Event Detection Using Local Binary Pattern Based Dynamic Textures

Size: px
Start display at page:

Download "Event Detection Using Local Binary Pattern Based Dynamic Textures"

Transcription

1 Event Detetion Using Loal Binary Pattern Based Dynami Textures Abstrat Deteting susiious events from video surveillane ameras has been an imortant task reently. Many trajetory based desritors were develoed, suh as to detet eole running or moving in oosite diretion. However, these trajetory based desritors are not working well in the rowd environments like airorts, rail stations, beause those desritors assume erfet motion/objet segmentation. In this aer, we resent an event detetion method using dynami texture desritor. The dynami texture desritor is an extension of the loal binary atterns. The image sequenes are divided into regions. A flow is formed based on the similarity of the dynami texture desritors on the regions. We used real dataset for exeriments. The results are romising. 1. Introdution Yunqian Ma Honeywell International In Douglas Drive North Golden Valley, MN 55442, USA yunqian.ma@honeywell.om The event reognition in video surveillane is an imortant researh toi. Normally the objet (suh as a erson or a ar) is deteted, and traked as a single objet. Then a simle ativity reognition, inluding eole walking, running, skiing, an be erformed [1][2]. However, the assumtion that objets an be searated and traked often fails in the rowd environment. For examle, surveillane ameras in airort an ature a lot of ersons walking together. Thus the ommonly seen ativities, suh as eole moving in different diretions, rowd formation and disersal, beome hard to be deteted and be reresented reliably. There is muh interest to the event detetion in rowd environment. Ali and Shah [3] develoed an ativity reresentation by modeling the rowded sene as a fluid flow to byass objet detetion and traking. They used the Lagrangian Partile Dynamis to segment high density rowd flows and detet flow instabilities. Andrade et al. [4] roosed a tehnique to automatially detet abnormal events in rowds. They haraterized rowd behavior by observing the rowd otial flow and used unsuervised feature extration to enode normal rowd behavior. Marana et al. [5] resented a tehnique for rowd density Petr Cisar Honeywell Prague Labs V Parku 2326/18, 14800, Prague, Czeh Reubli etr.isar@honeywell.om estimation based on Minkowski fratal dimension. Reisman et al. [6] resented a real time system that was able to detet rowds at distanes of u to 70m. The system used slies in the satiotemoral domain to detet inward motion as well as intersetions between multile moving objets. Ma and Cisar used dynami texture for eole segmentation in the rowd environment [7]. For a more omrehensive survey on ativity reognition in rowded environments, we refer the reader to [8]. In this aer, we resent an event detetion method using the dynami texture desritor. The dynami textures are the textures with motion. Seifially, we use the Loal Binary Patterns from Three Orthogonal Planes (LBP-TOP) desritor. We first artition the image frame into multile regions. Eah region and the onseutive several frames regions form a volume. The LBP-TOP desritor is alulated on the volume. Next, we form a flow by onneting several volume regions together along the time axis. Then the desritor for the event is reresented by the LBP-TOP desritors along the flow. For the lassifiation on the event, the distane between the test sequene s desritor and the model sequene s desritor is alulated using the log-likelihood statistis. This allows us to reognize events of eole and ars in different video senarios. This aer is organized as follows. Setion 2 gives an overview of dynami texture desritor. Setion 3 resents the roosed methods using the dynami texture for the event reognition. We resent exerimental results in Setion 4. Setion 5 is disussion. 2. Dynami texture desritor 2.1. Previous work In this setion, we briefly desribe the revious work for the Loal Binary Pattern (LBP), its extension to the LBP-TOP desritor [9][10][11][13][14][15]. The LBP was introdued as a texture desritor [9][10]. An LBP desritor for a loal neighborhood on a enter ixel is alulated with the eight neighbors using the grey level of the enter ixel as a threshold. The LBP desritor atures the satial struture of loal image texture, and has been suessfully used in the aliation of texture lassifiation [10] /09/$ IEEE 38

2 Zhao and Pietikäinen [11] extended the LBP desritor to Volume LBP to ature the dynami texture on the image sequenes. However, the number of atterns will beome very large when the number of neighboring ixels inreases. Therefore the LBP-TOP desritor was develoed [13] for a fast alulation of the LBP features for dynami texture. The LBP-TOP desritor is a onatenation LBP on three orthogonal lanes, XY, XT and YT. Zhao and Pietikäinen [14] alied the LBP-TOP desritor for the aliation of faial exression reognition. They first divided the fae image into several regions. The LBP-TOP desritor is alulated for eah region. They viewed the faial exression reognition roblem as a lassifiation roblem. The distane between a samle histogram and the model histogram is alulated using the log-likelihood statistis. Kellokumu, Zhao and Pietikäinen [15] alied the LBP-TOP desritor for ation reognition inluding eole bending, juming when a erson is well seerated. They only used the XT lane and the YT lane to alulate the LBP-TOP desritor LBP-TOP desritor Before we resent the LBP-TOP desritor, we first resent the LBP desritor. The original LBP desritor on a enter ixel is alulated with the eight neighbors using the grey level of the enter ixel as a threshold. Ojala et al. [10] defined a texture T in a loal neighborhood of a gray image as a joint distribution of the gray level of the enter ixel and those of its neighborhood ixels T = t( g, go,..., gp 1) (1) where g is the gray level of the enter ixel and P is the number of neighborhoods. Then we subtrat the gray level of the enter ixels and fatorize the joint distribution. T t( g) t( go g,..., gp 1 g) (2) Normally t( g ) is omitted, sine it reresents the whole luminane of an image. Moreover, in order to have the invariane with the sales of the gray level, only the signs of the differene are onsidered, so the LBP ode is reresented as follows: P 1 = 0 LBP( x, y ) = s( g g )2, (3) 1, x 0 ( x) = 0, x < 0 s (4) The reason to all the LBP ode is beause a binomial weight 2 is assigned to eah indiation funtion between the gray level of the enter ixel with the gray level of eah neighborhood ixel. The texture in one image an be extended to dynami texture in one image sequene. Consider a volume neighborhood entered at ixel ( x, y ) at time t, the volume LBP is defined as the joint distribution of the gray levels of 3P+3 image ixels on the urrent frame t, the revious neighboring frame, and the next neighboring frame t L t + L as follows: 3P + 1 = 0 V LBP( x, y, t ) = s( g g )2 (5) where g reresents the gray level of the enter ( x, y ) at time t, and g reresents the gray level of the neighborhood ixels within the satiotemoral volume. (a) (b) Figure 1: Illustration of the LBP-TOP desritor (a) Calulation of three LBP odes for eah oint of dynami texture through sanning, (b) histograms of LBP odes of three orthogonal lanes. When the number of neighborhood inreases, the 3 2 number of atterns for the VLBP inreases by 2 P +, so the number will be very large, next we resent the LBP- TOP desritor [13]. The LBP-TOP desritor is a desritor onatenating the LBP on the three orthogonal lanes: XY lane, XT lane, and the YT lane. In Figure 39

