Image-based Motion Stabilization for Maritime Surveillance
|
|
- Mitchell Wells
- 5 years ago
- Views:
Transcription
1 Image-based Moton Stablzaton for Martme Survellance Danel D. Morrs, Bran R. Colonna and Franln D. Snyder General Dynamcs Robotc Systems, 151 Ardmore Blvd, Pttsburgh, PA * ABSTRACT Robust mage-based moton stablzaton s developed to enable vsual survellance n the martme doman. The algorthm developed s nether a dense regstraton method nor a tradtonal feature-based method, but rather t captures the best aspects of each of these approaches. It avods feature tracng and so can handle large ntra-frame motons, and at the same tme t s robust to large lghtng varatons and movng clutter. It s thus well-suted for challenges n the martme doman. Advantage s taen of the martme envronment ncludng use of the horzon and shorelne, and fused data from an nexpensve nertal measurement unt. Results of real-tme operaton on an n-water buoy are presented. Keywords: Optcal stablzaton, feature regstraton, martme, buoy survellance, computer vson, nertal measurement unt, water surface, fuson, horzon, shorelne. 1. INTRODUCTION The frst step n survellance s usually stablzaton for camera moton [3,4,9,11], and that s the focus of ths paper. Whle there has been much wor n ground and aeral survellance, the martme doman has not yet drawn sgnfcant attenton. Yet the martme doman presents a number of unque challenges and opportuntes for moton stablzaton. Floatng sensors must deal wth constant moton of ther own and of the water surface around them. Waves may generate hgh-texture features, but ther moton s non-rgd and ther appearance changes rapdly. Martme lghtng typcally has greater contrast than on land due to drect sunlght reflectons wth a resultng loss of detal for cameras wth lmted dynamc range. Rapd changes n lghtng can be countered by an auto-rs, but ths leads to changes n object appearance and detals. Fnally water spray can lead to droplets and salt deposts on the camera protectve cover, causng dstortons and clutter n the magery. Here algorthms are developed for robust mage stablzaton on a floatng buoy. Whle t s possble to use a gyro-based sensor to do stablzaton, ths requres a hgh-precson devce whch s typcally expensve and buly. Drectly usng mages enables stablzaton down to sub-pxel precson, whch s precsely the level needed for moton-based detecton algorthms. There are two general approaches to mage stablzaton: dense technques and feature-based technques. In dense technques mages patches are drectly warped onto each other or correlated wth each other usng moton models, for example see [8,9]. On the other hand, feature-based technques rely on tracng features between mages and drectly calculatng moton from them, see [2,3,4,1,12]. Advantages of dense methods nclude more pxels beng used and requrng explct feature correspondences s avoded. But these methods are typcally not robust to many of the challenges n martme envronments such as rapdly movng specular reflectons and large changes n gan and contrast due to lghtng changes. Feature-based methods can be qute robust to lghtng varatons as well as to movng clutter n the scene, however they face the challenge of mantanng feature tracs especally when moton s large. They also have dffcultes f the scene does not have stable corner features. Here a hybrd technque for moton stablzaton s presented. It acheves robustness to lghtng varatons and movng clutter n a smlar way as feature technques, but at the same tme, le the dense technques, t does not requre fndng corner features or tracng features between frames. It can thus wor wth very large ntra-frame moton and wth large lghtng varatons and movng clutter. The geometry of the martme doman s leveraged ncludng use of the horzon and shorelne as well as an nertal measurement unt (IMU) f avalable. Stablzaton was mplemented n a real-tme system onboard a buoy. Sample results are llustrated. * Wor was performed n part at Northrop Grumman Corp, 151 Ardmore Blvd, Pttsburgh PA
2 The paper s organzed as follows. Frst our assumptons are stated n Secton 2. Then stablzaton of the vertcal axs s descrbed n Secton 3, followed by stablzaton of headng n Secton 4. Flterng to combne nertal and mage measurements s descrbed n Secton 5. Fnally results are gven and dscussed n the concluson. 2. ASSUMPTIONS Stablzaton s performed usng a 36-degree feld of vew, 5-camera array that has been calbrated such that for each u, v there s a nown unt 3-vector, p ˆ, gvng the drecton of the ray ncdent on that pont, pxel n each camera, ( ) namely: f u v s the calbraton functon. where (, ) ( ) p ˆ = f u, v, (1) Snce the cameras are close together compared to the dstance to detected objects, ther optcal centers are approxmated as beng concdent. By worng n sphercal coordnates, data from all cameras can be treated unformly. It s assumed that over short tme perods the buoy translaton s neglgble compared to the objects t observes. Furthermore t s assumed that the horzon or dstant shorelne s vsble for vertcal stablzaton, and that shorelne features are avalable for headng estmaton. 3. VERTICAL STABILIZATION Image moton can be explaned as a rotaton of the platform, and hence stablzaton s acheved by estmatng the platform rotaton. The approach here s to dvde rotaton estmaton s nto two sequental steps: frst vertcal axs estmaton and then headng estmaton. Vertcal axs estmaton s descrbed n ths secton. The ey property of the martme doman that ads stablzaton s that the vsble horzon or dstant shorelne defnes a horzontal plane. Fgure 1 llustrates a buoy rotated by W B R n world coordnates wth respect to a reference frame on the horzontal plane, H. The thrd row of W R, s B B z, the transpose of the vertcal axs n the buoy reference frame. In Euler coordnates ths s [ sn( p),cos( p)sn( r),cos( p)cos( r) ] T W, see 5 pg. 46, where r and p are the roll and ptch around the world x and y axes respectvely. Thus fndng the vertcal vector, B z W, or equvalently the horzontal plane, n buoy coordnates s suffcent to determne the buoy roll and ptch. W R B z B z W H y W x W Fgure 1 The world coordnate system s defned such that z W s perpendcular to the horzontal plane H. The buoy coordnate system s rotated wth respect to ths by W R. B It s assumed that the horzon (or a suffcently dstant shorelne) s vsble as a contrast change n part of the 36-degree mage. However the mages wll typcally be hghly textured wth waves, clouds and shorelne provdng clutter from whch the horzon must be extracted. The followng robust technque was used to determne the horzontal plane.
