Detection and Recognition of Non-Occluded Objects using Signature Map

Size: px
Start display at page:

Download "Detection and Recognition of Non-Occluded Objects using Signature Map"

Transcription

1 6th WSEAS International Conferene on CIRCUITS, SYSTEMS, ELECTRONICS,CONTROL & SIGNAL PROCESSING, Cairo, Egypt, De 9-31, Detetion and Reognition of Non-Oluded Objets using Signature Map Sangbum Park, Youngjoon Han, Hernsoo Hahn College of Information Tehnology Soongsil University Sangdo-5Dong, Dongjak-Gu, Seoul Republi of KOREA Abstrat: - For onstruting a flexible bin piking system where parts an be provided with arbitrarily staked in a workspae, detetion and reognition of non-oluded objets are essential proess. For implementing suh proess, this paper proposes a new algorithm whih determines whether an objet is oluded or not and at the same time whih objet it is in the DB of objet models. It is based on a signature map whih is onstruted by deteting the objets in an input image and drawing the signatures of the whole image with referene to individual objets. Thus the number of signature maps is equal to the number of the objets deteted in the input image. A signature map shows the outer ontour and inside edge features. Olusion by other objets appears as distortions in the outer ontour of the signature map. The inside edge features are used for diserning the objets having the same outer ontour by different inside shape. To make the manipulator pik up a seleted part, a pose estimation method for elliptial objets is also proposed. The performane of the proposed algorithm has been tested with the task of piking the top or non-overlapped objet from a stak of arbitrarily loated objets. In the experiment, a reognition rate of 98% has been ahieved. Key-Words: - Bin-piking, Signature map, Contour traing, Objet detetion, Objet reognition 1 Introdution In many automati assembly systems, the known parts are palletized and thus reognition proess is not needed. However, if the parts an be delivered with unsorted, the palletizing devies are not needed but a omplex reognition and pose estimation proesses are required. For this reason, how effiiently represent 3D objets using the features that an be easily extrated has drawn a great attention from many researhers working for developing automati assembly systems. However, detetion of the top objet on a stak of arbitrarily loated objets still remains as the ore problem in onstrution of the bin piking system without pallets.[1,] Many researhers have proposed different solutions for bin-piking problem that a manipulator grasps an objet loated in a pallet onstraining the pose of the objet or on a onveyer belt without onstraints. To exatly loate the objet s pose, an objet representation sheme whih may provide suh information from its D image should be developed. Most objet representation shemes proposed for this purpose onstrut have been based on the shape from ontour method.[3,4] The features extrated from the D image are used for mathing with the objet models in the reognition module. When objets are overlapped in the image, the approahes based on the shape from ontour method generate many problems. One of them is that it requires an exessive omputation time sine all models in the database should be ompared with a test objet. The other one is that inorret mathing results may our if some parts of the objet features are oluded.[5] The approahes using T-juntion analysis for reognizing overlapped objets are suitable for diserning the objets having the linear ontours. When ontours are urved ones then it does not work appropriately.[6] For solving these problems, this paper propose a new signature map tehnique for extrating geometrial features of 3D objets using a D image to detet and reognize the top objet on a stak of 3D objets. The proposed method onsists of two parts: the generation of signature maps of an input image and the detetion and loalization of the top objet. To generate the signature map, we use an effetive and robust edge detetor to redue the noise or to reonstrut the lost portion of edges. For this reason, a ontour traing method whih is based on a ubi spline interpolation

2 6th WSEAS International Conferene on CIRCUITS, SYSTEMS, ELECTRONICS,CONTROL & SIGNAL PROCESSING, Cairo, Egypt, De 9-31, is used in the preproessing module. It is in order to inlude urved edges as well as linear edges in the appliation domain of the proposed method. Based on the proposed representation sheme, this paper proposes a new algorithm to find overlapped objet using bending point information. The algorithm memorizes the number of bending points of the objet models and ompares it with that of a test objet. If that of a test objet is bigger than that of the objet model, then the objet model is seleted as the model of the test objet. Finally, the depth information inluded on the signature map is extrated for estimating the pose of the objet. The depth information of the objets in the signature map is generated from ontours of objet. This signature map also desribes the objet features loated inside the boundary. This information is very useful to disern the objet having the same outer boundary but different inner shapes. The rest of this paper is onstruted as follows: Setion explains how to generate a signature map and how to use it for objet reognition. Setion 3 illustrates how to detet overlap of objets and selet the top objet. Setion 4 shows how to determine the pose of a deteted objet and Setion 5 illustrates the performane of the proposed algorithm by the experiments. Objet Reognition using Signature Map.1 Constrution of a signature map The signature of a 3D objet is generated from its D image. It draws the distanes of the boundary points from the enter of the objet in a D plane by inreasing the angle to the ounter-lok diretion as shown in Fig. 1. Thus the auray of a signature depends on how learly the boundary is deteted. To extrat the boundary for this purpose, ontour traing or boundary traking method is used in general. These methods are basially edge traking tehniques. They searh all neighboring pixels around the referene edge to test the onnetivity with it. Thus, they are very sensitive to noise or disonnetion of an edge sine suh things generate unertainty in determining the diretion to follow. To solve this problem, the signature map proposed in this paper desribes the internal and external edge features. Thus, even in the ase where there are objets having the same outer ontour shape but different internal edge features as shown in Fig. 1, the proposed algorithm an separate them learly. Fig. 1(a) shows the ase of having irular and Fig. 1(b) does the ase of having retangular arves, inside the outer boundary. Although both objets have the same outer ontour in signature map, the proposed method easily diserns one objet from another using the internal edge features. (a)cirular holes inluded (b)retangular arves inluded Fig. 1 The signature maps for the objets having the same outer ontour but different inside edge features When multiple objets are given in an image, the signature maps orresponding to individual objets are generated as shown in Fig.. If an objet is not oluded by any other objet, then the signature map generated with referene to the enter of this objet may generate the same signature as that of the objet model as shown in Fig. (a). However, if an objet is oluded by other objets as shown in Fig. (b), then the signature map generated with referene to the objet beomes distorted and it also shows whih objet is oluding the referene objet. (a)not-oluded ase (b)oluded ase Fig. The signature maps in the ases of oluded and not-oluded If a signature map is used, then a reognition task an be defined as a proess of testing if the signature of a test objet is mathing with whih objet model s signature. In order to simplify the signature omparison proess, the proposed algorithm uses the signature features suh as the number of poles(n p ), the angles between the poles(θ i ), the number of ontours(l) and the distane between ontours(d i ).

