Improving 2D Reactive Navigators with Kinect
|
|
- Mabel Rogers
- 5 years ago
- Views:
Transcription
1 Improving 2D Reacive Navigaors wih Kinec Javier Gonzalez-Jimenez, J.R. Ruiz-Sarmieno, and Cipriano Galindo Sysem Enginnering and Auomaion Dp., Malaga, Spain {javiergonzalez, joaraul, Keywords: Absrac: Kinec, Reacive Navigaion, Obsacle Deecion, Mobile Robo. Mos successful mobile robos rely on 2D radial laser scanners for perceiving he environmen. The use of hese sensors for reacive navigaion has a serious limiaion: he robo can only deec obsacles in he plane scanned by he sensor, wih he consequen risk of collision wih objecs ou of his plane. The recen commercializaion of RGB-D cameras, like Kinec, opens new possibiliies in his respec. In his paper we address he maer of adding he 3D informaion provided by hese cameras o a reacive navigaor designed o work wih radial laser scanners. We experimenally analyze he suiabiliy of Kinec o deec small objecs and propose a simple bu effecive mehod o combine readings from boh ype of sensors as well as o overcome some of he drawbacks ha Kinec presens. Experimens wih a real robo and a paricular reacive algorihm have been conduced, proving a significan upgrade in performance. INTRODUCTION Mos successful mobile robos rely on 2D radial laser scanners for perceiving he environmen and on a hybrid navigaion approach (Fiorini and Shiller, 988), including a reacive algorihm o deal wih obsacle avoidance (Blanco e al., 2008). The usage of 2D scanners for reacive navigaion bears a serious limiaion: he robo can only deec obsacles on he plane scanned by he sensor, ypically a plane parallel o he floor. Obviously, his enails a collision risk wih objecs a a differen heigh or wih salien pars. Such a limiaion can only be ackled by gahering 3D informaion of he robo s surrounding from a hree-dimensional fieldof-view. Pas soluions for obaining 3D daa includes he so-called acuaed laser range finders (alrf), which are expensive and no quick enough for mobile robo navigaion purposes (Holz e al., 2008, Marder-Eppsein e al., 200). Nowadays, his hurdle can be overcome by RGB-D cameras, like Kinec (Kinec, 203). Kinec has been developed by Microsof as a naural inerface for videogames. Addiionally, i presens cerain feaures ha urn i ino an aracive device for mobile roboics: I is a compac and lighweigh sensor which provides boh RGB and range images. I is fas, working a a frequency of 30 Hz. The operaion range is accepable for indoor applicaions: from 0.5 o 3.5m. I is cheap: around 50 nowadays. Wih he aim of improving he reacive navigaion capabiliies of a mobile robo, in his work we address he problem of replacing (or enhancing) a radial laser scanner which feeds a reacive navigaor wih a Kinec sensor. I is imporan o remark ha our ineres is no in he modificaion of he reacive algorihm, bu in adaping he Kinec deph image in order o provide he navigaion algorihm wih a virual 2D scan, encapsulaing he 3D world informaion. For such a goal, wo major drawbacks need o be overcome. On he one hand, he deph image of Kinec, which has a resoluion of 640x480 pixels, needs o be effecively condensed in a 2D scan forma, losing as less meaningful informaion as possible for he moion algorihm. On he oher hand, Kinec has a large blind zone, boh in angle (i.e. narrow field-of-view) and for shor disances. For a soluion o hese problems we propose a wo-seps posprocesing of he Kinec daa:
2 Figure. Kinec sensor and coordinae sysem (aken from (Garcia and Zalevsky, 2008)). i) The range image can be seen as he oupu of 480 radial scanners heading o differen il angles. We simplify ha informaion by projecing he perceived obsacles around he robo on a virual horizonal scanning plane. ii) A shor-erm memory of sensed obsacles is implemened such ha unobserved obsacles lying in he blind zone of he sensor are incorporaed ino he virual scan. Alhough here are some works ha use Kinec as an inpu sensor for reacive navigaion (see for example (Cunha e al., 20, Biswas and Veloso, 20)), o he bes knowledge of he auhors he commened drawbacks have no been explicily addressed. In order o es he suiabiliy of he proposed approach, a se of experimens has been conduced wihin cluered scenarios. The experimens have validaed he improvemen in performance of a paricular reacive navigaor (Blanco e al., 2008), hough he soluion presened here can be applied o any oher reacive algorihm ha uilizes a 2D represenaion of he space, i.e. only relying on 2D laser scanners. Nex secion gives a descripion of he Kinec device. Secion III presens he proposed soluion for he usage of Kinec as an addiional inpu sensor for any reacive navigaion algorihm based on a 2D obsacle represenaion. In secion IV resuls from he conduced experimens are presened and discussed. Finally, some conclusions are oulined. 2 THE KINECT SENSOR 2. Descripion The Kinec device (see figure ) is equipped wih an RGB camera, a deph sensor, a marix of microphones, a moorized base which endows he sensor wih a il movemen of 27º, and a 3-axis acceleromeer. Focusing on he deph sensor, also called range camera, i is composed of an infrared ligh projecor combined wih a monochrome CMOS sensor. I has a VGA resoluion (640x480 pixels) wih -bi resoluion deph, and a daa refresh raio of 30 Hz. Is nominal field of view is 58º in he horizonal plane and 45º in he verical one. The operaional range repored by he manufacurer is from.2 m. o 3.5, hough in our experimens we have esed ha he sensor is able o deec objecs placed a 0.5 m. (see secion 2.3). 2.2 Working Principle of he Range Camera The range camera of Kinec consiss of wo devices: an infrared (IR) ligh projecor which cass a paern of poins ono he scene and a sandard CMOS monochrome sensor (IR camera) (Freedman e al., 200). Boh are aligned along he X axis, wih parallel opical axis separaed a disance (baseline) of 75mm (see figure ). This configuraion eases he compuaion of he range image, which is performed hrough he riangulaion beween he IR rays and heir corresponding do projecions ono he image. The mehod o compue he correspondence beween rays and pixels relies on innovaive echnique called Ligh Coding (Garcia and Zalevsky, 2008), paened by PrimeSense (PrimeSense, 203), which enails a very paricular facory calibraion. In his calibraion, a se of images of he poin paern, as projeced on a planar surface a differen known disances, are sored in he sensor. These are he socalled reference images. Kinec works like a correlaion-based sereo sysem wih an ideal configuraion (i.e. idenical cameras, aligned axes separaed along he X axis) where he IR rays are virually replaced by line-ofsigh of he poins in he reference images. As in sereo, deph a each image poin is derived from is dispariy along he X axis, which is compued by correlaing a small window over he reference image. Furher informaion abou his calculaion can be found in (Khoshelham, 20). Regarding he accuracy of his mehod, he disance errors are lower han 2 cm. for close objecs (up o 2m.), linearly increasing unil an average error of 0 cm. a 4m.