3 Fgure 2 Peas and troughs of the vertcal gradents are found n each mage column n the regon around the horzon. These ponts nclude the horzon, dstant shorelne and other clutter. The horzon s found by determnng the plane that explans the most peas n all smultaneous mages. For each column of the smoothed vertcal gradent mages of all the cameras, all the local maxma and mnma n the regon around the predcted horzon and above a small threshold are found. A subset of these wll correspond to the horzon. Each of the maxma and mnma s mapped to a pont on the unt sphere, p ˆ, usng Eq. (1). Now the horzon ponts wll all le on the plane H, and at the same tme t s unlely that there wll be any other plane through the orgn generatng a large number of ponts p ˆ. Thus a robust technque, such as RANSAC 6, s used to fnd the best plane fttng these ponts. Pars of ponts are suffcent to defne the perpendcular to a plane through ther cross product: v = pˆ p ˆ (2) j The vector v wth the most nlers s the ntal estmate for B z W, and a least squares estmate usng the nlers can be obtaned as the egenvector correspondng to the mnmum egenvalue of: T A = p p. (3) Examples of stablzaton are shown n Fgures 8 and 9. nlers 4. HEADING STABILIZATION The next step s to determne the change n headng. Our approach to achevng ths s to temporally algn vertcal features on the vsble shorelne. We want these features to be robust to lghtng varaton and we want to avod tracng ndvdual features. A technque that acheves ths s based on vertcal curves. Vertcal curves trace the vertcal edges of objects and landmars on the shorelne, see Fgure 3. They are obtaned wth sub-pxel accuracy and are nvarant to brghtness and contrast changes. Frst the horzontal gradents of all the mages are found. The maxma and mnma of the gradent for each row are parabolcally ft to sub-pxel accuracy, and roughly vertcal contour-based curves are created by connectng close-by maxma and mnma between adjacent horzontal rows as llustrated n Fgure 3.
4 (a) (b) Fgure 3 (a) Curves found on objects on the shorelne. (b) Close-up showng the peas and troughs of the horzontal gradent (red and blue dots), and the curves traced through them. Curves are bult n mage space, but then transformed onto the unt sphere usng Eq. (1). They are then stablzed wth T R wth zero headng. After ths the elevaton and azmuth angles, ( ϕ, θ ) respect to roll and ptch by rotatng by W B each transformed pont, p ˆ, on each curve can be calculated up to an unnown overall headng: 2 2 ( p p p ) ϕ = arctan +, (4) x y z ( p p ) θ = arctan, (5) y x It s assumed that a porton of shorelne s vsble above the horzon, and ths s used for fndng headng change as s ϕ ; θ, at a set of elevatons ϕ and tme t of the transformed curves are made, follows. A seres of horzontal slces, ( ) t and for each slce the locatons, θ, of all curve ntersectons are recorded wth a ± 1 pxels dependng on the sgn of the curve at that pont, see Fgure 4. Correspondng slces are made through subsequent mages, and the relatve headng found by a crcular convoluton of these slces wth the slces at prevous tmes. Crcular convolutons can be effcently calculated S ϕ ; θ s the FFT of wth the use of fast Fourer transforms and ther nverses: FFTs and IFFTs respectvely. If ( ) s ( ϕ ; θ ) and S ( ϕ ; θ ) t t the complex conjugate, then the sum of the crcular convolutons wth slces at tme t m s gven by: ( θ ) = IFFT { ( ϕ ; θ ) ( θ ) ( ϕ ; θ )} tm tm t slces w S G S (6) where G( θ ) s the FFT of a Gaussan added for smoothng and to reduce senstvty to calbraton mprecson. There s no need for zero paddng as the convoluton s crcular. The locaton of the pea of ( ) tm w θ gves the headng wth respect to tme t. Ths s robust to movng objects and spurous curves, snce curves that do not have a match do not contrbute to the result. Hence a robust and precse headng s obtaned. t, for
5 (a) (b) Fgure 4 (a) Usng the roll and ptch estmated prevously, vertcal curves are transformed nto the ( ϕ, θ ) space. A seres of horzontal slces cut through these at varous elevatons above the horzon. The nterpolated locaton of these curves on one of these slces s shown n (b) (a) -5 5 (b) Fgure 5 (a) Convoluton w ( θ ) from Eq. (6) of the slces n Fgure 4. The lower chart tm s a close-up showng a small change n headng at the maxmum n degrees. 5. FILTERING Rotaton estmates can be mproved by flterng. Ths enables the ncluson of a buoy dynamc model and moton estmates from the IMU. A standard Kalman flter was mplemented to acheve ths wth the followng partcular propertes. The buoy dynamcs were modeled as ndependent damped harmonc oscllators n roll and ptch, and damped angular speed model n headng. Wth state vector, x = [ r, r, p, p, h, h ] T, contanng roll, ptch, headng and ther tme dervatves, the equaton of moton s: x = Fx + u( t). (7) The component of x for roll s [ r ṙ ] T and ts dynamcs are descrbed by:
6 1 F roll = 2 (8) ω γ where ω and γ are the characterstc buoy angular speeds and dampng respectvely. Analogous expressons apply to ptch and headng (wth ω = for the latter). Together they form a bloc-dagonal F, and state transfer functon: Φ = exp F t. (9) ( ) The drvng term, u ( t), s the acton of the waves and s unnown, and so s modeled as system nose, Q. It acts as a contnuous acceleraton term and so to ntegrate t nto our dscrete formulaton the followng equaton was used for roll nose (and smlar equatons for ptch and headng): T Q roll = Froll Qroll + Qroll Froll + 2, (1) σ where where 2 σ s the measure of the acceleraton from wave moton. Ths can be re-wrtten n the form: q = Mq + (11) 2 σ The soluton s gven by: q 2 11 q11 q12 2 q 12,, and roll ω γ 1 q12 q 22 2 q 22 2ω 2γ q = Q = M =. ( ( t) ) 1 q = M exp M I, (12) 2 σ from whch Q roll s obtaned. Q ptch and Q headng are obtaned n a smlar manner and together form the bloc-dagonal Q. The measurement matrx, H, defned by Hx = z where z contans the measured quanttes, s smple to calculate. The measurements nclude r, r, p, p, h, ḣ drectly from the IMU, and r, p, h from the mages, where h s the headng relatve to the prevous mage. The covarance, R, on the measurements was chosen to have much larger terms on the IMU components than the mage components. All these terms are plugged nto standard dscrete Kalman flter equatons and produce a fused mage and nertal stablzaton system. For completeness these equatons are summarzed as follows: x = Φ x ( ) ( + ) t t t 1 P = Φ P Φ + Q ( ) ( + ) T t t t 1 t t 1 T ( ) ( ) K = P H H P H + R ( ) T ( ) t t t t t t t x = x + K z H x ( + ) ( ) ( ) t t t t t t P = P K H P ( + ) ( ) ( ) t t t t t 1 (13) 6. RESULTS Stablzaton through horzon-fndng n fve cameras turned out to be very robust. Examples are shown n Fgures 7, 8 and 9. Usng an nexpensve nertal measurement devce sgnfcantly sped up the computaton by reducng the search space as well as the percentage of outlers to be dealt wth by the RANSAC operaton. Relatve headng estmaton was fast, requrng only 1D FFTs and gave pxel-level precson, see Fgure 5. A comparson of IMU and mage-stablzaton as well as fused results s gven n Fgure 6. Dstant shps can help n short-term stablzaton, although over longer term ther
7 moton relatve to the shorelne can be detected. Stablzaton was easly calculated wth a Pentum III processor wth data from 5 124x768 cameras at 7 frames per second. 1 Roll Deg Ptch Deg Headng Deg 55 IMU Image Flter Tme (sec) Fgure 6 Comparson rotaton estmates from IMU and the mage-based algorthm and a fltered approach that fuses these. The IMU s rated to accurate to a RMS accuracy of 2 whereas the mage-based headng s accurate down to at least pxel resoluton, whch for these cameras s ±.2. In ths example of low acceleraton, the IMU accuracy s much hgher than ts rated value and comparable to the mage technque. For larger motons, however, the IMU accuracy degrades as can be seen n Fgure 9, whereas the mage-based technque mantans hgh accuracy. 7. CONCLUSION An effcent and robust mage-based moton stablzaton technque was developed for the martme doman. The use of features based on local maxma and mnma of the gradent mages gave robustness to rapd lghtng changes. The use of curves rather than corners s more approprate to martme envronments where corner features may be rare. Avodng the need to trac features maes the technque robust to large ntra-frame moton. Usng sphercal coordnates enables measurements from cameras pontng n all drectons to be used, greatly reducng ambgutes n horzon-fndng that occur n sngle-camera solutons. The next step s to use the moton stablzaton to acheve movng object detecton. The curved features developed here can be used for ths. Obtanng the absolute vertcal, as ths does, rather than smply an ncremental change n rotaton, enables precse survellance applcatons that search for objects close to the horzon. A lmtaton of mage-based technques s that they depend on envronmental condtons. Fog or haze can obstruct the vew of the horzon or shorelne. In these cases t may be necessary to rely on nertal measurements whch can easly be done wth our flterng approach. A useful advantage of the mage-based approach s that accuracy can ncreased smply by addng more cameras wth hgher resoluton.
