Lecture 9: Other Applications of CNNs

Size: px
Start display at page:

Download "Lecture 9: Other Applications of CNNs"

Transcription

1 Applications of Convolutional Neual Netwoks CSED703R: Deep Leaning fo Visual Recognition (2016S) Lectue 9: Othe Applications of CNNs Bohyung Han Compute Vision Lab. Face ecognition and veification Peson eidentification Text egion detection Neual atistic style Object geneation Visual analogy Autonomous diving Many othes 2 Definition Face Veification Given two faces, detemine whethe they ae same peson o not. Binay decision by one-to-one matching Related poblem Face detection: finding faces Face ecognition: multi-class classification poblem Standad pipeline Siamese Netwok Deep Disciminative Metic Leaning (DDML) Leaning a distance metic! " $ %,$ ' = ) $ % ) $ ' Repesentation leaning Two banches shae weights. Objective + %',! " $ %, $ ' > 1 + %' = 1: same ID + %' = 1: diffeent ID Face Detection Face Alignment Featue Extaction Binay Classification, > [Hu2014] J. Hu, J. Lu, Y.-P. Tan: Disciminative Deep Metic Leaning fo Face Veification in the Wild. CVPR 2014

2 DeepID I CNN Achitectue Deep hidden IDentity featues (DeepID) 97.45% veification accuacy: as good as human pefomance (97.53%) CNN achitectue Type equation hee. Multiple scales > ' = max 0, B C D % E D %,' + C % E %,' + G ' % [Sun2014a] Y. Sun, X. Wang, X. Tang: Deep Leaning Face Repesentation fom Pedicting 10,000 Classes. CVPR Pepocessing Face detection Featue Extaction Landmak detection: two eyes, nose tip and two mouth cones Global face alignment: by tansfomation using two eye centes and mid-point of two mouth cones Featue extaction by CNN Extacted fom 10 sub-egions, thee scales, and {RGB, gay} 60 featues in total ConvNets 60 CNNs coesponding to 60 desied featues 160 dimensional vecto fo each featue Hoizontal flipping Length of DeepID: 160x2x60=19,200 8 Joint Bayesian Veification Algoithm $ = H + I, whee H is face identity and J is inta-class vaiation H ~ L 0, M H and I ~ L 0, M I Compute N $ O,$ P = log S $ O, $ P T U S $ O,$ P T V, which has a closed-fom solution. Neual netwoks highly-coelated subfeatue (640D) 60 goups

3 9 11 Compaison between Two Veifies Joint Bayesian is bette than neual netwok. Test accuacy (%) Joint identification-veification Numbe of classes fo taining DeepID II Face identification: inceases the inte-pesonal vaiations by dawing DeepID2 featues extacted fom diffeent identities apat Face veification: educes the inta-pesonal vaiations by pulling DeepID2 featues extacted fom the same identity togethe Featue extaction ) = Conv C; Z [ [Sun2014b] Y. Sun, Y. Chen, X. Wang, X. Tang: Deep Leaning Face Repesentation by Joint Identification- Veification. NIPS Results Compaison of state-of-the-at face veification methods on LFW Method Accuacy (%) No. of points No. of outside images images Featue dimension Joint Bayesian [8] (o) 5 99, ConvNet-RBM [31] (o) 3 87,628 N/A CMD+SLBP [17] (u) 3 N/A 2302 Fishe vecto faces [29] (u) 9 N/A Tom-vs-Pete classifies [2] (o+) 95 20, High-dim LBP [9] (o) 27 99, TL Joint Bayesian [6] (o+u) 27 99, DeepFace [32] (o+u) ,400, ,000, DeepID on CelebFaces (o) 5 87, DeepID on CelebFaces (o) 5 202, DeepID on CelebFaces+ & TL (o+u) 5 202, : esticted taining potocol, whee 6000 face pais given by LFW ae used fo 10-fold coss-validation u: unesticted taining potocol, whee moe taining pais can be geneated fom LFW using identity o: using outside taining data, howeve, without using taining data fom LFW o+: using both outside data and LFW data in the esticted potocol fo taining o+u: using both outside data and LFW data in the unesticted potocol fo taining TL: Joint Bayesian tansfe leaning fom CelebFaces+ to LFW 12 Human-level pefomance: Two loss functions Identification loss: coss-entopy Ident ), ^; Z %_ Veification loss Veif ) %,) ', > %' ; Z gh = Z gh = j Taining CNN b = B `% log ` % = log ` d %cd 1 2 ) % ) ' 1 2 max 0, j ) % ) ' ) = Conv C; Z [ Z %_ : paametes of softmax laye if > %' = 1 if > %' = 1