3 Legend Objec deeced Objec no deeced No measuremens available Cenral measures Cenral measures Figure 2. Resuls for he small obsacle deecion experimen. The verical axis represens he 6 cenral columns of he range image. The horizonal axis is he disance, discreized ino inervals of 5 cm., from Kinec o he sick horizonally placed in fron of he robo. Each cell encodes wheher he sick was deeced a any of he image rows considered. Figure 3. Experimen seup o es he visual acuiy of Kinec for deecing small obsacle. In his paricular case, he obsacle is a horizonal sick wih a hickness of 4 cm. 2.3 Kinec Reliabiliy for Deecing Thin Obsacles To assess how much reliable Kinec is o feed a robo reacive navigaion sysem, i is of ineres o analyze is capaciy o deec surrounding obsacles, paricularly hose ha are hardly deecable by oher sensors, eiher because of heir small size or because of heir posiion in he scene, e.g. he salien board of a able, he legs of a chairs, coa sands, ec. We have performed a number of experimens where sicks of differen hickness (, 2, and 4 cm.) were horizonally placed in fron of he sensor, a a cerain heigh, verifying wheher hey are deeced a differen disances. The experimens were conduced in a corridor wih he Kinec sensor mouned on a mobile robo (see figure 3). To exrac he meaningful daa for his analysis we only focused on a recangular window of he range image, concreely he 6 cenral columns of a small number of consecuive image rows a he heigh where he sick is expeced o be. We mus accoun for an inerval of rows since here is no guaranee ha he sick is observed in a single, fixed row during all he robo run. Noice ha, hough he sick is roughly horizonal, is projecion on he range image may cover differen rows and also may change from one posiion o anoher. Saring a a disance of 4 meers from he obsacle, he robo gradually moves owards i a discree incremens, while recording range images as well as he robo odomery a each posiion. This experimen was repeaed 5 imes for each hickness (, 2, and 4 cm.). Figure 2 displays he resuls of wo of hese robo runs, for he and 2cm. sick. I is ineresing o see
4 how he 2cm.-hick sick was almos always observed over he full operaional inerval (from 0.5 o 3.5 m.). The plo for he 4cm.-wide sick has been omied because i was always deeced. These resuls reveal he Kinec s poenial for deecing small obsacles up o an accepable disance. Noe how in he case of he obsacle of cm is deecion is no sable: hough i sars o be deeced a 2.3 m, i laer disappears because of he discree spaial sampling of he sensor. 3 KINECT AS INPUT SENSOR OF A 2D REACTIVE NAVIGATOR In general, he use of Kinec o feed a reacive navigaor based on a 2D space represenaion presens wo difficulies: i) he huge amoun of daa i provides, and ii) he exisence of a blind zone boh a shor disance and because of he narrow horizonal field-of-view (in comparison o laser radial scanners). Our soluion o overcome hese issues consiss of a pos-processing sage o convenienly adap he daa o he specific needs of he reacive navigaor, which may also receive sensorial informaion from oher sources, e.g. a 2D laser scanner (see figure 4). The firs sep of such a pos-processing sage aims a reducing he huge amoun of daa while keeping he relevan 3D sensorial informaion abou obsacles. A second phase srives for coping wih he problem of he blind zone by creaing a shor-erm memory which emporally recalls he perceived obsacles around he robo. This memory is hen ransformed o a scan forma suiable o be exploied by he reacive navigaor. Nex, hese processes are described. 3. Projecion of he Poin Cloud o 2D The Kinec sensor provides more han measures per frame a 30Hz. This inense flow of daa provides he robo wih very valuable informaion abou he surrounding bu enails wo problems for a reacive navigaor: Firs, i becomes a significan compuaional burden ha could hamper he robo o concurrenly execue oher asks, e.g. robo localizaion, mapping, ec. Second, hese daa canno be direcly exploied by convenional robo reacive algorihms designed o be fed wih 2D scans, such as Virual Force Field (Borensein and Koren, 989), Nearness diagram (Minguez and Monano, 2004), PTG-based navigaor (Blanco e al., 2008), ec. Our approach o overcome hese wo problems consiss in condensing he 3D Kinec daa ino a 2D scan by selecing he minimum measured disance from each column of he range image. This is a simple and efficien procedure whose resuls is a virual scan of 640 ranges (he number of columns in he image) ha capures he closes obsacle poin for all he differen heighs (image rows), as shown figure 5. Please, noice ha, by exracing a virual scan for differen heigh inervals, his soluion could cope wih robos wih varying polygonal secions. The soluion implemened in his work, hereby, is a paricular case of his general approach. 3.2 Shor Term Memory A serious limiaion of Kinec is is inabiliy o deec close objecs, boh below is minimum operaional range and ou of he field-of-view (FOV). The minimum range depends on he surface color and maerial, and is ypically beween 0.5 and m., while he horizonal and verical FOV are 58 and 45 degrees, respecively. This blind zone becomes a serious drawback for a reacive navigaor, since when he robo approaches an obsacle (boh wih roaional or ranslaional movemens) i suddenly disappears and he space becomes obsacle-free, causing he robo o crash ino i. To overcome his problem we propose a shor-erm memory around he robo locaion which mainains previous measuremens emporally. Such a memory has been implemened hrough a grid, similarly o an occupancy map (see figure 6), which is formalized as follows. Kinec Laser scanner 3D obsacle projecion in 2D Shor erm memory Virual scan Scanner simulaion Obsacle Grid Map Robo Localizaion Reacive Navigaor Figure 4. General diagram of he proposed sysem o combine daa from a laser scanner and a Kinec sensor o feed a reacive navigaor.
