where ~n = ( ) t is the normal o the plane (ie, Q ~ t ~n =,8 Q ~ ), =( ~ X Y Z ) t and ~t = (t X t Y t Z ) t are the camera rotation and translation,
|
|
- Katrina Chapman
- 6 years ago
- Views:
Transcription
1 Multi-Frame Alignment o Planes Lihi Zelnik-Manor Michal Irani Dept o Computer Science and Applied Math The Weizmann Institute o Science Rehovot, Israel Abstract Traditional plane alignment techniques are typically perormed between pairs o rames In this paper we present a method or extending existing two-rame planar-motion estimation techniques into a simultaneous multi-rame estimation, by exploiting multi-rame geometric constraints o planar suraces The paper has three main contributions: (i) we show that when the camera calibration does not change, the collection o all parametric image motions o a planar surace in the scene across multiple rames is embedded in a low dimensional linear subspace (ii) we show that the relative image motion o multiple planar suraces across multiple rames is embedded in a yet lower dimensional linear subspace, even with varying camera calibration and (iii) we show how these multi-rame constraints can be incorporated into simultaneous multi-rame estimation o planar motion, without explicitly recovering any D inormation, or camera calibration The resulting multi-rame estimation process is more constrained than the individual two-rame estimations, leading to more accurate alignment, even when applied to small image regions Introduction Plane stabilization (\D parametric alignment") is essential or many video-related applications: it is used or video stabilization and visualization, or D analysis (eg, using the Plane+Parallax approach []), or moving object detection, mosaicing, etc Many techniques have been proposed or estimating the D parametric motion o a planar surace between two rames Some examples are [,,,,] While these techniques are very robust and perorm well when the planar surace captures a large image region, they tend to be highly inaccurate when applied to small image regions Moreover, errors can accumulate over a sequence o rames when the motion estimation is perormed between successive pairs o rames (as is oten done in mosaic construction) An elegant approach was presented in [9] or automatically estimating an optimal (usually virtual) reerence rame or a sequence o images with the corresponding motion parameters that relate each rame to the virtual reerence rame This overcomes the problem associated with error accumulation in sequential rame alignment However, the alignment method used or estimating the motion between the virtual reerence rame and all other rames remains a two-rame alignment method Sequential two-rame parametric alignment methods do not exploit the act that all rames imaging the same planar surace share the same plane geometry In this paper we present a method or extending traditional two-rame planar-motion estimation techniques into a simultaneous multi-rame estimation method, by exploiting multi-rame linear subspace constraints o planar motions (Section ) The use o linear subspace constraints, or motions analysis, has been introduced by Tomasi and Kanade [] They used these constraints or actoring D correspondences into D motion and shape inormation In contrast, here we use linear subspace constraints or constraining our D planar motion estimation and not or actoringout any D inormation This results in a multi-rame estimation technique which is more constrained than the individual two-rame estimation processes, leading to more accurate alignment, even when applied to small image regions Furthermore, multi-rame rigidity constraints relating multiple planar suraces are applied to urther enhance parametric motion estimation in scenes with multiple planar suraces (Section ) Basic Model and Notations The instantaneous image motion o a D planar surace, between two image rames can be expressed as a D quadratic transormation [8,,,]: ~u(~x ~p) =X(~x) ~p () where X(~x) is a matrix which depends only on the pixel coordinates (~x) =(x y): X(~x) = h x y x i xy x y xy y : and ~p =(p p ::: p 8 ) t is a parameter vector: p = (tx +Y ) p = ( + t X ) ; tz ; p = ; ( Z ; tx ) p = (ty ; X ) p = ( Z + ty ) p = ( + t Y ) ; tz ; p = ( Y ; tz ) p8 = ; ( X + tz ) ()
2 where ~n = ( ) t is the normal o the plane (ie, Q ~ t ~n =,8 Q ~ ), =( ~ X Y Z ) t and ~t = (t X t Y t Z ) t are the camera rotation and translation, respectively, and and are the camera ocal lengths used or obtaining the two images The instantaneous motion model is valid when the camera rotation is small and the orward translation is small relative to the depth Two-Frame Parametric Alignment In this paper, we extend the direct two-rame motion estimation approach o [, ] to multiple rames To make the paper sel contained, we briey outline the basic two-rame technique below Two image rames (whose parametric image motion is being estimated) are reerred to by the names \reerence" image J and \inspection" image K A Gaussian pyramid is constructed or J and K, and the motion parameters rom J to K are estimated in a coarseto-ne manner Within each pyramid level the sum o squared linearized dierences (ie, the linearized brightness constancy measure) is used as a match measure This measure (Err) is minimized with respect to the unknown D motion parameters ~p o Eq (): (K(~x) ; J(~x)) + rj(~x) t ~u(~x ~p) Err(~p) = P (~x) where (~u(~x ~p)) is dened in Eq (), J(~x) and K(~x) denote the brightness value o image J and K at pixel ~x, respectively, and rj(~x) denotes the spatial gradient o J at ~x: @y (~x) The sum is computed over all the points within a region o interest (oten the entire image) Deriving Err with respect to the unknown parameters ~p and setting to zero, yields eight linear equations in the eight unknowns: C~p = ~ b () where C is an 8 8 matrix: C = P h i (~x) X(~x) t rj(~x) rj(~x) t X(~x) and ~ b is an 8 vector: P h i ~ b = X(~x) t rj(~x) (J(~x) ; K(~x)) : (~x) This leads to the linear solution ~p = C ; ~ b Note that C and ~ b are constructed o measurable image quantities, hence the word direct estimation This process does not require recovery o any D inormation Let ~p i denote the estimate o the quadratic parameters at iteration i p i+ ~ = ~p i + p ~ can be solved or by estimating the innitesimal increment p ~ Ater iterating certain number o times