4 13 Goal Taining CNN Loss ) %, ) ',^, > %' ; Z [, Z %_, Z gh = Ident ), ^; Z %_ + oveif ) %,) ', > %' ; Z gh Taining Z [ while Z %_ and Z gh should be tained but ae not used in testing Magin j: a special case Cannot be updated by SGD since this will collapse to zeo Fixed and updated evey L(= 200,000) taining pai so that it minimizes veification eo of the pevious L taining pais while not convege do t t +1 sample two taining samples (x i,l i ) and (x j,l j ) fom χ f i = Conv(x i, θ c ) and f j = Conv(x j, θ c ) θ id = Ident(fi,li,θid) + Ident(fj,lj,θid) θid θid θ ve = λ Veif(fi,fj,yij,θve), whee y θve ij =1if l i = l j, and y ij = 1 othewise. f i = Ident(fi,li,θid) fi f j = Ident(fj,lj,θid) fj θ c = f i Conv(xi,θc) θc + λ Veif(fi,fj,yij,θve) fi + λ Veif(fi,fj,yij,θve) fj + f j Conv(xj,θc) θc update θ id = θ id η(t) θ id, θ ve = θ ve η(t) θ ve, and θ c = θ c η(t) θ c. end while output θ c method accuacy (%) High-dim LBP [4] ± 1.13 TL Joint Bayesian [2] ± 1.08 DeepFace [21] ± 0.25 DeepID [20] ± 0.26 GaussianFace [13] ± 0.66 DeepID ± 0.13 Human-level pefomance: Results on LFW 14 Featue extaction Veification Algoithm Detect 21 facial landmaks by SDM algoithm and align faces globally Cop 400 face patches with vaiations in positions, scales, colo channels, and hoizontal flipping ConvNet 200 CNNs: geneate 400 DeepID2 featue vectos with hoizontal flipping Featue vecto: 160D Featue dimensionality eduction Select 25 patches in a geedy manne PCA fom 25x160D to 180D Main goal Selected 25 face patches Neual Atistic Style Joint Bayesian fo veification Synthesizing two images epesenting both content and style Exploiting a petainedcnn fo image classification CNN VGG 19 laye net without fully connected layes No fine-tuning Aveage pooling: impoves gadient flow and get moe appealing esults 15 [Gatys15] L. A. Gatys, A. S. Ecke, M. Bethge: A Neual Algoithm of Atistic Style. axiv: ,

5 Method Optimization Notations Input: content Input: style Final Output output + Loss in featue map Loss in featue map coelation CNN p and q : oiginal content image and its featue map in the +-th laye $ and s : geneated image and its featue map in the +-th laye t and u : oiginal style image and its featue map in the +-th laye s,q, u R x y { y, whee L is the numbe of featue maps and is the size of featue map = width height ~ %' Å %' Loss s 'Ä u 'Ä = Ä s %Ä R x y x y : coelation of featue maps in the +-th laye = Ä u %Ä R x y x y : coelation of featue maps in the +-th laye Ç ÉÑÉÖÜ p, t, $ = áç àñâéäâé p, $ + ãç åéçüä t, $ Ç àñâéäâé p, $, + = 1 2 B s %' %,' q %' è E Ç åéçüä t, $ = 1 2 B 4L B ~ %' %,' Å %' Eo back-popagation Optimization Content: select a paticula laye such as conv4_2 Update ule: Ç àñâéäâé p, $, + = 1 2 B s %' ëç àñâéäâé ës %' q %' Style: use conv*_1 with equal weights (E = 0.2) Ç åéçüä t, $ = 1 2 BE ê Update ule: ëç åéçüä ës %' = ëç åéçüä ëê è ëê ës %' = í s %' = ï %,' q %' if s %' 0 if s %' 0 < 0 1 ê = 4L B ~ %' 1 2 E s '% ~ %' %,' Å %' Å %' if s %' 0 if s %' 0 < 0 Geneated Images Style1: The Stay Night Souce Style2: The Sceam [Gatys15] L. A. Gatys, A. S. Ecke, M. Bethge: A Neual Algoithm of Atistic Style. axiv: ,