3 1(a), the XY lane reresents the image frame; the XT lane reresents the dynamis in the horizontal diretion, and the YT lane reresents the dynamis in the vertial diretion. In Figure 1(b), the LBP ode is alulated on the XY, XT, and the YT lanes. The XY-LBP ode reresents the satial information, and the XT-LBP ode and the YT- LBP ode reresent the satial temoral information. The 3 2 number of bins is only 3 2 rather than 2 P+ for VLBP. In LBP-TOP, all the ixels are alulated as the enter ixel, and then the statistis is reresented as a histogram on eah lane. The three histograms are onatenated into one histogram as LBP-TOP desritor. H = I{ LBP( x, y, t) = i (6) } i, j x, y, t 1 I ( A) = 0 ( x, y, t A_ is _ true o. w. where LBP ) reresents the LBP ode of enter ixel (x, y, t) in the jth lane (j = 0: XY lane, j = 1:XT lane, and j = 2: YT lane). The radius in the time axis does not need to be the same as the radius in the sae axis. We denote the radius in axe X is R, the radius in axe Y is R, and the radius X in axe T is R T. Also, the number neighborhood oints in XY, XT and YT lane orresonds to P XY, P XT, and P YT. Then the notation of the LBP-TOP desritor an be reresented as LBP TOP P XY, PXT, PYT, RX, RY, R. T The distane between two LBP-TOP desritors an be measured using the log-likelihood statisti as follows: B b d( H, H ) H b log H (7) = = where B is the number of bins, Y 2 b H 1 b reresents the samle s robability at bin b for Histogram 1, and 2 H b reresents the samle s robability at bin b for Histogram 2. Other distane between the two histograms, suh as histogram intersetion distane an be used. 3. Proosed method In this setion, we resent a region based method using the LBP-TOP desritor. We artition the image frame into regions. Eah region in the urrent frame and its next several frames form a satio-temoral volume, as shown in Figure 2. Eah satio-temoral region is a three dimension of width X, height Y, and number of time frames T. The satio-temoral regions an be overlaing or non-overlaing. If two satio-temoral regions overla, we denote Xo, Yo as the distane between enters of the regions in X axe and Y axe resetively, and To as the differene between entral frames in T axe. Figure 2: Image regions from onseutive frames. The LBP-TOP desritor of the region is alulated using the method (6) in Setion 2. The event may over many frames, whih is longer than the number of frames forming the volume region, so the regions are onneted temorally to form a flow. There are three omonents to form a flow using the regions: temoral assoiation of the athes, a sto riterion for the temoral assoiation, and flow editing to remove noise. Temoral assoiation is to onnet a region at time t to a region at time t+1. We assume that the ath at time t + 1 that is onneted to a ath B i (t) at time t lies in its satial neighborhood. A ath Bˆ j ( t + 1) is assoiated with B i (t) ˆ j = argmin d(h( B i (t)), H( Bj (t + 1))) (8) where the d(.) is the distane between the two LBP-TOP desritors (7). This roedure is ontinued until a stoing riterion is satisfied. We onsidered two stoing riteria. First, if all nine neighboring athes at time t + 1 do not exhibit any motion, we assume that the objet either stos moving or has left the sene. The orresonding flow forming is eased. Seond, if objets overla leading to the olusion of the objet in onsideration, the LBP-TOP desritors of all nine neighborhood athes will differ greatly with the LBP-TOP desritors of the urrent ath B i (t). In artiular, if the distane >μ+3δ, where μ is the mean and δ is the standard deviation of the distanes alulated during the flow formation, the orresonding flow is eased. Figure 3 shows an examle of flows formed in an olude situation using the seond sto riteria. The uer three image frames in Figure 3 reresents an image sequene. The first image frame shows two ersons move towards in the left of the image, the seond image frame shows the two ersons get oluded, and the third image frame shows the two ersons then searate. The lower 40

4 image in Figure 3 resents the flows orresonding to the oluded erson get divided at the time of the olusion using the stoing riteria desribed above. So there are two red flows orresond to the erson got oluded. Figure 3: Uer images are an examle of overlaing movement; lower image is the formed streamlines, the overlaed objet is divided into two arts aording to the sto riteria After that, we erform flow editing. We filter out three tyes of noise. First, we filter out the flows with the starting region on the boundary of the image. Those flows may join neighboring regions out of the boundaries of the image in the next few frames. Seond, flows with no signifiant hange of oordinates are onsidered noisy flows and are removed. These flows orresond to isolated movement observed in the bakground. Third, surious flows with their lengths shorter than a redefined threshold are filtered out. The resulting flows are a robust set of flows that an be used for the event detetion. Eah flow is reresented by the LBP-TOP desritors along the flow. The distane between the two flows is defined as a distane for lassifiation of the flows event. Suose a test flow Sq and a model flow S in the database, we an alulate n 1 d ( Sq, S ) = d( H( Bq ( t)),h( B ( t))) (9) n t= 1 where n is number of the LBP-TOP desritors in eah flow. The LBP-TOP desritors for eah volume region along the flow desribe the dynami information of the flow. 4. Exerimental results In this setion, we resent the exerimental results for the roosed event reognition method. We onduted the exeriments on three sets of data. The first one is the edestrian dataset used in [16]. The seond one is the retail esalator data and the vehile traffi data from the UCF dataset [3]. The third data is a subway dataset from ilid dataset [17]. The edestrian dataset [16] was used for the first exeriment. The dataset ontains video of high traffi of edestrians from a stationary amera. The resolution of the video sequene is 238*157 at 10 frames er seond. The edestrians in the dataset are moving in two diretions: moving right-u and moving left-down. We extrated the art of the data where high density of the rowd is resented with many olusions of the edestrian. We use 22 flows eah with 7 frames for training of the LBP-TOP desritor for two ativities. For eah tye of event, 11 flows ontaining the ativity were seleted. The model was alulated and stored in the database. We used 400 image frames for testing the roosed method. The video sequene was divided into satio-temoral overlaing regions with the size X = 8, Y = 9 ixels and T = 7 frames of overlaing Xo = 4, Yo = 4, and To = 1. The arameter setting for the LBP-TOP desritor is LBP- TOP 10,10,10,5,5,3. In the testing hase, eah region was lassified into one of the trained lasses using the distane defined by (9). Figure 4 shows the event reognition results. The red athes show the eole moving right-u diretion, while the green athes show the eole moving left-down diretion using our method. The results showed that the method we resented is suitable for the edestrian dataset. In the seond exeriment, we used the UCF dataset [3]. We use two sets of data from this dataset: the retail esalator data and the vehile traffi data. Figure 5 shows two frames of the event reognition results on the retail esalator set of videos. Figure 6 resents the event reognition results on the vehile traffi set of videos from the dataset. Eah region is olored by the olor that orresonds to the olor of the event lass. In the third exeriment, we used the i-lid dataset. The i-lid dataset onsists of video data of subway latform where eole enter or leave the train. Different levels of eole density are resented in the video data, and eole are overla often. The original resolution of the video data is 720*576 with 25 frames er seond. The video data was down samled the video data to 188*144 with 12.5 frame er seond for faster roessing. 41