within a pyramid level, the process continues at the next ner level, etc Figs, i show an example o applying this parametric alignment method This is an airborne sequence taken rom a large distance, hence the camera induced motion can be described by a single D parametric transormation o Eq () Fig c was the reerence image and Fig b was the inspection image Fig e shows the amount o misalignment between the two input images When the method is applied to the entire image region, it yields accurate alignment (at subpixel accuracy), as can be seen in Figs and i However, once the same method is applied to a small image region (such as the rectangular region marked in Figs g, j), its accuracy degrades signicantly The arther a pixel is rom the region o analysis, the more misaligned it is In the next section we show how employing multiple rames (as opposed to two) can be used to increase accuracy o image alignment even when applied to small image regions Multi-Frame Parametric Alignment In this section we present a method or extending the two-rame technique reviewed in section into a multi-rame technique, which exploits multi-rame constraints on the image motion o a planar surace In section we derive such a multi-rame constraint, and in section we showhow it can be incorporated into the D parametric estimation o planar motion, without requiring any recovery o D inormation, or camera calibration Single Plane Geometric Constraint Let J be a reerence rame, and let K ::: K F be a sequence o F inspection rames imaging the same planar surace with the same ocal length Let ~p ::: ~p F be the corresponding quadratic parameter vectors o the planar motion (see Eq ()) The instantaneous motion model o Eq () is a good approximation o the motion over short video segments, as the camera does not gain large motions in short periods o time In some cases, such as airborne video, this approximation is good also or very long sequences Choosing the reerence rame as the middle rame extends the applicability othemodeltotwice as many rames We arrange ~p ::: ~p F in an 8 F matrix P where each column corresponds to one rame From Eq (): P = ~ ~p ~p F 8F = S t ::: ~t F 8 ~ ~ F where S = ; ; ; ; ; ; ; F () and ~t j ~ j, are the camera translation and rotation, between the reerence rame J and rame K j (j = ()
3 (a) (b) (c) (d) (e) () (g) (h) (i) (j) (k) Figure : (a,b,c,d) Sample rames rom a -rame airborne video clip Apart rom camera motion, there is also a small moving car Fig c was the reerence rame (e) The absolute dierences between two input rames (b and c) indicate initial misalignment (,i) High quality alignment (at sub-pixel accuracy) rom applying the two-rame technique to the entire image region shows absolute dierences ater alignment, while i shows the average o the two aligned images Only the independently moving car is misaligned (g,j) Poor alignment rom applying the two-rame alignment to a small image region, marked by a rectangle Although the rectangular region is well aligned (apart rom the moving car), large misalignments can be detected in image pixels which are distant rom the analysis region (h,k) High quality alignment rom applying the constrained multi-rame alignment to the same small rectangular region It was applied simultaneously to all rames Even pixels distant rom the analysis window appear well aligned ::F ) Note that the shape matrix S is common to all rames, because they all share the same plane normal ~n =( ) t and ocal length The dimensionality o the matrices on the right hand side o Eq () implies that, without noise, the parameter matrix P is o rank at most This implies that the collection o all the p j 's (j =::F ) resides in a low dimensional linear subspace The actual rank o P may be even lower than, depending on the complexity o the camera motion over the sequence (eg, in case o uniorm motion it will be ) Incorporating Sub-Space Constraint into Multi-Frame Estimation In this section we show how the low-rank constraint on P can be incorporated into the estimation o ~p ::: ~p F, without explicitly solving or any D inormation, nor or camera calibration It is not advisable to rst solve or P and then project its columns ontoalower dimensional subspace, because then the individual ~p j 's will already be very erroneous Instead, we would like to use the low dimensionality constraint toconstrain the estimation o the individual ~p j 's a-priori We next show how we can apply this constraint directly to measurable image quantities prior to solving or the individual ~p j 's Since all inspection rames K ::: K F share the same reerence rame J, Eq () can be extended to multiple rames as: h i C 88 ~p ~p F = ~ 8F b ~ b F () 8F or, in short: CP = B Eq () implies that rank(b) rank(p ) B contains only measurable image quantities Thereore, instead o applying the low-rank constraint top,we apply it directly to B, and only then solve orp Namely: at each iteration i o the algorithm, rst compute B i =[ ~ b i ~ b F i ], and then project its columns onto a lower-dimensional linear subspace by seeking a matrix ^Bi o rank r (r ), which is closest to B i (in the Frobenius norm) Then solve or P i = C i ; ^B i, which yields the desired ~p j 's The advantage o applying the constraint tob instead o P can also be explained as ollows: Note that the matrix C in Eq () is the posterior inverse covariance matrix o the parameter vector ~p Thereore, applying the constraint tob is equivalent to applying it to the matrix P, but ater normalizing its columns by the inverse covariance matrix C (Note that all ~p j 's share the same C) To equalize the eect o subspace projection on all matrix entries, and to urther condition the numerical
