Nonlinear Mean Shift for Robust Pose Estimation

Size: px
Start display at page:

Download "Nonlinear Mean Shift for Robust Pose Estimation"

Transcription

1 Nonlinear Mean Shift for Robust Pose Estimation Raghav Subbarao Yakup Genc Peter Meer ECE Department Real-time Vision and Modeling Department Rutgers University Siemens Corporate Research Piscataway, NJ Princeton, NJ Abstract We propose a new robust estimator for camera pose estimation based on a recently developed nonlinear mean shift algorithm. This allows us to treat pose estimation as a clustering problem in the presence of outliers. We compare our method to RANSAC, which is the standard robust estimator for computer vision problems. We also show that under fairly general assumptions our method is provably better than RANSAC. Synthetic and real examples to support our claims are provided. 1. Introduction Real time estimation of camera pose is an important problem in computer vision. Pose estimation along with scene structure estimation is known as the Structure-From- Motion (SFM) problem which is the central goal of vision. It is widely accepted that once good estimates of the structure and motion are known, they can be improved using offline methods like bundle adjustment [19]. However, to get a starting point, a system needs to account for both noise and gross errors which do not satisfy the geometric constraints being enforced. Such errors are known as outliers. Pose estimation is also a part of other applications such as augmented reality (AR). For AR only the pose of the camera is needed, although some structure may also be estimated. The pose is required in real time and offline methods such as bundle adjustment are not applicable here. Random Sample Consensus (RANSAC) and its variations, which follow a hypothesise-and-test procedure, are the standard ways of handling outliers in SFM. In this paper we propose a new robust estimator for camera pose estimation. The estimator is based on the nonlinear mean shift algorithm of [15, 20] applied to the Special Euclidean Group which is the set of all rigid body motions in 3D and is equivalent to the set of all camera poses. We show theoretically and experimentally that our method requires fewer hypotheses than any hypothesise-and-test algorithm for the same level of performance. We discuss some of the previous work related to our approach in Section 2. In Section 3 we introduce the nonlinear mean shift algorithm. In Section 4 we develop a robust pose estimator based on this algorithm and outline a proof of why we expect the mean shift based estimator to be better than RANSAC. Finally, in Section 5 we present the results of experiments on synthetic and real data sets. 2. Previous Work Classical methods reconstruct the scene using correspondences across images and estimating the epipolar geometry between pairs of frames or the trifocal tensor for three frames. These reconstructions are then stitched together into a single frame [14]. The Euclidean equivalent of this is the relative pose estimation problem given image correspondences between two images [8]. Alternatively, the motion and structure can be estimated in a single coordinate frame [12]. Such methods require absolute camera pose estimation based on correspondences between 3D world points and 2D image points [1, 6]. An important aspect of these algorithms is that whenever any geometrical constraint is being enforced, there will be outliers which do not satisfy the constraint. These outliers occur due to errors in lower level modules such as the image feature tracker. When estimating the motion and structure it is necessary to detect and remove these outliers. The standard way of handling outliers in computer vision is the RANSAC algorithm [4]. In RANSAC, parameter hypotheses are generated by randomly choosing a minimal number of elements required to generate a hypothesis. The hypotheses are scored based on their likelihood to have generated the observed data and the best hypothesis is retained. Based on the noise model assumed, different scoring function have been proposed to develop variations of RANSAC [17, 18]. Another important contribution has been the development of preemptive forms of RANSAC [2, 10] which allow RANSAC to be used in real-time SFM systems. In such methods, all the hypotheses are not scored completely. Some hypotheses are preemptively dropped. Unlike RANSAC where a single hypothesis is generated and scored while only retaining the most likely hypothesis, preemptive RANSAC [10] proceeds by generating all the hypotheses at the beginning. The likelihood of the hypotheses 1

2 is incrementally estimated while the number of hypotheses are continually reduced. Different methods exist for generating a pose hypotheses given a set of point correspondences. The 5-point method [9] can be used for the relative pose between two frames given image correspondences across the frames. Alternatively, given three 3D world to 2D image point correspondences, the 3-point method [6] gives upto four different estimates. The elemental subset can be augmented with another point to decide between the hypotheses and this gives a 4-point hypotheses generation algorithm [10]. All robust methods in the RANSAC family try to find the best hypothesis among the hypotheses generated. Consequently, other inlier hypothesis (hypotheses generated only from inliers) which lie close to the true pose, are neglected. Our robust estimator combines all the inlier hypothesis rather than simply trying to find the best one. In this way, we utilize the information available in a more complete manner than the hypothesise-and-test framework. 3. Nonlinear Mean Shift We briefly discuss standard mean shift which is applicable to vector spaces. We would like to work in space of all pose estimates, which is not a vector space. This space is a standard geometrical space known as the Special Euclidean Group, denoted by SE(3). A mean shift algorithm for SE(3) is discussed in Section The Original Mean Shift Given n data points x i, i = 1,..., n lying in the Euclidean space R d, the kernel density estimate ˆf k (x) = c k,h n k ( x x i 2 /h 2) (1) with bandwidth h and profile function k satisfying k(z) 0 for z 0, is a nonparametric estimator of the density at x. The constant c k,h is chosen to ensure that ˆf integrates to 1. Let g(x) = k (x). From [3], taking the gradient of (1) m h (x) = g ( x x i 2 /h 2) x i g ( x (2) x x i 2 /h 2) where, m h (x) is the mean shift vector which is proportional to the normalized density gradient estimate. The iteration x j+1 = m h (x j ) + x j is a gradient ascent technique converging to a stationary point of the density [3]. Saddle points can be detected and removed, to obtain the modes Mean Shift over SE(3) Mean shift for Lie groups was proposed in [20]. This algorithm was generalized to the class of all analytic manifolds in [15]. The special Euclidean group is a matrix Lie group. Here, we outline details of the mean shift algorithm for the SE(3). Further details can be found in [15, 20]. The special Euclidean group consists of 4 4 matrices of the form [ ] R t X = (3) 0 1 where, t is a 3-vector and R is a 3 3 orthogonal matrix i.e. R T R = I. Each element of SE(3) has 12 elements but due to orthogonality it has just 6 degrees of freedom. Note, that SE(3) is not a vector space. Given two points X 1, X 2 SE(3), X 1 + X 2 does not lie in SE(3) but X 1 X 2 SE(3). The group operation for elements of SE(3) is matrix multiplication and not matrix addition. The group SE(3) has a closely associated vector space (Lie algebra) se(3). The correspondence between SE(3) and se(3) is established through the exponential operator exp : se(3) SE(3) and its inverse, the logarithm operator log : SE(3) se(3). The computational details of the exp and log operators for SE(3) can be found in [20]. Following standard notation in such cases, we denote elements of SE(3) by capital bold letters and elements of se(3) with small, bold letters. The usage of the same letter indicates a correspondence, x = log(x) and X = exp(x). Elements of se(3) are 4 4 matrices of the form x = [ Ω u 0 0 where, u is a 3-vector and Ω is skew-symmetric Ω = ] 0 ω z ω y ω z 0 ω x ω y ω x 0 (4). (5) Note, that elements of se(3) are defined by 6 distinct numbers. Although, the elements of se(3) are organized in the form of a matrix, when we talk about vectors in se(3) we mean the vector ( ω x, ω y, ω z, u T ) T. Therefore, se(3) is a six-dimensional vector space. We define a norm on se(3) through a 6 6 positive, definite matrix H as [11] x 2 H = x T Hx. (6) This allows us to define the distance between X and Y as log(x 1 Y) H. The exp and log operators have two useful properties. Firstly, a neighbourhood of the identity in SE(3) maps onto