5 Z Y Z X Figure 5. Lef, image of he scene capured by he RGB camera. Middle, op view of he scene perceived by he range camera. Righ, laeral view of he same scene. The green poins correspond o discarded measuremens, and he blue ones are hose considered for he virual scan Memory A shor-erm memory M is defined as an n x m marix, which discreizes a cerain bi-dimensional area around he robo. Le M(j) represen he probabiliy of he cell c j o be occupied by an obsacle, based on he observaions, o,, o k, of he robo, ha is: Robo M (, i j) p( c o,..., o ) () j For he calculaion of such a probabiliy i is convenien o use he so-called log-odds (refer o (Thrun, 2003) for furher deail), which requires he compuaion, for each c j a ime, of he expression: pc ( o,..., o) j k ( j) log pc ( jo,..., ok ) l c The memory cells are iniialized wih he value: l pc ( ) 0 j ( c j) log p ( c j ) k (2) (3) where p(c j ) has been se o 0.5. Given l i is possible o rerieve he probabiliy of each cell as: pc ( o,..., o) e j k l ( c i, j ) (4) and from ha, we creae an obsacle map by considering ha a cell c j is occupied if is probabiliy is above a given hreshold. To feed he reacive navigaor, a scanner simulaor convers his obsacle grid map ino a scan forma. Sensor blind zone Robo Observaion in k Figure 6. Shor-erm memory a ime k. The memory sores a se of previous sensor measuremens ino a grid. Righ, he obsacles considered by he reacive navigaor are formed by he inegraion of poins from he blind zone (in red) and he curren virual scan (in blue), which is obained from he Kinec daa (in green) Memory updae Robo Obsacles aken ino accoun by he reacive navigaion algorihm in k Le o be a virual scan observaion derived from Kinec a ime. Le c k be he cell where he k-h measuremen of he scan lies, given he curren robo pose. Using he Bayes rule and log-odds, he updaing of he value l (c j ) as a consequence of a new scan o is performed hrough he following expression (see (Thrun, 2003)): cij ck, pc ( j o) pc (, ) i j l ( c j) l ( c j) log log pc ( o) pc ( ) j j (5)
6 Figure 7. Mobile robo SANCHO, equipped wih 2 Hokuyo laser scanners and a Kinec sensor for obsacle avoidance. where he a poseriori probabiliy pc ( j o ) is calculaed wih he Bayes rule using he following sensor model: 2 ( o d j) 2 po ( M, c j ) e 2 2 (6) where d,j is he disance o he cener of he cell c j. pc (, ) i j The erm log is a consan which pc ( j) depends on he seleced value of he a priori probabiliy pc ( j). Therefore, considering pc ( j) 0.5, he calculaion of he memory updae is simplified o: pc ( j o) ij k, ( j ) ( j ) log p ( c j o ) c c l c l c (7) Noice ha, according o his updae mechanism a cell requires persisen observaions o change from occupied o free, and viceversa. Also, noe ha non-observed cells are no updaed, i.e., hey keep heir values. 4 IMPLEMENTATION AND DISCUSSION The proposed approach has been implemened in he mobile robo SANCHO (Gonzalez e al, 2009) (see figure 7). The size of he shor-erm memory was se o 00 x 00 cells, for a 2 x 2m. area around he robo, i.e., wih a cell size of 2 cm. SANCHO, buil upon a commercial Pioneer 3DX base, is equipped wih wo Hokuyo laser scanners (Hokuyo, 203) placed a 30 cm. over he floor (scanning he fron and he rear of he robo) and a Kinec sensor in is fron upper par (see figure 7). The reacive navigaion sysem of SANCHO, called PTG-based navigaor, ransforms he 2D local obsacles in he 3D Configuraion Space of he robo ino he so-called Trajecory Parameer Spaces (TP-Spaces). A TP-Space is a 2D represenaion of all he poses he robo could reach if i moved according o a cerain pah model. Since several pah models are considered by he reacive sysem, several TP-Spaces are buil. The mahemaical ransformaion beween he C-Space and he TP- Spaces is done by Parameerized Trajecory Generaors or PTGs, each one represening a pah model (e.g. circular, urn&move-sraigh, ec.) ha fulfills cerain geomerical and opological properies. As a resul of his ransformaion he robo in he TP-space becomes a free-flying poin whose moion migh be solved by any holonomic obsacle avoidance, such as Virual Force Field (Borensein and Koren, 989) or Nearess Hisogram (Minguez and Monano, 2004). Please, refer o (Blanco e al., 2008) for a more deailed explanaion of he PTG-based navigaor. An ineresed feaure of he PTG-based navigaor is ha i can deal wih several sensors ha provide surrounding informaion simulaneously. When using only he wo radial laser scanners, SANCHO is prone o crash wih many unobserved objecs ha i may encouner in a ypical environmen, e.g. ables, chairs, boxes, plans, coa sands, shelves, ec. Afer incorporaed he Kinec sensor his problem has been drasically reduced, hough no compleely eliminaed. Since a precise quanificaion of he improvemen level of he proposed approach is no possible we have ried o validae he mehod wih wo differen ess. In he firs, we have repeaed a number of robo local navigaions, i.e. go from A o B, wih he wo sensing configuraions (wih and wihou Kinec) and varying he obsacles along he pah. Figure 8 shows one of hese seups in our lab, wih obsacles a differen heighs, including a papers box, he base of anoher robo, he board of a able, and a coa sand wih jackes. Some of he rajecories followed by he robo are shown in figure 9. The red one
7 5 CONCLUSIONS Figure 8. Scenario where some of he experimens were conduced. 4 3 In his paper we have presened mehods o convenienly adap he 3D informaion provided by a Kinec device o work wih a reacive navigaor designed o cope wih radial laser scanners. I has been proposed soluions for wo of he major Kinec drawbacks: he huge amoun of daa provided by he sensor, more han measures per frame a 30Hz, and is large blind zone due o boh is narrow field-of-view and he lower limi of is operaional range (from 0.5 o m., depending on he surface characerisics). We have experimenally demonsraed he Kinec poenial o deec small obsacles, a key aspec for safey during a reacive navigaion. Finally, a number of ess have been conduced, validaing he suiabiliy of he proposed mehods Figure 9. Pahs followed by he robo during four differen navigaions. The colored circles represen he iniial posiion of he robo, and he crosses correspond o he arge locaions. Black poins are obsacles deeced by he laser range finders. The recangles and circles have been added manually, and represen he obsacles undeeced by he laser scanners. Axis unis are meers. corresponds o he navigaion performed using only he radial laser scanners, which ends up wih he robo bumping ino he cardboard box. On he conrary, when using Kinec (he oher hree pahs), SANCHO manages o negoiae all he obsacles, so reaching he goal successfully. A second experimen has consised of robo SANCHO moving randomly for more han 20 hours (in sessions of around 2 hours) in he environmen represened in he map of figure 0. The reacive navigaion in his case was running as he lower par of a hybrid navigaional sysem wih a opological navigaion on op (Fernández-Madrigal e al., 2004). During all hese sessions SANCHO suffered 5 collisions: hree when passing doorways and 2 when making rapid urns. ACKNOWLEDGEMENTS This work has been suppored by wo projecs: GiraffPlus, funded by EU under conrac FP7 - ICT - #28873, and TAROTH: New developmens oward a robo a home, funded by he Spanish Governmen and he European Regional Developmen Fund ERDF under conrac DPI REFERENCES Biswas, J., Veloso, M., 20. Deph Camera based Localizaion and Navigaion for Indoor Mobile Robos. In RGB-D Workshop a RSS 20. Blanco, J.L., Gonzalez, J., Fernandez-Madrigal, J.A., Exending Obsacle Avoidance Mehods hrough Muliple Parameer-Space Transformaions. In Auonomous Robos, vol. 24 (). Borensein, J., Koren, Y., 989. Real-ime Obsacle Avoidance for Fas Mobile Robos. In IEEE Transacions on Sysems, Man, and Cyberneics, vol. 9, no. 5. Cunha, J., Pedrosa, E., Cruz, C., Neves, A., Lau, N., 20. Using a Deph Camera for Indoor Robo Localizaion and Navigaion. In RGB-D Workshop a RSS 20. Fernández-Madrigal, J.A., Galindo, C., González, J., Assisive navigaion of a roboic wheelchair using a mulihierarchical model of he environmen. In Inegraed Compuer-Aided Engineering vol., no. 4.