6 Moe Examples Balance between Content and Style [Gatys15] L. A. Gatys, A. S. Ecke, M. Bethge: A Neual Algoithm of Atistic Style. axiv: , 2015 [Gatys15] L. A. Gatys, A. S. Ecke, M. Bethge: A Neual Algoithm of Atistic Style. axiv: , Multiple Styles Disciminative vs. Geneative CNN Disciminative CNN CNN Style1: The Stay Night Geneative CNN Object class Viewpoint Style Souce Style2: The Sceam [Gatys15] L. A. Gatys, A. S. Ecke, M. Bethge: A Neual Algoithm of Atistic Style. axiv: , Object class Viewpoint Style

7 Goal Geneate an object based on high-level inputs such as Class Oientation with espect to camea Additional paametes Rotation, tanslation, zoom Stetching hoizontally o vetically Hue, satuation, bightness Knowledge tansfe Geneative CNN leans the manifold of chais. Intepolation between viewpoints and diffeent objects Data Using 3D chai model dataset [Auby14] Oiginal dataset: 1393 chai models, 62 viewpoints, 31 azimuth angles, 2 elevation angles Sanitized vesion: 809 models, tight copping, esizing to 128x128 Notations ñ = ó D, ò D,Z D, ó, ò, Z,, ó x, ò x, Z x ó: class label ò: viewpoint Z: additional paametes ö = $ D, õ D, $, õ,, $ x, õ x $: taget RGB output image õ: segmentation mask 25 [Dosovitskiy15] A. Dosovitskiy, J. T. Spingenbeg, T. Box: Leaning to Geneate Chais with Convolutional Neual Netwoks. CVPR 2015 Netwok Achitectue 26 [Auby14] M. Auby, D. Matuana, A. Efos, and J. Sivic, Seeing 3D Chais: Exempla Pat-based 2D-3D Alignment using a Lage Dataset of CAD Models. CVPR 2014 Opeations h ù Unpooling: 2x2 Fixed location unpooling Deconvolution: 5x5 32M paametes altogethe û = ù h ReLU 27 28

8 Taining Netwok Capacity Objective function Minimizing the Euclidean eo in 2D of x Reconstuction of the segmented-out chai image Segmentation mask min B o ù h ó %, ò %, Z % $ % õ % + ùåä h ó %, ò %, Z % õ % %cd Visualization of uconv-3 laye filtes in 128x128 netwok RGB steam Tanslation Rotation Zoom Stetch Satuation Segmentation steam Bightness Colo [Saxe14] A. M. Saxe, J. L. McClelland, and S. Ganguli, Leaning a Nonlinea Embedding by Peseving Class Neighbouhood. ICLR Mophing Diffeent Chais Autonomous Diving Two pevious appoaches Mediated peception: pasing the entie scene to make a diving decision (e.g., Mobileye, Google) Behavio eflex: diectly mapping an input image to a diving decision by an egesso (ALVINN, LeCun et al.) Mediated Peception Input Image Diving Contol Behavio Reflex Diect Peception (ous) 31 Viewpoints in taining set [Chen15] C. Chen, A. Seff, A. Konhause, J. Xiao: DeepDiving: Leaning Affodance fo Diect Peception in Autonomous Diving. ICCV