8 (a) (b) -12 (c) Fgure 7 (a) A porton of the feld of vew of the camera array ncludng shorelne and watercraft. (b) Horzon and curves are shown overlad. (c) Curves are transformed nto stablzed, sphercal coordnates. ACKNOWLEDGEMENT Ths wor was performed under the sponsorshp of ONR FNC-AO-IA, PM Marc Stenberg, #N421-3-C-27 and # DAAD REFERENCES: 1. H. Asada, M. Brady, The Curvature Prmal Setch, IEEE PAMI 8(1):2-14, D. Burscha, G. Hager, Vson-based control of moble robots, n Proc. Internatonal Conference on Robotcs and Automaton, pages , A. Cens, A. Fusello, and V. Roberto, "Image stablzaton by features tracng," n Proc. 1th Int. Conf. Image Analyss and Processng, Sep 1999, pp I. Cohen, G. Medon Detectng and tracng movng objects n vdeo survellance, Proc IEEE Conf Computer Vson and Pattern Recognton 1999; II: J.J. Crag, Introducton to Robotcs Mechancs and Control, Second Edton, Addson Wesley Longman, M.A. Fschler, R.C. Bolles. Random sample consensus: A paradgm for model fttng wth applcatons to mage analyss and automated cartography, n Comm. of the ACM, volume 24, pages , C. Harrs, M. Stephens, "A combned corner and edge detector", n Alvey Vson Conf., 1988, pp Iran, M., Rousso, B., and Peleg, S., "Recovery of Ego-Moton Usng Image Stablzaton," CVPR 1994, pp C.D. Kugln, D.C. Hnes. The phase correlaton mage algnment method, IEEE Conference on Cybernetcs and Socety, p , A. Ltvn, J. Konrad, W.C. Karl Probablstc vdeo stablzaton usng Kalman flterng and mosacng Image and Vdeo Communcaton and Processng 23, SPIE Vo. 522, pp
9 11. D.G. Lowe, Object recognton from local scale-nvarant features, Internatonal Conference on Computer Vson, Corfu, Greece (September 1999), pp L. Marcenaro, G. Vernazza, C.S. Regazzon, Image stablzaton algorthms for vdeo-survellance applcatons, n Proc. Int. Conf. Image Processng 21, Vo1 1, pp E. Shlat, M. Werman, Y. Gdalyahu, Rdge s corner detecton and correspondence, IEEE Proc. CVPR, 1997, pp Fgure 8 Horzon stablzaton shown on 3 of 5 mages. Top row shows orgnal mages. The vertcal offsets and radal dstortons are unmportant as they are accounted for n the calbraton, Eq (1). Blue lnes n center row show regon bounded by uncertanty of the IMU. In ths regon the yellow dots show all the vertcal gradent peas. Usng RANSAC a subset of these are determned to be nlers to the horzon and these are plotted n the bottom row wth the blue lnes beng the bounds on the nlers. The fnal estmate of the horzon s shown by the orange lne and s obtaned as a least squares ft to the nlers, see Eq. (3). Fgure 9 Another example of horzon fttng wth very large roll and ptch shown n 3 of the 5 cameras. The two blue curves are bounds of the search regon gven by the IMU and centered around ts estmate whch shows sgnfcant error compared to the fnal mage-estmate. Gradent peas are hghlghted n ths regon. Applcaton of RANSAC fnds nlers to the horzontal plane, here mared as whte.
SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision
SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,
More informationImprovement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration
Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,
More informationR s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes
SPH3UW Unt 7.3 Sphercal Concave Mrrors Page 1 of 1 Notes Physcs Tool box Concave Mrror If the reflectng surface takes place on the nner surface of the sphercal shape so that the centre of the mrror bulges
More informationFitting & Matching. Lecture 4 Prof. Bregler. Slides from: S. Lazebnik, S. Seitz, M. Pollefeys, A. Effros.
Fttng & Matchng Lecture 4 Prof. Bregler Sldes from: S. Lazebnk, S. Setz, M. Pollefeys, A. Effros. How do we buld panorama? We need to match (algn) mages Matchng wth Features Detect feature ponts n both
More informationA Fast Visual Tracking Algorithm Based on Circle Pixels Matching
A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng
More informationImage Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline
mage Vsualzaton mage Vsualzaton mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and Analyss outlne mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and
More informationStructure from Motion
Structure from Moton Structure from Moton For now, statc scene and movng camera Equvalentl, rgdl movng scene and statc camera Lmtng case of stereo wth man cameras Lmtng case of multvew camera calbraton
More informationRange images. Range image registration. Examples of sampling patterns. Range images and range surfaces
Range mages For many structured lght scanners, the range data forms a hghly regular pattern known as a range mage. he samplng pattern s determned by the specfc scanner. Range mage regstraton 1 Examples
More informationAn efficient method to build panoramic image mosaics
An effcent method to buld panoramc mage mosacs Pattern Recognton Letters vol. 4 003 Dae-Hyun Km Yong-In Yoon Jong-Soo Cho School of Electrcal Engneerng and Computer Scence Kyungpook Natonal Unv. Abstract
More informationMOTION BLUR ESTIMATION AT CORNERS
Gacomo Boracch and Vncenzo Caglot Dpartmento d Elettronca e Informazone, Poltecnco d Mlano, Va Ponzo, 34/5-20133 MILANO boracch@elet.polm.t, caglot@elet.polm.t Keywords: Abstract: Pont Spread Functon Parameter
More informationCS 534: Computer Vision Model Fitting
CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust
More informationMOTION PANORAMA CONSTRUCTION FROM STREAMING VIDEO FOR POWER- CONSTRAINED MOBILE MULTIMEDIA ENVIRONMENTS XUNYU PAN
MOTION PANORAMA CONSTRUCTION FROM STREAMING VIDEO FOR POWER- CONSTRAINED MOBILE MULTIMEDIA ENVIRONMENTS by XUNYU PAN (Under the Drecton of Suchendra M. Bhandarkar) ABSTRACT In modern tmes, more and more
More informationElectrical analysis of light-weight, triangular weave reflector antennas
Electrcal analyss of lght-weght, trangular weave reflector antennas Knud Pontoppdan TICRA Laederstraede 34 DK-121 Copenhagen K Denmark Emal: kp@tcra.com INTRODUCTION The new lght-weght reflector antenna
More informationParallelism for Nested Loops with Non-uniform and Flow Dependences
Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr
More informationContent Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers
IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth
More informationA Binarization Algorithm specialized on Document Images and Photos
A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a
More informationSkew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach
Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research
More informationS1 Note. Basis functions.
S1 Note. Bass functons. Contents Types of bass functons...1 The Fourer bass...2 B-splne bass...3 Power and type I error rates wth dfferent numbers of bass functons...4 Table S1. Smulaton results of type
More informationAnalysis of Continuous Beams in General
Analyss of Contnuous Beams n General Contnuous beams consdered here are prsmatc, rgdly connected to each beam segment and supported at varous ponts along the beam. onts are selected at ponts of support,
More informationMathematics 256 a course in differential equations for engineering students
Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the
More informationEdge Detection in Noisy Images Using the Support Vector Machines
Edge Detecton n Nosy Images Usng the Support Vector Machnes Hlaro Gómez-Moreno, Saturnno Maldonado-Bascón, Francsco López-Ferreras Sgnal Theory and Communcatons Department. Unversty of Alcalá Crta. Madrd-Barcelona
More informationCorner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity
Journal of Sgnal and Informaton Processng, 013, 4, 114-119 do:10.436/jsp.013.43b00 Publshed Onlne August 013 (http://www.scrp.org/journal/jsp) Corner-Based Image Algnment usng Pyramd Structure wth Gradent
More informationLEAST SQUARES. RANSAC. HOUGH TRANSFORM.