8 Figure 0. Topological and meric maps used in he second experimen mapping 6 rooms conneced by a large corridor. Red nodes represen opological locaions and blue lines he possible pahs beween hem. Orders o he robo were o navigae randomly beween nodes during periods of 2 hours. The meric map was used for localizaion purposes. Fiorin P., Shiller, Z., 988. Moion Planning in Dynamic Environmens using Velociy Obsacles. In The Inernaional Journal of Roboics Research, vol. 7, no. 7. Freedman, B., Shpun, A., Machline, M., Ariel Y., 200. Deph Mapping using Projeced Paerns. Paen No.: US 200/0823 A. Garcia, J., Zalevsky, Z., Range Mapping Using Speckle Decorrelaion. Paen No.: US 7,433,024 B2. Gonzalez, J., Galindo, C., Blanco, J.L., Fernandez- Madrigal, J.A., Arevalo, V., Moreno, F.A., SANCHO, a Fair Hos Robo. A Descripion. In IEEE Inernaional Conference on Mecharonics (ICM), Malaga, Spain. Holz, D., Lörken, C., Surmann H., Coninuous 3D Sensing for Navigaion and SLAM in Cluered and Dynamic Environmens. In Inernaional Conference on Informaion Fusion of he (FUSION). Cologne, Germany. Hokuyo: hp:// Kinec: hp:// Khoshelham, K., 20. Accuracy analysis of kinec deph daa. In ISPRS Workshop Laser Scanning, Calgary, Canada. Marder-Eppsein, E., Berger, E., Fooe, T., Gerkey, B., Konolige, K., 200. The Office Marahon: Robus navigaion in an indoor office environmen. In IEEE Inernaional Conference on Roboics and Auomaion (ICRA). Minguez, J., Monano, L., Nearness Diagram (ND) Navigaion: Collision Avoidance in Troublesome Scenarios. In IEEE Transacions on Roboics and Auomaion, vol.20, no.. PrimeSense: hp:// Thrun, S., Learning occupancy Grid Maps wih Forward Sensor models. Auonomous Robos, n. 5.
CAMERA CALIBRATION BY REGISTRATION STEREO RECONSTRUCTION TO 3D MODEL
CAMERA CALIBRATION BY REGISTRATION STEREO RECONSTRUCTION TO 3D MODEL Klečka Jan Docoral Degree Programme (1), FEEC BUT E-mail: xkleck01@sud.feec.vubr.cz Supervised by: Horák Karel E-mail: horak@feec.vubr.cz
More informationSTEREO PLANE MATCHING TECHNIQUE
STEREO PLANE MATCHING TECHNIQUE Commission III KEY WORDS: Sereo Maching, Surface Modeling, Projecive Transformaion, Homography ABSTRACT: This paper presens a new ype of sereo maching algorihm called Sereo
More informationMobile Robots Mapping
Mobile Robos Mapping 1 Roboics is Easy conrol behavior percepion modelling domain model environmen model informaion exracion raw daa planning ask cogniion reasoning pah planning navigaion pah execuion
More informationImproving Occupancy Grid FastSLAM by Integrating Navigation Sensors
Improving Occupancy Grid FasSLAM by Inegraing Navigaion Sensors Chrisopher Weyers Sensors Direcorae Air Force Research Laboraory Wrigh-Paerson AFB, OH 45433 Gilber Peerson Deparmen of Elecrical and Compuer
More informationA Matching Algorithm for Content-Based Image Retrieval
A Maching Algorihm for Conen-Based Image Rerieval Sue J. Cho Deparmen of Compuer Science Seoul Naional Universiy Seoul, Korea Absrac Conen-based image rerieval sysem rerieves an image from a daabase using
More informationSam knows that his MP3 player has 40% of its battery life left and that the battery charges by an additional 12 percentage points every 15 minutes.
8.F Baery Charging Task Sam wans o ake his MP3 player and his video game player on a car rip. An hour before hey plan o leave, he realized ha he forgo o charge he baeries las nigh. A ha poin, he plugged
More informationImplementing Ray Casting in Tetrahedral Meshes with Programmable Graphics Hardware (Technical Report)
Implemening Ray Casing in Terahedral Meshes wih Programmable Graphics Hardware (Technical Repor) Marin Kraus, Thomas Erl March 28, 2002 1 Inroducion Alhough cell-projecion, e.g., [3, 2], and resampling,
More informationVisual Indoor Localization with a Floor-Plan Map
Visual Indoor Localizaion wih a Floor-Plan Map Hang Chu Dep. of ECE Cornell Universiy Ihaca, NY 14850 hc772@cornell.edu Absrac In his repor, a indoor localizaion mehod is presened. The mehod akes firsperson
More informationImage segmentation. Motivation. Objective. Definitions. A classification of segmentation techniques. Assumptions for thresholding
Moivaion Image segmenaion Which pixels belong o he same objec in an image/video sequence? (spaial segmenaion) Which frames belong o he same video sho? (emporal segmenaion) Which frames belong o he same
More informationOptimal Crane Scheduling
Opimal Crane Scheduling Samid Hoda, John Hooker Laife Genc Kaya, Ben Peerson Carnegie Mellon Universiy Iiro Harjunkoski ABB Corporae Research EWO - 13 November 2007 1/16 Problem Track-mouned cranes move
More informationRobot localization under perceptual aliasing conditions based on laser reflectivity using particle filter
Robo localizaion under percepual aliasing condiions based on laser refleciviy using paricle filer DongXiang Zhang, Ryo Kurazume, Yumi Iwashia, Tsuomu Hasegawa Absrac Global localizaion, which deermines
More informationImproved TLD Algorithm for Face Tracking
Absrac Improved TLD Algorihm for Face Tracking Huimin Li a, Chaojing Yu b and Jing Chen c Chongqing Universiy of Poss and Telecommunicaions, Chongqing 400065, China a li.huimin666@163.com, b 15023299065@163.com,
More informationA Fast Stereo-Based Multi-Person Tracking using an Approximated Likelihood Map for Overlapping Silhouette Templates
A Fas Sereo-Based Muli-Person Tracking using an Approximaed Likelihood Map for Overlapping Silhouee Templaes Junji Saake Jun Miura Deparmen of Compuer Science and Engineering Toyohashi Universiy of Technology
More informationMOTION TRACKING is a fundamental capability that
TECHNICAL REPORT CRES-05-008, CENTER FOR ROBOTICS AND EMBEDDED SYSTEMS, UNIVERSITY OF SOUTHERN CALIFORNIA 1 Real-ime Moion Tracking from a Mobile Robo Boyoon Jung, Suden Member, IEEE, Gaurav S. Sukhame,
More informationA High-Speed Adaptive Multi-Module Structured Light Scanner
A High-Speed Adapive Muli-Module Srucured Ligh Scanner Andreas Griesser 1 Luc Van Gool 1,2 1 Swiss Fed.Ins.of Techn.(ETH) 2 Kaholieke Univ. Leuven D-ITET/Compuer Vision Lab ESAT/VISICS Zürich, Swizerland
More informationVideo Content Description Using Fuzzy Spatio-Temporal Relations
Proceedings of he 4s Hawaii Inernaional Conference on Sysem Sciences - 008 Video Conen Descripion Using Fuzzy Spaio-Temporal Relaions rchana M. Rajurkar *, R.C. Joshi and Sananu Chaudhary 3 Dep of Compuer
More informationDesign Alternatives for a Thin Lens Spatial Integrator Array
Egyp. J. Solids, Vol. (7), No. (), (004) 75 Design Alernaives for a Thin Lens Spaial Inegraor Array Hala Kamal *, Daniel V azquez and Javier Alda and E. Bernabeu Opics Deparmen. Universiy Compluense of
More informationLAMP: 3D Layered, Adaptive-resolution and Multiperspective Panorama - a New Scene Representation
Submission o Special Issue of CVIU on Model-based and Image-based 3D Scene Represenaion for Ineracive Visualizaion LAMP: 3D Layered, Adapive-resoluion and Muliperspecive Panorama - a New Scene Represenaion
More informationDynamic Route Planning and Obstacle Avoidance Model for Unmanned Aerial Vehicles
Volume 116 No. 24 2017, 315-329 ISSN: 1311-8080 (prined version); ISSN: 1314-3395 (on-line version) url: hp://www.ijpam.eu ijpam.eu Dynamic Roue Planning and Obsacle Avoidance Model for Unmanned Aerial
More informationNetwork management and QoS provisioning - QoS in Frame Relay. . packet switching with virtual circuit service (virtual circuits are bidirectional);
QoS in Frame Relay Frame relay characerisics are:. packe swiching wih virual circui service (virual circuis are bidirecional);. labels are called DLCI (Daa Link Connecion Idenifier);. for connecion is
More informationAn Adaptive Spatial Depth Filter for 3D Rendering IP
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, VOL.3, NO. 4, DECEMBER, 23 175 An Adapive Spaial Deph Filer for 3D Rendering IP Chang-Hyo Yu and Lee-Sup Kim Absrac In his paper, we presen a new mehod
More informationMOTION DETECTORS GRAPH MATCHING LAB PRE-LAB QUESTIONS
NME: TE: LOK: MOTION ETETORS GRPH MTHING L PRE-L QUESTIONS 1. Read he insrucions, and answer he following quesions. Make sure you resae he quesion so I don hae o read he quesion o undersand he answer..