9 Diect peception Deep Diving Estimating the affodance fo divinginstead of visually pasing the entie scene o blindly mapping an image to steeing angles Mapping an input image to a small numbe of key peception indicatos that diectly elate to the affodance of a oad/taffic state fo diving Poviding a set of compact yet complete desciptions of the scene to enable a simple contolle to dive autonomously Appoach Built upon deep convolutional neual netwok Tained and tested on TORCS (The Open Racing Ca Simulato) Automatically lean image featues fo estimating affodance elated to autonomous diving Much simple stuctue than the typical mediated peception appoach Moe intepetable than the typical behavio eflex appoach System achitectue RC Envionment Image peed ite Read haed Memo Diving Contols Platfom Read Image peed C Focusing on highway diving with multiple lanes Diving Contolle Thee configuations: a oad of one lane, two lanes, o thee lanes Read ite angle toma ing... dist... Contolle utput (a) one-lane (b) two-lane, left (c) two-lane, ight (d) thee-lane (e) inne lane mak. (f) bounday lane mak. Convolutional Neual Netwok Affodance Indicato Pediction of affodance indicato CNN angle tomaking_ll dist_ll tomaking_l dist_l always in lane system on making system always: 1) angle: angle between the ca s heading and the tangent of the oad in lane system, when diving in the lane: 2) tomaking LL: distance to the left lane making of the left lane 3) tomaking ML: distance to the left lane making of the cuent lane 4) tomaking MR: distance to the ight lane making of the cuent lane 5) tomaking RR: distance to the ight lane making of the ight lane 6) dist LL: distance to the peceding ca in the left lane 7) dist MM: distance to the peceding ca in the cuent lane 8) dist RR: distance to the peceding ca in the ight lane on making system, when diving on the lane making: 9) tomaking L: distance to the left lane making 10) tomaking M: distance to the cental lane making 11) tomaking R: distance to the ight lane making 12) dist L: distance to the peceding ca in the left lane 13) dist R: distance to the peceding ca in the ight lane (a) angle (b) in lane: tomaking (c) in lane: dist (d) on mak.: tomaking (e) on making: dist (f) ovelapping aea 35 36

10 Contolle Logic while (in autonomous diving mode) ConvNet outputs affodance indicatos check availability of both the left and ight lanes if (appoaching the peceding ca in the same lane) if (left lane exists and available and lane changing allowable) left lane changing decision made else if (ight lane exists and available and lane changing allowable) ight lane changing decision made else slow down decision made if (nomal diving) cente line= cente line of cuent lane else if (left/ight lane changing) cente line= cente line of objective lane compute steeing command compute desied speed compute acceleation/bake command based on desied speed Contolle Logic Steeing command: desied diection Desied speed steecmd = C angle dist_cente oad_width angle Ø, Ø dist_cente: distance to the cente line of the lane If the ca is tuning, a desied speed dop is computed accoding to the past few steeing angles. If thee is a peceding ca in close ange and a slow down decision is made, the desied speed is also detemined by the distance to the peceding ca. ^ = Ö 1 exp Æ Ö dist ^! dist ^ : distance to the peceding ca Implementation Achitectue and taining details Extension of AlexNet Input size: convolutional layes and 4 fully connected layes (4096, 4096, 256, 13 nodes) Mini-batch size: 64 Initial leaning ate: ,815 images fo taining: no copping and flipping Euclidean loss of nomalized output to [0.1, 0.9] Numbe of iteations: 140,000 Data geneation Using 7 tacks and 22 taffic cas in TORCS Geneating vaious taffic pattens of the taffic cas Manually diving the host ca on each tack multiple times Ceating exteme diving conditions (e.g. off the oad, collide with othe cas) Moe effective than automatic data collection using an AI ca 40 Testing Implementation Infomation fom TORCS: font facing image and speed of the host ca Contol fequency: 10 Hz, which is sufficient fo diving below 80 km/h Assumption The host ca is faste than the taffic when ovetaking cas in its left/ight lane. This assumption is equie because the system cannot see things behind.