LEAS SQUARES. RANSAC. HOUGH RANSFORM. he sldes are from several sources through James Has (Brown); Srnvasa Narasmhan (CMU); Slvo Savarese (U. of Mchgan); Bll Freeman and Antono orralba (MI), ncludng ther
More informationMETRIC ALIGNMENT OF LASER RANGE SCANS AND CALIBRATED IMAGES USING LINEAR STRUCTURES
METRIC ALIGNMENT OF LASER RANGE SCANS AND CALIBRATED IMAGES USING LINEAR STRUCTURES Lorenzo Sorg CIRA the Italan Aerospace Research Centre Computer Vson and Vrtual Realty Lab. Outlne Work goal Work motvaton
More informationEcient Computation of the Most Probable Motion from Fuzzy. Moshe Ben-Ezra Shmuel Peleg Michael Werman. The Hebrew University of Jerusalem
Ecent Computaton of the Most Probable Moton from Fuzzy Correspondences Moshe Ben-Ezra Shmuel Peleg Mchael Werman Insttute of Computer Scence The Hebrew Unversty of Jerusalem 91904 Jerusalem, Israel Emal:
More informationUser Authentication Based On Behavioral Mouse Dynamics Biometrics
User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA
More informationA Fast Content-Based Multimedia Retrieval Technique Using Compressed Data
A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,
More informationEnvironmental Mapping by Trinocular Vision for Self-Localization Using Monocular Vision
OS3-3 Envronmental Mappng by rnocular Vson for Self-Localzaton Usng Monocular Vson Yoo OGAWA, Nobutaa SHIMADA, Yosha SHIRAI Rtsumean Unversty, 1-1-1 No-hgash, Kusatu, Shga, Japan he hrd Jont Worshop on
More informationReducing Frame Rate for Object Tracking
Reducng Frame Rate for Object Trackng Pavel Korshunov 1 and We Tsang Oo 2 1 Natonal Unversty of Sngapore, Sngapore 11977, pavelkor@comp.nus.edu.sg 2 Natonal Unversty of Sngapore, Sngapore 11977, oowt@comp.nus.edu.sg
More informationLarge Motion Estimation for Omnidirectional Vision
Large Moton Estmaton for Omndrectonal Vson Jong Weon Lee, Suya You, and Ulrch Neumann Computer Scence Department Integrated Meda Systems Center Unversty of Southern Calforna Los Angeles, CA 98978, USA
More informationFitting and Alignment
Fttng and Algnment Computer Vson Ja-Bn Huang, Vrgna Tech Many sldes from S. Lazebnk and D. Hoem Admnstratve Stuffs HW 1 Competton: Edge Detecton Submsson lnk HW 2 wll be posted tonght Due Oct 09 (Mon)
More informationMulti-stable Perception. Necker Cube
Mult-stable Percepton Necker Cube Spnnng dancer lluson, Nobuuk Kaahara Fttng and Algnment Computer Vson Szelsk 6.1 James Has Acknowledgment: Man sldes from Derek Hoem, Lana Lazebnk, and Grauman&Lebe 2008
More informationy and the total sum of
Lnear regresson Testng for non-lnearty In analytcal chemstry, lnear regresson s commonly used n the constructon of calbraton functons requred for analytcal technques such as gas chromatography, atomc absorpton
More informationTN348: Openlab Module - Colocalization
TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages
More informationLobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide
Lobachevsky State Unversty of Nzhn Novgorod Polyhedron Quck Start Gude Nzhn Novgorod 2016 Contents Specfcaton of Polyhedron software... 3 Theoretcal background... 4 1. Interface of Polyhedron... 6 1.1.
More informationA high precision collaborative vision measurement of gear chamfering profile
Internatonal Conference on Advances n Mechancal Engneerng and Industral Informatcs (AMEII 05) A hgh precson collaboratve vson measurement of gear chamferng profle Conglng Zhou, a, Zengpu Xu, b, Chunmng
More informationLine-based Camera Movement Estimation by Using Parallel Lines in Omnidirectional Video
01 IEEE Internatonal Conference on Robotcs and Automaton RverCentre, Sant Paul, Mnnesota, USA May 14-18, 01 Lne-based Camera Movement Estmaton by Usng Parallel Lnes n Omndrectonal Vdeo Ryosuke kawansh,
More informationUAV global pose estimation by matching forward-looking aerial images with satellite images
The 2009 IEEE/RSJ Internatonal Conference on Intellgent Robots and Systems October -5, 2009 St. Lous, USA UAV global pose estmaton by matchng forward-lookng aeral mages wth satellte mages Kl-Ho Son, Youngbae
More informationDetection of an Object by using Principal Component Analysis
Detecton of an Object by usng Prncpal Component Analyss 1. G. Nagaven, 2. Dr. T. Sreenvasulu Reddy 1. M.Tech, Department of EEE, SVUCE, Trupath, Inda. 2. Assoc. Professor, Department of ECE, SVUCE, Trupath,
More informationHermite Splines in Lie Groups as Products of Geodesics
Hermte Splnes n Le Groups as Products of Geodescs Ethan Eade Updated May 28, 2017 1 Introducton 1.1 Goal Ths document defnes a curve n the Le group G parametrzed by tme and by structural parameters n the
More informationDistance Calculation from Single Optical Image
17 Internatonal Conference on Mathematcs, Modellng and Smulaton Technologes and Applcatons (MMSTA 17) ISBN: 978-1-6595-53-8 Dstance Calculaton from Sngle Optcal Image Xao-yng DUAN 1,, Yang-je WEI 1,,*
More informationImage Fusion With a Dental Panoramic X-ray Image and Face Image Acquired With a KINECT