5 X = 15, Y = 13 ixels and T = 5 frames with overlaing Xo = 6, Yo = 6 and To = 1 and desritor LBP- TOP 9,9,9,5,5,3. The otimal width and height of satiotemoral volume should orresond to the ¼ of the objets in the sene and the overlaing should orresond to the ½ of the size of the volume. The lassifiation auray is very good for these four ativities. The events are not simle beause it ontains many overlas of the objets. TABLE I CLASSIFICATION ACCURACY - SUBWAY DATASET Ativity Down U Left Right Down 96% 0% 4% 0% U 0% 96% 0% 4% Left 30% 0% 70% 0% Right 0% 0% 0% 100% Figure 4: Samle results of ativity reognition into two lasses using the LBP desrition, red = athes with right-u motion, green = athes with left-bottom motion. We seleted n video sequenes for eah different ativity (lass). Eah sequene was divided into satiotemoral regions, and the flows were formed. The flows were formed for eah testing sequene and eah flow s event was automatially lassified by roosed aroah. After that we omared with the ground truth to alulate the onfusion matrix as shown in the Table I. There are four events in the dataset: eole moving u, eole moving down, eole moving left, and eole moving right. Figure 7 shows examles of the event in the subway dataset for the orresonding event. For eah lass we had more than 16 flows for training. For testing we have 4 sequenes and 83 flows on the average for eah lass. In the table I we resent the onfusion matrix for the four tyes of events. These results were obtained with following settings: satio-temoral volumes with the size 5. Disussion Event detetion in video surveillane is imortant. The trajetory based desritor, suh as satial oordinate, veloity, and shae works if the individual objet an be segmented and traked. However, the high density environment is ommon in video surveillane data, where the trajetory based ativity desritor work oorly in this environment. In this aer, we resent an event detetion using the dynami texture desritor. The dynami texture atures the stationary roerties in time [18]. We use the LBP- TOP desritors. We first artition image sequenes into regions. Then we form motion flow by temorally onneting the region in the urrent frame to the ath in the next frame. Event reresentation is from the LBP-TOP desritors extrated from the flow. We use various real data sets to test the roosed method. The exerimental results show good erformane for the event reognition. Referenes [1] Y. Ma, S. B. Damelin, O. Masoud, N. Paanikolooulos, Ativity Reognition Via Classifiation Constrained Diffusion Ma. In: International Symosium on Visual Comuting,. 1 8, 2006 [2] Y. Ma, B. Miller, P. Buddharaju, M. Bazakos, Ativity Awareness: From Predefined Events to New Pattern Disovery, In: IEEE International Conferene on Vision Systems, New York, NY, USA, January 5-7, [3] S. Ali, M. Shah, A Lagrangian Partile Dynami Aroah for Crowd Flow Segmentation and Stability 42

6 Analysis, in IEEE Conferene on Comuter Vision and Pattern Reognition, Minneaolis, MN [4] E. Andrade, S. Blunsden, and R. Fisher, Detetion of emergeny events in rowded senes. In IEEE International Symosium on Imaging for Crime Detetion and Prevention, [5] A. Marana, L. Costa, R. Lotufo and S. Velastin, Estimating Crowd Density with Minkowski Fratal Dimension, IEEE International Conferene on Aoustis, Seeh, and Signal Proessing, [6] P. Reisman, O. Mano, S. Avidan, A. Shashua, M. Ltd, and I. Jerusalem, Crowd detetion in video sequenes, IEEE Intelligent Vehiles Symosium, [7] Y. Ma and P. Cisar, Motion Analysis Using Dynami Texture in Crowd Environment, Image Analysis - From Theory to Aliations, Researh Publishing, 2008, [8] B. Zhan, N. Monekosso, P. Remagnino, S. Velastin, and L. Xu, Crowd analysis: a survey, In Mahine Vision and Aliations, 2008, 19, [9] T. Ojala, M. Pietikäinen and D. Harwood, A omarative study of texture measures with lassifiation based on featured distributions, Pattern Reognition 29, , [10] T. Ojala, M. Pietikäinen, and T. Mäenää, Multiresolution gray-sale and rotation invariant texture lassifiation with loal binary atterns, IEEE Transation on Pattern Analysis and Mahine Intelligene, vol. 24, no. 7, , [11] G. Zhao and M. Pietikäinen, Dynami Texture Reognition Using Volume Loal Binary Patterns, Pro. Euroean Conferene on Comuter Vision, 2006 Worksho on Dynamial Vision, Graz, Austria. [12] htt:// [13] G. Zhao and M. Pietikäinen, Loal Binary Pattern Desritors for Dynami Texture Reognition, in International Conferene on Pattern Reognition, 2006, [14] G. Zhao and M. Pietikäinen, Dynami Texture reognition Using Loal Binary Patterns With an Aliation to Faial Exressions, in IEEE Transation on Pattern Analysis and Mahine Intelligene, vol. 29, no.6, , 2007 [15] V. Kellokumu, G. Zhao, M. Pietikäinen, Human Ativity Reognition Using a Dynami Texture Based Method, in British Mahine Vision Conferene (BMVC), 2008 [16] A. Chan and N. Vasonelos, Modeling, Clustering, and Segmenting Video with Mixtures of Dynami Textures, IEEE Transation on Pattern Analysis and Mahine Intelligene, vol. 30(5), , May [17] i-lids dataset for avss, [18] G. Doretto, A. Chiuso, S. Soatto, and Y. Wu, Dynami textures, International Journal of Comuter Vision, Vol. 51, no.2, , Figure 5: Ativity reognition shown for samle frames from the UCF retail esalator dataset. The red and green arrows denote the two major motion atterns observed in the video sequenes. The orresonding olor oded athes denote the labels oututted by our system. Figure 6: Ativity reognition shown for samle frames from the UCF traffi dataset. The red and green arrows denote the two major motion atterns. The orresonding olor oded athes denote the oututted ativity labels. The small resolution of objets in the sene auses some athes to be erroneously lassified. 43

7 Figure 7: Examles of four events in the i-lid dataset: erson moving down, erson moving left, erson moving right. 44

Exponential Particle Swarm Optimization Approach for Improving Data Clustering

Exponential Particle Swarm Optimization Approach for Improving Data Clustering International Journal of Eletrial and Eletronis Engineering 3:4 9 Exonential Partile Swarm Otimization Aroah for Imroving Data Clustering eveen I. Ghali, ahed El-Dessoui, Mervat A.., and Lamiaa Barawi

More information

p[4] p[3] p[2] p[1] p[0]

p[4] p[3] p[2] p[1] p[0] CMSC 425 : Sring 208 Dave Mount and Roger Eastman Homework Due: Wed, Marh 28, :00m. Submit through ELMS as a df file. It an either be distilled from a tyeset doument or handwritten, sanned, and enhaned

More information

A Novel Validity Index for Determination of the Optimal Number of Clusters

A Novel Validity Index for Determination of the Optimal Number of Clusters IEICE TRANS. INF. & SYST., VOL.E84 D, NO.2 FEBRUARY 2001 281 LETTER A Novel Validity Index for Determination of the Optimal Number of Clusters Do-Jong KIM, Yong-Woon PARK, and Dong-Jo PARK, Nonmembers

More information

The official electronic file of this thesis or dissertation is maintained by the University Libraries on behalf of The Graduate School at Stony Brook

The official electronic file of this thesis or dissertation is maintained by the University Libraries on behalf of The Graduate School at Stony Brook Stony Brook University The offiial eletroni file of this thesis or dissertation is maintained by the University Libraries on behalf of The Graduate Shool at Stony Brook University. Alll Rigghht tss Reesseerrvveedd

More information

Bias Error Reduction of Digital Image Correlation Based on Kernel

Bias Error Reduction of Digital Image Correlation Based on Kernel Vol.81 (CST 15),.16- htt://dx.doi.org/1.1457/astl.15.81.4 Bias Error Redution of Digital Image Correlation Based on Kernel Huan Shen 1,, eize Zhang 1, and Xiang Shen 1 Energy and ower College, anjing Uniersity

More information

timestamp, if silhouette(x, y) 0 0 if silhouette(x, y) = 0, mhi(x, y) = and mhi(x, y) < timestamp - duration mhi(x, y), else

timestamp, if silhouette(x, y) 0 0 if silhouette(x, y) = 0, mhi(x, y) = and mhi(x, y) < timestamp - duration mhi(x, y), else 3rd International Conferene on Multimedia Tehnolog(ICMT 013) An Effiient Moving Target Traking Strateg Based on OpenCV and CAMShift Theor Dongu Li 1 Abstrat Image movement involved bakground movement and