3 a neighbourhood of the zero matrix in se(3), and there exists a neighbourhood where these operators are one-to-one. Secondly, for x, y se(3) [13] exp(x)exp(y) = exp ( x + y + O( (x, y) 2 ) ) (7) and therefore, for small x, y SE(3), exp(x)exp(y) exp(x + y). (8) Now, given a set of points X i SE(3), i = 1,..., n, we define the density estimator at X SE(3) as ˆf k (X) = c k,h n k ( log(x 1 X i ) /h 2) (9) and we obtain the mean shift vector g ( log(x 1 X i ) /h 2) log ( X 1 ) X i m h (X) = g ( (10) log(x 1 X i ) /h 2) where, g is defined as before. Note, all the g( ) terms are scalars and the log ( X 1 X i ) terms lie in se(3). Therefore, m h (X) lies in se(3). To get back to the group SE(3), the mean shift iteration now becomes, X j+1 = X j exp ( m h (X j ) ). (11) 4. Robust Pose Estimation The first step of our algorithm is hypothesis generation. These hypotheses are clustered over SE(3) using nonlinear mean shift. The most dominant detected mode is retained as the pose. The pose hypotheses based on data from a single frame are plotted in Figure 1 using the rotation elements as coordinates. We integrated this robust estimator into the camera tracking system of [16]. The world coordinate frame is based on a set of easily identifiable markers. Initially, the pose is estimated from these markers and there are no outliers. Features in the rest of the scene are triangulated using these pose estimates. The camera is then allowed to move freely without being required to keep the markers in view. Triangulated features are used to estimate pose while further features are constantly reconstructed. At this stage, the robust estimator is required to prevent mismatches in the image tracking from leading to erroneous pose estimates. In practice, a robust pose estimator is not sufficient for good results. Each robust fit is used to remove outliers and the final pose is estimated using only the inliers. When used in a SFM system, the mean shift estimator also allows us to take advantage of the continuity of the Figure 1. Sampled rotations mapped to the Lie algebra using data from a frame. The cluster around the true pose is clearly visible. camera movement. Since the pose estimates of two consecutive frames will not be very different from each other, rather than starting a mean shift iteration at each hypothesis, we only try to find the mode closest to the previous frame s pose. Therefore a single mean shift iteration is initialized at the previous pose estimate. The point of convergence is taken as the next pose estimate Mean Shift versus RANSAC We outline a simple proof of why mean shift performs better than hypothesis-and-test algorithms. Assume the data consists only of noisy inliers. With perfect data all hypotheses will be at the true pose. For noisy data, the hypotheses P i, i = 1,..., m are distributed around the true pose. We assume the algorithm for hypothesis generation is unbiased. The generated hypotheses will form a unimodal distribution with the made at the true pose. This mode is modeled as a Gaussian with mean at the true pose P o and covariance Σ. Since SE(3) is a 6-dimensional manifold in 12-dimensional space, Σ is a matrix of rank 6 [7]. The squared Mahalanobis distances of the hypotheses from P o forms a χ 2 distribution with 6 degrees of freedom (dof). Let f and F be the density and distribution functions of a 6 dof χ 2 distribution. Let P r be the RANSAC result and P a be the average of m hypotheses. We compare the two estimates based on their Mahalanobis distances from P o. RANSAC will always return one of the generated hypotheses. Ideally, it will return the hypothesis with the lowest Mahalanobis distance to P o. The probability of the lowest Mahalanobis distance being d and all the others being greater than d is p( P r P o 2 Σ = d 2 ) = mf(d 2 )(1 F (d 2 )) m 1. (12) The mean of m Gaussian variables is a Gaussian random variable with the same mean but an m times less covariance. Therefore, P a is a Gaussian random variable with mean P o

4 Figure 2. Comparison of the error densities for RANSAC and averaging as given by (12) and (13). (a) m = 10 for both curves. (b) m = 100 for both curves. (c) m = 100 for RANSAC and m = 25 for averaging. and covariance Σ/m. Consequently, m P a P o 2 Σ is a χ2 variable and this gives p( P a P o 2 Σ = d 2 ) = mf(md 2 ). (13) The distributions for m = 10 and m = 100 are compared in the first two images of Figure 2. The averaged estimates are closer to the true pose, and as m increases this difference becomes more obvious. Therefore, averaging requires fewer hypotheses to perform as well as RANSAC. In the presence of outliers, the hypotheses will no longer form a unimodal distribution around the true pose. However, the pose estimates generated using only inliers will still be distributed in the same way. Ideally, RANSAC will return the closest of these estimates, and the above analysis for RANSAC still holds. To prevent outlier hypotheses from affecting the averaging, the averaging needs to be robust. Mean shift (with the Epanechnikov kernel) is the mean of all the points lying within the basin of attraction [3]. For an appropriately chosen bandwidth, the mean shift estimate will be the average of all the inlier hypotheses and the distance of this value from the true pose will follow the distribution (13). Since averaging requires fewer hypotheses for the same level of performance and the major bottleneck in the hypothesis-and-test procedure is the generation of the hypotheses, less time is spent removing outliers. In practice, the above assumptions may not hold. The hypotheses need not be normally distributed, although for low noise this does not lead to serious problems. More importantly, the bandwidth of the mean shift is usually conservative and not all inlier hypothesis are averaged. Therefore, the parameter m differs for mean shift and RANSAC. In the third curve of Figure 2, we compare the RANSAC error density of (12) for m = 100 and the averaging error density of (13) for m = 25. As these densities are comparable, mean shift needs to average only 25 good hypotheses to be as good as RANSAC with 100 inlier hypotheses. 5. Results In this section we compare the performance of our algorithm with RANSAC, on real and synthetic data sets, and verify the claims made in the previous section Synthetic Experiments We generated a random cloud of 80 3D world points. The points were projected to the image with the identity pose. To estimate the covariance of the RANSAC and mean shift estimates we use bootstrapping. In each trial, Gaussian noise, of standard deviation 0.1 for 3D points and standard deviation 0.01 for 2D, was added to the data. Then 20 randomly generated outliers were also added to the data set. This was repeated 100 times and the RANSAC and mean shift were run on each data set. The means of both RANSAC and mean shift estimates are close to the true pose. The sample covariance matrix for both sets of estimates is of rank 6, and the singular vectors corresponding to nonzero singular values lie in the tangent plane of the manifold SE(3) [7]. Secondly, the covariance of the RANSAC estimates is greater than the covariance of the mean shift estimates. The nonzero singular values are listed in Table 1. Table 1. Nonzero Singular Values of Covariance Matrices. Mean Shift RANSAC