Image Fuson Wth a Dental Panoramc X-ray Image and Face Image Acqured Wth a KINECT Kohe Kawa* 1, Koch Ogawa* 1, Aktosh Katumata* 2 * 1 Graduate School of Engneerng, Hose Unversty * 2 School of Dentstry,
More informationDelayed Features Initialization for Inverse Depth Monocular SLAM
Delayed Features Intalzaton for Inverse Depth Monocular SLAM Rodrgo Mungua and Anton Grau Department of Automatc Control, Techncal Unversty of Catalona, UPC c/ Pau Gargallo, 5 E-0808 Barcelona, Span, {rodrgo.mungua;anton.grau}@upc.edu
More informationImage Alignment CSC 767
Image Algnment CSC 767 Image algnment Image from http://graphcs.cs.cmu.edu/courses/15-463/2010_fall/ Image algnment: Applcatons Panorama sttchng Image algnment: Applcatons Recognton of object nstances
More informationMULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION
MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and
More informationMulti-view 3D Position Estimation of Sports Players
Mult-vew 3D Poston Estmaton of Sports Players Robbe Vos and Wlle Brnk Appled Mathematcs Department of Mathematcal Scences Unversty of Stellenbosch, South Afrca Emal: vosrobbe@gmal.com Abstract The problem
More informationFeature-Area Optimization: A Novel SAR Image Registration Method
Feature-Area Optmzaton: A Novel SAR Image Regstraton Method Fuqang Lu, Fukun B, Lang Chen, Hao Sh and We Lu Abstract Ths letter proposes a synthetc aperture radar (SAR) mage regstraton method named Feature-Area
More informationAccounting for the Use of Different Length Scale Factors in x, y and z Directions
1 Accountng for the Use of Dfferent Length Scale Factors n x, y and z Drectons Taha Soch (taha.soch@kcl.ac.uk) Imagng Scences & Bomedcal Engneerng, Kng s College London, The Rayne Insttute, St Thomas Hosptal,
More informationContours Planning and Visual Servo Control of XXY Positioning System Using NURBS Interpolation Approach
Inventon Journal of Research Technology n Engneerng & Management (IJRTEM) ISSN: 2455-3689 www.jrtem.com olume 1 Issue 4 ǁ June. 2016 ǁ PP 16-23 Contours Plannng and sual Servo Control of XXY Postonng System
More informationAIMS Computer vision. AIMS Computer Vision. Outline. Outline.
AIMS Computer Vson 1 Matchng, ndexng, and search 2 Object category detecton 3 Vsual geometry 1/2: Camera models and trangulaton 4 Vsual geometry 2/2: Reconstructon from multple vews AIMS Computer vson
More informationProgramming in Fortran 90 : 2017/2018
Programmng n Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Exercse 1 : Evaluaton of functon dependng on nput Wrte a program who evaluate the functon f (x,y) for any two user specfed values
More informationFrom: AAAI-82 Proceedings. Copyright 1982, AAAI ( All rights reserved.
From: AAAI-82 Proceedngs. Copyrght 1982, AAAI (www.aaa.org). All rghts reserved. TRACKING KNOWN THREE-DIMENSIONAL OBJECTS* Donald B. Gennery Robotcs and Teleoperator Group Jet Propulson Laboratory Pasadena,
More informationRELATIVE ORIENTATION ESTIMATION OF VIDEO STREAMS FROM A SINGLE PAN-TILT-ZOOM CAMERA. Commission I, WG I/5
RELATIVE ORIENTATION ESTIMATION OF VIDEO STREAMS FROM A SINGLE PAN-TILT-ZOOM CAMERA Taeyoon Lee a, *, Taeung Km a, Gunho Sohn b, James Elder a a Department of Geonformatc Engneerng, Inha Unersty, 253 Yonghyun-dong,
More informationVanishing Hull. Jinhui Hu, Suya You, Ulrich Neumann University of Southern California {jinhuihu,suyay,
Vanshng Hull Jnhu Hu Suya You Ulrch Neumann Unversty of Southern Calforna {jnhuhusuyay uneumann}@graphcs.usc.edu Abstract Vanshng ponts are valuable n many vson tasks such as orentaton estmaton pose recovery
More informationA Comparison and Evaluation of Three Different Pose Estimation Algorithms In Detecting Low Texture Manufactured Objects
Clemson Unversty TgerPrnts All Theses Theses 12-2011 A Comparson and Evaluaton of Three Dfferent Pose Estmaton Algorthms In Detectng Low Texture Manufactured Objects Robert Krener Clemson Unversty, rkrene@clemson.edu
More information3D vector computer graphics
3D vector computer graphcs Paolo Varagnolo: freelance engneer Padova Aprl 2016 Prvate Practce ----------------------------------- 1. Introducton Vector 3D model representaton n computer graphcs requres
More informationLearning the Kernel Parameters in Kernel Minimum Distance Classifier
Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department
More informationA Probabilistic Approach to Detect Urban Regions from Remotely Sensed Images Based on Combination of Local Features
A Probablstc Approach to Detect Urban Regons from Remotely Sensed Images Based on Combnaton of Local Features Berl Sırmaçek German Aerospace Center (DLR) Remote Sensng Technology Insttute Weßlng, 82234,
More informationLecture 5: Multilayer Perceptrons
Lecture 5: Multlayer Perceptrons Roger Grosse 1 Introducton So far, we ve only talked about lnear models: lnear regresson and lnear bnary classfers. We noted that there are functons that can t be represented
More informationProblem Definitions and Evaluation Criteria for Computational Expensive Optimization
Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty
More informationThe Codesign Challenge
ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.