3 6th WSEAS International Conferene on CIRCUITS, SYSTEMS, ELECTRONICS,CONTROL & SIGNAL PROCESSING, Cairo, Egypt, De 9-31, Feature extration from a signature map The signature basially shows the shape of an objet. Therefore, a pole in a signature orresponds to a onvex vertex of an objet in a D image and the number of poles tells the number of orners. The pole is deteted analyzing the variation of signature as shown in Fig. 3(a). For a given signature, a hain ode is used to find a pole. However, a onventional hain ode representation is easily ontaminated by noise[7]. Therefore, this paper uses a false pole elimination tehnique using the forward and bakward detetion window given in Fig. 3(b). (a) Pole detetion by testing urvature variation (b) Bakward and forward detetion window () Pole andidate detetion (d) False pole elemination Fig. 3 Pole extration from a signature Let s assume that a signature as shown in Fig. 3() is given and the traing has begun from the leftmost top pixel shaped in the figure to generate an index sequene In the sequene, the pixel marked as B are onsidered as a pole andidate sine the index hange ours at the pixels. However a new edge is not generated from pixel B and the pattern is repeated, they are onsidered as a part of the edge and ontinues until pixel C. Sine a new index is appeared at pixel C, it is onsidered as a pole andidate and a new traing starts from it. If a new sequene is long enough to be onsidered as an edge, then pixel C is determined as a pole pixel. However, if the length of a new edge is too short as shown in Fig. 3(d) then it is onsidered as a part of an edge. Bakward detetion window is used to find a branhing point. When the poles are deteted in the signature map, the angle between the neighboring poles is same as the distane between poles in the signature map and it should be larger than a threshold Fig. 4 The internal features of the objet Differently from the outer ontour, the detetion of inside edge features requires more attention to eliminate false features generated by noise. Shadows or refletion aused by light soures may generate noisy features. To eliminate suh features, every feature is tested if it has the area larger than a threshold. If it is smaller than the threshold, then it is onsidered as a noisy region..3 Model registration and deision rule for mathing The signature map of eah model(m i ) is registered in the database as a feature vetor, M i ={ontour feature(f out ), internal feature(f in )}. F out and F in are defined as F out ={the number of pole(n p ), the angle between poles(θ i ), the number of ontour(l), the distane between ontours(d i )} and F in ={f in f i in= {Shape(S i ), Position(P i ), average intensity (I avg )}}, respetively. The mathing funtion T in Eq.(1) is utilized to deide for if two feature vetors A and B are oinide. The Boolean funtion T returns TRUE(1) if the differene between two features A and B is smaller than the error threshold(α). Otherwise, it returns FALSE(0). The error threshold (α) is deided by the experiments. T( A, B, α ) = BOOL 0< A α A B Using T, the deision rule omparing two feature vetors is defined as Eq. () whih tests the math of individual elements of the feature vetors. ( θ, θ, α) ( μ, μ, α) (,, α) (, d, α ) T = T T T L L m out m m m T d m In Eq. (), the subsript m and are the indies of the model and test objets. If the number of model objets mathed with the test objet is more than, the internal features are ompared using Eq.(3). ( ( ), ( ), α ) (,, α ) (, I, α ) T = T CS CS T p p m in m m T I m (1) () (3)