More information

A Coarse-to-Fine Classification Scheme for Facial Expression Recognition

A Coarse-to-Fine Classification Scheme for Facial Expression Recognition A Coarse-to-Fine Classifiation Sheme for Faial Expression Reognition Xiaoyi Feng 1,, Abdenour Hadid 1 and Matti Pietikäinen 1 1 Mahine Vision Group Infoteh Oulu and Dept. of Eletrial and Information Engineering

More information

Social Network Analysis Based on BSP Clustering Algorithm

Social Network Analysis Based on BSP Clustering Algorithm Communiations of the IIMA Volume 7 Issue 4 Artile 5 7 Soial Network Analysis Based on BSP Clustering Algorithm ong Shool of Business Administration China University of Petroleum Follow this and additional

More information

arxiv: v2 [cs.cv] 25 Nov 2015

arxiv: v2 [cs.cv] 25 Nov 2015 Pose-Guided Human Parsing with Dee-Learned Features Fangting Xia, Jun Zhu, Peng Wang, Alan Yuille University of California, Los Angeles arxiv:158.3881v2 [s.cv] 25 Nov 215 Abstrat Parsing human body into

More information

KERNEL SPARSE REPRESENTATION WITH LOCAL PATTERNS FOR FACE RECOGNITION

KERNEL SPARSE REPRESENTATION WITH LOCAL PATTERNS FOR FACE RECOGNITION KERNEL SPARSE REPRESENTATION WITH LOCAL PATTERNS FOR FACE RECOGNITION Cuiui Kang 1, Shengai Liao, Shiming Xiang 1, Chunhong Pan 1 1 National Laboratory of Pattern Reognition, Institute of Automation, Chinese

More information

Smooth Trajectory Planning Along Bezier Curve for Mobile Robots with Velocity Constraints

Smooth Trajectory Planning Along Bezier Curve for Mobile Robots with Velocity Constraints Smooth Trajetory Planning Along Bezier Curve for Mobile Robots with Veloity Constraints Gil Jin Yang and Byoung Wook Choi Department of Eletrial and Information Engineering Seoul National University of

More information

Reconfigurable Shape-Adaptive Template Matching Architectures

Reconfigurable Shape-Adaptive Template Matching Architectures Reonfigurable Shae-Adative Temlate Mathing Arhitetures Jörn Gause 1, Peter Y.K. Cheung 1, Wayne Luk 2 1 Deartment of Eletrial and Eletroni Engineering, Imerial College, London SW7 2BT, England. 2 Deartment

More information

FOREGROUND OBJECT EXTRACTION USING FUZZY C MEANS WITH BIT-PLANE SLICING AND OPTICAL FLOW

FOREGROUND OBJECT EXTRACTION USING FUZZY C MEANS WITH BIT-PLANE SLICING AND OPTICAL FLOW FOREGROUND OBJECT EXTRACTION USING FUZZY C EANS WITH BIT-PLANE SLICING AND OPTICAL FLOW SIVAGAI., REVATHI.T, JEGANATHAN.L 3 APSG, SCSE, VIT University, Chennai, India JRF, DST, Dehi, India. 3 Professor,

More information

Figure 1. LBP in the field of texture analysis operators.

Figure 1. LBP in the field of texture analysis operators. L MEHODOLOGY he loal inary pattern (L) texture analysis operator is defined as a gray-sale invariant texture measure, derived from a general definition of texture in a loal neighorhood. he urrent form

More information

Learning Motion Patterns in Crowded Scenes Using Motion Flow Field

Learning Motion Patterns in Crowded Scenes Using Motion Flow Field Learning Motion Patterns in Crowded Scenes Using Motion Flow Field Min Hu, Saad Ali and Mubarak Shah Comuter Vision Lab, University of Central Florida {mhu,sali,shah}@eecs.ucf.edu Abstract Learning tyical

More information

Robust Multithreaded Object Tracker through Occlusions for Spatial Augmented Reality

Robust Multithreaded Object Tracker through Occlusions for Spatial Augmented Reality ETRI Journal, Volume 40, Number 2, Aril, 2018 246 Robust Multithreaded Objet Traker through Olusions for Satial Augmented Reality Ahyun Lee and Insung Jang A satial augmented reality (SAR) system enables

More information

Projector Calibration for 3D Scanning Using Virtual Target Images

Projector Calibration for 3D Scanning Using Virtual Target Images INTERNATIONAL JOURNAL OF RECISION ENGINEERING AND MANUFACTURING Vol. 13, No. 1,. 125-131 JANUARY 2012 / 125 DOI: 10.1007/s12541-012-0017-3 rojetor Calibration for 3D Sanning Using Virtual Target Images

More information

A rich discrete labeling scheme for line drawings of curved objects

A rich discrete labeling scheme for line drawings of curved objects A rih disrete labeling sheme for line drawings of urved objets Martin C. Cooer, IRIT, University of Toulouse III, 31062 Toulouse, Frane ooer@irit.fr Abstrat We resent a disrete labeling sheme for line

More information

Pose-Guided Human Parsing by an AND/OR Graph Using Pose-Context Features

Pose-Guided Human Parsing by an AND/OR Graph Using Pose-Context Features Proeedings of the Thirtieth AAAI Conferene on Artifiial Intelligene (AAAI-16) Pose-Guided Human Parsing by an AND/OR Grah Using Pose-Context Features Fangting Xia and Jun Zhu and Peng Wang and Alan L.

More information

Detection and Recognition of Non-Occluded Objects using Signature Map

Detection and Recognition of Non-Occluded Objects using Signature Map 6th WSEAS International Conferene on CIRCUITS, SYSTEMS, ELECTRONICS,CONTROL & SIGNAL PROCESSING, Cairo, Egypt, De 9-31, 007 65 Detetion and Reognition of Non-Oluded Objets using Signature Map Sangbum Park,

More information

Improved Vehicle Classification in Long Traffic Video by Cooperating Tracker and Classifier Modules

Improved Vehicle Classification in Long Traffic Video by Cooperating Tracker and Classifier Modules Improved Vehile Classifiation in Long Traffi Video by Cooperating Traker and Classifier Modules Brendan Morris and Mohan Trivedi University of California, San Diego San Diego, CA 92093 {b1morris, trivedi}@usd.edu

More information

A DYNAMIC ACCESS CONTROL WITH BINARY KEY-PAIR

A DYNAMIC ACCESS CONTROL WITH BINARY KEY-PAIR Malaysian Journal of Computer Siene, Vol 10 No 1, June 1997, pp 36-41 A DYNAMIC ACCESS CONTROL WITH BINARY KEY-PAIR Md Rafiqul Islam, Harihodin Selamat and Mohd Noor Md Sap Faulty of Computer Siene and

More information

An Efficient Coding Method for Coding Region-of-Interest Locations in AVS2

An Efficient Coding Method for Coding Region-of-Interest Locations in AVS2 An Efficient Coding Method for Coding Region-of-Interest Locations in AVS2 Mingliang Chen 1, Weiyao Lin 1*, Xiaozhen Zheng 2 1 Deartment of Electronic Engineering, Shanghai Jiao Tong University, China

More information

Video Data and Sonar Data: Real World Data Fusion Example

Video Data and Sonar Data: Real World Data Fusion Example 14th International Conferene on Information Fusion Chiago, Illinois, USA, July 5-8, 2011 Video Data and Sonar Data: Real World Data Fusion Example David W. Krout Applied Physis Lab dkrout@apl.washington.edu