More informationLow-Cost WLAN based. Dr. Christian Hoene. Computer Science Department, University of Tübingen, Germany
Low-Cos WLAN based Time-of-fligh fligh Trilaeraion Precision Indoor Personnel Locaion and Tracking for Emergency Responders Third Annual Technology Workshop, Augus 5, 2008 Worceser Polyechnic Insiue, Worceser,
More informationA METHOD OF MODELING DEFORMATION OF AN OBJECT EMPLOYING SURROUNDING VIDEO CAMERAS
A METHOD OF MODELING DEFORMATION OF AN OBJECT EMLOYING SURROUNDING IDEO CAMERAS Joo Kooi TAN, Seiji ISHIKAWA Deparmen of Mechanical and Conrol Engineering Kushu Insiue of Technolog, Japan ehelan@is.cnl.kuech.ac.jp,
More informationMATH Differential Equations September 15, 2008 Project 1, Fall 2008 Due: September 24, 2008
MATH 5 - Differenial Equaions Sepember 15, 8 Projec 1, Fall 8 Due: Sepember 4, 8 Lab 1.3 - Logisics Populaion Models wih Harvesing For his projec we consider lab 1.3 of Differenial Equaions pages 146 o
More informationCENG 477 Introduction to Computer Graphics. Modeling Transformations
CENG 477 Inroducion o Compuer Graphics Modeling Transformaions Modeling Transformaions Model coordinaes o World coordinaes: Model coordinaes: All shapes wih heir local coordinaes and sies. world World
More informationGauss-Jordan Algorithm
Gauss-Jordan Algorihm The Gauss-Jordan algorihm is a sep by sep procedure for solving a sysem of linear equaions which may conain any number of variables and any number of equaions. The algorihm is carried
More informationSLAM in Large Indoor Environments with Low-Cost, Noisy, and Sparse Sonars
SLAM in Large Indoor Environmens wih Low-Cos, Noisy, and Sparse Sonars Teddy N. Yap, Jr. and Chrisian R. Shelon Deparmen of Compuer Science and Engineering Universiy of California, Riverside, CA 92521,
More informationReinforcement Learning by Policy Improvement. Making Use of Experiences of The Other Tasks. Hajime Kimura and Shigenobu Kobayashi
Reinforcemen Learning by Policy Improvemen Making Use of Experiences of The Oher Tasks Hajime Kimura and Shigenobu Kobayashi Tokyo Insiue of Technology, JAPAN genfe.dis.iech.ac.jp, kobayasidis.iech.ac.jp
More informationRao-Blackwellized Particle Filtering for Probing-Based 6-DOF Localization in Robotic Assembly
MITSUBISHI ELECTRIC RESEARCH LABORATORIES hp://www.merl.com Rao-Blackwellized Paricle Filering for Probing-Based 6-DOF Localizaion in Roboic Assembly Yuichi Taguchi, Tim Marks, Haruhisa Okuda TR1-8 June
More information4.1 3D GEOMETRIC TRANSFORMATIONS
MODULE IV MCA - 3 COMPUTER GRAPHICS ADMN 29- Dep. of Compuer Science And Applicaions, SJCET, Palai 94 4. 3D GEOMETRIC TRANSFORMATIONS Mehods for geomeric ransformaions and objec modeling in hree dimensions
More informationCOSC 3213: Computer Networks I Chapter 6 Handout # 7
COSC 3213: Compuer Neworks I Chaper 6 Handou # 7 Insrucor: Dr. Marvin Mandelbaum Deparmen of Compuer Science York Universiy F05 Secion A Medium Access Conrol (MAC) Topics: 1. Muliple Access Communicaions:
More informationVoltair Version 2.5 Release Notes (January, 2018)
Volair Version 2.5 Release Noes (January, 2018) Inroducion 25-Seven s new Firmware Updae 2.5 for he Volair processor is par of our coninuing effors o improve Volair wih new feaures and capabiliies. For
More informationPoint Cloud Representation of 3D Shape for Laser- Plasma Scanning 3D Display
Poin Cloud Represenaion of 3D Shape for Laser- Plasma Scanning 3D Displa Hiroo Ishikawa and Hideo Saio Keio Universi E-mail {hiroo, saio}@ozawa.ics.keio.ac.jp Absrac- In his paper, a mehod of represening
More informationNEWTON S SECOND LAW OF MOTION
Course and Secion Dae Names NEWTON S SECOND LAW OF MOTION The acceleraion of an objec is defined as he rae of change of elociy. If he elociy changes by an amoun in a ime, hen he aerage acceleraion during
More informationVirtual Recovery of Excavated Archaeological Finds
Virual Recovery of Excavaed Archaeological Finds Jiang Yu ZHENG, Zhong Li ZHANG*, Norihiro ABE Kyushu Insiue of Technology, Iizuka, Fukuoka 820, Japan *Museum of he Terra-Coa Warrlors and Horses, Lin Tong,
More informationLocation. Electrical. Loads. 2-wire mains-rated. 0.5 mm² to 1.5 mm² Max. length 300 m (with 1.5 mm² cable). Example: Belden 8471
Produc Descripion Insallaion and User Guide Transiser Dimmer (454) The DIN rail mouned 454 is a 4channel ransisor dimmer. I can operae in one of wo modes; leading edge or railing edge. All 4 channels operae
More informationIn fmri a Dual Echo Time EPI Pulse Sequence Can Induce Sources of Error in Dynamic Magnetic Field Maps
In fmri a Dual Echo Time EPI Pulse Sequence Can Induce Sources of Error in Dynamic Magneic Field Maps A. D. Hahn 1, A. S. Nencka 1 and D. B. Rowe 2,1 1 Medical College of Wisconsin, Milwaukee, WI, Unied
More informationWORKSHOP SAFETY IN MOBILE APPLICATION
WORKSHOP SAFETY IN MOBILE APPLICATION Renaa Mondelaers Seven Bellens SICK SEW Cerified Funcional Safey Applicaion Exper Technology Leader Smar Facory CFSAE by SGS/TÜV Saar MOBILE APPLICATION AVAILABLE
More informationA time-space consistency solution for hardware-in-the-loop simulation system
Inernaional Conference on Advanced Elecronic Science and Technology (AEST 206) A ime-space consisency soluion for hardware-in-he-loop simulaion sysem Zexin Jiang a Elecric Power Research Insiue of Guangdong
More informationReal Time Integral-Based Structural Health Monitoring
Real Time Inegral-Based Srucural Healh Monioring The nd Inernaional Conference on Sensing Technology ICST 7 J. G. Chase, I. Singh-Leve, C. E. Hann, X. Chen Deparmen of Mechanical Engineering, Universiy
More informationA new algorithm for small object tracking based on super-resolution technique