4 6th WSEAS International Conferene on CIRCUITS, SYSTEMS, ELECTRONICS,CONTROL & SIGNAL PROCESSING, Cairo, Egypt, De 9-31, In Eq. (3), C is the funtion of testing how lose to a irle, defined as Eq. (4). ( ) C S np = (4) π s ( L /) where n p is the number of pixel in the area S, L s is the distane of long axis 3 Overlap Deision and Reognition 3.1 Contour traing in the signature map Sine the ontour of a irular objet does not hange sharply, overlap of objets an be easily deteted by ontour traing. Fig. 8 illustrates the ontour deteting method used in this paper when the ontour is ontaminated by noise or disonnetion. If a ontour has a disonneted part, the algorithm estimates the diretion of ontour and alulates onnetive strength to apply the spline interpolation. This spline interpolation assumes that the ontour is differentiable at every points and its urvature does not hange a lot. Therefore, the algorithm selet those points whih are rendering a urvature smaller than a threshold among the neighboring points. For example, in Fig. 5, when disonneted point is deteted at the n-th pixel in setion A, the algorithm searhes the nearest edge in the shaded region. If found, then a setional polynomial-funtion whih is differentiable in the setion [x 0, x n ] is inserted to onnet the ontour given in setion A and the newly found edge. The onneted edge region is defined as a new setion A. In the same way, this ontour traing ontinues until it annot find the onneted edges any more. Setion B shows the reonstruted region by the interpolation proess urvature hanges abruptly. In the proess of ontour traing, a andidate for an olusion point is seleted by testing the following onditions given Eq. (5) whih tests the urvature variation range. d p p d + min max min max d p p d 0 α α max In Eq. (5), p p ± is a linear distane between two points, α [-π, π] is the angle between p and p ±, d min, d max and α max are the referene values to be used as the thresholds. α ( p) at an olusion point an be represented as the inlination between the edges, β (p)=π - α (p). Sine d min and d max define the angle differene, they are determined to be inversely proportional to the objet size (a) Cirular objets (b) Ellipse objets Fig. 6 Distorted signature by oluding objets 4 Pose Estimation of The Top Objet To ontrol a manipulator to pik up the target objet, its pose must be estimated with error smaller than the tolerable error. Fig. 7 shows onfiguration of the pose estimation proess where O is the world frame, C is the amera frame, and T is the objet frame. (5) Fig. 5 The ontour traing method 3. Overlap estimation If the target objet is overlapped, the signature beomes distorted as shown in Fig. 6. This distortion an be deteted by searhing the points where the Fig. 7 The onfiguration of the pose estimation proess To ontrol the manipulator, the relation, o H, between the world frame and the amera frame should be known. One o H is known, then the objet frame in the world frame an be extrated through measuring

5 6th WSEAS International Conferene on CIRCUITS, SYSTEMS, ELECTRONICS,CONTROL & SIGNAL PROCESSING, Cairo, Egypt, De 9-31, the objet frame with referene to the amera frame. Then, o H an be expressed by Eq. (6). HT = HC HT osθ sinθ 0 a (6) sinθ osα osθosα sinα sinαd HT = sinθsinα osθsinα osα osαd O O C O Under these relationships among the frames, as shown in Fig. 8(a), the objet pose an be represented by two rotation angles about X axis and Z axis and translation in the (X,Y) plane. The position of the objet frame with referene to the amera image frame (x,y) is determined first. After loating the amera so that the origin of the amera image frame and the objet enter, the amera is rotated about Z axis of the amera image frame by θ degrees to oinide the X axes of the amera image frame and the objet frame. Then it is rotated one more about the X axis of the amera image frame by α degrees to oinide the Z axes of the amera image frame and the objet frame. α an be by Eq.(7) using the lengths of the irular objet measured from Fig. 8(b). 1 ll α = os (7) l S By applying these pose parameters to Eq. (6), the pose of the objet in the world frame an be extrated. (a) Pose parameters (b) Definition of α Fig. 8 Definition of pose parameters 5 Experimental Results To evaluate the performane of the proposed algorithm, the algorithm has been implemented on the 6-DOF manipulator having a single amera mounted on the gripper. It is asked to detet and reognize and pik up the top or non-oluded objet among arbitrarily staked multiple objets. Six different types of objets are used to make a stak of objets. Their shapes and signature features are given in Table Reognition and detetion of the top objet To test the reognition auray, eah objet model is loated at an arbitrary position in a D plane and the algorithm is applied. This test has been repeated 100 times per eah objet model. Sine the result will be same if an objet is loated separately from other objets and it is segmented suessfully, the reognition performane is tested in this way. The experimental results testing the reognition proess are summarized in Table. The proess extrats the signature map with referene to the test objet and mathes with those of the 6 objet models, to find the best mathing objet model. Table1 The DB of the 6 objet models. Type External N p /θ i 48/8 0/0 0/0 L/d i /6,36 /10,38 3/3,0,38 Internal S i p i I avg Type External N p /θ i 0/0 6/60 0/0 L/d i /10,38 /18,7,4/1,17,5,7 Internal S i p i I avg Table The reognition rate [%]. Type Deision A B C D E F Corret Inorret Not-available As an be notied, the reognition rate depends on the shape of a test objet. In the ases of objet model B and D having the same outer ontour, reognition errors are ourred when the math proess is performed with only the outer ontours. However, if the inner features are also used, they an be suessfully diserned. In the ases of objet model A, E and F whih have distintive shapes of outer boundaries, the reognition is also suessful but there are hane to be failed sine there exists no inside edge feature. In ontrast, the objet model C whih has the