More information

New Fuzzy Object Segmentation Algorithm for Video Sequences *

New Fuzzy Object Segmentation Algorithm for Video Sequences * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 24, 521-537 (2008) New Fuzzy Obet Segmentation Algorithm for Video Sequenes * KUO-LIANG CHUNG, SHIH-WEI YU, HSUEH-JU YEH, YONG-HUAI HUANG AND TA-JEN YAO Department

More information

GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION

GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION GENERATING A PERSPECTIVE IMAGE FROM A PANORAMIC IMAGE BY THE SWUNG-TO-CYLINDER PROJECTION Che-Han Chang Wei-Sheng Lai Yung-Yu Chuang HTC UC Mered National Taiwan University ABSTRACT This aer rooses a swung-to-ylinder

More information

Face Recognition Based on Wavelet Transform and Adaptive Local Binary Pattern

Face Recognition Based on Wavelet Transform and Adaptive Local Binary Pattern Face Recognition Based on Wavelet Transform and Adative Local Binary Pattern Abdallah Mohamed 1,2, and Roman Yamolskiy 1 1 Comuter Engineering and Comuter Science, University of Louisville, Louisville,

More information

Approximate Labeling via the Primal-Dual Schema

Approximate Labeling via the Primal-Dual Schema Aroximate Labeling via the Primal-Dual Shema Nikos Komodakis and Georgios Tziritas Tehnial Reort CSD-TR-2005-01 February 1, 2005 Aroximate Labeling via the Primal-Dual Shema Nikos Komodakis and Georgios

More information

特集 Road Border Recognition Using FIR Images and LIDAR Signal Processing

特集 Road Border Recognition Using FIR Images and LIDAR Signal Processing デンソーテクニカルレビュー Vol. 15 2010 特集 Road Border Reognition Using FIR Images and LIDAR Signal Proessing 高木聖和 バーゼル ファルディ Kiyokazu TAKAGI Basel Fardi ヘンドリック ヴァイゲル Hendrik Weigel ゲルド ヴァニーリック Gerd Wanielik This paper

More information

Multivariate Texture-based Segmentation of Remotely Sensed. Imagery for Extraction of Objects and Their Uncertainty

Multivariate Texture-based Segmentation of Remotely Sensed. Imagery for Extraction of Objects and Their Uncertainty Multivariate Texture-based Segmentation of Remotely Sensed Imagery for Extration of Objets and Their Unertainty Arko Luieer*, Alfred Stein* & Peter Fisher** * International Institute for Geo-Information

More information

Research Article Intuitionistic Fuzzy Possibilistic C Means Clustering Algorithms

Research Article Intuitionistic Fuzzy Possibilistic C Means Clustering Algorithms Hindawi Publishing Cororation Advanes in Fuzzy Systems Volume 2015, Artile ID 2827, 17 ages htt://dx.doi.org/10.1155/2015/2827 Researh Artile Intuitionisti Fuzzy Possibilisti C Means Clustering Algorithms

More information

arxiv: v1 [cs.db] 13 Sep 2017

arxiv: v1 [cs.db] 13 Sep 2017 An effiient lustering algorithm from the measure of loal Gaussian distribution Yuan-Yen Tai (Dated: May 27, 2018) In this paper, I will introdue a fast and novel lustering algorithm based on Gaussian distribution

More information

Plot-to-track correlation in A-SMGCS using the target images from a Surface Movement Radar

Plot-to-track correlation in A-SMGCS using the target images from a Surface Movement Radar Plot-to-trak orrelation in A-SMGCS using the target images from a Surfae Movement Radar G. Golino Radar & ehnology Division AMS, Italy ggolino@amsjv.it Abstrat he main topi of this paper is the formulation

More information

Trajectory Tracking Control for A Wheeled Mobile Robot Using Fuzzy Logic Controller

Trajectory Tracking Control for A Wheeled Mobile Robot Using Fuzzy Logic Controller Trajetory Traking Control for A Wheeled Mobile Robot Using Fuzzy Logi Controller K N FARESS 1 M T EL HAGRY 1 A A EL KOSY 2 1 Eletronis researh institute, Cairo, Egypt 2 Faulty of Engineering, Cairo University,

More information

Performance of Histogram-Based Skin Colour Segmentation for Arms Detection in Human Motion Analysis Application

Performance of Histogram-Based Skin Colour Segmentation for Arms Detection in Human Motion Analysis Application World Aademy of Siene, Engineering and Tehnology 8 009 Performane of Histogram-Based Skin Colour Segmentation for Arms Detetion in Human Motion Analysis Appliation Rosalyn R. Porle, Ali Chekima, Farrah

More information

Supplementary Material: Geometric Calibration of Micro-Lens-Based Light-Field Cameras using Line Features

Supplementary Material: Geometric Calibration of Micro-Lens-Based Light-Field Cameras using Line Features Supplementary Material: Geometri Calibration of Miro-Lens-Based Light-Field Cameras using Line Features Yunsu Bok, Hae-Gon Jeon and In So Kweon KAIST, Korea As the supplementary material, we provide detailed

More information

Unsupervised Stereoscopic Video Object Segmentation Based on Active Contours and Retrainable Neural Networks

Unsupervised Stereoscopic Video Object Segmentation Based on Active Contours and Retrainable Neural Networks Unsupervised Stereosopi Video Objet Segmentation Based on Ative Contours and Retrainable Neural Networks KLIMIS NTALIANIS, ANASTASIOS DOULAMIS, and NIKOLAOS DOULAMIS National Tehnial University of Athens

More information

Face and Facial Feature Tracking for Natural Human-Computer Interface

Face and Facial Feature Tracking for Natural Human-Computer Interface Fae and Faial Feature Traking for Natural Human-Computer Interfae Vladimir Vezhnevets Graphis & Media Laboratory, Dept. of Applied Mathematis and Computer Siene of Mosow State University Mosow, Russia

More information

the data. Structured Principal Component Analysis (SPCA)

the data. Structured Principal Component Analysis (SPCA) Strutured Prinipal Component Analysis Kristin M. Branson and Sameer Agarwal Department of Computer Siene and Engineering University of California, San Diego La Jolla, CA 9193-114 Abstrat Many tasks involving

More information

ARABIC OCR SYSTEM ANALOGOUS TO HMM-BASED ASR SYSTEMS; IMPLEMENTATION AND EVALUATION

ARABIC OCR SYSTEM ANALOGOUS TO HMM-BASED ASR SYSTEMS; IMPLEMENTATION AND EVALUATION ARABIC OCR SYSTEM ANALOGOUS TO HMM-BASED ASR SYSTEMS; IMPLEMENTATION AND EVALUATION M.A.A. RASHWAN, M.W.T. FAKHR, M. ATTIA, M.S.M. EL-MAHALLAWY 4 ABSTRACT Desite 5 years of R&D on the roblem of Otial harater

More information

Learning Convention Propagation in BeerAdvocate Reviews from a etwork Perspective. Abstract

Learning Convention Propagation in BeerAdvocate Reviews from a etwork Perspective. Abstract CS 9 Projet Final Report: Learning Convention Propagation in BeerAdvoate Reviews from a etwork Perspetive Abstrat We look at the way onventions propagate between reviews on the BeerAdvoate dataset, and

More information

The Minimum Redundancy Maximum Relevance Approach to Building Sparse Support Vector Machines

The Minimum Redundancy Maximum Relevance Approach to Building Sparse Support Vector Machines The Minimum Redundany Maximum Relevane Approah to Building Sparse Support Vetor Mahines Xiaoxing Yang, Ke Tang, and Xin Yao, Nature Inspired Computation and Appliations Laboratory (NICAL), Shool of Computer

More information

We P9 16 Eigenray Tracing in 3D Heterogeneous Media

We P9 16 Eigenray Tracing in 3D Heterogeneous Media We P9 Eigenray Traing in 3D Heterogeneous Media Z. Koren* (Emerson), I. Ravve (Emerson) Summary Conventional two-point ray traing in a general 3D heterogeneous medium is normally performed by a shooting

More information

Context-Aware Activity Modeling using Hierarchical Conditional Random Fields

Context-Aware Activity Modeling using Hierarchical Conditional Random Fields Context-Aware Ativity Modeling using Hierarhial Conditional Random Fields Yingying Zhu, Nandita M. Nayak, and Amit K. Roy-Chowdhury Abstrat In this paper, rather than modeling ativities in videos individually,

More information

Interactive Image Segmentation

Interactive Image Segmentation Interactive Image Segmentation Fahim Mannan (260 266 294) Abstract This reort resents the roject work done based on Boykov and Jolly s interactive grah cuts based N-D image segmentation algorithm([1]).