11 Visualization of Leaned Models Deep Diving Demo Response map of KITTI-based ConvNet model 41 Response map of TORCS-based ConvNet model 42 C. Chen, A. Seff, A. Konhause,J. Xiao: DeepDiving: Leaning Affodance fo Diect Peception in Autonomous Diving. ICCV

Lecture 10: Other Applications of CNNs

Lecture 10: Other Applications of CNNs Applications of Convolutional Neural Networks CSED703: Deep Learning for Visual ecognition (207F) Lecture 0: Other Applications of CNNs Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr Face recognition

More information

Journal of World s Electrical Engineering and Technology J. World. Elect. Eng. Tech. 1(1): 12-16, 2012

Journal of World s Electrical Engineering and Technology J. World. Elect. Eng. Tech. 1(1): 12-16, 2012 2011, Scienceline Publication www.science-line.com Jounal of Wold s Electical Engineeing and Technology J. Wold. Elect. Eng. Tech. 1(1): 12-16, 2012 JWEET An Efficient Algoithm fo Lip Segmentation in Colo

More information

Detection and Recognition of Alert Traffic Signs

Detection and Recognition of Alert Traffic Signs Detection and Recognition of Alet Taffic Signs Chia-Hsiung Chen, Macus Chen, and Tianshi Gao 1 Stanfod Univesity Stanfod, CA 9305 {echchen, macuscc, tianshig}@stanfod.edu Abstact Taffic signs povide dives

More information

Controlled Information Maximization for SOM Knowledge Induced Learning

Controlled Information Maximization for SOM Knowledge Induced Learning 3 Int'l Conf. Atificial Intelligence ICAI'5 Contolled Infomation Maximization fo SOM Knowledge Induced Leaning Ryotao Kamimua IT Education Cente and Gaduate School of Science and Technology, Tokai Univeisity

More information

Topic -3 Image Enhancement

Topic -3 Image Enhancement Topic -3 Image Enhancement (Pat 1) DIP: Details Digital Image Pocessing Digital Image Chaacteistics Spatial Spectal Gay-level Histogam DFT DCT Pe-Pocessing Enhancement Restoation Point Pocessing Masking

More information

Positioning of a robot based on binocular vision for hand / foot fusion Long Han

Positioning of a robot based on binocular vision for hand / foot fusion Long Han 2nd Intenational Confeence on Advances in Mechanical Engineeing and Industial Infomatics (AMEII 26) Positioning of a obot based on binocula vision fo hand / foot fusion Long Han Compute Science and Technology,

More information

Prof. Feng Liu. Fall /17/2016

Prof. Feng Liu. Fall /17/2016 Pof. Feng Liu Fall 26 http://www.cs.pdx.edu/~fliu/couses/cs447/ /7/26 Last time Compositing NPR 3D Gaphics Toolkits Tansfomations 2 Today 3D Tansfomations The Viewing Pipeline Mid-tem: in class, Nov. 2

More information

Lecture # 04. Image Enhancement in Spatial Domain

Lecture # 04. Image Enhancement in Spatial Domain Digital Image Pocessing CP-7008 Lectue # 04 Image Enhancement in Spatial Domain Fall 2011 2 domains Spatial Domain : (image plane) Techniques ae based on diect manipulation of pixels in an image Fequency

More information

Image Enhancement in the Spatial Domain. Spatial Domain

Image Enhancement in the Spatial Domain. Spatial Domain 8-- Spatial Domain Image Enhancement in the Spatial Domain What is spatial domain The space whee all pixels fom an image In spatial domain we can epesent an image by f( whee x and y ae coodinates along

More information

Color Correction Using 3D Multiview Geometry

Color Correction Using 3D Multiview Geometry Colo Coection Using 3D Multiview Geomety Dong-Won Shin and Yo-Sung Ho Gwangju Institute of Science and Technology (GIST) 13 Cheomdan-gwagio, Buk-ku, Gwangju 500-71, Republic of Koea ABSTRACT Recently,

More information

Module 6 STILL IMAGE COMPRESSION STANDARDS

Module 6 STILL IMAGE COMPRESSION STANDARDS Module 6 STILL IMAE COMPRESSION STANDARDS Lesson 17 JPE-2000 Achitectue and Featues Instuctional Objectives At the end of this lesson, the students should be able to: 1. State the shotcomings of JPE standad.