6 6th WSEAS International Conferene on CIRCUITS, SYSTEMS, ELECTRONICS,CONTROL & SIGNAL PROCESSING, Cairo, Egypt, De 9-31, inside edge features an be easily reognized even when other objets have the same outer boundary, sine it has enough inside edge features. The top objet detetion proess is tested with the 100 images in whih 3 to 10 objets of 6 types are arbitrarily staked. The task is to segment all not-oluded objets in the image. It is onfirmed by the experiments that the suessful detetion rate is over 98%. 5. Pose estimation of the top objet To test the auray of the pose estimation algorithm, the poses of the deteted not-oluded objets are estimated. Here the pose resolution of the manipulator is assumed less than 1.0[mm]. The rotation is expressed by the angles rotated with referene to the X and Z axes of the manipulator, and the position of the objet enter is expressed by the (X,Y) oordinates in the manipulator frame. The experimental results are summarized in Table 3. The error inluded in rotation estimation about the X axis inreases as rotation angle gets larger, but the error inluded in rotation estimation about the Z axis does not hange depending on the rotation angle, as an be expeted. Translation error also inreases if the objet is loated far from the origin of the amera image frame. As shown in Table 3, both rotation and translation errors are small enough to be used for guiding the manipulator to pik up an objet. Table 3 The errors inluded in the pose estimations. Contents Average Error X axis Rotation [degree] Z axis Translation [mm] Conlusions We have presented a new algorithm for detetion and reognition of the top objet on a stak of arbitrarily loated objets, using a signature map. A signature map is the signature of whole image generated with seleting the enter of a referene objet in the image as the enter of the signature. In a signature map, sine the signature of the referene objet is not distorted if it is not oluded, it an be determined of the referene objet is on the top or not. Of ourse, if an objet is loated without olusion, it is also onsidered as the top objet that an be grasped. The experimental results have show that the proposed method has several advantages in deteting and reognizing the top objet. The first one is that the method simultaneously detets and reognizes the top objet by analyzing the signature map. The seond one is that the method an disern those objets having the same boundaries but having different inside features. Above all, the an detet and reognize the objet even when the boundary of a referene objet is not ompletely onneted. To obtain these advantages, one weakness that must be enhaned is that the time omplexity inreases as the number of objets in the input image inreases. Referenes: [1] Berger. M, Bahler. G, Sherer. S, "Vision Guided Bin Piking and Mounting in a Flexible Assembly Cell," IEA/AIE 000, pp , 000. [] Dmitry Chetverikov, "A Simple and Effiient Algorithm for Detetion of High Curvature Points in Planar Curves," Computer Analysis of Image and Pattern 003, pp , 003. [3] Adnan A.Y. Mustafa, "Boundary Signature Mathing for Objet Reognition," VI001 Vision Interfae Annual Conferene, pp.7-79, 001. [4] Adnan A.Y. Mustafa, "Mathing Inomplete Objet Using Boundary Signatures," Proeedings of the 4th International Workshop on Visual Form, pp , 001. [5] Ovidiu Ghita, Paul F. Whelan, and John Mallon, A bin piking system based on depth from defous," Journal of Eletroni Image, Vol.14, Issue, pp.34-44, 003. [6] Kirkegaard.J, Moeslund.T.B, "Bin-Piking based on Harmoni Shape Contexts and Graph-Based Mathing," ICPR06, pp , 006. [7] Fu Chang and Chun-Jen Chen, "A Component -Labeling Algorithm Using Contour Traing Tehnique, IEEE Doument Analysis and Reognition, pp , 003.

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

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

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

Measurement of the stereoscopic rangefinder beam angular velocity using the digital image processing method

Measurement of the stereoscopic rangefinder beam angular velocity using the digital image processing method Measurement of the stereosopi rangefinder beam angular veloity using the digital image proessing method ROMAN VÍTEK Department of weapons and ammunition University of defense Kouniova 65, 62 Brno CZECH

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

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

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

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

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

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

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

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

Algorithms for External Memory Lecture 6 Graph Algorithms - Weighted List Ranking

Algorithms for External Memory Lecture 6 Graph Algorithms - Weighted List Ranking Algorithms for External Memory Leture 6 Graph Algorithms - Weighted List Ranking Leturer: Nodari Sithinava Sribe: Andi Hellmund, Simon Ohsenreither 1 Introdution & Motivation After talking about I/O-effiient

More information

Pipelined Multipliers for Reconfigurable Hardware

Pipelined Multipliers for Reconfigurable Hardware Pipelined Multipliers for Reonfigurable Hardware Mithell J. Myjak and José G. Delgado-Frias Shool of Eletrial Engineering and Computer Siene, Washington State University Pullman, WA 99164-2752 USA {mmyjak,

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 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

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

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

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

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

Boosted Random Forest

Boosted Random Forest Boosted Random Forest Yohei Mishina, Masamitsu suhiya and Hironobu Fujiyoshi Department of Computer Siene, Chubu University, 1200 Matsumoto-ho, Kasugai, Aihi, Japan {mishi, mtdoll}@vision.s.hubu.a.jp,

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

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

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

MATH STUDENT BOOK. 12th Grade Unit 6

MATH STUDENT BOOK. 12th Grade Unit 6 MATH STUDENT BOOK 12th Grade Unit 6 Unit 6 TRIGONOMETRIC APPLICATIONS MATH 1206 TRIGONOMETRIC APPLICATIONS INTRODUCTION 3 1. TRIGONOMETRY OF OBLIQUE TRIANGLES 5 LAW OF SINES 5 AMBIGUITY AND AREA OF A TRIANGLE

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

Defect Detection and Classification in Ceramic Plates Using Machine Vision and Naïve Bayes Classifier for Computer Aided Manufacturing

