Multi-camera tracking algorithm study based on information fusion

Size: px
Start display at page:

Download "Multi-camera tracking algorithm study based on information fusion"

Transcription

1 International Conference on Avance Electronic Science an Technolog (AEST 016) Multi-camera tracking algorithm stu base on information fusion a Guoqiang Wang, Shangfu Li an Xue Wen School of Electronic Engineering, Heilongjiang Universit, Harbin , China. Abstract. Intelligent vieo surveillance technolog is a part of pattern recognition use for analzing, etracting an recognizing behavior characteristics of a moving target basing on computer algorithms. The target tracking algorithm combines particle filter an Mean-shift in overlapping multi-camera environment on the intelligent vieo surveillance sstem. Multicamera tracking is stuie using a fusion of SURF characteristics, color characteristics an geometric characteristic in Matlab. Eperimental results show that the metho of tracking between multiple cameras has goo accurac an stabilit. Kewors: characteristics fusion; target tracking; peestrian matching. 1 Introuction Intelligent vieo surveillance technolog is one aspect of pattern recognition, which uses a number of computer algorithms [1], analsis, etraction an recognition of moving objects within the vieo behavioral characteristics, an we use the computers to etermine whether the behavioral characteristics of the moving object are efine as "suspicious behavior". During the fift ears of research an evelopment, the target tracking has been largel use in various areas []. One camera can etect limite area, it is ifficult to track target with multiple perspectives, an long time an wie range, so using multiple cameras become inevitable. The avantages of multi-camera tracking are the wie fiel of view, comprehensive perspective an large monitoring area, which makes the multicamera tracking become popular. Metho summar Ever feature of object has its limitations when we match the object, so it is unable to reflect the characteristics of the target onl b using one feature, an it is also ifficult to match a target. Thus the robustness woul be improve if we use a various tpe of features. This paper uses SURF, color an geometric characteristics of peestrian profile to complete matching [3]. This metho is base on etecting, we shoul work out the SURF ke escriptor, color an geometric characteristics of the profile which are locate in the ivie target area, an then we calculate the size of the istance between the feature matries, as a result of those above, we coul complete the peestrian matching. The basic process of this paper shows below [4]. First of all, in orer to hanle the vieo sequences a Corresponing author : wangguoqiang@hlju.eu.cn 016. The authors - Publishe b Atlantis Press 50

2 from ifferent cameras, we shoul use backgroun subtraction to finish the motion segmentation an obtain the binar image of the target. The result is showe in Figure 1. Figure 1. The results of motion segmentation. 3 Feature etractions 3.1 SURF feature etraction SURF feature points matching metho is an improve metho of SIFT, mainl in terms of spee, an its efficienc is higher than the SIFT. SURF algorithm processes integral images an convolution that is onl relate to previous image, the own sampling is epening on applie increasing size of its core [5]. SURF algorithm can be analze at the same time several laers of image scale space, an eliminating the nee for two image sampling process, so the eecution time of the algorithm can be improve. SURF algorithm can be ivie into the following four steps: (1) Describe Gaussian prami structure scale space; () Locate feature points Position; (3) Determine the irection of the feature point; (4) Calculate SURF escriptors. (1) Describe Gaussian prami structure scale space The most important point of the reuce running time for SURF algorithm is that it uses the integral image. The formula (1) is given: i< j< I (1) = I ( ) (, ), i= 0 j= 0 The using filter is ifferent between SURF an SIFT when the buil the multi-scale space, SURF uses bo filter which is shown in Figure. Figure. Bo filter. SURF algorithm uses the Hessian matri eterminant approimation image. Formula () is the Hessian matri of one image piel: 51

3 H( f(, )) f f f f = () That is, each piel can orer out a Hessian matri. But because the feature point scale nee to have scale irrelevance, we nee to eecute Gaussian filter first, an then buil Hessian matri. The formula is given: L ( X, δ) L ( X, δ) H( X, δ ) = (, δ) (, δ) L X L X (3) δ Where, L ( X, δ) = G( δ)* I( X ), G( δ ) =, δ is the variance. L (, ) X δ is the image of a point of secon-orer filter with Gaussian convolution. L ( X, δ ), L ( X, δ ) is similar as above. Using mean filter to solve the secon erivative of the Gaussian in SURF, the approimation coefficients is w = 0.9, an then Hessian matri can be get b the formula above, the formula is: et( ) (0.9 ) H = D D D (4) () Locate feature points Position The principle of positioning feature points accuratel is that we shoul abanon all values which are lower than the setting etreme value, so that the number of iscoverable feature points can be reuce an ultimatel we can receive some points which have the most obvious features. (3) Determine the irection of the feature point After etecting the feature points, we nee to etermine the main irection of the feature point, to ensure that the feature points have a characteristic of rotation an scale invariance. We shoul select a ranom area corresponing to the regional scale in the vicinit of the points, an ientif the main orientation. SURF selects a circle area, an etermines the main orientation b using a metho of activit sector, the main orientation of a line can be realize. (4) Calculate SURF escriptors The metho of getting SURF escriptors: Select a 0s size of winow along the main orientation of the feature point position, an ivie it equall into a 4 4 rectangle, then calculate the Haar wavelet response of the feature points in each 5 5 rectangle space separatel, we can see that in Figure 3, is the Haar wavelet response of orientation, is the Haar wavelet response of orientation. Firstl, we shoul set a Gaussian-weighte for an intereste points. ( δ = 3.3 areas,, an in the vicinit of the center of s ) Then, we shoul calculate the cumulative sum of each rectangle. After this, each rectangle area has a 4-imentional intensit which represents a vector, its vector can be escribe as V s (,,, ), an finall we can get a 64-imentional feature vector. It can improve the robustness of the geometric istortion an positioning errors. = 5