More informationReal-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input
Real-tme Jont Tracng of a Hand Manpulatng an Object from RGB-D Input Srnath Srdhar 1 Franzsa Mueller 1 Mchael Zollhöfer 1 Dan Casas 1 Antt Oulasvrta 2 Chrstan Theobalt 1 1 Max Planc Insttute for Informatcs
More informationLecture 9 Fitting and Matching
In ths lecture, we re gong to talk about a number of problems related to fttng and matchng. We wll formulate these problems formally and our dscusson wll nvolve Least Squares methods, RANSAC and Hough
More informationFace Recognition University at Buffalo CSE666 Lecture Slides Resources:
Face Recognton Unversty at Buffalo CSE666 Lecture Sldes Resources: http://www.face-rec.org/algorthms/ Overvew of face recognton algorthms Correlaton - Pxel based correspondence between two face mages Structural
More informationSupport Vector Machines
/9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.
More informationResolving Ambiguity in Depth Extraction for Motion Capture using Genetic Algorithm
Resolvng Ambguty n Depth Extracton for Moton Capture usng Genetc Algorthm Yn Yee Wa, Ch Kn Chow, Tong Lee Computer Vson and Image Processng Laboratory Dept. of Electronc Engneerng The Chnese Unversty of
More informationVideo Object Tracking Based On Extended Active Shape Models With Color Information
CGIV'2002: he Frst Frst European Conference Colour on Colour n Graphcs, Imagng, and Vson Vdeo Object rackng Based On Extended Actve Shape Models Wth Color Informaton A. Koschan, S.K. Kang, J.K. Pak, B.
More informationComputer Animation and Visualisation. Lecture 4. Rigging / Skinning
Computer Anmaton and Vsualsaton Lecture 4. Rggng / Sknnng Taku Komura Overvew Sknnng / Rggng Background knowledge Lnear Blendng How to decde weghts? Example-based Method Anatomcal models Sknnng Assume
More informationA Robust Method for Estimating the Fundamental Matrix
Proc. VIIth Dgtal Image Computng: Technques and Applcatons, Sun C., Talbot H., Ourseln S. and Adraansen T. (Eds.), 0- Dec. 003, Sydney A Robust Method for Estmatng the Fundamental Matrx C.L. Feng and Y.S.
More informationReal-time Motion Capture System Using One Video Camera Based on Color and Edge Distribution
Real-tme Moton Capture System Usng One Vdeo Camera Based on Color and Edge Dstrbuton YOSHIAKI AKAZAWA, YOSHIHIRO OKADA, AND KOICHI NIIJIMA Graduate School of Informaton Scence and Electrcal Engneerng,
More informationAVO Modeling of Monochromatic Spherical Waves: Comparison to Band-Limited Waves
AVO Modelng of Monochromatc Sphercal Waves: Comparson to Band-Lmted Waves Charles Ursenbach* Unversty of Calgary, Calgary, AB, Canada ursenbach@crewes.org and Arnm Haase Unversty of Calgary, Calgary, AB,
More informationAssignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009.
Farrukh Jabeen Algorthms 51 Assgnment #2 Due Date: June 15, 29. Assgnment # 2 Chapter 3 Dscrete Fourer Transforms Implement the FFT for the DFT. Descrbed n sectons 3.1 and 3.2. Delverables: 1. Concse descrpton
More informationOutline. Type of Machine Learning. Examples of Application. Unsupervised Learning
Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton
More informationAn Entropy-Based Approach to Integrated Information Needs Assessment
Dstrbuton Statement A: Approved for publc release; dstrbuton s unlmted. An Entropy-Based Approach to ntegrated nformaton Needs Assessment June 8, 2004 Wllam J. Farrell Lockheed Martn Advanced Technology
More informationAngle-Independent 3D Reconstruction. Ji Zhang Mireille Boutin Daniel Aliaga
Angle-Independent 3D Reconstructon J Zhang Mrelle Boutn Danel Alaga Goal: Structure from Moton To reconstruct the 3D geometry of a scene from a set of pctures (e.g. a move of the scene pont reconstructon
More information3D Modeling Using Multi-View Images. Jinjin Li. A Thesis Presented in Partial Fulfillment of the Requirements for the Degree Master of Science
3D Modelng Usng Mult-Vew Images by Jnjn L A Thess Presented n Partal Fulfllment of the Requrements for the Degree Master of Scence Approved August by the Graduate Supervsory Commttee: Lna J. Karam, Char
More informationFeature Reduction and Selection
Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components
More informationDetection of hand grasping an object from complex background based on machine learning co-occurrence of local image feature
Detecton of hand graspng an object from complex background based on machne learnng co-occurrence of local mage feature Shnya Moroka, Yasuhro Hramoto, Nobutaka Shmada, Tadash Matsuo, Yoshak Shra Rtsumekan
More informationX- Chart Using ANOM Approach
ISSN 1684-8403 Journal of Statstcs Volume 17, 010, pp. 3-3 Abstract X- Chart Usng ANOM Approach Gullapall Chakravarth 1 and Chaluvad Venkateswara Rao Control lmts for ndvdual measurements (X) chart are
More informationDynamic wetting property investigation of AFM tips in micro/nanoscale
Dynamc wettng property nvestgaton of AFM tps n mcro/nanoscale The wettng propertes of AFM probe tps are of concern n AFM tp related force measurement, fabrcaton, and manpulaton technques, such as dp-pen
More informationLecture #15 Lecture Notes
Lecture #15 Lecture Notes The ocean water column s very much a 3-D spatal entt and we need to represent that structure n an economcal way to deal wth t n calculatons. We wll dscuss one way to do so, emprcal