Defect Detection and Classification in Ceramic Plates Using Machine Vision and Naïve Bayes Classifier for Computer Aided Manufacturing Defet Detetion and Classifiation in Cerami Plates Using Mahine Vision and Naïve Bayes Classifier for Computer Aided Manufaturing 1 Harpreet Singh, 2 Kulwinderpal Singh, 1 Researh Student, 2 Assistant Professor,

More information

Drawing lines. Naïve line drawing algorithm. drawpixel(x, round(y)); double dy = y1 - y0; double dx = x1 - x0; double m = dy / dx; double y = y0;

Drawing lines. Naïve line drawing algorithm. drawpixel(x, round(y)); double dy = y1 - y0; double dx = x1 - x0; double m = dy / dx; double y = y0; Naïve line drawing algorithm // Connet to grid points(x0,y0) and // (x1,y1) by a line. void drawline(int x0, int y0, int x1, int y1) { int x; double dy = y1 - y0; double dx = x1 - x0; double m = dy / dx;

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

Boundary Correct Real-Time Soft Shadows

Boundary Correct Real-Time Soft Shadows Boundary Corret Real-Time Soft Shadows Bjarke Jakobsen Niels J. Christensen Bent D. Larsen Kim S. Petersen Informatis and Mathematial Modelling Tehnial University of Denmark {bj, nj, bdl}@imm.dtu.dk, kim@deadline.dk

More information

1. Introduction. 2. The Probable Stope Algorithm

1. Introduction. 2. The Probable Stope Algorithm 1. Introdution Optimization in underground mine design has reeived less attention than that in open pit mines. This is mostly due to the diversity o underground mining methods and omplexity o underground

More information

Exploring the Commonality in Feature Modeling Notations

Exploring the Commonality in Feature Modeling Notations Exploring the Commonality in Feature Modeling Notations Miloslav ŠÍPKA Slovak University of Tehnology Faulty of Informatis and Information Tehnologies Ilkovičova 3, 842 16 Bratislava, Slovakia miloslav.sipka@gmail.om

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

Calculation of typical running time of a branch-and-bound algorithm for the vertex-cover problem

Calculation of typical running time of a branch-and-bound algorithm for the vertex-cover problem Calulation of typial running time of a branh-and-bound algorithm for the vertex-over problem Joni Pajarinen, Joni.Pajarinen@iki.fi Otober 21, 2007 1 Introdution The vertex-over problem is one of a olletion

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

PARAMETRIC SAR IMAGE FORMATION - A PROMISING APPROACH TO RESOLUTION-UNLIMITED IMAGING. Yesheng Gao, Kaizhi Wang, Xingzhao Liu

PARAMETRIC SAR IMAGE FORMATION - A PROMISING APPROACH TO RESOLUTION-UNLIMITED IMAGING. Yesheng Gao, Kaizhi Wang, Xingzhao Liu 20th European Signal Proessing Conferene EUSIPCO 2012) Buharest, Romania, August 27-31, 2012 PARAMETRIC SAR IMAGE FORMATION - A PROMISING APPROACH TO RESOLUTION-UNLIMITED IMAGING Yesheng Gao, Kaizhi Wang,

More information

Contour Box: Rejecting Object Proposals Without Explicit Closed Contours

Contour Box: Rejecting Object Proposals Without Explicit Closed Contours Contour Box: Rejeting Objet Proposals Without Expliit Closed Contours Cewu Lu, Shu Liu Jiaya Jia Chi-Keung Tang The Hong Kong University of Siene and Tehnology Stanford University The Chinese University

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

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

An Optimized Approach on Applying Genetic Algorithm to Adaptive Cluster Validity Index

An Optimized Approach on Applying Genetic Algorithm to Adaptive Cluster Validity Index IJCSES International Journal of Computer Sienes and Engineering Systems, ol., No.4, Otober 2007 CSES International 2007 ISSN 0973-4406 253 An Optimized Approah on Applying Geneti Algorithm to Adaptive

More information

Dubins Path Planning of Multiple UAVs for Tracking Contaminant Cloud

Dubins Path Planning of Multiple UAVs for Tracking Contaminant Cloud Proeedings of the 17th World Congress The International Federation of Automati Control Dubins Path Planning of Multiple UAVs for Traking Contaminant Cloud S. Subhan, B.A. White, A. Tsourdos M. Shanmugavel,

More information

A {k, n}-secret Sharing Scheme for Color Images

A {k, n}-secret Sharing Scheme for Color Images A {k, n}-seret Sharing Sheme for Color Images Rastislav Luka, Konstantinos N. Plataniotis, and Anastasios N. Venetsanopoulos The Edward S. Rogers Sr. Dept. of Eletrial and Computer Engineering, University

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

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

Outline: Software Design

Outline: Software Design Outline: Software Design. Goals History of software design ideas Design priniples Design methods Life belt or leg iron? (Budgen) Copyright Nany Leveson, Sept. 1999 A Little History... At first, struggling

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

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

Tracking Table Tennis Balls in Real Match Scenes for Umpiring Applications

Tracking Table Tennis Balls in Real Match Scenes for Umpiring Applications British Journal of Mathematis & Computer Siene 1(4): 228-241, 2011 SCIENCEDOMAIN international www.sienedomain.org Traking Tale Tennis Balls in Real Math Senes for Umpiring Appliations K. C. P. Wong 1*

More information

What are Cycle-Stealing Systems Good For? A Detailed Performance Model Case Study

What are Cycle-Stealing Systems Good For? A Detailed Performance Model Case Study What are Cyle-Stealing Systems Good For? A Detailed Performane Model Case Study Wayne Kelly and Jiro Sumitomo Queensland University of Tehnology, Australia {w.kelly, j.sumitomo}@qut.edu.au Abstrat The

More information

A Unified Subdivision Scheme for Polygonal Modeling

A Unified Subdivision Scheme for Polygonal Modeling EUROGRAPHICS 2 / A. Chalmers and T.-M. Rhyne (Guest Editors) Volume 2 (2), Number 3 A Unified Subdivision Sheme for Polygonal Modeling Jérôme Maillot Jos Stam Alias Wavefront Alias Wavefront 2 King St.