5 Figure 3. Comparison of mean shift and RANSAC for pose estimation on the Corridor sequence. The ground truth cameras are drawn with black dots and the robust pose estimates are drawn in solid red. The results of mean shift are on the left and RANSAC on the right The Corridor Sequence We tested the robust estimators on real data using the Corridor sequence from Oxford. The 409 visible points from the first image were taken as the initial data set. For this frame there are no outliers. The point matching system of [5] was used to track points across all the images. The outliers keep increasing at each matching step since the matcher makes errors, and more importantly, as points go out of view they get wrongly assigned to the best match available. To make the comparison between mean shift and RANSAC meaningful, the same elemental subsets were used in both cases. For the first frame both methods gave good results. As the number of outliers increased mean shift performs better than RANSAC. The mean shift estimate shows a visible error only for these last three frames when the number of inliers falls sharply from 248 at the eighth frame to 119 for the ninth frame, while RANSAC breaks down much earlier. In Figure 3, the robust pose estimates are compared with the ground truth. The pose is used to render the frames so that the difference can be visualized. The error between the robust estimates and the ground truth is also compared numerically. Let ˆR and ˆt be the ground truth pose and let R, t be robust estimates. The rotational error is given by the Frobenius norm of R T ˆR I and the translation error by the vector norm of t ˆt. The rotational error, translational error and number of inliers are plotted versus the frame number in Figure 4. to allow scene feature to be reconstructed. This is the set of frames lying along a line in the top left of the image. Later, the camera is allowed to move away from the markers and the robust estimator is used. We ran our experiments on a 2.4GHz Pentium 4 machine. RANSAC requires 100 hypothesis and takes 0.4ms to process them. Each hypothesis generation takes 0.05ms leading to a total of 5.4ms for the robust estimator. The mean shift estimator requires 50 hypothesis for similar performance and takes 1.2ms, on the average, to find the mode. This gives a total time of 3.7ms for the mean shift estimator Camera Tracking System The workspace scene from [16] was used to test our system. An image of this scene and the camera path and the reconstructed point cloud for a sequence are shown in Figure 5. Initially the camera is moved in front of the markers Figure 4. Errors in mean shift and RANSAC robust estimates and the number on inliers plotted as functions of the frame number for the Corridor sequence.

6 Figure 5. Results of the camera tracking. The scene used is shown on the left. The reconstructed point cloud and camera frames are on the right. 6. Conclusions We propose a new robust pose estimator. The estimator is based on the nonlinear mean shift algorithm and shows better performance on real and synthetic data. As future work we would like to test the effect different hypothesis generation schemes on the estimator. We would also like to extend the algorithm to handle cases where only image point correspondences are given [9]. In this case, the hypotheses no longer lie on SE(3) and this needs to be taken care of during the clustering. References [1] M. A. Ameller, L. Quan, and B. Triggs. Camera pose revisited: New linear algorithms. Machine Intelligence, 16(8): , [2] O. Chum and J. Matas. Randomized RANSAC with t d,d test. In British Machine Vision Conference, pages , [3] D. Comaniciu and P. Meer. Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Machine Intell., 24: , May [4] M. A. Fischler and R. C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. Assoc. Comp. Mach, 24(6): , [5] B. Georgescu and P. Meer. Point matching under large image deformations and illumination changes. IEEE Trans. Pattern Anal. Machine Intell., 26: , [6] R. Haralick, C. Lee, K. Ottenberg, and M. Nolle. Analysis and solutions of the three point perspective pose estimation problem. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Maui, HA, pages , [7] K. Kanatani. Statistical Optimization for Geometric Computation: Theory and Practice. Elsevier, [8] D. Nister. Preemptive RANSAC for live structure and motion estimation. In Proc. 9th Intl. Conf. on Computer Vision, Nice, France, volume I, pages , October [9] D. Nister. An efficient solution to the five-point relative pose problem. IEEE Trans. Pattern Anal. Machine Intell., 26(6): , [10] D. Nister. Preemptive RANSAC for live structure from motion. Machine Vision and Applications, 16(5): , [11] X. Pennec and N. Ayache. Uniform distribution, distance and expectation problems for geomteric feature processing. Journal of Mathematical Imaging and Vision, 9(1):49 67, [12] M. Pollefeys. Self calibration and metric reconstruction in spite of varying and unknown intrinsic camera parameters. International J. of Computer Vision, 32:7 25, [13] W. Rossmann. Lie Groups: An Introduction through Linear Groups. Oxford University Press, [14] F. Schaffalitzky and A. Zisserman. Multi-view matching for unordered image sets, or How do I organize my holiday snaps?. In Proceedings of the 7th European Conference on Computer Vision, Copenhagen, Denmark, volume 1, pages , [15] R. Subbarao and P. Meer. Nonlinear mean shift for clustering over analytic manifolds. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, New York, NY, volume I, pages , [16] R. Subbarao, P. Meer, and Y. Genc. A balanced approach to 3D tracking from image streams. In Proc. IEEE and ACM International Symposium on Mixed and Augmented Reality, pages 70 78, October [17] B. Tordoff and D. Murray. Guided sampling and consensus for motion estimation. In 7th European Conference on Computer Vision, volume I, pages 82 96, Copenhagen, Denmark, May [18] P. H. S. Torr and A. Zisserman. MLESAC: A new robust estimator with application to estimating image geometry. Computer Vision and Image Understanding, 78: , [19] B. Triggs, P. F. McLauchlan, R. I. Hartley, and A. W. Fitzgibbon. Bundle adjustment A modern synthesis. In B. Triggs, A. Zisserman, and R. Szelisky, editors, Vision Algorithms: Theory and Practice, pages Springer, [20] O. Tuzel, R. Subbarao, and P. Meer. Simultaneous multiple 3D motion estimation via mode finding on Lie groups. In Proc. 10th Intl. Conf. on Computer Vision, Beijing, China, volume 1, pages 18 25, 2005.