A new algorihm for small objec racking based on super-resoluion echnique Yabunayya Habibi, Dwi Rana Sulisyaningrum, and Budi Seiyono Ciaion: AIP Conference Proceedings 1867, 020024 (2017); doi: 10.1063/1.4994427
More informationProbabilistic Detection and Tracking of Motion Discontinuities
Probabilisic Deecion and Tracking of Moion Disconinuiies Michael J. Black David J. Flee Xerox Palo Alo Research Cener 3333 Coyoe Hill Road Palo Alo, CA 94304 fblack,fleeg@parc.xerox.com hp://www.parc.xerox.com/fblack,fleeg/
More informationLarge-scale 3D Outdoor Mapping and On-line Localization using 3D-2D Matching
Large-scale 3D Oudoor Mapping and On-line Localizaion using 3D-D Maching Takahiro Sakai, Kenji Koide, Jun Miura, and Shuji Oishi Absrac Map-based oudoor navigaion is an acive research area in mobile robos
More informationMORPHOLOGICAL SEGMENTATION OF IMAGE SEQUENCES
MORPHOLOGICAL SEGMENTATION OF IMAGE SEQUENCES B. MARCOTEGUI and F. MEYER Ecole des Mines de Paris, Cenre de Morphologie Mahémaique, 35, rue Sain-Honoré, F 77305 Fonainebleau Cedex, France Absrac. In image
More informationImproving Accuracy of Inertial Measurement Units using Support Vector Regression
Improving Accuracy of Inerial Measuremen Unis using Suppor Vecor Regression Saran Ahuja, Wisi Jiraigalachoe, and Ar Tosborvorn Absrac Inerial measuremen uni (IMU) is a sensor ha measures acceleraion and
More informationStereo Vision Based Navigation of a Six-Legged Walking Robot in Unknown Rough Terrain
Sereo Vision Based Navigaion of a Six-Legged Walking Robo in Unknown Rough Terrain Anne Selzer, Heiko Hirschmüller, Marin Görner Absrac This paper presens a visual navigaion algorihm for he six-legged
More informationImage Based Computer-Aided Manufacturing Technology
Sensors & Transducers 03 by IFSA hp://www.sensorsporal.com Image Based Compuer-Aided Manufacuring Technology Zhanqi HU Xiaoqin ZHANG Jinze LI Wei LI College of Mechanical Engineering Yanshan Universiy
More informationDefinition and examples of time series
Definiion and examples of ime series A ime series is a sequence of daa poins being recorded a specific imes. Formally, le,,p be a probabiliy space, and T an index se. A real valued sochasic process is
More informationLearning in Games via Opponent Strategy Estimation and Policy Search
Learning in Games via Opponen Sraegy Esimaion and Policy Search Yavar Naddaf Deparmen of Compuer Science Universiy of Briish Columbia Vancouver, BC yavar@naddaf.name Nando de Freias (Supervisor) Deparmen
More informationLOW-VELOCITY IMPACT LOCALIZATION OF THE COMPOSITE TUBE USING A NORMALIZED CROSS-CORRELATION METHOD
21 s Inernaional Conference on Composie Maerials Xi an, 20-25 h Augus 2017 LOW-VELOCITY IMPACT LOCALIZATION OF THE COMPOSITE TUBE USING A NORMALIZED CROSS-CORRELATION METHOD Hyunseok Kwon 1, Yurim Park
More informationChapter 8 LOCATION SERVICES
Disribued Compuing Group Chaper 8 LOCATION SERVICES Mobile Compuing Winer 2005 / 2006 Overview Mobile IP Moivaion Daa ransfer Encapsulaion Locaion Services & Rouing Classificaion of locaion services Home
More informationIROS 2015 Workshop on On-line decision-making in multi-robot coordination (DEMUR 15)
IROS 2015 Workshop on On-line decision-making in muli-robo coordinaion () OPTIMIZATION-BASED COOPERATIVE MULTI-ROBOT TARGET TRACKING WITH REASONING ABOUT OCCLUSIONS KAROL HAUSMAN a,, GREGORY KAHN b, SACHIN
More informationAnalysis of Various Types of Bugs in the Object Oriented Java Script Language Coding
Indian Journal of Science and Technology, Vol 8(21), DOI: 10.17485/ijs/2015/v8i21/69958, Sepember 2015 ISSN (Prin) : 0974-6846 ISSN (Online) : 0974-5645 Analysis of Various Types of Bugs in he Objec Oriened
More informationSimultaneous Localization and Mapping with Stereo Vision
Simulaneous Localizaion and Mapping wih Sereo Vision Mahew N. Dailey Compuer Science and Informaion Managemen Asian Insiue of Technology Pahumhani, Thailand Email: mdailey@ai.ac.h Manukid Parnichkun Mecharonics
More informationPART 1 REFERENCE INFORMATION CONTROL DATA 6400 SYSTEMS CENTRAL PROCESSOR MONITOR
. ~ PART 1 c 0 \,).,,.,, REFERENCE NFORMATON CONTROL DATA 6400 SYSTEMS CENTRAL PROCESSOR MONTOR n CONTROL DATA 6400 Compuer Sysems, sysem funcions are normally handled by he Monior locaed in a Peripheral
More informationMulti-Target Detection and Tracking from a Single Camera in Unmanned Aerial Vehicles (UAVs)
2016 IEEE/RSJ Inernaional Conference on Inelligen Robos and Sysems (IROS) Daejeon Convenion Cener Ocober 9-14, 2016, Daejeon, Korea Muli-Targe Deecion and Tracking from a Single Camera in Unmanned Aerial
More informationMotor Control. 5. Control. Motor Control. Motor Control
5. Conrol In his chaper we will do: Feedback Conrol On/Off Conroller PID Conroller Moor Conrol Why use conrol a all? Correc or wrong? Supplying a cerain volage / pulsewidh will make he moor spin a a cerain
More informationProceeding of the 6 th International Symposium on Artificial Intelligence and Robotics & Automation in Space: i-sairas 2001, Canadian Space Agency,
Proceeding of he 6 h Inernaional Symposium on Arificial Inelligence and Roboics & Auomaion in Space: i-sairas 00, Canadian Space Agency, S-Huber, Quebec, Canada, June 8-, 00. Muli-resoluion Mapping Using
More informationSimultaneous Precise Solutions to the Visibility Problem of Sculptured Models
Simulaneous Precise Soluions o he Visibiliy Problem of Sculpured Models Joon-Kyung Seong 1, Gershon Elber 2, and Elaine Cohen 1 1 Universiy of Uah, Sal Lake Ciy, UT84112, USA, seong@cs.uah.edu, cohen@cs.uah.edu
More informationAssignment 2. Due Monday Feb. 12, 10:00pm.