More information

ASSESSMENT OF TWO CHEAP CLOSE-RANGE FEATURE EXTRACTION SYSTEMS

ASSESSMENT OF TWO CHEAP CLOSE-RANGE FEATURE EXTRACTION SYSTEMS ASSESSMENT OF TWO CHEAP CLOSE-RANGE FEATURE EXTRACTION SYSTEMS Ahmed Elaksher a, Mohammed Elghazali b, Ashraf Sayed b, and Yasser Elmanadilli b a Shool of Civil Engineering, Purdue University, West Lafayette,

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

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

Fitting conics to paracatadioptric projections of lines

Fitting conics to paracatadioptric projections of lines Computer Vision and Image Understanding 11 (6) 11 16 www.elsevier.om/loate/viu Fitting onis to paraatadioptri projetions of lines João P. Barreto *, Helder Araujo Institute for Systems and Robotis, Department

More information

Time delay estimation of reverberant meeting speech: on the use of multichannel linear prediction

Time delay estimation of reverberant meeting speech: on the use of multichannel linear prediction University of Wollongong Researh Online Faulty of Informatis - apers (Arhive) Faulty of Engineering and Information Sienes 7 Time delay estimation of reverberant meeting speeh: on the use of multihannel

More information

A Fast Sub-pixel Motion Estimation Algorithm for. H.264/AVC Video Coding

A Fast Sub-pixel Motion Estimation Algorithm for. H.264/AVC Video Coding A Fast Sub-pixel Motion Estimation Algorithm or H.64/AVC Video Coding Weiyao Lin Krit Panusopone David M. Baylon Ming-Ting Sun 3 Zhenzhong Chen 4 and Hongxiang Li 5 Institute o Image Communiation and Inormation

More information

ASL Recognition Based on a Coupling Between HMMs and 3D Motion Analysis

ASL Recognition Based on a Coupling Between HMMs and 3D Motion Analysis An earlier version of this paper appeared in the proeedings of the International Conferene on Computer Vision, pp. 33 3, Mumbai, India, January 4 7, 18 ASL Reognition Based on a Coupling Between HMMs and

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

NONLINEAR BACK PROJECTION FOR TOMOGRAPHIC IMAGE RECONSTRUCTION. Ken Sauer and Charles A. Bouman

NONLINEAR BACK PROJECTION FOR TOMOGRAPHIC IMAGE RECONSTRUCTION. Ken Sauer and Charles A. Bouman NONLINEAR BACK PROJECTION FOR TOMOGRAPHIC IMAGE RECONSTRUCTION Ken Sauer and Charles A. Bouman Department of Eletrial Engineering, University of Notre Dame Notre Dame, IN 46556, (219) 631-6999 Shool of

More information

Chapter 2: Introduction to Maple V

Chapter 2: Introduction to Maple V Chapter 2: Introdution to Maple V 2-1 Working with Maple Worksheets Try It! (p. 15) Start a Maple session with an empty worksheet. The name of the worksheet should be Untitled (1). Use one of the standard

More information

Automatic Physical Design Tuning: Workload as a Sequence Sanjay Agrawal Microsoft Research One Microsoft Way Redmond, WA, USA +1-(425)

Automatic Physical Design Tuning: Workload as a Sequence Sanjay Agrawal Microsoft Research One Microsoft Way Redmond, WA, USA +1-(425) Automati Physial Design Tuning: Workload as a Sequene Sanjay Agrawal Mirosoft Researh One Mirosoft Way Redmond, WA, USA +1-(425) 75-357 sagrawal@mirosoft.om Eri Chu * Computer Sienes Department University

More information

Relevance for Computer Vision

Relevance for Computer Vision The Geometry of ROC Spae: Understanding Mahine Learning Metris through ROC Isometris, by Peter A. Flah International Conferene on Mahine Learning (ICML-23) http://www.s.bris.a.uk/publiations/papers/74.pdf

More information

Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors

Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors Eurographis Symposium on Geometry Proessing (003) L. Kobbelt, P. Shröder, H. Hoppe (Editors) Rotation Invariant Spherial Harmoni Representation of 3D Shape Desriptors Mihael Kazhdan, Thomas Funkhouser,

More information

Using Augmented Measurements to Improve the Convergence of ICP

Using Augmented Measurements to Improve the Convergence of ICP Using Augmented Measurements to Improve the onvergene of IP Jaopo Serafin, Giorgio Grisetti Dept. of omputer, ontrol and Management Engineering, Sapienza University of Rome, Via Ariosto 25, I-0085, Rome,

More information

System-Level Parallelism and Throughput Optimization in Designing Reconfigurable Computing Applications