More information

A Minutiae-based Fingerprint Matching Algorithm Using Phase Correlation

A Minutiae-based Fingerprint Matching Algorithm Using Phase Correlation A Minutiae-based Fingepint Matching Algoithm Using Phase Coelation Autho Chen, Weiping, Gao, Yongsheng Published 2007 Confeence Title Digital Image Computing: Techniques and Applications DOI https://doi.og/10.1109/dicta.2007.4426801

More information

17/5/2009. Introduction

17/5/2009. Introduction 7/5/9 Steeo Imaging Intoduction Eample of Human Vision Peception of Depth fom Left and ight eye images Diffeence in elative position of object in left and ight eyes. Depth infomation in the views?? 7/5/9

More information

Shape Matching / Object Recognition

Shape Matching / Object Recognition Image Pocessing - Lesson 4 Poduction Line object classification Object Recognition Shape Repesentation Coelation Methods Nomalized Coelation Local Methods Featue Matching Coespondence Poblem Alignment

More information

Multidimensional Testing

Multidimensional Testing Multidimensional Testing QA appoach fo Stoage netwoking Yohay Lasi Visuality Systems 1 Intoduction Who I am Yohay Lasi, QA Manage at Visuality Systems Visuality Systems the leading commecial povide of

More information

Effects of Model Complexity on Generalization Performance of Convolutional Neural Networks

Effects of Model Complexity on Generalization Performance of Convolutional Neural Networks Effects of Model Complexity on Genealization Pefomance of Convolutional Neual Netwoks Tae-Jun Kim 1, Dongsu Zhang 2, and Joon Shik Kim 3 1 Seoul National Univesity, Seoul 151-742, Koea, E-mail: tjkim@bi.snu.ac.k

More information

a Not yet implemented in current version SPARK: Research Kit Pointer Analysis Parameters Soot Pointer analysis. Objectives

a Not yet implemented in current version SPARK: Research Kit Pointer Analysis Parameters Soot Pointer analysis. Objectives SPARK: Soot Reseach Kit Ondřej Lhoták Objectives Spak is a modula toolkit fo flow-insensitive may points-to analyses fo Java, which enables expeimentation with: vaious paametes of pointe analyses which

More information

CSE 165: 3D User Interaction

CSE 165: 3D User Interaction CSE 165: 3D Use Inteaction Lectue #6: Selection Instucto: Jugen Schulze, Ph.D. 2 Announcements Homewok Assignment #2 Due Fiday, Januay 23 d at 1:00pm 3 4 Selection and Manipulation 5 Why ae Selection and

More information

Multiview plus depth video coding with temporal prediction view synthesis

Multiview plus depth video coding with temporal prediction view synthesis 1 Multiview plus depth video coding with tempoal pediction view synthesis Andei I. Puica, Elie G. Moa, Beatice Pesquet-Popescu, Fellow, IEEE, Maco Cagnazzo, Senio Membe, IEEE and Bogdan Ionescu, Senio

More information

RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES

RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES Svetlana Avetisyan Mikayel Samvelyan* Matun Kaapetyan Yeevan State Univesity Abstact In this pape, the class

More information

Segmentation of Casting Defects in X-Ray Images Based on Fractal Dimension

Segmentation of Casting Defects in X-Ray Images Based on Fractal Dimension 17th Wold Confeence on Nondestuctive Testing, 25-28 Oct 2008, Shanghai, China Segmentation of Casting Defects in X-Ray Images Based on Factal Dimension Jue WANG 1, Xiaoqin HOU 2, Yufang CAI 3 ICT Reseach

More information

UCB CS61C : Machine Structures

UCB CS61C : Machine Structures inst.eecs.bekeley.edu/~cs61c UCB CS61C : Machine Stuctues Lectue SOE Dan Gacia Lectue 28 CPU Design : Pipelining to Impove Pefomance 2010-04-05 Stanfod Reseaches have invented a monitoing technique called

More information

A Two-stage and Parameter-free Binarization Method for Degraded Document Images

A Two-stage and Parameter-free Binarization Method for Degraded Document Images A Two-stage and Paamete-fee Binaization Method fo Degaded Document Images Yung-Hsiang Chiu 1, Kuo-Liang Chung 1, Yong-Huai Huang 2, Wei-Ning Yang 3, Chi-Huang Liao 4 1 Depatment of Compute Science and