More informationAccelerating X-Ray data collection using Pyramid Beam ray casting geometries
Acceleratng X-Ray data collecton usng Pyramd Beam ray castng geometres Amr Averbuch Guy Lfchtz Y. Shkolnsky 3 School of Computer Scence Department of Appled Mathematcs, School of Mathematcal Scences Tel
More informationObject Recognition Based on Photometric Alignment Using Random Sample Consensus
Vol. 44 No. SIG 9(CVIM 7) July 2003 3 attached shadow photometrc algnment RANSAC RANdom SAmple Consensus Yale Face Database B RANSAC Object Recognton Based on Photometrc Algnment Usng Random Sample Consensus
More informationAccuracy of Measuring Camera Position by Marker Observation
J. Software Engneerng & Applcatons, 2010, 3, 906-913 do:10.4236/jsea.2010.310107 Publshed Onlne October 2010 (http://www.scrp.org/journal/jsea) Accuracy of Measurng Camera Poston by Marker Observaton Vladmr
More informationModule 6: FEM for Plates and Shells Lecture 6: Finite Element Analysis of Shell
Module 6: FEM for Plates and Shells Lecture 6: Fnte Element Analyss of Shell 3 6.6. Introducton A shell s a curved surface, whch by vrtue of ther shape can wthstand both membrane and bendng forces. A shell
More informationAn Image Fusion Approach Based on Segmentation Region
Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua
More informationSubspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;
Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features
More informationn others; multple brghtness values n one mage may map to a sngle brghtness value n the other mage, and vce versa. In other words, the two mages are us
Robust Mult-Sensor Image Algnment Mchal Iran Dept. of Appled Math and CS The Wezmann Insttute of Scence 76100 Rehovot, Israel P. Anandan Mcrosoft Corporaton One Mcrosoft Way Redmond, WA 98052, USA Abstract
More informationSimultaneous Object Pose and Velocity Computation Using a Single View from a Rolling Shutter Camera
Smultaneous Object Pose and Velocty Computaton Usng a Sngle Vew from a Rollng Shutter Camera Omar At-Ader, Ncolas Andreff, Jean Marc Lavest, and Phlppe Martnet Unversté Blase Pascal Clermont Ferrand, LASMEA
More information2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements
Module 3: Element Propertes Lecture : Lagrange and Serendpty Elements 5 In last lecture note, the nterpolaton functons are derved on the bass of assumed polynomal from Pascal s trangle for the fled varable.
More informationProf. Feng Liu. Spring /24/2017
Prof. Feng Lu Sprng 2017 ttp://www.cs.pd.edu/~flu/courses/cs510/ 05/24/2017 Last me Compostng and Mattng 2 oday Vdeo Stablzaton Vdeo stablzaton ppelne 3 Orson Welles, ouc of Evl, 1958 4 Images courtesy
More informationFace Tracking Using Motion-Guided Dynamic Template Matching
ACCV2002: The 5th Asan Conference on Computer Vson, 23--25 January 2002, Melbourne, Australa. Face Trackng Usng Moton-Guded Dynamc Template Matchng Lang Wang, Tenu Tan, Wemng Hu atonal Laboratory of Pattern
More informationHierarchical clustering for gene expression data analysis
Herarchcal clusterng for gene expresson data analyss Gorgo Valentn e-mal: valentn@ds.unm.t Clusterng of Mcroarray Data. Clusterng of gene expresson profles (rows) => dscovery of co-regulated and functonally
More informationColor in OpenGL Polygonal Shading Light Source in OpenGL Material Properties Normal Vectors Phong model
Color n OpenGL Polygonal Shadng Lght Source n OpenGL Materal Propertes Normal Vectors Phong model 2 We know how to rasterze - Gven a 3D trangle and a 3D vewpont, we know whch pxels represent the trangle
More informationOutline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1
4/14/011 Outlne Dscrmnatve classfers for mage recognton Wednesday, Aprl 13 Krsten Grauman UT-Austn Last tme: wndow-based generc obect detecton basc ppelne face detecton wth boostng as case study Today:
More informationRecognizing Faces. Outline
Recognzng Faces Drk Colbry Outlne Introducton and Motvaton Defnng a feature vector Prncpal Component Analyss Lnear Dscrmnate Analyss !"" #$""% http://www.nfotech.oulu.f/annual/2004 + &'()*) '+)* 2 ! &
More informationComparison of traveltime inversions on a limestone structure
Comparson of traveltme nversons on a lmestone structure Comparson of traveltme nversons on a lmestone structure Matthew D. Allen and Robert R. Stewart ABSRAC Four traveltme nverson technques were appled
More informationRobot Navigation Using 1D Panoramic Images
In 26 IEEE Intl. Conference on Robotcs and Automaton (ICRA 26), Orlando, FL, May 26 Robot Navgaton Usng 1D Panoramc Images Amy Brggs Yunpeng L Danel Scharsten Matt Wlder Dept. of Computer Scence, Mddlebury
More informationImage Matching Algorithm based on Feature-point and DAISY Descriptor
JOURNAL OF MULTIMEDIA, VOL. 9, NO. 6, JUNE 2014 829 Image Matchng Algorthm based on Feature-pont and DAISY Descrptor L L School of Busness, Schuan Agrcultural Unversty, Schuan Dujanyan 611830, Chna Abstract
More informationClassifier Swarms for Human Detection in Infrared Imagery
Classfer Swarms for Human Detecton n Infrared Imagery Yur Owechko, Swarup Medasan, and Narayan Srnvasa HRL Laboratores, LLC 3011 Malbu Canyon Road, Malbu, CA 90265 {owechko, smedasan, nsrnvasa}@hrl.com
More information