More information

Extracting Partition Statistics from Semistructured Data

Extracting Partition Statistics from Semistructured Data Extrating Partition Statistis from Semistrutured Data John N. Wilson Rihard Gourlay Robert Japp Mathias Neumüller Department of Computer and Information Sienes University of Strathlyde, Glasgow, UK {jnw,rsg,rpj,mathias}@is.strath.a.uk

More information

Machine Vision. Laboratory Exercise Name: Student ID: S

Machine Vision. Laboratory Exercise Name: Student ID: S Mahine Vision 521466S Laoratory Eerise 2011 Name: Student D: General nformation To pass these laoratory works, you should answer all questions (Q.y) with an understandale handwriting either in English

More information

Graph-Based vs Depth-Based Data Representation for Multiview Images

Graph-Based vs Depth-Based Data Representation for Multiview Images Graph-Based vs Depth-Based Data Representation for Multiview Images Thomas Maugey, Antonio Ortega, Pasal Frossard Signal Proessing Laboratory (LTS), Eole Polytehnique Fédérale de Lausanne (EPFL) Email:

More information

Abstract. Key Words: Image Filters, Fuzzy Filters, Order Statistics Filters, Rank Ordered Mean Filters, Channel Noise. 1.

Abstract. Key Words: Image Filters, Fuzzy Filters, Order Statistics Filters, Rank Ordered Mean Filters, Channel Noise. 1. Fuzzy Weighted Rank Ordered Mean (FWROM) Filters for Mixed Noise Suppression from Images S. Meher, G. Panda, B. Majhi 3, M.R. Meher 4,,4 Department of Eletronis and I.E., National Institute of Tehnology,

More information

Control CPR: A Branch Height Reduction Optimization for EPIC Architectures

Control CPR: A Branch Height Reduction Optimization for EPIC Architectures Control CPR: A Branh Height Redution Otimization for EPIC Arhitetures Mihael Shlansker, Sott Mahlke, Rihard Johnson HP Laboratories Palo Alto HPL-1999-34 February, 1999 E-mail: [shlansk,mahlke]@hl.h.om

More information

Capturing Large Intra-class Variations of Biometric Data by Template Co-updating

Capturing Large Intra-class Variations of Biometric Data by Template Co-updating Capturing Large Intra-lass Variations of Biometri Data by Template Co-updating Ajita Rattani University of Cagliari Piazza d'armi, Cagliari, Italy ajita.rattani@diee.unia.it Gian Lua Marialis University

More information

3-D IMAGE MODELS AND COMPRESSION - SYNTHETIC HYBRID OR NATURAL FIT?

3-D IMAGE MODELS AND COMPRESSION - SYNTHETIC HYBRID OR NATURAL FIT? 3-D IMAGE MODELS AND COMPRESSION - SYNTHETIC HYBRID OR NATURAL FIT? Bernd Girod, Peter Eisert, Marus Magnor, Ekehard Steinbah, Thomas Wiegand Te {girod eommuniations Laboratory, University of Erlangen-Nuremberg

More information

Gray Codes for Reflectable Languages

Gray Codes for Reflectable Languages Gray Codes for Refletable Languages Yue Li Joe Sawada Marh 8, 2008 Abstrat We lassify a type of language alled a refletable language. We then develop a generi algorithm that an be used to list all strings

More information

Implicit Representation of Molecular Surfaces

Implicit Representation of Molecular Surfaces Imliit Reresentation of Moleular Surfaes Julius Parulek Ivan Viola Deartment of Informatis, University of Bergen Deartment of Informatis, University of Bergen. (a) (b) () (d) (e) (f) (g) (h) Figure : Ray-asting

More information

A PROTOTYPE OF INTELLIGENT VIDEO SURVEILLANCE CAMERAS

A PROTOTYPE OF INTELLIGENT VIDEO SURVEILLANCE CAMERAS INTERNATIONAL JOURNAL OF INFORMATION AND SYSTEMS SCIENCES Volume 1, 3, Number 1, 3, Pages 1-22 365-382 2007 Institute for Sientifi Computing and Information A PROTOTYPE OF INTELLIGENT VIDEO SURVEILLANCE

More information

Stable Road Lane Model Based on Clothoids

Stable Road Lane Model Based on Clothoids Stable Road Lane Model Based on Clothoids C Gakstatter*, S Thomas**, Dr P Heinemann*, Prof Gudrun Klinker*** *Audi Eletronis Venture GmbH, **Leibniz Universität Hannover, ***Tehnishe Universität Münhen

More information

Chromaticity-matched Superimposition of Foreground Objects in Different Environments

Chromaticity-matched Superimposition of Foreground Objects in Different Environments FCV216, the 22nd Korea-Japan Joint Workshop on Frontiers of Computer Vision Chromatiity-mathed Superimposition of Foreground Objets in Different Environments Yohei Ogura Graduate Shool of Siene and Tehnology

More information

BeautyGAN: Instance-level Facial Makeup Transfer with Deep Generative Adversarial Network

BeautyGAN: Instance-level Facial Makeup Transfer with Deep Generative Adversarial Network eautygan: Instane-level Faial Makeu Transfer with Dee Generative Adversarial Network Tingting Li Tsinghua-erkeley Shenzhen Institute, Tsinghua University litt.thu@foxmail.om Ruihe Qian Institue of Information

More information

A Novel Iris Segmentation Method for Hand-Held Capture Device

A Novel Iris Segmentation Method for Hand-Held Capture Device A Novel Iris Segmentation Method for Hand-Held Cature Device XiaoFu He and PengFei Shi Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200030, China {xfhe,

More information

Gradient based progressive probabilistic Hough transform

Gradient based progressive probabilistic Hough transform Gradient based progressive probabilisti Hough transform C.Galambos, J.Kittler and J.Matas Abstrat: The authors look at the benefits of exploiting gradient information to enhane the progressive probabilisti

More information

Performance Improvement of TCP on Wireless Cellular Networks by Adaptive FEC Combined with Explicit Loss Notification

Performance Improvement of TCP on Wireless Cellular Networks by Adaptive FEC Combined with Explicit Loss Notification erformane Improvement of TC on Wireless Cellular Networks by Adaptive Combined with Expliit Loss tifiation Masahiro Miyoshi, Masashi Sugano, Masayuki Murata Department of Infomatis and Mathematial Siene,

