute conic, the relative pose between the camera and the mirror, and the shape of the reflective surface can be recovered using a geometric construction based on the conic loci where the lines are projected. This result is valid for any central catadioptric system and generalizes previous results for paracatadioptric sensors. Moreover, it is proven that systems with a hyperbolic/elliptical mirror can be calibrated from the image of two lines. If both the shape and the pose of the mirror are known, then two line images are enough to determine the image of the absolute conic encoding the camera's intrinsic parameters. The sensitivity to errors is evaluated and the approach is used to calibrate a real camera.

Paracatadioptric sensors combine a parabolic shaped mirror and a camera inducing an orthographic projection. Such a configuration provides a wide field of view while keeping a single effective viewpoint. Previous work in central catadioptric sensors proved that a line projects into a conic curve and that three line images are enough to calibrate the system. However the estimation of the conic curves where lines are mapped is hard to accomplish. In general only a small arc of the conic is visible in the image and conventional conic fitting techniques are unable to correctly estimate the curve. The present work shows that a set of conic curves corresponds to paracatadioptric line images if, and only if, certain properties are verified. These properties are used to constraint the search space and correctly estimate the curves. The accurate estimation of a minimum of three line images allows the complete calibration of the paracatadioptric camera. If the camera is skewless and the aspect ratio is known then the conic fitting problem is solved naturally by an eigensystem. For the general situation the conic curves are estimated using non-linear optimization.

An imaging system with a single effective viewpoint is called a central projection system. The conventional perspective camera is an example of a central projection system. Systems using mirrors to enhance the field of view while keeping a unique center of projection are also examples of central projection systems. Perspective image formation can be described by a linear model with well known properties. In general central catadioptric imaging, the mapping between points in the world and in the image is highly nonlinear. The paper establishes a general model for central catadioptric image formation made up of three functions: a linear function mapping the world into an oriented projective plane, a nonlinear transformation between two oriented projective planes, and a collineation in the plane. The model is used to study issues in the projection of lines. The equations and geometric properties of general catadioptric imaging of lines are derived. The application of the results in auto-calibration of central catadioptric systems and reconstruction are discussed. A method to calibrate the system using three line images is presented.

Deals with active tracking of 3D moving targets. Visual tracking is presented as a regulation control problem. The performance and robustness in visual control of motion depends both on the vision algorithms and the control structure. Delays and system latencies substantially affect the performance of visually guided systems. We discuss ways to cope with delays while improving system performance. Model predictive control strategies are proposed to compensate for the mechanical latency in visual control of motion.

A system for tracking multiple targets in 3D is described. The system is made up of two pan-and-tilt units that are attached to the extremities of a rotating arm. This configuration has several advantages and can deal with several specific instances of tracking more than one target. A control strategy that guarantees equal target disparities in both images whenever targets are seen by both cameras is presented. This has advantages for segmentation and trajectory reconstruction. Target images are simultaneously visible in the cameras, enabling the recovery of the targets 3D trajectory. It is also shown that mutual occlusion occurs in a well-defined configuration and can therefore be dealt with.

The performance of a binocular active vision system depends mainly on two aspects: vision/image processing and control. We characterize the monocular performance of smooth pursuit. This system is used to track binocularly targets in a surveillance environment. One of the aspects of this characterization was the inclusion of the vision processing. To characterize the performance from the control point of view four standard types of inputs were used: step, ramp, parabola and sinusoid. The responses can be used to identify which subsystems can be optimized. We show that prediction and a velocity estimate are essential for a good tracking performance.