Faculy of rs and Science Universiy of Torono CSC 358 - Inroducion o Compuer Neworks, Winer 218, LEC11 ssignmen 2 Due Monday Feb. 12, 1:pm. 1 Quesion 1 (2 Poins): Go-ack n RQ In his quesion, we review how
More informationMIC2569. Features. General Description. Applications. Typical Application. CableCARD Power Switch
CableCARD Power Swich General Descripion is designed o supply power o OpenCable sysems and CableCARD hoss. These CableCARDs are also known as Poin of Disribuion (POD) cards. suppors boh Single and Muliple
More informationIn Proceedings of CVPR '96. Structure and Motion of Curved 3D Objects from. using these methods [12].
In Proceedings of CVPR '96 Srucure and Moion of Curved 3D Objecs from Monocular Silhouees B Vijayakumar David J Kriegman Dep of Elecrical Engineering Yale Universiy New Haven, CT 652-8267 Jean Ponce Compuer
More informationWheelchair-user Detection Combined with Parts-based Tracking
Wheelchair-user Deecion Combined wih Pars-based Tracking Ukyo Tanikawa 1, Yasuomo Kawanishi 1, Daisuke Deguchi 2,IchiroIde 1, Hiroshi Murase 1 and Ryo Kawai 3 1 Graduae School of Informaion Science, Nagoya
More informationElite Acoustics Engineering A4-8 Live-Performance Studio Monitor with 4 Channels, Mixer, Effects, and Bluetooth Quick Start Guide
Elie Acousics Engineering A4-8 Live-Performance Sudio Monior wih 4 Channels, Mixer, Effecs, and Blueooh Quick Sar Guide WHAT IS IN THE BOX Your A4-8 package conains he following: (1) Speaker (1) 12V AC
More informationAlgorithm for image reconstruction in multi-slice helical CT
Algorihm for image reconsrucion in muli-slice helical CT Kasuyuki Taguchi a) and Hiroshi Aradae Medical Engineering Laboraory, Toshiba Corporaion, 1385 Shimoishigami, Oawara, Tochigi 324-855, Japan Received
More informationScale Recovery for Monocular Visual Odometry Using Depth Estimated with Deep Convolutional Neural Fields
Scale Recovery for Monocular Visual Odomery Using Deph Esimaed wih Deep Convoluional Neural Fields Xiaochuan Yin, Xiangwei Wang, Xiaoguo Du, Qijun Chen Tongji Universiy yinxiaochuan@homail.com,wangxiangwei.cpp@gmail.com,
More informationDetection Tracking and Recognition of Human Poses for a Real Time Spatial Game
Deecion Tracking and Recogniion of Human Poses for a Real Time Spaial Game Feifei Huo, Emile A. Hendriks, A.H.J. Oomes Delf Universiy of Technology The Neherlands f.huo@udelf.nl Pascal van Beek, Remco
More informationIntentSearch:Capturing User Intention for One-Click Internet Image Search
JOURNAL OF L A T E X CLASS FILES, VOL. 6, NO. 1, JANUARY 2010 1 InenSearch:Capuring User Inenion for One-Click Inerne Image Search Xiaoou Tang, Fellow, IEEE, Ke Liu, Jingyu Cui, Suden Member, IEEE, Fang
More informationModeling and Tracking of Dynamic Obstacles for Logistic Plants using Omnidirectional Stereo Vision
Modeling and Tracing of Dynamic Obsacles for Logisic Plans using Omnidirecional Sereo Vision Andrei Vaavu, Arhur D. Cosea, and Sergiu Nedevschi, Members, IEEE Absrac In his wor we presen an obsacle deecion
More informationON THE 3D PARAMETRIC MODELING OF MANUFACTURING SYSTEMS UDC: ; ; 338.3;
3 rd 7 h June, 2013. year, Belgrade, Serbia. ON THE 3D PARAMETRIC MODEING OF MANUFACTURING SYSTEMS UDC: 519.876.5; 004.896; 338.3; Agahocles A. Krimpenis 1, Nikolaos A. Founas 2, George D. Noeas 3, Dimiris
More informationA Face Detection Method Based on Skin Color Model
A Face Deecion Mehod Based on Skin Color Model Dazhi Zhang Boying Wu Jiebao Sun Qinglei Liao Deparmen of Mahemaics Harbin Insiue of Technology Harbin China 150000 Zhang_dz@163.com mahwby@hi.edu.cn sunjiebao@om.com
More informationVision based leader-follower formation control for mobile robots
Scholars' Mine Masers Theses Suden Theses and Disseraions Fall 7 Vision based leader-follower formaion conrol for mobile robos Gerard Sequeira Follow his and addiional works a: hp://scholarsmine.ms.edu/masers_heses
More informationReal-Time Avatar Animation Steered by Live Body Motion
Real-Time Avaar Animaion Seered by Live Body Moion Oliver Schreer, Ralf Tanger, Peer Eiser, Peer Kauff, Bernhard Kaspar, and Roman Engler 3 Fraunhofer Insiue for Telecommunicaions/Heinrich-Herz-Insiu,
More informationEECS 487: Interactive Computer Graphics
EECS 487: Ineracive Compuer Graphics Lecure 7: B-splines curves Raional Bézier and NURBS Cubic Splines A represenaion of cubic spline consiss of: four conrol poins (why four?) hese are compleely user specified
More informationThe Impact of Product Development on the Lifecycle of Defects
The Impac of Produc Developmen on he Lifecycle of Rudolf Ramler Sofware Compeence Cener Hagenberg Sofware Park 21 A-4232 Hagenberg, Ausria +43 7236 3343 872 rudolf.ramler@scch.a ABSTRACT This paper invesigaes
More informationEvaluation and Improvement of Region-based Motion Segmentation
Evaluaion and Improvemen of Region-based Moion Segmenaion Mark Ross Universiy Koblenz-Landau, Insiue of Compuaional Visualisics, Universiässraße 1, 56070 Koblenz, Germany Email: ross@uni-koblenz.de Absrac
More informationImproving the Efficiency of Dynamic Service Provisioning in Transport Networks with Scheduled Services
Improving he Efficiency of Dynamic Service Provisioning in Transpor Neworks wih Scheduled Services Ralf Hülsermann, Monika Jäger and Andreas Gladisch Technologiezenrum, T-Sysems, Goslarer Ufer 35, D-1585
More informationNonparametric CUSUM Charts for Process Variability
Journal of Academia and Indusrial Research (JAIR) Volume 3, Issue June 4 53 REEARCH ARTICLE IN: 78-53 Nonparameric CUUM Chars for Process Variabiliy D.M. Zombade and V.B. Ghue * Dep. of aisics, Walchand
More informationWe are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists. International authors and editors
We are InechOpen, he world s leading publisher of Open Access books Buil by scieniss, for scieniss 4,000 116,000 120M Open access books available Inernaional auhors and ediors Downloads Our auhors are
More informationMotion Level-of-Detail: A Simplification Method on Crowd Scene