4 process, we use the coordinate normalization technique suggested by [] (Also used in the two-rame method) Fig shows a comparison o applying the two-rame and multi-rame alignment techniques Figs g and j show the result o applying the two-rame alignment technique (See section ) to a small image region The region o interest (marked rectangle) is indeed aligned, but the rest o the image is completely distorted In contrast, the multi-rame constrained alignment (applied to rames), successully aligned the entire image eventhough applied only to the same small region This can be seen in Figs h and k Fig shows a quantitative comparison o the tworame and multi-rame alignment techniques When applying two-rame motion estimation to the small region, the arther the pixel is rom the center o the region the larger the error is However, when applying multi-rame motion estimation to the same small region, the errors everywhere are at sub-pixel level Fig shows another comparison o applying tworame alignment and multi-rame alignment to small image regions The sequence contains rames taken by a moving camera Because the camera is imaging the scene rom a short distance, and because its motion also contains a translation, thereore dierent planar suraces (eg, the house, the road-sign, etc) induce dierent D parametric motions As long as the house was not occluded, the two-rame alignment, when applied only to the house region, stabilized the house reasonably well However, once the house was partially occluded by the road-sign, and was not ully in the camera's eld o view, the quality o the two-rame alignment degraded drastically (see Figs and j) The multi-rame constrained alignment, on the other hand, successully aligned the house, even in rames where only a small portion o the house was visible (see Figs g and k) In this case, the actual rank used was much smaller than (it was ), and was detected rom studying the rate o decay o the eigenvalues o the matrix B Extending to Multiple Planes In this section we show that in scenes containing multiple planar suraces, even stronger geometric constraints can be derived and used to improve the parametric motion estimation We present two dierent multi rame geometric constraints or sequences with multiple planes The second constraint does not require constant camera calibration The Multi-Plane Rank- Constraint Let ::: m be m planar suraces with normals ~n =[ ] t,, ~n m =[ m m m ] t, respectively Let P ::: P m be the corresponding quadratic motion parameter matrices, and let S ::: S m be the Figure : A quantitative comparison o two-rame and multi-rame alignment The values in the graph correspond to misalignments in Figs g and h These errors are displayed as a unction o the distance rom the center o the rectangular region in Fig The results o two-rame alignment applied to the entire imageregion (Fig ) were usedasground truth corresponding shape matrices, as dened by Eqs () and () We can stack thep ( =:::m) matrices to orm an 8m F matrix P, where each column corresponds to one rame Since all planar suraces share the same D camera motion between a pair o rames, we get rom Eq (): P = P P m = S S m 8m ~ t ::: ~t F ~ ~ F F () The dimensionality o the matrices on the right hand side o Eq () implies that, without noise, the parameter matrix P is also o rank at most (As beore, the actual rank o P may beeven lower than, depending on the complexity and variability o the camera motion over the sequence) Incorporating Multi-Plane Rank- Constraint into Estimation Again we would like to apply the constraint to measurable image quantities We show next how this can be done Let C ::: C m be the matrices corresponding to planes ::: m Note that the matrices C 's are dierent rom each other due to the dierence in the region o summation, which is the region o each planar surace in the reerence rame We can write: C C Cm P Pm = B Bm (8) or, in short: CP= B Note that here, as opposed to Eq (), P B and C contain inormation rom all planar suraces Eq (8) implies that rank(b) rank(p)
5 (a) (b) (c) (d) (e) () (g) (h) (i) (j) (k) (l) (m) Figure : (a,b,c,d,e) sample images rom a sequence orames Image b was used as the reerence rame () Bad two-rame alignment o the house region between the reerence rame b and rame d The rame was completely distorted because the house region was signicantly occluded by the road-sign (j) shows same result overlayed on top o the reerence image b (g) The corresponding result rom applying the constrained multi-rame alignment The house is now well aligned even though only a small portion o the house is visible (see overlay image (k)), while the rest o the image is not distorted The road sign is not aligned because is at a dierent depth, and displays accurate D parallax (h,l) Badly distorted tworame alignment applied totheroad-sign between rames b and a (where the sign is barely visible) Although the sign appears aligned, the rest o the image is distorted, and the house displays wrong parallax (i,m) The corresponding result (to (h,l)) rom applying the constrained multi-plane (multi-rame) alignment to the sign (see text) The house displays now accurate D parallax We thus project the columns o matrix B onto a lowerdimensional subspace, at each iteration, resulting in ^B (which is closest to B in the Frobenius norm), and then solve orp = C ; B In other words, we solve or all parametric motions o all planar suraces, across all rames, simultaneously The low-rank constraint is stronger here than in the single plane case, because the matrix B is o a larger dimension (8m F ) Relative Motion Rank- Constraint Moreover, by looking at the relative motion o planar suraces we can get an even stronger geometric constraint, which is true even or the case o varying camera ocal length Let and j be the ocal length o the rame J and rame K j, respectively Let r be an arbitrary planar surace ( r could be one o ::: m ) Denote ~p j = ~p j ; ~p j r ( = :::m) It is easy to see rom Eq () that taking the dierence ~p j eliminates all eects o camera rotation, leaving only eects o camera translation and the ocal length: [~p j ] 8 =[~ S ] 8 [~ j ] (9) where ~ j =[ j t j X j t j Y T = tj Z ]t,and: S ~ = ( ; r) ( ; r) ;( ; r) ( ; r) ( ; r) ( ; r) ( ; r) ;( ; r) ; ( ; r) ; ( ; r) S ~ is common to all rames The camera translation ~t j and ocal length j are common to all planes (between the reerence rame J and rame K j ) We can thereore extend Eq (9) to multiple planes and multiple rames as ollows: P S~ P = = [~ :::~ F ] F P m S m ~ 8m () The dimensionality o the matrices on the right hand side o Eq () implies that, without noise, the dier-