More information

AUTOMATIC EXTRACTION OF BUILDING OUTLINE FROM HIGH RESOLUTION AERIAL IMAGERY

AUTOMATIC EXTRACTION OF BUILDING OUTLINE FROM HIGH RESOLUTION AERIAL IMAGERY AUTOMATIC EXTRACTION OF BUILDING OUTLINE FROM HIGH RESOLUTION AERIAL IMAGERY Yandong Wang EagleView Technology Cor. 5 Methodist Hill Dr., Rochester, NY 1463, the United States yandong.wang@ictometry.com

More information

A scheme for racquet sports video analysis with the combination of audio-visual information

A scheme for racquet sports video analysis with the combination of audio-visual information A sheme for raquet sports video analysis with the ombination of audio-visual information Liyuan Xing a*, Qixiang Ye b, Weigang Zhang, Qingming Huang a and Hua Yu a a Graduate Shool of the Chinese Aadamy

More information

Face Recognition Using Legendre Moments

Face Recognition Using Legendre Moments Face Recognition Using Legendre Moments Dr.S.Annadurai 1 A.Saradha Professor & Head of CSE & IT Research scholar in CSE Government College of Technology, Government College of Technology, Coimbatore, Tamilnadu,

More information

Dr.Hazeem Al-Khafaji Dept. of Computer Science, Thi-Qar University, College of Science, Iraq

Dr.Hazeem Al-Khafaji Dept. of Computer Science, Thi-Qar University, College of Science, Iraq Volume 4 Issue 6 June 014 ISSN: 77 18X International Journal of Advaned Researh in Computer Siene and Software Engineering Researh Paper Available online at: www.ijarsse.om Medial Image Compression using

More information

3D Shadows: Computer Vision for an Unencumbered Interface

3D Shadows: Computer Vision for an Unencumbered Interface 3D Shadows: Computer Vision for an Unenumbered Interfae Robert Virtue University of British Columbia 356 Main Mall Vanouver, BC Canada 604-8-053 virtue@ee.ub.a ABSTRACT In this paper we desribe a real-time

More information

SKIN CANCER LESION CLASSIFICATION USING LBP BASED HYBRID CLASSIFIER

SKIN CANCER LESION CLASSIFICATION USING LBP BASED HYBRID CLASSIFIER DOI: htt://dx.doi.org/10.26483/ijarcs.v8i7.4469 Volume 8, No. 7, July August 2017 International Journal of Advanced Research in Comuter Science RESEARCH PAPER Available Online at www.ijarcs.info ISSN No.

More information

Cluster-Based Cumulative Ensembles

Cluster-Based Cumulative Ensembles Cluster-Based Cumulative Ensembles Hanan G. Ayad and Mohamed S. Kamel Pattern Analysis and Mahine Intelligene Lab, Eletrial and Computer Engineering, University of Waterloo, Waterloo, Ontario N2L 3G1,

More information

Bayesian Oil Spill Segmentation of SAR Images via Graph Cuts 1

Bayesian Oil Spill Segmentation of SAR Images via Graph Cuts 1 Bayesian Oil Sill Segmentation of SAR Images via Grah Cuts 1 Sónia Pelizzari and José M. Bioucas-Dias Instituto de Telecomunicações, I.S.T., TULisbon,Lisboa, Portugal sonia@lx.it.t, bioucas@lx.it.t Abstract.

More information

An Interactive-Voting Based Map Matching Algorithm

An Interactive-Voting Based Map Matching Algorithm Eleventh International Conferene on Mobile Data Management An Interative-Voting Based Map Mathing Algorithm Jing Yuan* University of Siene and Tehnology of China Hefei, China yuanjing@mail.ust.edu.n Yu

More information

Detecting Moving Targets in Clutter in Airborne SAR via Keystoning and Multiple Phase Center Interferometry

Detecting Moving Targets in Clutter in Airborne SAR via Keystoning and Multiple Phase Center Interferometry Deteting Moving Targets in Clutter in Airborne SAR via Keystoning and Multiple Phase Center Interferometry D. M. Zasada, P. K. Sanyal The MITRE Corp., 6 Eletroni Parkway, Rome, NY 134 (dmzasada, psanyal)@mitre.org

More information

Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition

Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition Spatio-Temporal Naive-Bayes Nearest-Neighbor () for Skeleton-Based Ation Reognition Junwu Weng Chaoqun Weng Junsong Yuan Shool of Eletrial and Eletroni Engineering Nanyang Tehnologial University, Singapore

More information

Real-time Modeling of 3D Soccer Ball Trajectories from Multiple Fixed Cameras

Real-time Modeling of 3D Soccer Ball Trajectories from Multiple Fixed Cameras Real-time Modeling o 3D Soer Ball rajetories rom Multile Fixed Cameras Jinhang Ren, James rwell, Graeme A Jones and Ming u Astrat n this aer, model-ased aroahes or real-time 3D soer all traing are roosed,

More information

Active Compliant Motion Control for Grinding Robot

Active Compliant Motion Control for Grinding Robot Proeedings of the 17th World Congress The International Federation of Automati Control Ative Compliant Motion Control for Grinding Robot Juyi Park*, Soo Ho Kim* and Sungkwun Kim** *Daewoo Shipbuilding

More information

Patterned Wafer Segmentation

Patterned Wafer Segmentation atterned Wafer Segmentation ierrick Bourgeat ab, Fabrice Meriaudeau b, Kenneth W. Tobin a, atrick Gorria b a Oak Ridge National Laboratory,.O.Box 2008, Oak Ridge, TN 37831-6011, USA b Le2i Laboratory Univ.of

More information

Transition Detection Using Hilbert Transform and Texture Features

Transition Detection Using Hilbert Transform and Texture Features Amerian Journal of Signal Proessing 1, (): 35-4 DOI: 1.593/.asp.1.6 Transition Detetion Using Hilbert Transform and Texture Features G. G. Lashmi Priya *, S. Domni Department of Computer Appliations, National

More information

Expert Systems with Applications

Expert Systems with Applications Expert Systems with Appliations 39 (2012) 2842 2855 Contents lists available at SiVerse SieneDiret Expert Systems with Appliations journal homepage: www.elsevier.om/loate/eswa An automated vision system

More information

Single character type identification

Single character type identification Single character tye identification Yefeng Zheng*, Changsong Liu, Xiaoqing Ding Deartment of Electronic Engineering, Tsinghua University Beijing 100084, P.R. China ABSTRACT Different character recognition

More information

Type of document: Usebility Checklist

Type of document: Usebility Checklist Projet: JEGraph Type of doument: Usebility Cheklist Author: Max Bryan Version: 1.30 2011 Envidate GmbH Type of Doumet Developer guidelines User guidelines Dutybook Speifiation Programming and testing Test

More information

Superpixel Tracking. School of Information and Communication Engineering, Dalian University of Technology, China 2

Superpixel Tracking. School of Information and Communication Engineering, Dalian University of Technology, China 2 Superpixel Traking Shu Wang1, Huhuan Lu1, Fan Yang1, and Ming-Hsuan Yang2 1 Shool of Information and Communiation Engineering, Dalian University of Tehnology, China 2 Eletrial Engineering and Computer

More information

One Against One or One Against All : Which One is Better for Handwriting Recognition with SVMs?