arxiv: v1 [cs.cv] 28 Sep 2018

arxiv: v1 [cs.cv] 28 Sep 2018 Camera Pose Estimation from Sequence of Calibrated Images arxiv:1809.11066v1 [cs.cv] 28 Sep 2018 Jacek Komorowski 1 and Przemyslaw Rokita 2 1 Maria Curie-Sklodowska University, Institute of Computer Science,

More information

Stereo and Epipolar geometry

Stereo and Epipolar geometry Previously Image Primitives (feature points, lines, contours) Today: Stereo and Epipolar geometry How to match primitives between two (multiple) views) Goals: 3D reconstruction, recognition Jana Kosecka

More information

Beyond RANSAC: User Independent Robust Regression

Beyond RANSAC: User Independent Robust Regression Beyond RANSAC: User Independent Robust Regression Raghav Subbarao and Peter Meer Department of Electrical and Computer Engineering Rutgers University, Piscataway NJ 08854, USA rsubbara,meer@caip.rutgers.edu

More information

Augmenting Reality, Naturally:

Augmenting Reality, Naturally: Augmenting Reality, Naturally: Scene Modelling, Recognition and Tracking with Invariant Image Features by Iryna Gordon in collaboration with David G. Lowe Laboratory for Computational Intelligence Department

More information

arxiv: v1 [cs.cv] 28 Sep 2018

arxiv: v1 [cs.cv] 28 Sep 2018 Extrinsic camera calibration method and its performance evaluation Jacek Komorowski 1 and Przemyslaw Rokita 2 arxiv:1809.11073v1 [cs.cv] 28 Sep 2018 1 Maria Curie Sklodowska University Lublin, Poland jacek.komorowski@gmail.com

More information

Projection Based M-Estimators

Projection Based M-Estimators 1 Projection Based M-Estimators Raghav Subbarao, Peter Meer, Senior Member, IEEE Electrical and Computer Engineering Department Rutgers University, 94 Brett Road, Piscataway, NJ, 08854-8058 rsubbara, meer@caip.rutgers.edu

More information

A Summary of Projective Geometry

A Summary of Projective Geometry A Summary of Projective Geometry Copyright 22 Acuity Technologies Inc. In the last years a unified approach to creating D models from multiple images has been developed by Beardsley[],Hartley[4,5,9],Torr[,6]

More information

Euclidean Reconstruction Independent on Camera Intrinsic Parameters

Euclidean Reconstruction Independent on Camera Intrinsic Parameters Euclidean Reconstruction Independent on Camera Intrinsic Parameters Ezio MALIS I.N.R.I.A. Sophia-Antipolis, FRANCE Adrien BARTOLI INRIA Rhone-Alpes, FRANCE Abstract bundle adjustment techniques for Euclidean

More information

Visual Odometry for Non-Overlapping Views Using Second-Order Cone Programming

Visual Odometry for Non-Overlapping Views Using Second-Order Cone Programming Visual Odometry for Non-Overlapping Views Using Second-Order Cone Programming Jae-Hak Kim 1, Richard Hartley 1, Jan-Michael Frahm 2 and Marc Pollefeys 2 1 Research School of Information Sciences and Engineering

More information

Robust Geometry Estimation from two Images

Robust Geometry Estimation from two Images Robust Geometry Estimation from two Images Carsten Rother 09/12/2016 Computer Vision I: Image Formation Process Roadmap for next four lectures Computer Vision I: Image Formation Process 09/12/2016 2 Appearance-based

More information

Quasiconvex Optimization for Robust Geometric Reconstruction

Quasiconvex Optimization for Robust Geometric Reconstruction Quasiconvex Optimization for Robust Geometric Reconstruction Qifa Ke and Takeo Kanade, Computer Science Department, Carnegie Mellon University {Qifa.Ke,tk}@cs.cmu.edu Abstract Geometric reconstruction

More information

Robustness in Motion Averaging

Robustness in Motion Averaging Robustness in Motion Averaging Venu Madhav Govindu venu@narmada.org HIG-25, Simhapuri Layout Visakhapatnam, AP, 5347 INDIA Abstract. The averaging of multiple pairwise relative motions in a sequence provides

More information

Instance-level recognition part 2

Instance-level recognition part 2 Visual Recognition and Machine Learning Summer School Paris 2011 Instance-level recognition part 2 Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique,

More information

Instance-level recognition II.

Instance-level recognition II. Reconnaissance d objets et vision artificielle 2010 Instance-level recognition II. Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique, Ecole Normale

More information

Perception and Action using Multilinear Forms

Perception and Action using Multilinear Forms Perception and Action using Multilinear Forms Anders Heyden, Gunnar Sparr, Kalle Åström Dept of Mathematics, Lund University Box 118, S-221 00 Lund, Sweden email: {heyden,gunnar,kalle}@maths.lth.se Abstract

More information

Minimal Projective Reconstruction for Combinations of Points and Lines in Three Views

Minimal Projective Reconstruction for Combinations of Points and Lines in Three Views Minimal Projective Reconstruction for Combinations of Points and Lines in Three Views Magnus Oskarsson, Andrew Zisserman and Kalle Åström Centre for Mathematical Sciences Lund University,SE 221 00 Lund,

More information

THE TRIFOCAL TENSOR AND ITS APPLICATIONS IN AUGMENTED REALITY

THE TRIFOCAL TENSOR AND ITS APPLICATIONS IN AUGMENTED REALITY THE TRIFOCAL TENSOR AND ITS APPLICATIONS IN AUGMENTED REALITY Jia Li A Thesis submitted to the Faculty of Graduate and Postdoctoral Studies in partial fulfillment of the requirements for the degree of

More information

Computing the relations among three views based on artificial neural network

Computing the relations among three views based on artificial neural network Computing the relations among three views based on artificial neural network Ying Kin Yu Kin Hong Wong Siu Hang Or Department of Computer Science and Engineering The Chinese University of Hong Kong E-mail:

More information

Vision par ordinateur

Vision par ordinateur Epipolar geometry π Vision par ordinateur Underlying structure in set of matches for rigid scenes l T 1 l 2 C1 m1 l1 e1 M L2 L1 e2 Géométrie épipolaire Fundamental matrix (x rank 2 matrix) m2 C2 l2 Frédéric

More information

RANSAC: RANdom Sampling And Consensus

RANSAC: RANdom Sampling And Consensus CS231-M RANSAC: RANdom Sampling And Consensus Roland Angst rangst@stanford.edu www.stanford.edu/~rangst CS231-M 2014-04-30 1 The Need for RANSAC Why do I need RANSAC? I know robust statistics! Robust Statistics

More information

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 263

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 263 Index 3D reconstruction, 125 5+1-point algorithm, 284 5-point algorithm, 270 7-point algorithm, 265 8-point algorithm, 263 affine point, 45 affine transformation, 57 affine transformation group, 57 affine

More information

Two-view geometry Computer Vision Spring 2018, Lecture 10

Two-view geometry Computer Vision Spring 2018, Lecture 10 Two-view geometry http://www.cs.cmu.edu/~16385/ 16-385 Computer Vision Spring 2018, Lecture 10 Course announcements Homework 2 is due on February 23 rd. - Any questions about the homework? - How many of

More information

Automatic estimation of the inlier threshold in robust multiple structures fitting.

Automatic estimation of the inlier threshold in robust multiple structures fitting. Automatic estimation of the inlier threshold in robust multiple structures fitting. Roberto Toldo and Andrea Fusiello Dipartimento di Informatica, Università di Verona Strada Le Grazie, 3734 Verona, Italy

More information

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 253

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 253 Index 3D reconstruction, 123 5+1-point algorithm, 274 5-point algorithm, 260 7-point algorithm, 255 8-point algorithm, 253 affine point, 43 affine transformation, 55 affine transformation group, 55 affine

More information

RANSAC RANdom SAmple Consensus

RANSAC RANdom SAmple Consensus Talk Outline importance for computer vision principle line fitting epipolar geometry estimation RANSAC RANdom SAmple Consensus Tomáš Svoboda, svoboda@cmp.felk.cvut.cz courtesy of Ondřej Chum, Jiří Matas

More information

3D Model Acquisition by Tracking 2D Wireframes

3D Model Acquisition by Tracking 2D Wireframes 3D Model Acquisition by Tracking 2D Wireframes M. Brown, T. Drummond and R. Cipolla {96mab twd20 cipolla}@eng.cam.ac.uk Department of Engineering University of Cambridge Cambridge CB2 1PZ, UK Abstract

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

More information

Fast and Reliable Two-View Translation Estimation

Fast and Reliable Two-View Translation Estimation Fast and Reliable Two-View Translation Estimation Johan Fredriksson 1 1 Centre for Mathematical Sciences Lund University, Sweden johanf@maths.lth.se Olof Enqvist 2 Fredrik Kahl 1,2 2 Department of Signals

More information

A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM INTRODUCTION

A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM INTRODUCTION A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM Karthik Krish Stuart Heinrich Wesley E. Snyder Halil Cakir Siamak Khorram North Carolina State University Raleigh, 27695 kkrish@ncsu.edu sbheinri@ncsu.edu

More information

CSE 252B: Computer Vision II

CSE 252B: Computer Vision II CSE 252B: Computer Vision II Lecturer: Serge Belongie Scribes: Jeremy Pollock and Neil Alldrin LECTURE 14 Robust Feature Matching 14.1. Introduction Last lecture we learned how to find interest points

More information

Segmentation and Tracking of Partial Planar Templates

Segmentation and Tracking of Partial Planar Templates Segmentation and Tracking of Partial Planar Templates Abdelsalam Masoud William Hoff Colorado School of Mines Colorado School of Mines Golden, CO 800 Golden, CO 800 amasoud@mines.edu whoff@mines.edu Abstract

More information

Observations. Basic iteration Line estimated from 2 inliers

Observations. Basic iteration Line estimated from 2 inliers Line estimated from 2 inliers 3 Observations We need (in this case!) a minimum of 2 points to determine a line Given such a line l, we can determine how well any other point y fits the line l For example:

More information

Contents. 1 Introduction Background Organization Features... 7

Contents. 1 Introduction Background Organization Features... 7 Contents 1 Introduction... 1 1.1 Background.... 1 1.2 Organization... 2 1.3 Features... 7 Part I Fundamental Algorithms for Computer Vision 2 Ellipse Fitting... 11 2.1 Representation of Ellipses.... 11

More information

A REAL-TIME TRACKING SYSTEM COMBINING TEMPLATE-BASED AND FEATURE-BASED APPROACHES

A REAL-TIME TRACKING SYSTEM COMBINING TEMPLATE-BASED AND FEATURE-BASED APPROACHES A REAL-TIME TRACKING SYSTEM COMBINING TEMPLATE-BASED AND FEATURE-BASED APPROACHES Alexander Ladikos, Selim Benhimane, Nassir Navab Department of Computer Science, Technical University of Munich, Boltzmannstr.

More information

Multiple View Geometry in Computer Vision Second Edition

Multiple View Geometry in Computer Vision Second Edition Multiple View Geometry in Computer Vision Second Edition Richard Hartley Australian National University, Canberra, Australia Andrew Zisserman University of Oxford, UK CAMBRIDGE UNIVERSITY PRESS Contents

More information

The Geometry of Dynamic Scenes On Coplanar and Convergent Linear Motions Embedded in 3D Static Scenes

The Geometry of Dynamic Scenes On Coplanar and Convergent Linear Motions Embedded in 3D Static Scenes EXTENDED VERSION SHORT VERSION APPEARED IN THE 13TH BMVC, CARDIFF, SEPTEMBER 2002. The Geometry of Dynamic Scenes On Coplanar and Convergent Linear Motions Embedded in 3D Static Scenes Adrien Bartoli,

More information

Structure from Motion. Introduction to Computer Vision CSE 152 Lecture 10

Structure from Motion. Introduction to Computer Vision CSE 152 Lecture 10 Structure from Motion CSE 152 Lecture 10 Announcements Homework 3 is due May 9, 11:59 PM Reading: Chapter 8: Structure from Motion Optional: Multiple View Geometry in Computer Vision, 2nd edition, Hartley