6 ence parameter matrix P is o rank at most It is possible to obtain a similar constraint (with rank ), or general homographies case [] (as opposed to the instantaneous case) The rank- constraint is an extension to the constraint shown by [] Shashua and Avidan presented a rank- constraint on the collection o homographies o multiple planes between a pair o rames In our case [] the constraints are on multiple planes across multiple rames We reer the reader to [] or more details In the next section () we show how the multiplane rank- constraint can be incorporated into the multi-rame estimation process to urther enhance planar-motion estimation Incorporating the Rank- Constraint into Multi-Frame Estimation Assume that or one planar surace, r,weknowthe collection o all its parametric motions, P r (This is either given to us, or estimated at previous iteration) We would like to use the (rank ) constraint to rene the estimation o the collection o parametric motions P ::: P m, o all other planes Using Eq (8) we derive: CP = B ;C P r B m ;C m P r = B () Thereore rank(b ) rank(p) To Incorporate the constraint into the estimation o the individual P 's, we project the columns o the matrix B onto alower-dimensional ( ) subspace at each iteration, resulting in ^B (which is closest to B in Frobenius norm) Thereore, (rom Eq ()) we can estimate a new matrix B B = CP= C C m P r + ^B () and then solve or P = C ; B Note that here B and B are constructed rom measurable image quantities (B and C), as well as rom the parameters P r, which are either known or else estimated at previous iteration The process is repeated at each iteration Note: (i) I we know that the ocal length does not change along the sequence, we can also apply the constraint rank(b ) rank(p) prior to solving or P (ii) r can alternate between the planes, but we ound it to work best when r was chosen to be a \dominant" plane (ie, one whose matrix C r is best conditioned) Fig also presents a comparison o regular (unconstrained) two-rame alignment with the multi-plane constrained alignment, applied to the road-sign The motion parameters o the house region were rst estimated using the single-plane multi-rame constrained alignment (see Section ) These were then used as inputs or constraining the estimation o the sequence o D motion parameters o the road-sign The two-rame alignment technique did not perorm well in cases when the sign was only partially visible (see Figs h and l) The multi-plane (multi-rame) constrained alignment, on the other hand, stabilized the sign well even in cases when the sign was only partially visible (see Figs i and m) [] G Adiv Determining three-dimensional motion and structure rom optical ow generated by several moving objects PAMI, ():8{, July 98 [] S Ayer and H Sawhney Layered representation o motion video using robust maximum-likelihood estimation o mixture models and mdl encoding In ICCV, pages {8, 99 [] J Bergen, P Anandan, K Hanna, and R Hingorani Hierarchical model-based motion estimation In ECCV, pages {, 99 [] R I Hartley In deence o the 8-point algorithm PAMI, 9():8{9, June 99 [] M Irani, B Rousso, and P peleg Recovery o egomotion using region alignment PAMI, 9():8{, March 99 [] M Irani, B Rousso, and S Peleg Computing occluding and transparent motions IJCV, :{, February 99 [] S Ju, M J Black, and A D Jepson Multi-layer, locally ane optical ow and regularization with transparency In CVPR, pages {, 99 [8] H Longuet-Higgins Visual ambiguity o a moving plane Proceedings o The Royal Society o London B, :{, 98 [9] H Sawhney and R Kumar True multi-image alignment and its application to mosaic[k]ing and lens distortion correction In CVPR, pages {, 99 [] A Shashua and S Avidan The rank constraint in multiple () view geometry In ECCV, 99 [] C Tomasi and T Kanade Shape and motion rom image streams under orthography: A actorization method IJCV, 9:{, November 99 [] J Wang and E Adelson Layered representation or motion analysis In CVPR, pages {, 99 [] L Zelnik-Manor and M Irani Multi-rame subspace constraints on homographies MSc thesis, The Weizmann Institute o Science, Israel, March 999
Multi-Frame Alignment of Planes
Multi-Frame Alignment of Planes Lihi Zelnik-Manor Michal Irani Dept. of Computer Science and Applied Math The Weizmann Institute of Science 76100 Rehovot, Israel Abstract Traditional plane alignment techniques
More informationp w2 μ 2 Δp w p 2 epipole (FOE) p 1 μ 1 A p w1
A Unied Approach to Moving Object Detection in 2D and 3D Scenes Michal Irani P. Anandan David Sarno Research Center CN5300, Princeton, NJ 08543-5300, U.S.A. Email: fmichal,anandang@sarno.com Abstract The
More informationMulti-Frame Correspondence Estimation Using Subspace Constraints
International Journal of Computer ision 483), 173 194, 2002 c 2002 Kluwer Academic Publishers. Manufactured in The Netherlands. Multi-Frame Correspondence Estimation Using Subspace Constraints MICHAL IRANI
More informationP T p y T O Fig.. The coordinate system. The coordinate system ( ) is attached to the camera, and the corresponding image coordinates (x y) on the ima
Recovery of Ego-Motion Using Region Alignment Michal Irani Benny Rousso Shmuel Peleg Abstract A method for computing the 3D camera motion (the egomotion) in a static scene is introduced, which is based
More informationParticle Tracking. For Bulk Material Handling Systems Using DEM Models. By: Jordan Pease
Particle Tracking For Bulk Material Handling Systems Using DEM Models By: Jordan Pease Introduction Motivation for project Particle Tracking Application to DEM models Experimental Results Future Work References
More informationMAPI Computer Vision. Multiple View Geometry
MAPI Computer Vision Multiple View Geometry Geometry o Multiple Views 2- and 3- view geometry p p Kpˆ [ K R t]p Geometry o Multiple Views 2- and 3- view geometry Epipolar Geometry The epipolar geometry
More informationINTERACTIVE CONTENT-BASED VIDEO INDEXING AND BROWSING
INTERACTIVE CONTENT-BASED VIDEO INDEXING AND BROWSING Miclial Irani Dept. of Applied Math and CS The Weixmann Institute of Science 76100 Rehovot, Israel H.S. Sawhney R. Kumar P. Anandan David Sarnoff Research
More informationMultiple Plane Segmentation Using Optical Flow
Multiple Plane Segmentation Using Optical Flow Marco Zucchelli José Santos-Victor Henrik I. Christensen CVAP & CAS, Royal Institute of Technology, Stockholm, Sweden S100 44 Vislab, Instituto Superior Técnico,
More informationVideo Alignment. Final Report. Spring 2005 Prof. Brian Evans Multidimensional Digital Signal Processing Project The University of Texas at Austin
Final Report Spring 2005 Prof. Brian Evans Multidimensional Digital Signal Processing Project The University of Texas at Austin Omer Shakil Abstract This report describes a method to align two videos.