More information

Frequency Domain Approach for Face Recognition Using Optical Vanderlugt Filters

Frequency Domain Approach for Face Recognition Using Optical Vanderlugt Filters Optics and Photonics Jounal, 016, 6, 94-100 Published Online August 016 in SciRes. http://www.scip.og/jounal/opj http://dx.doi.og/10.436/opj.016.68b016 Fequency Domain Appoach fo Face Recognition Using

More information

Goal. Rendering Complex Scenes on Mobile Terminals or on the web. Rendering on Mobile Terminals. Rendering on Mobile Terminals. Walking through images

Goal. Rendering Complex Scenes on Mobile Terminals or on the web. Rendering on Mobile Terminals. Rendering on Mobile Terminals. Walking through images Goal Walking though s -------------------------------------------- Kadi Bouatouch IRISA Univesité de Rennes I, Fance Rendeing Comple Scenes on Mobile Teminals o on the web Rendeing on Mobile Teminals Rendeing

More information

All lengths in meters. E = = 7800 kg/m 3

All lengths in meters. E = = 7800 kg/m 3 Poblem desciption In this poblem, we apply the component mode synthesis (CMS) technique to a simple beam model. 2 0.02 0.02 All lengths in metes. E = 2.07 10 11 N/m 2 = 7800 kg/m 3 The beam is a fee-fee

More information

MapReduce Optimizations and Algorithms 2015 Professor Sasu Tarkoma

MapReduce Optimizations and Algorithms 2015 Professor Sasu Tarkoma apreduce Optimizations and Algoithms 2015 Pofesso Sasu Takoma www.cs.helsinki.fi Optimizations Reduce tasks cannot stat befoe the whole map phase is complete Thus single slow machine can slow down the

More information

Mobility Pattern Recognition in Mobile Ad-Hoc Networks

Mobility Pattern Recognition in Mobile Ad-Hoc Networks Mobility Patten Recognition in Mobile Ad-Hoc Netwoks S. M. Mousavi Depatment of Compute Engineeing, Shaif Univesity of Technology sm_mousavi@ce.shaif.edu H. R. Rabiee Depatment of Compute Engineeing, Shaif

More information

Voting-Based Grouping and Interpretation of Visual Motion

Voting-Based Grouping and Interpretation of Visual Motion Voting-Based Gouping and Intepetation of Visual Motion Micea Nicolescu Depatment of Compute Science Univesity of Nevada, Reno Reno, NV 89557 micea@cs.un.edu Géad Medioni Integated Media Systems Cente Univesity

More information

AN ANALYSIS OF COORDINATED AND NON-COORDINATED MEDIUM ACCESS CONTROL PROTOCOLS UNDER CHANNEL NOISE

AN ANALYSIS OF COORDINATED AND NON-COORDINATED MEDIUM ACCESS CONTROL PROTOCOLS UNDER CHANNEL NOISE AN ANALYSIS OF COORDINATED AND NON-COORDINATED MEDIUM ACCESS CONTROL PROTOCOLS UNDER CHANNEL NOISE Tolga Numanoglu, Bulent Tavli, and Wendi Heinzelman Depatment of Electical and Compute Engineeing Univesity

More information

Optical Flow for Large Motion Using Gradient Technique

Optical Flow for Large Motion Using Gradient Technique SERBIAN JOURNAL OF ELECTRICAL ENGINEERING Vol. 3, No. 1, June 2006, 103-113 Optical Flow fo Lage Motion Using Gadient Technique Md. Moshaof Hossain Sake 1, Kamal Bechkoum 2, K.K. Islam 1 Abstact: In this

More information

t [ Background removed

t [ Background removed HANDS-ON > HOE1 Taining 1 Pictues You decide to ceate a memoies slide show fo you siste and he husband, who wee ecently maied. You include thei high school Sweetheat Ball image, engagement and wedding