More information

Real Time Localization and 3D Reconstruction

Real Time Localization and 3D Reconstruction Real Time Localization and 3D Reconstruction E. Mouragnon, M. Lhuillier, M. Dhome, F. Dekeyser, P. Sayd LASMEA UMR 6602, Université Blaise Pascal/CNRS, 63177 Aubière Cedex, France Image and embedded computer

More information

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University. 3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction

More information

Nonparametric estimation of multiple structures with outliers

Nonparametric estimation of multiple structures with outliers Nonparametric estimation of multiple structures with outliers Wei Zhang and Jana Kosecka Department of Computer Science, George Mason University, 44 University Dr. Fairfax, VA 223 USA {wzhang2,kosecka}@cs.gmu.edu

More information

Computer Vision I - Robust Geometry Estimation from two Cameras

Computer Vision I - Robust Geometry Estimation from two Cameras Computer Vision I - Robust Geometry Estimation from two Cameras Carsten Rother 16/01/2015 Computer Vision I: Image Formation Process FYI Computer Vision I: Image Formation Process 16/01/2015 2 Microsoft

More information

Homographies and RANSAC

Homographies and RANSAC Homographies and RANSAC Computer vision 6.869 Bill Freeman and Antonio Torralba March 30, 2011 Homographies and RANSAC Homographies RANSAC Building panoramas Phototourism 2 Depth-based ambiguity of position

More information

3D Computer Vision. Structure from Motion. Prof. Didier Stricker

3D Computer Vision. Structure from Motion. Prof. Didier Stricker 3D Computer Vision Structure from Motion Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Structure

More information

Geometry for Computer Vision

Geometry for Computer Vision Geometry for Computer Vision Lecture 5b Calibrated Multi View Geometry Per-Erik Forssén 1 Overview The 5-point Algorithm Structure from Motion Bundle Adjustment 2 Planar degeneracy In the uncalibrated

More information

Exponential Maps for Computer Vision

Exponential Maps for Computer Vision Exponential Maps for Computer Vision Nick Birnie School of Informatics University of Edinburgh 1 Introduction In computer vision, the exponential map is the natural generalisation of the ordinary exponential

More information

RANSAC and some HOUGH transform

RANSAC and some HOUGH transform RANSAC and some HOUGH transform Thank you for the slides. They come mostly from the following source Dan Huttenlocher Cornell U Matching and Fitting Recognition and matching are closely related to fitting

More information

What Do Four Points in Two Calibrated Images Tell Us About the Epipoles?

What Do Four Points in Two Calibrated Images Tell Us About the Epipoles? What Do Four Points in Two Calibrated Images Tell Us About the Epipoles? David Nistér and Frederik Schaffalitzky Sarnoff Corporation CN5300, Princeton, NJ 08530, USA dnister@sarnoff.com Australian National

More information

Nonparametric estimation of multiple structures with outliers

Nonparametric estimation of multiple structures with outliers Nonparametric estimation of multiple structures with outliers Wei Zhang and Jana Kosecka George Mason University, 44 University Dr. Fairfax, VA 223 USA Abstract. Common problem encountered in the analysis

More information

An Improved Evolutionary Algorithm for Fundamental Matrix Estimation

An Improved Evolutionary Algorithm for Fundamental Matrix Estimation 03 0th IEEE International Conference on Advanced Video and Signal Based Surveillance An Improved Evolutionary Algorithm for Fundamental Matrix Estimation Yi Li, Senem Velipasalar and M. Cenk Gursoy Department

More information

Week 2: Two-View Geometry. Padua Summer 08 Frank Dellaert

Week 2: Two-View Geometry. Padua Summer 08 Frank Dellaert Week 2: Two-View Geometry Padua Summer 08 Frank Dellaert Mosaicking Outline 2D Transformation Hierarchy RANSAC Triangulation of 3D Points Cameras Triangulation via SVD Automatic Correspondence Essential

More information

EECS 442: Final Project

EECS 442: Final Project EECS 442: Final Project Structure From Motion Kevin Choi Robotics Ismail El Houcheimi Robotics Yih-Jye Jeffrey Hsu Robotics Abstract In this paper, we summarize the method, and results of our projective

More information

Agenda. Rotations. Camera calibration. Homography. Ransac

Agenda. Rotations. Camera calibration. Homography. Ransac Agenda Rotations Camera calibration Homography Ransac Geometric Transformations y x Transformation Matrix # DoF Preserves Icon translation rigid (Euclidean) similarity affine projective h I t h R t h sr

More information

Target Tracking Using Mean-Shift And Affine Structure

Target Tracking Using Mean-Shift And Affine Structure Target Tracking Using Mean-Shift And Affine Structure Chuan Zhao, Andrew Knight and Ian Reid Department of Engineering Science, University of Oxford, Oxford, UK {zhao, ian}@robots.ox.ac.uk Abstract Inthispaper,wepresentanewapproachfortracking

More information

External camera calibration for synchronized multi-video systems

External camera calibration for synchronized multi-video systems External camera calibration for synchronized multi-video systems Ivo Ihrke Lukas Ahrenberg Marcus Magnor Max-Planck-Institut für Informatik D-66123 Saarbrücken ihrke@mpi-sb.mpg.de ahrenberg@mpi-sb.mpg.de

More information

Summary Page Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems

Summary Page Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems Summary Page Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems Is this a system paper or a regular paper? This is a regular paper. What is the main contribution in terms of theory,

More information

Coplanar circles, quasi-affine invariance and calibration

Coplanar circles, quasi-affine invariance and calibration Image and Vision Computing 24 (2006) 319 326 www.elsevier.com/locate/imavis Coplanar circles, quasi-affine invariance and calibration Yihong Wu *, Xinju Li, Fuchao Wu, Zhanyi Hu National Laboratory of

More information

Generalized Principal Component Analysis CVPR 2007

Generalized Principal Component Analysis CVPR 2007 Generalized Principal Component Analysis Tutorial @ CVPR 2007 Yi Ma ECE Department University of Illinois Urbana Champaign René Vidal Center for Imaging Science Institute for Computational Medicine Johns

More information

On Robust Regression in Photogrammetric Point Clouds

On Robust Regression in Photogrammetric Point Clouds On Robust Regression in Photogrammetric Point Clouds Konrad Schindler and Horst Bischof Institute of Computer Graphics and Vision Graz University of Technology, Austria {schindl,bischof}@icg.tu-graz.ac.at

More information

Multiple View Geometry

Multiple View Geometry Multiple View Geometry CS 6320, Spring 2013 Guest Lecture Marcel Prastawa adapted from Pollefeys, Shah, and Zisserman Single view computer vision Projective actions of cameras Camera callibration Photometric