More informationLucas-Kanade Without Iterative Warping
3 LucasKanade Without Iterative Warping Alex RavAcha School of Computer Science and Engineering The Hebrew University of Jerusalem 91904 Jerusalem, Israel EMail: alexis@cs.huji.ac.il Abstract A significant
More informationObject and Motion Recognition using Plane Plus Parallax Displacement of Conics
Object and Motion Recognition using Plane Plus Parallax Displacement of Conics Douglas R. Heisterkamp University of South Alabama Mobile, AL 6688-0002, USA dheister@jaguar1.usouthal.edu Prabir Bhattacharya
More informationFrame n. Raw Video Frames ... Synopsis Mosaic
1 Video Indexing Based on Mosaic Representations Michal Irani Abstract Videois a rich source of information. It provides visual information about scenes. However, this information is implicitly buried
More informationA 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 informationOnline Video Registration of Dynamic Scenes using Frame Prediction
Online Video Registration of Dynamic Scenes using Frame Prediction Alex Rav-Acha Yael Pritch Shmuel Peleg School of Computer Science and Engineering The Hebrew University of Jerusalem 91904 Jerusalem,
More informationRecently, there has been a growing interest in the use of mosaic images to represent the information contained in video sequences. This paper systemat
Ecient Representations of Video Sequences and Their Applications Michal Irani P. Anandan Jim Bergen Rakesh Kumar Steve Hsu David Sarno Research Center CN5300, Princeton, NJ-08530, U.S.A. Email: michal@sarno.com
More informationcalibrated 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 informationA Quantitative Comparison of 4 Algorithms for Recovering Dense Accurate Depth
A Quantitative Comparison o 4 Algorithms or Recovering Dense Accurate Depth Baozhong Tian and John L. Barron Dept. o Computer Science University o Western Ontario London, Ontario, Canada {btian,barron}@csd.uwo.ca
More informationQ-warping: Direct Computation of Quadratic Reference Surfaces
Q-warping: Direct Computation of Quadratic Reference Surfaces Y. Wexler A. Shashua wexler@cs.umd.edu Center for Automation Research University of Maryland College Park, MD 20742-3275 shashua@cs.huji.ac.il
More informationMotion Tracking and Event Understanding in Video Sequences
Motion Tracking and Event Understanding in Video Sequences Isaac Cohen Elaine Kang, Jinman Kang Institute for Robotics and Intelligent Systems University of Southern California Los Angeles, CA Objectives!
More informationFig. 3.1: Interpolation schemes for forward mapping (left) and inverse mapping (right, Jähne, 1997).
Eicken, GEOS 69 - Geoscience Image Processing Applications, Lecture Notes - 17-3. Spatial transorms 3.1. Geometric operations (Reading: Castleman, 1996, pp. 115-138) - a geometric operation is deined as
More informationA 3D Shape Constraint on Video
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 28, NO. 6, JUNE 2006 1 A 3D Shape Constraint on Video Hui Ji and Cornelia Fermuller, Member, IEEE Abstract We propose to combine the
More informationCS 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 informationFlow Estimation. Min Bai. February 8, University of Toronto. Min Bai (UofT) Flow Estimation February 8, / 47
Flow Estimation Min Bai University of Toronto February 8, 2016 Min Bai (UofT) Flow Estimation February 8, 2016 1 / 47 Outline Optical Flow - Continued Min Bai (UofT) Flow Estimation February 8, 2016 2
More informationTwo-View Geometry (Course 23, Lecture D)
Two-View Geometry (Course 23, Lecture D) Jana Kosecka Department of Computer Science George Mason University http://www.cs.gmu.edu/~kosecka General Formulation Given two views of the scene recover the
More informationGlobal Flow Estimation. Lecture 9
Motion Models Image Transformations to relate two images 3D Rigid motion Perspective & Orthographic Transformation Planar Scene Assumption Transformations Translation Rotation Rigid Affine Homography Pseudo
More informationSegmentation 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 informationMosaicing with Parallax using Time Warping Λ
Mosaicing with Parallax using Time Warping Λ Alex Rav-Acha Yael Shor y Shmuel Peleg School of Computer Science and Engineering The Hebrew University of Jerusalem 994 Jerusalem, Israel E-Mail: falexis,yaelshor,pelegg@cs.huji.ac.il
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational
More informationCenter for Automation Research, University of Maryland. The independence measure is the residual normal
Independent Motion: The Importance of History Robert Pless, Tomas Brodsky, and Yiannis Aloimonos Center for Automation Research, University of Maryland College Park, MD, 74-375 Abstract We consider a problem
More informationVideo Alignment. Literature Survey. Spring 2005 Prof. Brian Evans Multidimensional Digital Signal Processing Project The University of Texas at Austin
Literature Survey Spring 2005 Prof. Brian Evans Multidimensional Digital Signal Processing Project The University of Texas at Austin Omer Shakil Abstract This literature survey compares various methods
More informationLocal Image Registration: An Adaptive Filtering Framework
Local Image Registration: An Adaptive Filtering Framework Gulcin Caner a,a.murattekalp a,b, Gaurav Sharma a and Wendi Heinzelman a a Electrical and Computer Engineering Dept.,University of Rochester, Rochester,
More informationA Subspace Approach to Layer Extraction, Patch-Based SFM, and Video Compression
A Subspace Approach to Layer Extraction, Patch-Based SFM, and Video Compression Qifa Ke and Takeo Kanade December 2001 CMU-CS-01-168 School of Computer Science Carnegie Mellon University Pittsburgh, PA
More informationTextureless Layers CMU-RI-TR Qifa Ke, Simon Baker, and Takeo Kanade
Textureless Layers CMU-RI-TR-04-17 Qifa Ke, Simon Baker, and Takeo Kanade The Robotics Institute Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA 15213 Abstract Layers are one of the most well
More information521466S Machine Vision Exercise #1 Camera models
52466S Machine Vision Exercise # Camera models. Pinhole camera. The perspective projection equations or a pinhole camera are x n = x c, = y c, where x n = [x n, ] are the normalized image coordinates,
More informationSeparating Transparent Layers of Repetitive Dynamic Behaviors