4 Figure 3. The ke escriptors constitute. The similarit between the two images is etermine b using the Eucliean istance of the ke feature vector in SURF algorithm [6]. We take a critical point within the first image an search the former two feature points in the secon image which has a minimum Eucliean istance with the critical point. If the value that the minimum istance ivies the secon-smallest istance is lower than the set threshol value, we amit the two matche points [7]. 3. Color feature etraction Color feature has an important role in most object tracking methos because of its avantages, for eample, it has the invariance. It is changeless with object s changing imensions as well as rotatio n. Firstl, we translate the target image from the RGB color space to HSV color space. Then, after getting SURF ke point coorinates (,, ) we shoul calculate the H, S an V mean value of a 3 3 neighborhoo of the ke point. Finall, the piel values of ke point (, ) have been translate from ( RGB,, ) space into HSV space an escribe as the mean values (h,s,v), which is 3D color feature vector V c =[h, s, v]. 3.3 Geometric characteristics of the target profile The geometric characteristics of the peestrian s profile are escribe b the contour of the peestrian an the positional relationship of curve. In that case, we can etract several special points through the peestrian contour ege, calculate Eucliean istance between SURF feature points an etracte points, an efine the istance as the geometric characteristics of the peestrian profile. We use Cann operator to acquire the ege of the peestrian profile image, then use the results of binar image segmentation to remove the backgroun image of peestrian area an use a black backgroun to replace the original backgroun, so we ensure basicall that the Cann ege etraction operator is integrate, which is shown in Figure 4. Figure 4. Geometric features an its contour map. Select several special points from the ege of the image outline to etract the geometrical features of a peestrian (shown in Figure 4): (1) The maimum istance of the peestrian outline is efine as the long ais AD, which 53

5 represents the height of a peestrian profile; () Accoring to AD, we efine a horizontal ais BC which is perpenicular to the longituinal ais AD an place it at 1/4 AD, which represents the with of the peestrian contour; (3) Assume an SURF ke point P an the istance from P to A, D, B, C which constitutes the object contour feature vector V p : PA PD PB PC V p =,,, (5) AD AD AD AD Because the various features of V p is performe b calculating the ratio, V p possesses the invariance propert when the image is in a conition of rotation, translation an scale change. Detecte feature vectors have the same feature point in an peestrian image, an each feature point is a stable feature escriptor, which consists of the following parts: SURF escriptor V represents local S features characteristic points, color vector V c represents the color characteristics, geometric vector V p can remove local similar feature. So each point escriptor vector can be epresse as: F = αv, β, (1 α β) s Vc V p (6) In formula (6), α an β are weight an balance features, we aopt α = 0.3, β = Target tracking base on fusion We suppose that at t moment, there are M targets in the fiel of Camera i, which are segmente an marke; there are N targets in the fiel of Camera j, which are segmente an marke, M an N perhaps be equal. i We efine the - peestrian in Camera i is O, the number of SURF ke points obtaine is a ; j the - peestrian in Camera j is O, the number of SURF ke points obtaine is b ; calculate V c an V p which are in the 3*3 vicinit of the SURF ke points at the same time an get the feature vector matri value [ a *135] an [ b *135]. Give two feature escriptors F i an F i, then D can be got b the formula (7): where, 63 3 α β α β i j sik sjk ij pik pjk k= 0 k= 0 D = F F = ( V V ) + + (1 ) ( V V ) (7) ij = ( h h ) + ( s s ) h + s + h + s (8) The similarit of two matche is given: ( D 1 1, D,..., D ) DO (, O)= a a (9) The step of the algorithm is as follows: (1) The quantitative istribution of the whole peestrian areas in Camera i is 1~ M, an the quantitative istribution of the whole peestrian areas in Camera j is 1~ N. 54

6 () We select a peestrian area p an a multi-feature vector escriptor z in the fiel of Camera i, an calculate the istance D b formula (7) with all the escriptors in the whole peestrian area q of Camera j. Search the minimum similarit istance D between two escriptors an get the similarit istance between p an q b formula (9). (3) Back to step () an stop until we go through all the peestrian area of Camera i. Get the similarit istance between all the peestrian areas of Camera i an Camera j. (4) For an peestrian area in Camera i, the peestrian area in Camera j is matche to the one which has the minimum similarit istance. 5 Eperimental results an analsis Figure 5 is one image of Camera i an j, the image size is piel. There is a smaller overlapping area between Camera 1 an Camera. There is onl one peestrian in the fiel of Camera. We calculate the istance between the peestrian in Camera an the three peestrians in Camera 1 b formula (7) an (9) respectivel, an then we compare them an fin that the minimum istance is successfull matche with the camera 1. The match results are shown in Table 1. Table 1. The results of matching. Target in camera The istance The tracking results are shown in Figure 6, an the operating environment is MATLAB010a, the computer configuration is Pentium (R) Dual-Core processor TL GHz, G memor, Winows7 (3-bit) operating sstems. (a) The view of camera 1 (b) The view of camera Figure 5. The image of Camera 1 an Camera. (a) The results of camera 1 (b) The results of camera Figure 6. The results of tracking. 55

7 6 Summar This paper is in the framework of multi-camera vieo monitoring an analsis sstem, we use a fusion of SURF feature escriptors, colors an the geometric characteristics of the peestrian s profile to match the targets, an aim at improving the accurac of peestrian matching. Further stu will focus on how to link capture information from each camera an how to improve the efficienc of collaboration between multiple cameras in terms of time an accurac. References 1. C. Dorin, Kernel-base object tracking. IEEE Trans on Patern Analsis an Machine Intelligence, 5, (013). J. Czz, B. Ristic, B. Macq, A particle filter for joint etection an tracking of color objects. Image Vision Computing, 5, (01) 3. R.Mazzon, P. A.Cavallaro, Multi-camera tracking using a Multi-Goal Social Force Moel. Neurocomputing, 100, 41-50(013) 4. M. Piccari, E. D. Cheng, Track matching over isjoint camera views base on an incremental major color spectrum histogram. IEEE conference on Avance Vieo an Signal Base Surveillance. Como, (01) 5. G. Y. Lian, J. H. Lain, W. S. Zheng, Spatial-temporal consistent labeling of tracke peestrians across non-overlapping camera views. Pattern Recognition, 44, (010) 6. P. L. Mazzeo, P. Spagnolo, T. D Orazio, Object Tracking b Non-overlapping Distribute Camera Network., (ACIVS, 01) 7. X. G. Wang, Intelligent multi-camera vieo surveillance: A review. Pattern Recognition Letters, 34, 3-19(013) 56

STEREOSCOPIC ROBOT VISION SYSTEM

STEREOSCOPIC ROBOT VISION SYSTEM Palinko Oskar, ipl. eng. Facult of Technical Sciences, Department of Inustrial Sstems Engineering an Management, 21 000 Novi Sa, Dositej Obraovic Square 6, Serbia & Montenegro STEREOSCOPIC ROBOT VISION

More information

PHOTOGRAMMETRIC MEASUREMENT OF LINEAR OBJECTS WITH CCD CAMERAS SUPER-ELASTIC WIRES IN ORTHODONTICS AS AN EXAMPLE

PHOTOGRAMMETRIC MEASUREMENT OF LINEAR OBJECTS WITH CCD CAMERAS SUPER-ELASTIC WIRES IN ORTHODONTICS AS AN EXAMPLE PHOTOGRAMMETRIC MEASUREMENT OF LINEAR OBJECTS WITH CCD CAMERAS SUPER-ELASTIC WIRES IN ORTHODONTICS AS AN EAMPLE Tim SUTHAU, Matthias HEMMLEB, Dietmar URAN, Paul-Georg JOST-BRINKMANN Technical Universit

More information

X y. f(x,y,d) f(x,y,d) Peak. Motion stereo space. parameter space. (x,y,d) Motion stereo space. Parameter space. Motion stereo space.