System-Level Parallelism and Throughput Optimization in Designing Reconfigurable Computing Applications System-Level Parallelism and hroughput Optimization in Designing Reonfigurable Computing Appliations Esam El-Araby 1, Mohamed aher 1, Kris Gaj 2, arek El-Ghazawi 1, David Caliga 3, and Nikitas Alexandridis

More information

A Load-Balanced Clustering Protocol for Hierarchical Wireless Sensor Networks

A Load-Balanced Clustering Protocol for Hierarchical Wireless Sensor Networks International Journal of Advanes in Computer Networks and Its Seurity IJCNS A Load-Balaned Clustering Protool for Hierarhial Wireless Sensor Networks Mehdi Tarhani, Yousef S. Kavian, Saman Siavoshi, Ali

More information

OFF-LINE ROBOT VISION SYSTEM PROGRAMMING USING A COMPUTER AIDED DESIGN SYSTEM S. SRIDARAN. Thesis submitted to the Faculty of the

OFF-LINE ROBOT VISION SYSTEM PROGRAMMING USING A COMPUTER AIDED DESIGN SYSTEM S. SRIDARAN. Thesis submitted to the Faculty of the OFF-LINE ROBOT VISION SYSTEM PROGRAMMING USING A COMPUTER AIDED DESIGN SYSTEM by S. SRIDARAN Thesis submitted to the Faulty of the Virginia Polytehni Institute and State University in partial fulfillment

More information

The Implementation of RRTs for a Remote-Controlled Mobile Robot

The Implementation of RRTs for a Remote-Controlled Mobile Robot ICCAS5 June -5, KINEX, Gyeonggi-Do, Korea he Implementation of RRs for a Remote-Controlled Mobile Robot Chi-Won Roh*, Woo-Sub Lee **, Sung-Chul Kang *** and Kwang-Won Lee **** * Intelligent Robotis Researh

More information

HEXA: Compact Data Structures for Faster Packet Processing

HEXA: Compact Data Structures for Faster Packet Processing Washington University in St. Louis Washington University Open Sholarship All Computer Siene and Engineering Researh Computer Siene and Engineering Report Number: 27-26 27 HEXA: Compat Data Strutures for

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

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

Wide-baseline Multiple-view Correspondences

Wide-baseline Multiple-view Correspondences Wide-baseline Multiple-view Correspondenes Vittorio Ferrari, Tinne Tuytelaars, Lu Van Gool, Computer Vision Group (BIWI), ETH Zuerih, Switzerland ESAT-PSI, University of Leuven, Belgium {ferrari,vangool}@vision.ee.ethz.h,

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

Flow Demands Oriented Node Placement in Multi-Hop Wireless Networks

Flow Demands Oriented Node Placement in Multi-Hop Wireless Networks Flow Demands Oriented Node Plaement in Multi-Hop Wireless Networks Zimu Yuan Institute of Computing Tehnology, CAS, China {zimu.yuan}@gmail.om arxiv:153.8396v1 [s.ni] 29 Mar 215 Abstrat In multi-hop wireless

More information

Video stabilization based on a 3D perspective camera model

Video stabilization based on a 3D perspective camera model Vis Comput DOI 10.1007/s00371-009-0310-z ORIGINAL ARTICLE Video stabilization based on a 3D perspetive amera model Guofeng Zhang Wei Hua Xueying Qin Yuanlong Shao Hujun Bao Springer-Verlag 2009 Abstrat

More information

Methods for Multi-Dimensional Robustness Optimization in Complex Embedded Systems

Methods for Multi-Dimensional Robustness Optimization in Complex Embedded Systems Methods for Multi-Dimensional Robustness Optimization in Complex Embedded Systems Arne Hamann, Razvan Rau, Rolf Ernst Institute of Computer and Communiation Network Engineering Tehnial University of Braunshweig,

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

Introduction to Seismology Spring 2008

Introduction to Seismology Spring 2008 MIT OpenCourseWare http://ow.mit.edu 1.510 Introdution to Seismology Spring 008 For information about iting these materials or our Terms of Use, visit: http://ow.mit.edu/terms. 1.510 Leture Notes 3.3.007

More information

NOISE is inevitable in any image-capturing process. Even

NOISE is inevitable in any image-capturing process. Even IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 34, NO. 7, JULY 2012 1329 Differene-Based Image Noise Modeling Using Skellam Distribution Youngbae Hwang, Member, IEEE, Jun-Sik Kim,

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

Particle Swarm Optimization for the Design of High Diffraction Efficient Holographic Grating

Particle Swarm Optimization for the Design of High Diffraction Efficient Holographic Grating Original Artile Partile Swarm Optimization for the Design of High Diffration Effiient Holographi Grating A.K. Tripathy 1, S.K. Das, M. Sundaray 3 and S.K. Tripathy* 4 1, Department of Computer Siene, Berhampur

More information

Self-Adaptive Parent to Mean-Centric Recombination for Real-Parameter Optimization

Self-Adaptive Parent to Mean-Centric Recombination for Real-Parameter Optimization Self-Adaptive Parent to Mean-Centri Reombination for Real-Parameter Optimization Kalyanmoy Deb and Himanshu Jain Department of Mehanial Engineering Indian Institute of Tehnology Kanpur Kanpur, PIN 86 {deb,hjain}@iitk.a.in

More information

Decoding positional and color information from a coded pattern Nelson L. Chang, Suk Hwan Lim, and Feng Tang