Separating Transparent Layers of Repetitive Dynamic Behaviors Bernard Sarel Michal Irani Dept. of Computer Science and Applied Math. The Weizmann Institute of Science 76100 Rehovot, Israel Abstract In
More informationStereo 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 informationIntegrating Local Affine into Global Projective Images in the Joint Image Space
Integrating Local Affine into Global Projective Images in the Joint Image Space P. Anandan and Shai Avidan Microsoft Research, One Microsoft Way, Redmond, WA 98052, USA, {anandan,avidan}@microsoft.com
More informationHomography Tensors: On Algebraic Entities. Moving Planar Points. Amnon Shashua and Lior Wolf. The Hebrew University, Jerusalem 91904, Israel
Homography Tensors: On Algebraic Entities That Represent Three Views of Static or Moving Planar Points Amnon Shashua and Lior Wolf School of Computer Science and Engineering, The Hebrew University, Jerusalem
More informationLecture 16: Computer Vision
CS4442/9542b: Artificial Intelligence II Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field
More informationLecture 16: Computer Vision
CS442/542b: Artificial ntelligence Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field Methods
More informationUsing a Projected Subgradient Method to Solve a Constrained Optimization Problem for Separating an Arbitrary Set of Points into Uniform Segments
Using a Projected Subgradient Method to Solve a Constrained Optimization Problem or Separating an Arbitrary Set o Points into Uniorm Segments Michael Johnson May 31, 2011 1 Background Inormation The Airborne
More informationLinear Multi-View Reconstruction of Points, Lines, Planes and Cameras using a Reference Plane
Linear Multi-View Reconstruction of Points, Lines, Planes and Cameras using a Reference Plane Carsten Rother Computational Vision and Active Perception Laboratory (CVAP) Royal Institute of Technology (KTH),
More informationGlobal Flow Estimation. Lecture 9
Global Flow Estimation Lecture 9 Global Motion Estimate motion using all pixels in the image. Parametric flow gives an equation, which describes optical flow for each pixel. Affine Projective Global motion
More informationCompositing a bird's eye view mosaic
Compositing a bird's eye view mosaic Robert Laganiere School of Information Technology and Engineering University of Ottawa Ottawa, Ont KN 6N Abstract This paper describes a method that allows the composition
More informationAlignment of Non-Overlapping Sequences
Alignment of Non-Overlapping Sequences Yaron Caspi Michal Irani Dept. of Computer Science and Applied Math The Weizmann Institute of Science 76100 Rehovot, Israel PLEASE PRINT IN COLOR Abstract This paper
More information3D Reconstruction from Scene Knowledge
Multiple-View Reconstruction from Scene Knowledge 3D Reconstruction from Scene Knowledge SYMMETRY & MULTIPLE-VIEW GEOMETRY Fundamental types of symmetry Equivalent views Symmetry based reconstruction MUTIPLE-VIEW
More informationStructure from Motion. Prof. Marco Marcon
Structure from Motion Prof. Marco Marcon Summing-up 2 Stereo is the most powerful clue for determining the structure of a scene Another important clue is the relative motion between the scene and (mono)
More informationStructure 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 2 R 3,t 3 Camera 1 Camera
More informationLecture 19: Motion. Effect of window size 11/20/2007. Sources of error in correspondences. Review Problem set 3. Tuesday, Nov 20
Lecture 19: Motion Review Problem set 3 Dense stereo matching Sparse stereo matching Indexing scenes Tuesda, Nov 0 Effect of window size W = 3 W = 0 Want window large enough to have sufficient intensit
More informationZ (cm) Y (cm) X (cm)
Oceans'98 IEEE/OES Conference Uncalibrated Vision for 3-D Underwater Applications K. Plakas, E. Trucco Computer Vision Group and Ocean Systems Laboratory Dept. of Computing and Electrical Engineering Heriot-Watt
More informationCarnegie Mellon University. Pittsburgh, PA [6] require the determination of the SVD of. the measurement matrix constructed from the frame
Ecient Recovery of Low-dimensional Structure from High-dimensional Data Shyjan Mahamud Martial Hebert Dept. of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Abstract Many modeling tasks
More informationProceedings of the 6th Int. Conf. on Computer Analysis of Images and Patterns. Direct Obstacle Detection and Motion. from Spatio-Temporal Derivatives
Proceedings of the 6th Int. Conf. on Computer Analysis of Images and Patterns CAIP'95, pp. 874-879, Prague, Czech Republic, Sep 1995 Direct Obstacle Detection and Motion from Spatio-Temporal Derivatives
More informationMultiple Motion Scene Reconstruction from Uncalibrated Views
Multiple Motion Scene Reconstruction from Uncalibrated Views Mei Han C & C Research Laboratories NEC USA, Inc. meihan@ccrl.sj.nec.com Takeo Kanade Robotics Institute Carnegie Mellon University tk@cs.cmu.edu
More informationVision 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 informationPerception 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 informationA Robust Subspace Approach to Extracting Layers from Image Sequences
A Robust Subspace Approach to Extracting Layers from Image Sequences Qifa Ke CMU-CS-03-173 August 1, 2003 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Submitted in partial
More informationReal-Time Motion Analysis with Linear-Programming Λ
Real-ime Motion Analysis with Linear-Programming Λ Moshe Ben-Ezra Shmuel Peleg Michael Werman Institute of Computer Science he Hebrew University of Jerusalem 91904 Jerusalem, Israel Email: fmoshe, peleg,
More informationComputer Vision I Name : CSE 252A, Fall 2012 Student ID : David Kriegman Assignment #1. (Due date: 10/23/2012) x P. = z
Computer Vision I Name : CSE 252A, Fall 202 Student ID : David Kriegman E-Mail : Assignment (Due date: 0/23/202). Perspective Projection [2pts] Consider a perspective projection where a point = z y x P
More informationDistribution Fields with Adaptive Kernels for Large Displacement Image Alignment
MEARS et al.: DISTRIBUTION FIELDS WITH ADAPTIVE KERNELS 1 Distribution Fields with Adaptive Kernels or Large Displacement Image Alignment Benjamin Mears bmears@cs.umass.edu Laura Sevilla Lara bmears@cs.umass.edu