X y. f(x,y,d) f(x,y,d) Peak. Motion stereo space. parameter space. (x,y,d) Motion stereo space. Parameter space. Motion stereo space. 3D Shape Measurement of Unerwater Objects Using Motion Stereo Hieo SAITO Hirofumi KAWAMURA Masato NAKAJIMA Department of Electrical Engineering, Keio Universit 3-14-1Hioshi Kouhoku-ku Yokohama 223, Japan

More information

Shift-map Image Registration

Shift-map Image Registration Shift-map Image Registration Svärm, Linus; Stranmark, Petter Unpublishe: 2010-01-01 Link to publication Citation for publishe version (APA): Svärm, L., & Stranmark, P. (2010). Shift-map Image Registration.

More information

Try It. Implicit and Explicit Functions. Video. Exploration A. Differentiating with Respect to x

Try It. Implicit and Explicit Functions. Video. Exploration A. Differentiating with Respect to x SECTION 5 Implicit Differentiation Section 5 Implicit Differentiation Distinguish between functions written in implicit form an eplicit form Use implicit ifferentiation to fin the erivative of a function

More information

Text Particles Multi-band Fusion for Robust Text Detection

Text Particles Multi-band Fusion for Robust Text Detection Text Particles Multi-ban Fusion for Robust Text Detection Pengfei Xu, Rongrong Ji, Hongxun Yao, Xiaoshuai Sun, Tianqiang Liu, an Xianming Liu School of Computer Science an Engineering Harbin Institute

More information

Shift-map Image Registration

Shift-map Image Registration Shift-map Image Registration Linus Svärm Petter Stranmark Centre for Mathematical Sciences, Lun University {linus,petter}@maths.lth.se Abstract Shift-map image processing is a new framework base on energy

More information

4.2 Implicit Differentiation

4.2 Implicit Differentiation 6 Chapter 4 More Derivatives 4. Implicit Differentiation What ou will learn about... Implicitl Define Functions Lenses, Tangents, an Normal Lines Derivatives of Higher Orer Rational Powers of Differentiable

More information

Implicit and Explicit Functions

Implicit and Explicit Functions 60_005.q //0 :5 PM Page SECTION.5 Implicit Differentiation Section.5 EXPLORATION Graphing an Implicit Equation How coul ou use a graphing utilit to sketch the graph of the equation? Here are two possible

More information

Viewing Transformations I Comp 535

Viewing Transformations I Comp 535 Viewing Transformations I Comp 535 Motivation Want to see our virtual 3-D worl on a 2-D screen 2 Graphics Pipeline Moel Space Moel Transformations Worl Space Viewing Transformation Ee/Camera Space Projection

More information

NEW METHOD FOR FINDING A REFERENCE POINT IN FINGERPRINT IMAGES WITH THE USE OF THE IPAN99 ALGORITHM 1. INTRODUCTION 2.

NEW METHOD FOR FINDING A REFERENCE POINT IN FINGERPRINT IMAGES WITH THE USE OF THE IPAN99 ALGORITHM 1. INTRODUCTION 2. JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 13/009, ISSN 164-6037 Krzysztof WRÓBEL, Rafał DOROZ * fingerprint, reference point, IPAN99 NEW METHOD FOR FINDING A REFERENCE POINT IN FINGERPRINT IMAGES

More information

1. Introduction. 2. Existing Shape Distortion Measurement Algorithms

1. Introduction. 2. Existing Shape Distortion Measurement Algorithms A Moifie Distortion Measurement Algorithm for Shape Coing Ferous Ahme Sohel, Laurence S Doole an Gour C Karmaar Gippslan School of Computing an Information an Technolog Monash Universit, Churchill, Victoria,

More information

A Circle Detection Method Based on Optimal Parameter Statistics in Embedded Vision

A Circle Detection Method Based on Optimal Parameter Statistics in Embedded Vision A Circle Detection Method Based on Optimal Parameter Statistics in Embedded Vision Xiaofeng Lu,, Xiangwei Li, Sumin Shen, Kang He, and Songu Yu Shanghai Ke Laborator of Digital Media Processing and Transmissions

More information

Evolutionary Optimisation Methods for Template Based Image Registration

Evolutionary Optimisation Methods for Template Based Image Registration Evolutionary Optimisation Methos for Template Base Image Registration Lukasz A Machowski, Tshilizi Marwala School of Electrical an Information Engineering University of Witwatersran, Johannesburg, South

More information

Linderoth, Magnus; Robertsson, Anders; Åström, Karl; Johansson, Rolf

Linderoth, Magnus; Robertsson, Anders; Åström, Karl; Johansson, Rolf Vision Base Tracker for Dart-Catching Robot Lineroth, Magnus; Robertsson, Aners; Åström, Karl; Johansson, Rolf 9 Link to publication Citation for publishe version (APA): Lineroth, M., Robertsson, A., Åström,

More information

Multimodal Stereo Image Registration for Pedestrian Detection

Multimodal Stereo Image Registration for Pedestrian Detection Multimoal Stereo Image Registration for Peestrian Detection Stephen Krotosky an Mohan Trivei Abstract This paper presents an approach for the registration of multimoal imagery for peestrian etection when

More information

SECTION 2. Objectives. Identify appropriate coordinate systems for solving problems with vectors.