Moion Level-of-Deail: A Simplificaion Mehod on Crowd Scene Absrac Junghyun Ahn VR lab, EECS, KAIST ChocChoggi@vr.kais.ac.kr hp://vr.kais.ac.kr/~zhaoyue Recen echnological improvemen in characer animaion
More informationMichiel Helder and Marielle C.T.A Geurts. Hoofdkantoor PTT Post / Dutch Postal Services Headquarters
SHORT TERM PREDICTIONS A MONITORING SYSTEM by Michiel Helder and Marielle C.T.A Geurs Hoofdkanoor PTT Pos / Duch Posal Services Headquarers Keywords macro ime series shor erm predicions ARIMA-models faciliy
More informationMoBAN: A Configurable Mobility Model for Wireless Body Area Networks
MoBAN: A Configurable Mobiliy Model for Wireless Body Area Neworks Majid Nabi 1, Marc Geilen 1, Twan Basen 1,2 1 Deparmen of Elecrical Engineering, Eindhoven Universiy of Technology, he Neherlands 2 Embedded
More informationCollision-Free and Curvature-Continuous Path Smoothing in Cluttered Environments
Collision-Free and Curvaure-Coninuous Pah Smoohing in Cluered Environmens Jia Pan 1 and Liangjun Zhang and Dinesh Manocha 3 1 panj@cs.unc.edu, 3 dm@cs.unc.edu, Dep. of Compuer Science, Universiy of Norh
More informationA Framework for Applying Point Clouds Grabbed by Multi-Beam LIDAR in Perceiving the Driving Environment
Sensors 215, 15, 21931-21956; doi:1.339/s15921931 Aricle OPEN ACCESS sensors ISSN 1424-822 www.mdpi.com/journal/sensors A Framewor for Applying Poin Clouds Grabbed by Muli-Beam LIDAR in Perceiving he Driving
More informationOcclusion-Free Hand Motion Tracking by Multiple Cameras and Particle Filtering with Prediction
58 IJCSNS Inernaional Journal of Compuer Science and Nework Securiy, VOL.6 No.10, Ocober 006 Occlusion-Free Hand Moion Tracking by Muliple Cameras and Paricle Filering wih Predicion Makoo Kao, and Gang
More informationA Survey on mobility Models & Its Applications
A Survey on mobiliy Models & Is Applicaions Prof. Vikas Kumar Jain 1, Prof. Raju Sharma 2, Prof. Bhavana Gupa 3 1,2,3 Compuer Science & Engineering, CIST Absrac In his paper, we survey he curren scenario
More informationFIELD PROGRAMMABLE GATE ARRAY (FPGA) AS A NEW APPROACH TO IMPLEMENT THE CHAOTIC GENERATORS
FIELD PROGRAMMABLE GATE ARRAY (FPGA) AS A NEW APPROACH TO IMPLEMENT THE CHAOTIC GENERATORS Mohammed A. Aseeri and M. I. Sobhy Deparmen of Elecronics, The Universiy of Ken a Canerbury Canerbury, Ken, CT2
More informationUpper Body Tracking for Human-Machine Interaction with a Moving Camera
The 2009 IEEE/RSJ Inernaional Conference on Inelligen Robos and Sysems Ocober -5, 2009 S. Louis, USA Upper Body Tracking for Human-Machine Ineracion wih a Moving Camera Yi-Ru Chen, Cheng-Ming Huang, and
More informationTerrain Based GPS Independent Lane-Level Vehicle Localization using Particle Filter and Dead Reckoning
Terrain Based GPS Independen -Level Vehicle Localizaion using Paricle Filer and Dead Reckoning Hamad Ahmed and Muhammad Tahir Deparmen of Elecrical Engineering, Lahore Universiy of Managemen Sciences,
More informationWhy not experiment with the system itself? Ways to study a system System. Application areas. Different kinds of systems
Simulaion Wha is simulaion? Simple synonym: imiaion We are ineresed in sudying a Insead of experimening wih he iself we experimen wih a model of he Experimen wih he Acual Ways o sudy a Sysem Experimen
More information1 œ DRUM SET KEY. 8 Odd Meter Clave Conor Guilfoyle. Cowbell (neck) Cymbal. Hi-hat. Floor tom (shell) Clave block. Cowbell (mouth) Hi tom.
DRUM SET KEY Hi-ha Cmbal Clave block Cowbell (mouh) 0 Cowbell (neck) Floor om (shell) Hi om Mid om Snare Floor om Snare cross sick or clave block Bass drum Hi-ha wih foo 8 Odd Meer Clave Conor Guilfole
More informationLearning nonlinear appearance manifolds for robot localization
Learning nonlinear appearance manifolds for robo localizaion Jihun Hamm, Yuanqing Lin, and Daniel. D. Lee GRAS Lab, Deparmen of Elecrical and Sysems Engineering Universiy of ennsylvania, hiladelphia, A
More informationCoded Caching with Multiple File Requests
Coded Caching wih Muliple File Requess Yi-Peng Wei Sennur Ulukus Deparmen of Elecrical and Compuer Engineering Universiy of Maryland College Park, MD 20742 ypwei@umd.edu ulukus@umd.edu Absrac We sudy a
More informationBI-TEMPORAL INDEXING
BI-TEMPORAL INDEXING Mirella M. Moro Uniersidade Federal do Rio Grande do Sul Poro Alegre, RS, Brazil hp://www.inf.ufrgs.br/~mirella/ Vassilis J. Tsoras Uniersiy of California, Rierside Rierside, CA 92521,
More informationACQUIRING high-quality and well-defined depth data. Online Temporally Consistent Indoor Depth Video Enhancement via Static Structure
SUBMITTED TO TRANSACTION ON IMAGE PROCESSING 1 Online Temporally Consisen Indoor Deph Video Enhancemen via Saic Srucure Lu Sheng, Suden Member, IEEE, King Ngi Ngan, Fellow, IEEE, Chern-Loon Lim and Songnan
More informationA Bayesian Approach to Video Object Segmentation via Merging 3D Watershed Volumes
A Bayesian Approach o Video Objec Segmenaion via Merging 3D Waershed Volumes Yu-Pao Tsai 1,3, Chih-Chuan Lai 1,2, Yi-Ping Hung 1,2, and Zen-Chung Shih 3 1 Insiue of Informaion Science, Academia Sinica,
More information4 Error Control. 4.1 Issues with Reliable Protocols
4 Error Conrol Jus abou all communicaion sysems aemp o ensure ha he daa ges o he oher end of he link wihou errors. Since i s impossible o build an error-free physical layer (alhough some shor links can
More informationA lidar Perception Scheme for Intelligent Vehicle Navigation
lidar Percepion Scheme for Inelligen Vehicle Navigaion Julien Moras, Véronique Cherfaoui, Philippe Bonnifai To cie his version: Julien Moras, Véronique Cherfaoui, Philippe Bonnifai. lidar Percepion Scheme
More informationEXPERIMENTAL RESULTS GOT WITH THE OMNIDIRECTIONAL VISION SENSOR: SYCLOP
EXERIENTAL RESULTS GOT WITH THE ONIDIRECTIONAL ISION SENSOR: SYCLO Eric BRASSART, Lauren DELAHOCHE, Cyril CAUCHOIS, Cyril DROCOURT, Claude EGARD, El usapha OUADDIB CREA (Cenre de Roboique d Elecroechnique
More information