More informationA unified approach for motion analysis and view synthesis Λ
A unified approach for motion analysis and view synthesis Λ Alex Rav-Acha Shmuel Peleg School of Computer Science and Engineering The Hebrew University of Jerusalem 994 Jerusalem, Israel Email: falexis,pelegg@cs.huji.ac.il
More informationRobust Model-Free Tracking of Non-Rigid Shape. Abstract
Robust Model-Free Tracking of Non-Rigid Shape Lorenzo Torresani Stanford University ltorresa@cs.stanford.edu Christoph Bregler New York University chris.bregler@nyu.edu New York University CS TR2003-840
More informationIntroduction to Computer Vision
Introduction to Computer Vision Michael J. Black Nov 2009 Perspective projection and affine motion Goals Today Perspective projection 3D motion Wed Projects Friday Regularization and robust statistics
More informationA Robust Two Feature Points Based Depth Estimation Method 1)
Vol.31, No.5 ACTA AUTOMATICA SINICA September, 2005 A Robust Two Feature Points Based Depth Estimation Method 1) ZHONG Zhi-Guang YI Jian-Qiang ZHAO Dong-Bin (Laboratory of Complex Systems and Intelligence
More informationToday. Stereo (two view) reconstruction. Multiview geometry. Today. Multiview geometry. Computational Photography
Computational Photography Matthias Zwicker University of Bern Fall 2009 Today From 2D to 3D using multiple views Introduction Geometry of two views Stereo matching Other applications Multiview geometry
More informationFeature-Based Sequence-to-Sequence Matching
Feature-Based Sequence-to-Sequence Matching Yaron Caspi The Institute of Computer Science The Hebrew University of Jerusalem Jerusalem 91904, Israel Denis Simakov and Michal Irani Dept. of Computer Science
More informationHand-Eye Calibration from Image Derivatives
Hand-Eye Calibration from Image Derivatives Abstract In this paper it is shown how to perform hand-eye calibration using only the normal flow field and knowledge about the motion of the hand. The proposed
More informationChapter 3 Image Enhancement in the Spatial Domain
Chapter 3 Image Enhancement in the Spatial Domain Yinghua He School o Computer Science and Technology Tianjin University Image enhancement approaches Spatial domain image plane itsel Spatial domain methods
More informationOptical flow and tracking
EECS 442 Computer vision Optical flow and tracking Intro Optical flow and feature tracking Lucas-Kanade algorithm Motion segmentation Segments of this lectures are courtesy of Profs S. Lazebnik S. Seitz,
More informationMulti-stable Perception. Necker Cube
Multi-stable Perception Necker Cube Spinning dancer illusion, Nobuyuki Kayahara Multiple view geometry Stereo vision Epipolar geometry Lowe Hartley and Zisserman Depth map extraction Essential matrix
More informationA Bottom Up Algebraic Approach to Motion Segmentation
A Bottom Up Algebraic Approach to Motion Segmentation Dheeraj Singaraju and RenéVidal Center for Imaging Science, Johns Hopkins University, 301 Clark Hall, 3400 N. Charles St., Baltimore, MD, 21218, USA
More informationC280, Computer Vision
C280, Computer Vision Prof. Trevor Darrell trevor@eecs.berkeley.edu Lecture 11: Structure from Motion Roadmap Previous: Image formation, filtering, local features, (Texture) Tues: Feature-based Alignment
More informationBIL Computer Vision Apr 16, 2014
BIL 719 - Computer Vision Apr 16, 2014 Binocular Stereo (cont d.), Structure from Motion Aykut Erdem Dept. of Computer Engineering Hacettepe University Slide credit: S. Lazebnik Basic stereo matching algorithm
More informationTEMPORAL SYNCHRONIZATION FROM CAMERA MOTION. Lisa Spencer and Mubarak Shah. School of Computer Science University of Central Florida
TEMPORAL SYNCHRONIZATION FROM CAMERA MOTION Lisa Spencer and Mubarak Shah School of Computer Science University of Central Florida ABSTRACT This paper presents a method to recover the temporal synchronization
More informationOptical Flow Estimation
Optical Flow Estimation Goal: Introduction to image motion and 2D optical flow estimation. Motivation: Motion is a rich source of information about the world: segmentation surface structure from parallax
More informationFrom Reference Frames to Reference Planes: Multi-View Parallax Geometry and Applications
From Reference Frames to Reference Planes: Multi-View Parallax Geometry and Applications M. Irani 1, P. Anandan 2, and D. Weinshall 3 1 Dept. of Applied Math and CS, The Weizmann Inst. of Science, Rehovot,
More informationThe end of affine cameras
The end of affine cameras Affine SFM revisited Epipolar geometry Two-view structure from motion Multi-view structure from motion Planches : http://www.di.ens.fr/~ponce/geomvis/lect3.pptx http://www.di.ens.fr/~ponce/geomvis/lect3.pdf
More informationMotion. 1 Introduction. 2 Optical Flow. Sohaib A Khan. 2.1 Brightness Constancy Equation
Motion Sohaib A Khan 1 Introduction So far, we have dealing with single images of a static scene taken by a fixed camera. Here we will deal with sequence of images taken at different time intervals. Motion
More information1-2 Feature-Based Image Mosaicing
MVA'98 IAPR Workshop on Machine Vision Applications, Nov. 17-19, 1998, Makuhari, Chibq Japan 1-2 Feature-Based Image Mosaicing Naoki Chiba, Hiroshi Kano, Minoru Higashihara, Masashi Yasuda, and Masato
More informationMultiple 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 informationTwo-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 informationGeometric Registration for Deformable Shapes 2.2 Deformable Registration
Geometric Registration or Deormable Shapes 2.2 Deormable Registration Variational Model Deormable ICP Variational Model What is deormable shape matching? Example? What are the Correspondences? Eurographics
More informationStereo II CSE 576. Ali Farhadi. Several slides from Larry Zitnick and Steve Seitz
Stereo II CSE 576 Ali Farhadi Several slides from Larry Zitnick and Steve Seitz Camera parameters A camera is described by several parameters Translation T of the optical center from the origin of world
More informationThe Template Update Problem
The Template Update Problem Iain Matthews, Takahiro Ishikawa, and Simon Baker The Robotics Institute Carnegie Mellon University Abstract Template tracking dates back to the 1981 Lucas-Kanade algorithm.