SECTION 2. Objectives. Identify appropriate coordinate systems for solving problems with vectors. SECTION 2 Plan an Prepare Preview Vocabular Scientific Meaning The wor simultaneous is use for phenomena that occur together at the same time. Ask stuents to list some simultaneous phenomena, such as the

More information

Fast Window Based Stereo Matching for 3D Scene Reconstruction

Fast Window Based Stereo Matching for 3D Scene Reconstruction The International Arab Journal of Information Technology, Vol. 0, No. 3, May 203 209 Fast Winow Base Stereo Matching for 3D Scene Reconstruction Mohamma Mozammel Chowhury an Mohamma AL-Amin Bhuiyan Department

More information

A Neural Network Model Based on Graph Matching and Annealing :Application to Hand-Written Digits Recognition

A Neural Network Model Based on Graph Matching and Annealing :Application to Hand-Written Digits Recognition ITERATIOAL JOURAL OF MATHEMATICS AD COMPUTERS I SIMULATIO A eural etwork Moel Base on Graph Matching an Annealing :Application to Han-Written Digits Recognition Kyunghee Lee Abstract We present a neural

More information

Classical Mechanics Examples (Lagrange Multipliers)

Classical Mechanics Examples (Lagrange Multipliers) Classical Mechanics Examples (Lagrange Multipliers) Dipan Kumar Ghosh Physics Department, Inian Institute of Technology Bombay Powai, Mumbai 400076 September 3, 015 1 Introuction We have seen that the

More information

Learning convex bodies is hard

Learning convex bodies is hard Learning convex boies is har Navin Goyal Microsoft Research Inia navingo@microsoftcom Luis Raemacher Georgia Tech lraemac@ccgatecheu Abstract We show that learning a convex boy in R, given ranom samples

More information

A Plane Tracker for AEC-automation Applications

A Plane Tracker for AEC-automation Applications A Plane Tracker for AEC-automation Applications Chen Feng *, an Vineet R. Kamat Department of Civil an Environmental Engineering, University of Michigan, Ann Arbor, USA * Corresponing author (cforrest@umich.eu)

More information

Frequency Domain Parameter Estimation of a Synchronous Generator Using Bi-objective Genetic Algorithms

Frequency Domain Parameter Estimation of a Synchronous Generator Using Bi-objective Genetic Algorithms Proceeings of the 7th WSEAS International Conference on Simulation, Moelling an Optimization, Beijing, China, September 15-17, 2007 429 Frequenc Domain Parameter Estimation of a Snchronous Generator Using

More information

Vision-based Multi-Robot Simultaneous Localization and Mapping

Vision-based Multi-Robot Simultaneous Localization and Mapping Vision-base Multi-Robot Simultaneous Localization an Mapping Hassan Hajjiab an Robert Laganière VIVA Research Lab School of Information Technology an Engineering University of Ottawa, Ottawa, Canaa, K1N

More information

Classifying Facial Expression with Radial Basis Function Networks, using Gradient Descent and K-means

Classifying Facial Expression with Radial Basis Function Networks, using Gradient Descent and K-means Classifying Facial Expression with Raial Basis Function Networks, using Graient Descent an K-means Neil Allrin Department of Computer Science University of California, San Diego La Jolla, CA 9237 nallrin@cs.ucs.eu

More information

Regularized Laplacian Zero Crossings as Optimal Edge Integrators

Regularized Laplacian Zero Crossings as Optimal Edge Integrators Regularize aplacian Zero rossings as Optimal Ege Integrators R. KIMME A.M. BRUKSTEIN Department of omputer Science Technion Israel Institute of Technology Technion ity, Haifa 32, Israel Abstract We view

More information

Fingerprint Distortion Removal and Enhancement by Effective Use of Contextual Filtering

Fingerprint Distortion Removal and Enhancement by Effective Use of Contextual Filtering Fingerprint Distortion Removal an Enhancement b Effective Use of Contetual Filtering b Mubeen Ghafoor PE0800 A thesis submitte to the Electronics Engineering Department in partial fulfillment of the requirements

More information

New Geometric Interpretation and Analytic Solution for Quadrilateral Reconstruction

New Geometric Interpretation and Analytic Solution for Quadrilateral Reconstruction New Geometric Interpretation an Analytic Solution for uarilateral Reconstruction Joo-Haeng Lee Convergence Technology Research Lab ETRI Daejeon, 305 777, KOREA Abstract A new geometric framework, calle

More information

Image Segmentation using K-means clustering and Thresholding

Image Segmentation using K-means clustering and Thresholding Image Segmentation using Kmeans clustering an Thresholing Preeti Panwar 1, Girhar Gopal 2, Rakesh Kumar 3 1M.Tech Stuent, Department of Computer Science & Applications, Kurukshetra University, Kurukshetra,

More information

A New Search Algorithm for Solving Symmetric Traveling Salesman Problem Based on Gravity

A New Search Algorithm for Solving Symmetric Traveling Salesman Problem Based on Gravity Worl Applie Sciences Journal 16 (10): 1387-1392, 2012 ISSN 1818-4952 IDOSI Publications, 2012 A New Search Algorithm for Solving Symmetric Traveling Salesman Problem Base on Gravity Aliasghar Rahmani Hosseinabai,

More information

Feature Extraction and Rule Classification Algorithm of Digital Mammography based on Rough Set Theory

Feature Extraction and Rule Classification Algorithm of Digital Mammography based on Rough Set Theory Feature Extraction an Rule Classification Algorithm of Digital Mammography base on Rough Set Theory Aboul Ella Hassanien Jafar M. H. Ali. Kuwait University, Faculty of Aministrative Science, Quantitative

More information

Rough Set Approach for Classification of Breast Cancer Mammogram Images

Rough Set Approach for Classification of Breast Cancer Mammogram Images Rough Set Approach for Classification of Breast Cancer Mammogram Images Aboul Ella Hassanien Jafar M. H. Ali. Kuwait University, Faculty of Aministrative Science, Quantitative Methos an Information Systems

More information

Study of Network Optimization Method Based on ACL

Study of Network Optimization Method Based on ACL Available online at www.scienceirect.com Proceia Engineering 5 (20) 3959 3963 Avance in Control Engineering an Information Science Stuy of Network Optimization Metho Base on ACL Liu Zhian * Department

More information

Skyline Community Search in Multi-valued Networks

Skyline Community Search in Multi-valued Networks Syline Community Search in Multi-value Networs Rong-Hua Li Beijing Institute of Technology Beijing, China lironghuascut@gmail.com Jeffrey Xu Yu Chinese University of Hong Kong Hong Kong, China yu@se.cuh.eu.h