Decoding positional and color information from a coded pattern Nelson L. Chang, Suk Hwan Lim, and Feng Tang Deoding positional and olor information from a oded pattern Nelson L. Chang, Suk Hwan Li and Feng Tang HP Laboratories HPL-2010-131 Keyword(s): single shot oded patter amera alibratio geometri alibratio

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

Approximate logic synthesis for error tolerant applications

Approximate logic synthesis for error tolerant applications Approximate logi synthesis for error tolerant appliations Doohul Shin and Sandeep K. Gupta Eletrial Engineering Department, University of Southern California, Los Angeles, CA 989 {doohuls, sandeep}@us.edu

More information

A Dual-Hamiltonian-Path-Based Multicasting Strategy for Wormhole-Routed Star Graph Interconnection Networks

A Dual-Hamiltonian-Path-Based Multicasting Strategy for Wormhole-Routed Star Graph Interconnection Networks A Dual-Hamiltonian-Path-Based Multiasting Strategy for Wormhole-Routed Star Graph Interonnetion Networks Nen-Chung Wang Department of Information and Communiation Engineering Chaoyang University of Tehnology,

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

CleanUp: Improving Quadrilateral Finite Element Meshes

CleanUp: Improving Quadrilateral Finite Element Meshes CleanUp: Improving Quadrilateral Finite Element Meshes Paul Kinney MD-10 ECC P.O. Box 203 Ford Motor Company Dearborn, MI. 8121 (313) 28-1228 pkinney@ford.om Abstrat: Unless an all quadrilateral (quad)

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

Improved flooding of broadcast messages using extended multipoint relaying

Improved flooding of broadcast messages using extended multipoint relaying Improved flooding of broadast messages using extended multipoint relaying Pere Montolio Aranda a, Joaquin Garia-Alfaro a,b, David Megías a a Universitat Oberta de Catalunya, Estudis d Informàtia, Mulimèdia

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

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

arxiv: v1 [cs.gr] 10 Apr 2015

arxiv: v1 [cs.gr] 10 Apr 2015 REAL-TIME TOOL FOR AFFINE TRANSFORMATIONS OF TWO DIMENSIONAL IFS FRACTALS ELENA HADZIEVA AND MARIJA SHUMINOSKA arxiv:1504.02744v1 s.gr 10 Apr 2015 Abstrat. This work introdues a novel tool for interative,

More information

An Event Display for ATLAS H8 Pixel Test Beam Data

An Event Display for ATLAS H8 Pixel Test Beam Data An Event Display for ATLAS H8 Pixel Test Beam Data George Gollin Centre de Physique des Partiules de Marseille and University of Illinois April 17, 1999 g-gollin@uiu.edu An event display program is now

More information

TUMOR DETECTION IN MRI BRAIN IMAGE SEGMENTATION USING PHASE CONGRUENCY MODIFIED FUZZY C MEAN ALGORITHM

TUMOR DETECTION IN MRI BRAIN IMAGE SEGMENTATION USING PHASE CONGRUENCY MODIFIED FUZZY C MEAN ALGORITHM TUMOR DETECTION IN MRI BRAIN IMAGE SEGMENTATION USING PHASE CONGRUENCY MODIFIED FUZZY C MEAN ALGORITHM M. Murugeswari 1, M.Gayathri 2 1 Assoiate Professor, 2 PG Sholar 1,2 K.L.N College of Information

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

DETECTION METHOD FOR NETWORK PENETRATING BEHAVIOR BASED ON COMMUNICATION FINGERPRINT

DETECTION METHOD FOR NETWORK PENETRATING BEHAVIOR BASED ON COMMUNICATION FINGERPRINT DETECTION METHOD FOR NETWORK PENETRATING BEHAVIOR BASED ON COMMUNICATION FINGERPRINT 1 ZHANGGUO TANG, 2 HUANZHOU LI, 3 MINGQUAN ZHONG, 4 JIAN ZHANG 1 Institute of Computer Network and Communiation Tehnology,

More information

Triangles. Learning Objectives. Pre-Activity

Triangles. Learning Objectives. Pre-Activity Setion 3.2 Pre-tivity Preparation Triangles Geena needs to make sure that the dek she is building is perfetly square to the brae holding the dek in plae. How an she use geometry to ensure that the boards

More information

SEGMENTATION OF IMAGERY USING NETWORK SNAKES

SEGMENTATION OF IMAGERY USING NETWORK SNAKES SEGMENTATION OF IMAGERY USING NETWORK SNAKES Matthias Butenuth Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover Nienburger Str. 1, 30167 Hannover, Germany butenuth@ipi.uni-hannover.de

More information

C 2 C 3 C 1 M S. f e. e f (3,0) (0,1) (2,0) (-1,1) (1,0) (-1,0) (1,-1) (0,-1) (-2,0) (-3,0) (0,-2)

C 2 C 3 C 1 M S. f e. e f (3,0) (0,1) (2,0) (-1,1) (1,0) (-1,0) (1,-1) (0,-1) (-2,0) (-3,0) (0,-2) SPECIAL ISSUE OF IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION: MULTI-ROBOT SSTEMS, 00 Distributed reonfiguration of hexagonal metamorphi robots Jennifer E. Walter, Jennifer L. Welh, and Nany M. Amato Abstrat

More information