More informationStructure 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 informationFeature Tracking and Optical Flow
Feature Tracking and Optical Flow Prof. D. Stricker Doz. G. Bleser Many slides adapted from James Hays, Derek Hoeim, Lana Lazebnik, Silvio Saverse, who 1 in turn adapted slides from Steve Seitz, Rick Szeliski,
More informationMidterm Exam Solutions
Midterm Exam Solutions Computer Vision (J. Košecká) October 27, 2009 HONOR SYSTEM: This examination is strictly individual. You are not allowed to talk, discuss, exchange solutions, etc., with other fellow
More informationMulti-body Factorization With Uncertainty: Revisiting Motion Consistency
Multi-body Factorization With Uncertainty: Revisiting Motion Consistency Lihi Zelnik-Manor (lihi@vision.caltech.edu) California Institute of Technology Pasadena, CA, USA Moshe Machline and Michal Irani
More informationVertical Parallax from Moving Shadows
Vertical Parallax from Moving Shadows Yaron Caspi Faculty of Mathematics and Computer Science The Weizmann Institute of Science Rehovot, 76100, Israel Michael Werman School of Computer Science and Engineering
More informationCombining 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 informationStereo Vision. MAN-522 Computer Vision
Stereo Vision MAN-522 Computer Vision What is the goal of stereo vision? The recovery of the 3D structure of a scene using two or more images of the 3D scene, each acquired from a different viewpoint in
More informationRecovering structure from a single view Pinhole perspective projection
EPIPOLAR GEOMETRY The slides are from several sources through James Hays (Brown); Silvio Savarese (U. of Michigan); Svetlana Lazebnik (U. Illinois); Bill Freeman and Antonio Torralba (MIT), including their
More informationImage Transfer Methods. Satya Prakash Mallick Jan 28 th, 2003
Image Transfer Methods Satya Prakash Mallick Jan 28 th, 2003 Objective Given two or more images of the same scene, the objective is to synthesize a novel view of the scene from a view point where there
More informationCapturing, Modeling, Rendering 3D Structures
Computer Vision Approach Capturing, Modeling, Rendering 3D Structures Calculate pixel correspondences and extract geometry Not robust Difficult to acquire illumination effects, e.g. specular highlights
More informationFeature-Based Image Mosaicing
Systems and Computers in Japan, Vol. 31, No. 7, 2000 Translated from Denshi Joho Tsushin Gakkai Ronbunshi, Vol. J82-D-II, No. 10, October 1999, pp. 1581 1589 Feature-Based Image Mosaicing Naoki Chiba and
More informationMETRIC PLANE RECTIFICATION USING SYMMETRIC VANISHING POINTS
METRIC PLANE RECTIFICATION USING SYMMETRIC VANISHING POINTS M. Lefler, H. Hel-Or Dept. of CS, University of Haifa, Israel Y. Hel-Or School of CS, IDC, Herzliya, Israel ABSTRACT Video analysis often requires
More informationComputational Optical Imaging - Optique Numerique. -- Single and Multiple View Geometry, Stereo matching --
Computational Optical Imaging - Optique Numerique -- Single and Multiple View Geometry, Stereo matching -- Autumn 2015 Ivo Ihrke with slides by Thorsten Thormaehlen Reminder: Feature Detection and Matching
More informationFeature Tracking and Optical Flow
Feature Tracking and Optical Flow Prof. D. Stricker Doz. G. Bleser Many slides adapted from James Hays, Derek Hoeim, Lana Lazebnik, Silvio Saverse, who in turn adapted slides from Steve Seitz, Rick Szeliski,
More informationRectification and Distortion Correction
Rectification and Distortion Correction Hagen Spies March 12, 2003 Computer Vision Laboratory Department of Electrical Engineering Linköping University, Sweden Contents Distortion Correction Rectification
More informationVC 11/12 T11 Optical Flow
VC 11/12 T11 Optical Flow Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos Miguel Tavares Coimbra Outline Optical Flow Constraint Equation Aperture
More informationextracted occurring from the spatial and temporal changes in an image sequence. An image sequence
Motion: Introduction are interested in the visual information that can be We from the spatial and temporal changes extracted in an image sequence. An image sequence occurring of a series of images (frames)
More information