More information

Exercises of PIV. incomplete draft, version 0.0. October 2009

Exercises of PIV. incomplete draft, version 0.0. October 2009 Exercises of PIV incomplete raft, version 0.0 October 2009 1 Images Images are signals efine in 2D or 3D omains. They can be vector value (e.g., color images), real (monocromatic images), complex or binary

More information

Bends, Jogs, And Wiggles for Railroad Tracks and Vehicle Guide Ways

Bends, Jogs, And Wiggles for Railroad Tracks and Vehicle Guide Ways Ben, Jogs, An Wiggles for Railroa Tracks an Vehicle Guie Ways Louis T. Klauer Jr., PhD, PE. Work Soft 833 Galer Dr. Newtown Square, PA 19073 lklauer@wsof.com Preprint, June 4, 00 Copyright 00 by Louis

More information

Scale Invariant Feature Transform (SIFT) CS 763 Ajit Rajwade

Scale Invariant Feature Transform (SIFT) CS 763 Ajit Rajwade Scale Invariant Feature Transform (SIFT) CS 763 Ajit Rajwade What is SIFT? It is a technique for detecting salient stable feature points in an image. For ever such point it also provides a set of features

More information

Object Recognition Using Colour, Shape and Affine Invariant Ratios

Object Recognition Using Colour, Shape and Affine Invariant Ratios Object Recognition Using Colour, Shape an Affine Invariant Ratios Paul A. Walcott Centre for Information Engineering City University, Lonon EC1V 0HB, Englan P.A.Walcott@city.ac.uk Abstract This paper escribes

More information

Using the disparity space to compute occupancy grids from stereo-vision

Using the disparity space to compute occupancy grids from stereo-vision The 2010 IEEE/RSJ International Conference on Intelligent Robots an Systems October 18-22, 2010, Taipei, Taiwan Using the isparity space to compute occupancy gris from stereo-vision Mathias Perrollaz,

More information

Coupling the User Interfaces of a Multiuser Program

Coupling the User Interfaces of a Multiuser Program Coupling the User Interfaces of a Multiuser Program PRASUN DEWAN University of North Carolina at Chapel Hill RAJIV CHOUDHARY Intel Corporation We have evelope a new moel for coupling the user-interfaces

More information

New Version of Davies-Bouldin Index for Clustering Validation Based on Cylindrical Distance

New Version of Davies-Bouldin Index for Clustering Validation Based on Cylindrical Distance New Version of Davies-Boulin Inex for lustering Valiation Base on ylinrical Distance Juan arlos Roas Thomas Faculta e Informática Universia omplutense e Mari Mari, España correoroas@gmail.com Abstract

More information

Research Article Research on Law s Mask Texture Analysis System Reliability

Research Article Research on Law s Mask Texture Analysis System Reliability Research Journal of Applie Sciences, Engineering an Technology 7(19): 4002-4007, 2014 DOI:10.19026/rjaset.7.761 ISSN: 2040-7459; e-issn: 2040-7467 2014 Maxwell Scientific Publication Corp. Submitte: November

More information

A Versatile Model-Based Visibility Measure for Geometric Primitives

A Versatile Model-Based Visibility Measure for Geometric Primitives A Versatile Moel-Base Visibility Measure for Geometric Primitives Marc M. Ellenrieer 1,LarsKrüger 1, Dirk Stößel 2, an Marc Hanheie 2 1 DaimlerChrysler AG, Research & Technology, 89013 Ulm, Germany 2 Faculty

More information

Robust Camera Calibration for an Autonomous Underwater Vehicle

Robust Camera Calibration for an Autonomous Underwater Vehicle obust Camera Calibration for an Autonomous Unerwater Vehicle Matthew Bryant, Davi Wettergreen *, Samer Aballah, Alexaner Zelinsky obotic Systems Laboratory Department of Engineering, FEIT Department of

More information

Figure 1: Schematic of an SEM [source: ]

Figure 1: Schematic of an SEM [source:   ] EECI Course: -9 May 1 by R. Sanfelice Hybri Control Systems Eelco van Horssen E.P.v.Horssen@tue.nl Project: Scanning Electron Microscopy Introuction In Scanning Electron Microscopy (SEM) a (bunle) beam

More information

Incremental Detection of Text on Road Signs

Incremental Detection of Text on Road Signs Incremental Detection o Tet on Roa Signs Wen Wu Xilin hen Jie Yang arch 9, 4 U-S-4-6 School o omputer Science arnegie ellon Universit ittsburgh, A 5 Abstract This paper presents a ramework or incremental

More information

Almost Disjunct Codes in Large Scale Multihop Wireless Network Media Access Control

Almost Disjunct Codes in Large Scale Multihop Wireless Network Media Access Control Almost Disjunct Coes in Large Scale Multihop Wireless Network Meia Access Control D. Charles Engelhart Anan Sivasubramaniam Penn. State University University Park PA 682 engelhar,anan @cse.psu.eu Abstract

More information

Improved SURF Algorithm and Its Application in Seabed Relief Image Matching

Improved SURF Algorithm and Its Application in Seabed Relief Image Matching Improved SURF Algorithm and Its Application in Seabed Relief Image Matching Hong-Mei ZHANG 1, Le YANG, Ming-Long LI1 1 Department of Automation, School of Power and Mechanical Engineering Wuhan Universit,

More information

AN INVESTIGATION OF FOCUSING AND ANGULAR TECHNIQUES FOR VOLUMETRIC IMAGES BY USING THE 2D CIRCULAR ULTRASONIC PHASED ARRAY

AN INVESTIGATION OF FOCUSING AND ANGULAR TECHNIQUES FOR VOLUMETRIC IMAGES BY USING THE 2D CIRCULAR ULTRASONIC PHASED ARRAY AN INVESTIGATION OF FOCUSING AND ANGULAR TECHNIQUES FOR VOLUMETRIC IMAGES BY USING THE D CIRCULAR ULTRASONIC PHASED ARRAY S. Monal Lonon South Bank University; Engineering an Design 103 Borough Roa, Lonon

More information

A new fuzzy visual servoing with application to robot manipulator

A new fuzzy visual servoing with application to robot manipulator 2005 American Control Conference June 8-10, 2005. Portlan, OR, USA FrA09.4 A new fuzzy visual servoing with application to robot manipulator Marco A. Moreno-Armenariz, Wen Yu Abstract Many stereo vision

More information

An Investigation in the Use of Vehicle Reidentification for Deriving Travel Time and Travel Time Distributions