More information

Agenda. Rotations. Camera models. Camera calibration. Homographies

Agenda. Rotations. Camera models. Camera calibration. Homographies Agenda Rotations Camera models Camera calibration Homographies D Rotations R Y = Z r r r r r r r r r Y Z Think of as change of basis where ri = r(i,:) are orthonormal basis vectors r rotated coordinate

More information

Motion Estimation for Multi-Camera Systems using Global Optimization

Motion Estimation for Multi-Camera Systems using Global Optimization Motion Estimation for Multi-Camera Systems using Global Optimization Jae-Hak Kim, Hongdong Li, Richard Hartley The Australian National University and NICTA {Jae-Hak.Kim, Hongdong.Li, Richard.Hartley}@anu.edu.au

More information

Fundamental Matrices from Moving Objects Using Line Motion Barcodes

Fundamental Matrices from Moving Objects Using Line Motion Barcodes Fundamental Matrices from Moving Objects Using Line Motion Barcodes Yoni Kasten (B), Gil Ben-Artzi, Shmuel Peleg, and Michael Werman School of Computer Science and Engineering, The Hebrew University of

More information

Instance-level recognition

Instance-level recognition Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction

More information

3D model search and pose estimation from single images using VIP features

3D model search and pose estimation from single images using VIP features 3D model search and pose estimation from single images using VIP features Changchang Wu 2, Friedrich Fraundorfer 1, 1 Department of Computer Science ETH Zurich, Switzerland {fraundorfer, marc.pollefeys}@inf.ethz.ch

More information

Camera Calibration Using Line Correspondences

Camera Calibration Using Line Correspondences Camera Calibration Using Line Correspondences Richard I. Hartley G.E. CRD, Schenectady, NY, 12301. Ph: (518)-387-7333 Fax: (518)-387-6845 Email : hartley@crd.ge.com Abstract In this paper, a method of

More information

Model Fitting, RANSAC. Jana Kosecka

Model Fitting, RANSAC. Jana Kosecka Model Fitting, RANSAC Jana Kosecka Fitting: Overview If we know which points belong to the line, how do we find the optimal line parameters? Least squares What if there are outliers? Robust fitting, RANSAC

More information

Image correspondences and structure from motion

Image correspondences and structure from motion Image correspondences and structure from motion http://graphics.cs.cmu.edu/courses/15-463 15-463, 15-663, 15-862 Computational Photography Fall 2017, Lecture 20 Course announcements Homework 5 posted.

More information

Lecture 9: Epipolar Geometry

Lecture 9: Epipolar Geometry Lecture 9: Epipolar Geometry Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Why is stereo useful? Epipolar constraints Essential and fundamental matrix Estimating F (Problem Set 2

More information

Closed-form Linear Solution To Motion Estimation In Disparity Space

Closed-form Linear Solution To Motion Estimation In Disparity Space Closed-form Linear Solution To Motion Estimation In Disparity Space Konstantinos G. Derpanis Vision Technologies Sarnoff Corporation Princeton, NJ 8543 Peng Chang ABSTRACT Real-time stereovision systems

More information

Computer Vision I - Algorithms and Applications: Multi-View 3D reconstruction

Computer Vision I - Algorithms and Applications: Multi-View 3D reconstruction Computer Vision I - Algorithms and Applications: Multi-View 3D reconstruction Carsten Rother 09/12/2013 Computer Vision I: Multi-View 3D reconstruction Roadmap this lecture Computer Vision I: Multi-View

More information

Real-time Incremental J-linkage for Robust Multiple Structures Estimation

Real-time Incremental J-linkage for Robust Multiple Structures Estimation Real-time Incremental J-linkage for Robust Multiple Structures Estimation Roberto Toldo and Andrea Fusiello Department of Computer Science - University of Verona Strada le grazie 15, Verona - Italy {roberto.toldo

More information

Instance-level recognition

Instance-level recognition Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction

More information

A Factorization Method for Structure from Planar Motion

A Factorization Method for Structure from Planar Motion A Factorization Method for Structure from Planar Motion Jian Li and Rama Chellappa Center for Automation Research (CfAR) and Department of Electrical and Computer Engineering University of Maryland, College

More information

Structure from Motion

Structure from Motion Structure from Motion Outline Bundle Adjustment Ambguities in Reconstruction Affine Factorization Extensions Structure from motion Recover both 3D scene geoemetry and camera positions SLAM: Simultaneous

More information

AUTOMATIC RECTIFICATION OF LONG IMAGE SEQUENCES. Kenji Okuma, James J. Little, David G. Lowe

AUTOMATIC RECTIFICATION OF LONG IMAGE SEQUENCES. Kenji Okuma, James J. Little, David G. Lowe AUTOMATIC RECTIFICATION OF LONG IMAGE SEQUENCES Kenji Okuma, James J. Little, David G. Lowe The Laboratory of Computational Intelligence The University of British Columbia Vancouver, British Columbia,

More information

New Conditional Sampling Strategies for Speeded-Up RANSAC

New Conditional Sampling Strategies for Speeded-Up RANSAC BOTTERILL, MILLS, GREEN: CONDITIONAL SAMPLING STRATEGIES FOR RANSAC 1 New Conditional Sampling Strategies for Speeded-Up RANSAC Tom Botterill 1, 2 tom.botterill@grcnz.com Steven Mills 2 steven.mills@grcnz.com

More information

3D reconstruction class 11

3D reconstruction class 11 3D reconstruction class 11 Multiple View Geometry Comp 290-089 Marc Pollefeys Multiple View Geometry course schedule (subject to change) Jan. 7, 9 Intro & motivation Projective 2D Geometry Jan. 14, 16

More information

Srikumar Ramalingam. Review. 3D Reconstruction. Pose Estimation Revisited. School of Computing University of Utah

Srikumar Ramalingam. Review. 3D Reconstruction. Pose Estimation Revisited. School of Computing University of Utah School of Computing University of Utah Presentation Outline 1 2 3 Forward Projection (Reminder) u v 1 KR ( I t ) X m Y m Z m 1 Backward Projection (Reminder) Q K 1 q Q K 1 u v 1 What is pose estimation?