One Against One or One Against All : Which One is Better for Handwriting Recognition with SVMs? One Against One or One Against All : Whih One is Better for Handwriting Reognition with SVMs? Jonathan Milgram, Mohamed Cheriet, Robert Sabourin To ite this version: Jonathan Milgram, Mohamed Cheriet,

More information

Unsupervised color film restoration using adaptive color equalization

Unsupervised color film restoration using adaptive color equalization Unsupervised olor film restoration using adaptive olor equalization A. Rizzi 1, C. Gatta 1, C. Slanzi 1, G. Cioa 2, R. Shettini 2 1 Dipartimento di Tenologie dell Informazione Università degli studi di

More information

FUZZY WATERSHED FOR IMAGE SEGMENTATION

FUZZY WATERSHED FOR IMAGE SEGMENTATION FUZZY WATERSHED FOR IMAGE SEGMENTATION Ramón Moreno, Manuel Graña Computational Intelligene Group, Universidad del País Vaso, Spain http://www.ehu.es/winto; {ramon.moreno,manuel.grana}@ehu.es Abstrat The

More information

Contents Contents...I List of Tables...VIII List of Figures...IX 1. Introduction Information Retrieval... 8

Contents Contents...I List of Tables...VIII List of Figures...IX 1. Introduction Information Retrieval... 8 Contents Contents...I List of Tables...VIII List of Figures...IX 1. Introdution... 1 1.1. Internet Information...2 1.2. Internet Information Retrieval...3 1.2.1. Doument Indexing...4 1.2.2. Doument Retrieval...4

More information

3D Model Based Pose Estimation For Omnidirectional Stereovision

3D Model Based Pose Estimation For Omnidirectional Stereovision 3D Model Based Pose Estimation For Omnidiretional Stereovision Guillaume Caron, Eri Marhand and El Mustapha Mouaddib Abstrat Robot vision has a lot to win as well with wide field of view indued by atadioptri

More information

On - Line Path Delay Fault Testing of Omega MINs M. Bellos 1, E. Kalligeros 1, D. Nikolos 1,2 & H. T. Vergos 1,2

On - Line Path Delay Fault Testing of Omega MINs M. Bellos 1, E. Kalligeros 1, D. Nikolos 1,2 & H. T. Vergos 1,2 On - Line Path Delay Fault Testing of Omega MINs M. Bellos, E. Kalligeros, D. Nikolos,2 & H. T. Vergos,2 Dept. of Computer Engineering and Informatis 2 Computer Tehnology Institute University of Patras,

More information

Detecting Outliers in High-Dimensional Datasets with Mixed Attributes

Detecting Outliers in High-Dimensional Datasets with Mixed Attributes Deteting Outliers in High-Dimensional Datasets with Mixed Attributes A. Koufakou, M. Georgiopoulos, and G.C. Anagnostopoulos 2 Shool of EECS, University of Central Florida, Orlando, FL, USA 2 Dept. of

More information

Wavelet Based Statistical Adapted Local Binary Patterns for Recognizing Avatar Faces

Wavelet Based Statistical Adapted Local Binary Patterns for Recognizing Avatar Faces Wavelet Based Statistical Adated Local Binary atterns for Recognizing Avatar Faces Abdallah A. Mohamed 1, 2 and Roman V. Yamolskiy 1 1 Comuter Engineering and Comuter Science, University of Louisville,

More information

Learning Discriminative and Shareable Features. Scene Classificsion

Learning Discriminative and Shareable Features. Scene Classificsion Learning Disriminative and Shareable Features for Sene Classifiation Zhen Zuo, Gang Wang, Bing Shuai, Lifan Zhao, Qingxiong Yang, and Xudong Jiang Nanyang Tehnologial University, Singapore, Advaned Digital

More information

Face Recognition with Local Binary Patterns

Face Recognition with Local Binary Patterns Face Recognition with Local Binary Patterns Ammad Ali, Shah Hussain, Farah Haroon, Sajid Hussain and M. Farhan Khan Abstract- This aer is about roviding efficient face recognition i.e. feature extraction

More information

The Mathematics of Simple Ultrasonic 2-Dimensional Sensing

The Mathematics of Simple Ultrasonic 2-Dimensional Sensing The Mathematis of Simple Ultrasoni -Dimensional Sensing President, Bitstream Tehnology The Mathematis of Simple Ultrasoni -Dimensional Sensing Introdution Our ompany, Bitstream Tehnology, has been developing

More information

Gait Based Human Recognition with Various Classifiers Using Exhaustive Angle Calculations in Model Free Approach

Gait Based Human Recognition with Various Classifiers Using Exhaustive Angle Calculations in Model Free Approach Ciruits and Systems, 2016, 7, 1465-1475 Published Online June 2016 in SiRes. http://www.sirp.org/journal/s http://dx.doi.org/10.4236/s.2016.78128 Gait Based Human Reognition with Various Classifiers Using

More information

Cross-layer Resource Allocation on Broadband Power Line Based on Novel QoS-priority Scheduling Function in MAC Layer

Cross-layer Resource Allocation on Broadband Power Line Based on Novel QoS-priority Scheduling Function in MAC Layer Communiations and Networ, 2013, 5, 69-73 http://dx.doi.org/10.4236/n.2013.53b2014 Published Online September 2013 (http://www.sirp.org/journal/n) Cross-layer Resoure Alloation on Broadband Power Line Based

More information

A Partial Sorting Algorithm in Multi-Hop Wireless Sensor Networks

A Partial Sorting Algorithm in Multi-Hop Wireless Sensor Networks A Partial Sorting Algorithm in Multi-Hop Wireless Sensor Networks Abouberine Ould Cheikhna Department of Computer Siene University of Piardie Jules Verne 80039 Amiens Frane Ould.heikhna.abouberine @u-piardie.fr

More information

521493S Computer Graphics Exercise 3 (Chapters 6-8)

521493S Computer Graphics Exercise 3 (Chapters 6-8) 521493S Comuter Grahics Exercise 3 (Chaters 6-8) 1 Most grahics systems and APIs use the simle lighting and reflection models that we introduced for olygon rendering Describe the ways in which each of

More information

A system for airport surveillance: detection of people running, abandoned objects and pointing gestures

A system for airport surveillance: detection of people running, abandoned objects and pointing gestures SPIE Defense & Security Symosium: Visual Information Processing 2011 A system for airort surveillance: detection of eole running, abandoned objects and ointing gestures Samuel Foucher, Marc Lalonde, Langis

More information

Weak Dependence on Initialization in Mixture of Linear Regressions

Weak Dependence on Initialization in Mixture of Linear Regressions Proeedings of the International MultiConferene of Engineers and Computer Sientists 8 Vol I IMECS 8, Marh -6, 8, Hong Kong Weak Dependene on Initialization in Mixture of Linear Regressions Ryohei Nakano

More information

4. Principles of Picture taking 4 hours

4. Principles of Picture taking 4 hours Leture 4 - - 0/3/003 Conet Hell/Pfeiffer February 003 4. Priniles of Piture taking 4 hours Aim: riniles of iture taking (normal ase, onvergent for oint measurements, flight lanning) flight lanning (arameter,

More information

Skip Strips: Maintaining Triangle Strips for View-dependent Rendering

Skip Strips: Maintaining Triangle Strips for View-dependent Rendering Ski Stris: Maintaining Triangle Stris for View-deendent Rendering Jihad El-Sana ; Elvir Azanli Amitabh Varshney Deartment of Mathematis and Comuter Siene Deartment of Comuter Siene Ben-Gurion University

More information

Multi-Piece Mold Design Based on Linear Mixed-Integer Program Toward Guaranteed Optimality

Multi-Piece Mold Design Based on Linear Mixed-Integer Program Toward Guaranteed Optimality INTERNATIONAL CONFERENCE ON MANUFACTURING AUTOMATION (ICMA200) Multi-Piee Mold Design Based on Linear Mixed-Integer Program Toward Guaranteed Optimality Stephen Stoyan, Yong Chen* Epstein Department of

More information