An Investigation in the Use of Vehicle Reidentification for Deriving Travel Time and Travel Time Distributions An Investigation in the Use of Vehicle Reientification for Deriving Travel Time an Travel Time Distributions Carlos Sun Department of Civil an Environmental Engineering, University of Missouri-Columbia,

More information

Short-term prediction of photovoltaic power based on GWPA - BP neural network model

Short-term prediction of photovoltaic power based on GWPA - BP neural network model Short-term preiction of photovoltaic power base on GWPA - BP neural networ moel Jian Di an Shanshan Meng School of orth China Electric Power University, Baoing. China Abstract In recent years, ue to China's

More information

Comparative Study of Projection/Back-projection Schemes in Cryo-EM Tomography

Comparative Study of Projection/Back-projection Schemes in Cryo-EM Tomography Comparative Stuy of Projection/Back-projection Schemes in Cryo-EM Tomography Yu Liu an Jong Chul Ye Department of BioSystems Korea Avance Institute of Science an Technology, Daejeon, Korea ABSTRACT In

More information

A fast embedded selection approach for color texture classification using degraded LBP

A fast embedded selection approach for color texture classification using degraded LBP A fast embee selection approach for color texture classification using egrae A. Porebski, N. Vanenbroucke an D. Hama Laboratoire LISIC - EA 4491 - Université u Littoral Côte Opale - 50, rue Ferinan Buisson

More information

A multiple wavelength unwrapping algorithm for digital fringe profilometry based on spatial shift estimation

A multiple wavelength unwrapping algorithm for digital fringe profilometry based on spatial shift estimation University of Wollongong Research Online Faculty of Engineering an Information Sciences - Papers: Part A Faculty of Engineering an Information Sciences 214 A multiple wavelength unwrapping algorithm for

More information

Real Time On Board Stereo Camera Pose through Image Registration*

Real Time On Board Stereo Camera Pose through Image Registration* 28 IEEE Intelligent Vehicles Symposium Einhoven University of Technology Einhoven, The Netherlans, June 4-6, 28 Real Time On Boar Stereo Camera Pose through Image Registration* Fai Dornaika French National

More information

Estimating Velocity Fields on a Freeway from Low Resolution Video

Estimating Velocity Fields on a Freeway from Low Resolution Video Estimating Velocity Fiels on a Freeway from Low Resolution Vieo Young Cho Department of Statistics University of California, Berkeley Berkeley, CA 94720-3860 Email: young@stat.berkeley.eu John Rice Department

More information

FINDING OPTICAL DISPERSION OF A PRISM WITH APPLICATION OF MINIMUM DEVIATION ANGLE MEASUREMENT METHOD

FINDING OPTICAL DISPERSION OF A PRISM WITH APPLICATION OF MINIMUM DEVIATION ANGLE MEASUREMENT METHOD Warsaw University of Technology Faculty of Physics Physics Laboratory I P Joanna Konwerska-Hrabowska 6 FINDING OPTICAL DISPERSION OF A PRISM WITH APPLICATION OF MINIMUM DEVIATION ANGLE MEASUREMENT METHOD.

More information

Animated Surface Pasting

Animated Surface Pasting Animate Surface Pasting Clara Tsang an Stephen Mann Computing Science Department University of Waterloo 200 University Ave W. Waterloo, Ontario Canaa N2L 3G1 e-mail: clftsang@cgl.uwaterloo.ca, smann@cgl.uwaterloo.ca

More information

5th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2015)

5th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2015) 5th International Conference on Avance Design an Manufacturing Engineering (ICADME 25) Research on motion characteristics an application of multi egree of freeom mechanism base on R-W metho Xiao-guang

More information

Approximation with Active B-spline Curves and Surfaces

Approximation with Active B-spline Curves and Surfaces Approximation with Active B-spline Curves an Surfaces Helmut Pottmann, Stefan Leopolseer, Michael Hofer Institute of Geometry Vienna University of Technology Wiener Hauptstr. 8 10, Vienna, Austria pottmann,leopolseer,hofer

More information

Object Recognition and Tracking for Scene Understanding of Outdoor Mobile Robot

Object Recognition and Tracking for Scene Understanding of Outdoor Mobile Robot Object Recognition an Tracking for Scene Unerstaning of Outoor Mobile Robot My-Ha Le Faculty of Electrical an Electronic Engineering Ho Chi Minh City University of Technology an Eucation No.1 Vo Van Ngan

More information

Intensive Hypercube Communication: Prearranged Communication in Link-Bound Machines 1 2

Intensive Hypercube Communication: Prearranged Communication in Link-Bound Machines 1 2 This paper appears in J. of Parallel an Distribute Computing 10 (1990), pp. 167 181. Intensive Hypercube Communication: Prearrange Communication in Link-Boun Machines 1 2 Quentin F. Stout an Bruce Wagar

More information

World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:10, No:4, 2016

World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:10, No:4, 2016 World Academ of Science, Engineering and Technolog X-Corner Detection for Camera Calibration Using Saddle Points Abdulrahman S. Alturki, John S. Loomis Abstract This paper discusses a corner detection

More information

6 Gradient Descent. 6.1 Functions

6 Gradient Descent. 6.1 Functions 6 Graient Descent In this topic we will iscuss optimizing over general functions f. Typically the function is efine f : R! R; that is its omain is multi-imensional (in this case -imensional) an output

More information

Refinement of scene depth from stereo camera ego-motion parameters

Refinement of scene depth from stereo camera ego-motion parameters Refinement of scene epth from stereo camera ego-motion parameters Piotr Skulimowski, Pawel Strumillo An algorithm for refinement of isparity (epth) map from stereoscopic sequences is propose. The metho

More information

Parts Assembly by Throwing Manipulation with a One-Joint Arm

Parts Assembly by Throwing Manipulation with a One-Joint Arm 21 IEEE/RSJ International Conference on Intelligent Robots an Systems, Taipei, Taiwan, October, 21. Parts Assembly by Throwing Manipulation with a One-Joint Arm Hieyuki Miyashita, Tasuku Yamawaki an Masahito

More information

CONTENT-BASED RETRIEVAL OF DEFECT IMAGES. Jukka Iivarinen and Jussi Pakkanen

CONTENT-BASED RETRIEVAL OF DEFECT IMAGES. Jukka Iivarinen and Jussi Pakkanen Proceeings of ACIVS 2002 (Avance Concepts for Intelligent Vision Systems), Ghent, Belgium, September 9-11, 2002 CONTENT-BASED RETRIEVAL OF DEFECT IMAGES Jukka Iivarinen an Jussi Pakkanen jukka.iivarinen@hut.fi,