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Today: dense 3D reconstruction The matching problem

More information

Unsupervised learning in Vision

Unsupervised learning in Vision Chapter 7 Unsupervised learning in Vision The fields of Computer Vision and Machine Learning complement each other in a very natural way: the aim of the former is to extract useful information from visual

More information

Computational Optical Imaging - Optique Numerique. -- Multiple View Geometry and Stereo --

Computational Optical Imaging - Optique Numerique. -- Multiple View Geometry and Stereo -- Computational Optical Imaging - Optique Numerique -- Multiple View Geometry and Stereo -- Winter 2013 Ivo Ihrke with slides by Thorsten Thormaehlen Feature Detection and Matching Wide-Baseline-Matching

More information

Occluded Facial Expression Tracking

Occluded Facial Expression Tracking Occluded Facial Expression Tracking Hugo Mercier 1, Julien Peyras 2, and Patrice Dalle 1 1 Institut de Recherche en Informatique de Toulouse 118, route de Narbonne, F-31062 Toulouse Cedex 9 2 Dipartimento

More information

Structure from motion

Structure from motion Structure from motion Structure from motion Given a set of corresponding points in two or more images, compute the camera parameters and the 3D point coordinates?? R 1,t 1 R 2,t R 2 3,t 3 Camera 1 Camera

More information

CS 664 Image Matching and Robust Fitting. Daniel Huttenlocher

CS 664 Image Matching and Robust Fitting. Daniel Huttenlocher CS 664 Image Matching and Robust Fitting Daniel Huttenlocher Matching and Fitting Recognition and matching are closely related to fitting problems Parametric fitting can serve as more restricted domain

More information

Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems

Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems Brian Clipp 1, Jae-Hak Kim 2, Jan-Michael Frahm 1, Marc Pollefeys 3 and Richard Hartley 2 1 Department of Computer Science 2 Research

More information

Factorization with Missing and Noisy Data

Factorization with Missing and Noisy Data Factorization with Missing and Noisy Data Carme Julià, Angel Sappa, Felipe Lumbreras, Joan Serrat, and Antonio López Computer Vision Center and Computer Science Department, Universitat Autònoma de Barcelona,

More information

Large Scale 3D Reconstruction by Structure from Motion

Large Scale 3D Reconstruction by Structure from Motion Large Scale 3D Reconstruction by Structure from Motion Devin Guillory Ziang Xie CS 331B 7 October 2013 Overview Rome wasn t built in a day Overview of SfM Building Rome in a Day Building Rome on a Cloudless

More information

Step-by-Step Model Buidling

Step-by-Step Model Buidling Step-by-Step Model Buidling Review Feature selection Feature selection Feature correspondence Camera Calibration Euclidean Reconstruction Landing Augmented Reality Vision Based Control Sparse Structure

More information

Simultaneous Pose and Correspondence Determination using Line Features

Simultaneous Pose and Correspondence Determination using Line Features Simultaneous Pose and Correspondence Determination using Line Features Philip David, Daniel DeMenthon, Ramani Duraiswami, and Hanan Samet Department of Computer Science, University of Maryland, College

More information

Epipolar Geometry and Stereo Vision

Epipolar Geometry and Stereo Vision Epipolar Geometry and Stereo Vision Computer Vision Jia-Bin Huang, Virginia Tech Many slides from S. Seitz and D. Hoiem Last class: Image Stitching Two images with rotation/zoom but no translation. X x

More information

Visualization 2D-to-3D Photo Rendering for 3D Displays

Visualization 2D-to-3D Photo Rendering for 3D Displays Visualization 2D-to-3D Photo Rendering for 3D Displays Sumit K Chauhan 1, Divyesh R Bajpai 2, Vatsal H Shah 3 1 Information Technology, Birla Vishvakarma mahavidhyalaya,sumitskc51@gmail.com 2 Information

More information

LUP. Centre for Mathematical Sciences. Lund University Publications. Institutional Repository of Lund University Found at:

LUP. Centre for Mathematical Sciences. Lund University Publications. Institutional Repository of Lund University Found at: Centre for Mathematical Sciences LUP Lund University Publications Institutional Repository of Lund University Found at: http://www.lu.se This is an author produced version of a paper presented at 16th

More information

calibrated coordinates Linear transformation pixel coordinates

calibrated coordinates Linear transformation pixel coordinates 1 calibrated coordinates Linear transformation pixel coordinates 2 Calibration with a rig Uncalibrated epipolar geometry Ambiguities in image formation Stratified reconstruction Autocalibration with partial

More information

Combining Two-view Constraints For Motion Estimation

Combining Two-view Constraints For Motion Estimation ombining Two-view onstraints For Motion Estimation Venu Madhav Govindu Somewhere in India venu@narmada.org Abstract In this paper we describe two methods for estimating the motion parameters of an image

More information

Camera Calibration from the Quasi-affine Invariance of Two Parallel Circles

Camera Calibration from the Quasi-affine Invariance of Two Parallel Circles Camera Calibration from the Quasi-affine Invariance of Two Parallel Circles Yihong Wu, Haijiang Zhu, Zhanyi Hu, and Fuchao Wu National Laboratory of Pattern Recognition, Institute of Automation, Chinese

More information

Multiple-View Structure and Motion From Line Correspondences

Multiple-View Structure and Motion From Line Correspondences ICCV 03 IN PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, NICE, FRANCE, OCTOBER 003. Multiple-View Structure and Motion From Line Correspondences Adrien Bartoli Peter Sturm INRIA

More information

Multiple View Geometry. Frank Dellaert

Multiple View Geometry. Frank Dellaert Multiple View Geometry Frank Dellaert Outline Intro Camera Review Stereo triangulation Geometry of 2 views Essential Matrix Fundamental Matrix Estimating E/F from point-matches Why Consider Multiple Views?

More information

CS231A Course Notes 4: Stereo Systems and Structure from Motion

CS231A Course Notes 4: Stereo Systems and Structure from Motion CS231A Course Notes 4: Stereo Systems and Structure from Motion Kenji Hata and Silvio Savarese 1 Introduction In the previous notes, we covered how adding additional viewpoints of a scene can greatly enhance

More information

CS 664 Structure and Motion. Daniel Huttenlocher

CS 664 Structure and Motion. Daniel Huttenlocher CS 664 Structure and Motion Daniel Huttenlocher Determining 3D Structure Consider set of 3D points X j seen by set of cameras with projection matrices P i Given only image coordinates x ij of each point

More information

Parameter estimation. Christiano Gava Gabriele Bleser

Parameter estimation. Christiano Gava Gabriele Bleser Parameter estimation Christiano Gava Christiano.Gava@dfki.de Gabriele Bleser gabriele.bleser@dfki.de Introduction Previous lectures: P-matrix 2D projective transformations Estimation (direct linear transform)

More information