More information

Data Mining: Clustering

Data Mining: Clustering Bi-Clustering COMP 790-90 Seminar Spring 011 Data Mining: Clustering k t 1 K-means clustering minimizes Where ist ( x, c i t i c t ) ist ( x m j 1 ( x ij i, c c t ) tj ) Clustering by Pattern Similarity

More information

Automation of Bird Front Half Deboning Procedure: Design and Analysis

Automation of Bird Front Half Deboning Procedure: Design and Analysis Automation of Bir Front Half Deboning Proceure: Design an Analysis Debao Zhou, Jonathan Holmes, Wiley Holcombe, Kok-Meng Lee * an Gary McMurray Foo Processing echnology Division, AAS Laboratory, Georgia

More information

THE APPLICATION OF ARTICLE k-th SHORTEST TIME PATH ALGORITHM

THE APPLICATION OF ARTICLE k-th SHORTEST TIME PATH ALGORITHM International Journal of Physics an Mathematical Sciences ISSN: 2277-2111 (Online) 2016 Vol. 6 (1) January-March, pp. 24-6/Mao an Shi. THE APPLICATION OF ARTICLE k-th SHORTEST TIME PATH ALGORITHM Hua Mao

More information

Particle Swarm Optimization Based on Smoothing Approach for Solving a Class of Bi-Level Multiobjective Programming Problem

Particle Swarm Optimization Based on Smoothing Approach for Solving a Class of Bi-Level Multiobjective Programming Problem BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 17, No 3 Sofia 017 Print ISSN: 1311-970; Online ISSN: 1314-4081 DOI: 10.1515/cait-017-0030 Particle Swarm Optimization Base

More information

Linear First-Order PDEs

Linear First-Order PDEs MODULE 2: FIRST-ORDER PARTIAL DIFFERENTIAL EQUATIONS 9 Lecture 2 Linear First-Orer PDEs The most general first-orer linear PDE has the form a(x, y)z x + b(x, y)z y + c(x, y)z = (x, y), (1) where a, b,

More information

Texture Defect Detection System with Image Deflection Compensation

Texture Defect Detection System with Image Deflection Compensation Texture Defect Detection System with Image Deflection Compensation CHUN-CHENG LIN CHENG-YU YEH Department of Electrical Engineering National Chin-Yi University of Technology 35, Lane 15, Sec. 1, Chungshan

More information

Wheelchair Detection in a Calibrated Environment

Wheelchair Detection in a Calibrated Environment Wheelchair Detection in a Calibrated Environment Ashish Mles Universit of Florida marcian@visto.com Dr. Niels Da Vitoria Lobo Universit of Central Florida niels@cs.ucf.edu Dr. Mubarak Shah Universit of

More information

Yet Another Parallel Hypothesis Search for Inverse Entailment Hiroyuki Nishiyama and Hayato Ohwada Faculty of Sci. and Tech. Tokyo University of Scien

Yet Another Parallel Hypothesis Search for Inverse Entailment Hiroyuki Nishiyama and Hayato Ohwada Faculty of Sci. and Tech. Tokyo University of Scien Yet Another Parallel Hypothesis Search for Inverse Entailment Hiroyuki Nishiyama an Hayato Ohwaa Faculty of Sci. an Tech. Tokyo University of Science, 2641 Yamazaki, Noa-shi, CHIBA, 278-8510, Japan hiroyuki@rs.noa.tus.ac.jp,

More information

Video Traffic Monitoring for Flow Optimization and Pollution Reduction

Video Traffic Monitoring for Flow Optimization and Pollution Reduction Vieo Traffic Monitoring for Flow Optimization an Pollution Reuction P. Payeur, Y. Liu Abstract - Vehicles are wiely recognize as one the main sources of pollution in urban areas. In the context of the

More information

Fundamentals of the stiffness method. Fundamentals of the stiffness method. Fundamentals of the stiffness method

Fundamentals of the stiffness method. Fundamentals of the stiffness method. Fundamentals of the stiffness method CHAPER 6 russ Analsis using Stiffness Metho Objectives เข าใจว ธ ของ stiffness metho ใช ว ธ stiffness metho ก บ russ, BM & rame จะพ ดถ งในบท หน า unamentals of the stiffness metho he stiffness metho: Is

More information

A Robust and Real-time Multi-feature Amalgamation. Algorithm for Fingerprint Segmentation

A Robust and Real-time Multi-feature Amalgamation. Algorithm for Fingerprint Segmentation A Robust and Real-time Multi-feature Amalgamation Algorithm for Fingerprint Segmentation Sen Wang Institute of Automation Chinese Academ of Sciences P.O.Bo 78 Beiing P.R.China100080 Yang Sheng Wang Institute

More information

MOTION IDENTIFICATION OF PLANAR FREE-FORM OBJECTS

MOTION IDENTIFICATION OF PLANAR FREE-FORM OBJECTS MOTION IDENTIFICATION OF PLANAR FREE-FORM OBJECTS Mustafa Unel Faculty of Engineering an Natural Sciences Sabanci University Orhanli-Tuzla 34956, Istanbul, Turkey email: munel@sabanciuniv.eu ABSTRACT It

More information

M-SIFT: A new method for Vehicle Logo Recognition

M-SIFT: A new method for Vehicle Logo Recognition 01 IEEE International Conference on Vehicular Electronics an Safety July 4-7, 01. Istanbul, Turkey M-SIFT: A new metho for Vehicle Logo Recognition Apostolos Psyllos, Christos-Nikolaos Anagnostopoulos,

More information

Calculation on diffraction aperture of cube corner retroreflector

Calculation on diffraction aperture of cube corner retroreflector November 10, 008 / Vol., No. 11 / CHINESE OPTICS LETTERS 8 Calculation on iffraction aperture of cube corner retroreflector Song Li (Ó Ø, Bei Tang (», an Hui Zhou ( ï School of Electronic Information,

More information

Texture Recognition with combined GLCM, Wavelet and Rotated Wavelet Features

Texture Recognition with combined GLCM, Wavelet and Rotated Wavelet Features International Journal of Computer an Electrical Engineering, Vol.3, No., February, 793-863 Texture Recognition with combine GLCM, Wavelet an Rotate Wavelet Features Dipankar Hazra Abstract Aim of this

More information

Using Vector and Raster-Based Techniques in Categorical Map Generalization

Using Vector and Raster-Based Techniques in Categorical Map Generalization Thir ICA Workshop on Progress in Automate Map Generalization, Ottawa, 12-14 August 1999 1 Using Vector an Raster-Base Techniques in Categorical Map Generalization Beat Peter an Robert Weibel Department

More information

Loop Scheduling and Partitions for Hiding Memory Latencies

Loop Scheduling and Partitions for Hiding Memory Latencies Loop Scheuling an Partitions for Hiing Memory Latencies Fei Chen Ewin Hsing-Mean Sha Dept. of Computer Science an Engineering University of Notre Dame Notre Dame, IN 46556 Email: fchen,esha @cse.n.eu Tel:

More information

Improving Spatial Reuse of IEEE Based Ad Hoc Networks

Improving Spatial Reuse of IEEE Based Ad Hoc Networks mproving Spatial Reuse of EEE 82.11 Base A Hoc Networks Fengji Ye, Su Yi an Biplab Sikar ECSE Department, Rensselaer Polytechnic nstitute Troy, NY 1218 Abstract n this paper, we evaluate an suggest methos

More information

Determining the 2d transformation that brings one image into alignment (registers it) with another. And

Determining the 2d transformation that brings one image into alignment (registers it) with another. And Last two lectures: Representing an image as a weighted combination of other images. Toda: A different kind of coordinate sstem change. Solving the biggest problem in using eigenfaces? Toda Recognition

More information

A Framework for Dialogue Detection in Movies

A Framework for Dialogue Detection in Movies A Framework for Dialogue Detection in Movies Margarita Kotti, Constantine Kotropoulos, Bartosz Ziólko, Ioannis Pitas, an Vassiliki Moschou Department of Informatics, Aristotle University of Thessaloniki

More information

WLAN Indoor Positioning Based on Euclidean Distances and Fuzzy Logic

WLAN Indoor Positioning Based on Euclidean Distances and Fuzzy Logic WLAN Inoor Positioning Base on Eucliean Distances an Fuzzy Logic Anreas TEUBER, Bern EISSFELLER Institute of Geoesy an Navigation, University FAF, Munich, Germany, e-mail: (anreas.teuber, bern.eissfeller)@unibw.e

More information

Advanced method of NC programming for 5-axis machining

Advanced method of NC programming for 5-axis machining Available online at www.scienceirect.com Proceia CIRP (0 ) 0 07 5 th CIRP Conference on High Performance Cutting 0 Avance metho of NC programming for 5-axis machining Sergej N. Grigoriev a, A.A. Kutin

More information

Correlation-based color mosaic interpolation using a connectionist approach

Correlation-based color mosaic interpolation using a connectionist approach Correlation-base color mosaic interpolation using a connectionist approach Gary L. Embler * Agilent Technologies, Inc. 75 Bowers Avenue, MS 87H Santa Clara, California 9554 USA ABSTRACT This paper presents

More information

Message Transport With The User Datagram Protocol

Message Transport With The User Datagram Protocol Message Transport With The User Datagram Protocol User Datagram Protocol (UDP) Use During startup For VoIP an some vieo applications Accounts for less than 10% of Internet traffic Blocke by some ISPs Computer

More information

Estimation of large-amplitude motion and disparity fields: Application to intermediate view reconstruction

Estimation of large-amplitude motion and disparity fields: Application to intermediate view reconstruction c 2000 SPIE. Personal use of this material is permitte. However, permission to reprint/republish this material for avertising or promotional purposes or for creating new collective works for resale or

More information

Research Article Scene Semantics Recognition Based on Target Detection and Fuzzy Reasoning

Research Article Scene Semantics Recognition Based on Target Detection and Fuzzy Reasoning Research Journal of Applied Sciences, Engineering and Technolog 7(5): 970-974, 04 DOI:0.906/rjaset.7.343 ISSN: 040-7459; e-issn: 040-7467 04 Mawell Scientific Publication Corp. Submitted: Januar 9, 03

More information

Computer Graphics Chapter 7 Three-Dimensional Viewing Viewing

Computer Graphics Chapter 7 Three-Dimensional Viewing Viewing Computer Graphics Chapter 7 Three-Dimensional Viewing Outline Overview of Three-Dimensional Viewing Concepts The Three-Dimensional Viewing Pipeline Three-Dimensional Viewing-Coorinate Parameters Transformation

More information

Dense Disparity Estimation in Ego-motion Reduced Search Space

Dense Disparity Estimation in Ego-motion Reduced Search Space Dense Disparity Estimation in Ego-motion Reuce Search Space Luka Fućek, Ivan Marković, Igor Cvišić, Ivan Petrović University of Zagreb, Faculty of Electrical Engineering an Computing, Croatia (e-mail:

More information

A Multi-scale Boosted Detector for Efficient and Robust Gesture Recognition

A Multi-scale Boosted Detector for Efficient and Robust Gesture Recognition A Multi-scale Booste Detector for Efficient an Robust Gesture Recognition Camille Monnier, Stan German, Anrey Ost Charles River Analytics Cambrige, MA, USA Abstract. We present an approach to etecting

More information

MORA: a Movement-Based Routing Algorithm for Vehicle Ad Hoc Networks

MORA: a Movement-Based Routing Algorithm for Vehicle Ad Hoc Networks : a Movement-Base Routing Algorithm for Vehicle A Hoc Networks Fabrizio Granelli, Senior Member, Giulia Boato, Member, an Dzmitry Kliazovich, Stuent Member Abstract Recent interest in car-to-car communications

More information

Exploring Context with Deep Structured models for Semantic Segmentation

Exploring Context with Deep Structured models for Semantic Segmentation 1 Exploring Context with Deep Structure moels for Semantic Segmentation Guosheng Lin, Chunhua Shen, Anton van en Hengel, Ian Rei between an image patch an a large backgroun image region. Explicitly moeling

More information

Deep Spatial Pyramid for Person Re-identification

Deep Spatial Pyramid for Person Re-identification Deep Spatial Pyrami for Person Re-ientification Sławomir Bąk Peter Carr Disney Research Pittsburgh, PA, USA, 15213 {slawomir.bak,peter.carr}@isneyresearch.com Abstract Re-ientification refers to the task

More information