More information

Illumination methods for optical wear detection

Illumination methods for optical wear detection Illumination methods fo optical wea detection 1 J. Zhang, 2 P.P.L.Regtien 1 VIMEC Applied Vision Technology, Coy 43, 5653 LC Eindhoven, The Nethelands Email: jianbo.zhang@gmail.com 2 Faculty Electical

More information

Structured Prediction using Convolutional Neural Networks

Structured Prediction using Convolutional Neural Networks Overview Structured Prediction using Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Structured predictions for low level computer

More information

IP Network Design by Modified Branch Exchange Method

IP Network Design by Modified Branch Exchange Method Received: June 7, 207 98 IP Netwok Design by Modified Banch Method Kaiat Jaoenat Natchamol Sichumoenattana 2* Faculty of Engineeing at Kamphaeng Saen, Kasetsat Univesity, Thailand 2 Faculty of Management

More information

Survey of Various Image Enhancement Techniques in Spatial Domain Using MATLAB

Survey of Various Image Enhancement Techniques in Spatial Domain Using MATLAB Suvey of Vaious Image Enhancement Techniques in Spatial Domain Using MATLAB Shailenda Singh Negi M.Tech Schola G. B. Pant Engineeing College, Paui Gahwal Uttaahand, India- 46194 ABSTRACT Image Enhancement

More information

An Extension to the Local Binary Patterns for Image Retrieval

An Extension to the Local Binary Patterns for Image Retrieval , pp.81-85 http://x.oi.og/10.14257/astl.2014.45.16 An Extension to the Local Binay Pattens fo Image Retieval Zhize Wu, Yu Xia, Shouhong Wan School of Compute Science an Technology, Univesity of Science

More information

(a, b) x y r. For this problem, is a point in the - coordinate plane and is a positive number.

(a, b) x y r. For this problem, is a point in the - coordinate plane and is a positive number. Illustative G-C Simila cicles Alignments to Content Standads: G-C.A. Task (a, b) x y Fo this poblem, is a point in the - coodinate plane and is a positive numbe. a. Using a tanslation and a dilation, show

More information

Color Interpolation for Single CCD Color Camera

Color Interpolation for Single CCD Color Camera Colo Intepolation fo Single CCD Colo Camea Yi-Ming Wu, Chiou-Shann Fuh, and Jui-Pin Hsu Depatment of Compute Science and Infomation Engineeing, National Taian Univesit, Taipei, Taian Email: 88036@csie.ntu.edu.t;

More information

IP Multicast Simulation in OPNET

IP Multicast Simulation in OPNET IP Multicast Simulation in OPNET Xin Wang, Chien-Ming Yu, Henning Schulzinne Paul A. Stipe Columbia Univesity Reutes Depatment of Compute Science 88 Pakway Dive South New Yok, New Yok Hauppuage, New Yok

More information

AUTOMATED LOCATION OF ICE REGIONS IN RADARSAT SAR IMAGERY

AUTOMATED LOCATION OF ICE REGIONS IN RADARSAT SAR IMAGERY AUTOMATED LOCATION OF ICE REGIONS IN RADARSAT SAR IMAGERY Chistophe Waceman (1), William G. Pichel (2), Pablo Clement-Colón (2) (1) Geneal Dynamics Advanced Infomation Systems, P.O. Box 134008 Ann Abo

More information

A Neural Network Model for Storing and Retrieving 2D Images of Rotated 3D Object Using Principal Components

A Neural Network Model for Storing and Retrieving 2D Images of Rotated 3D Object Using Principal Components A Neual Netwok Model fo Stong and Reteving 2D Images of Rotated 3D Object Using Pncipal Components Tsukasa AMANO, Shuichi KUROGI, Ayako EGUCHI, Takeshi NISHIDA, Yasuhio FUCHIKAWA Depatment of Contol Engineeng,

More information

Augmented Reality. Integrating Computer Graphics with Computer Vision Mihran Tuceryan. August 16, 1998 ICPR 98 1

Augmented Reality. Integrating Computer Graphics with Computer Vision Mihran Tuceryan. August 16, 1998 ICPR 98 1 Augmented Reality Integating Compute Gaphics with Compute Vision Mihan Tuceyan August 6, 998 ICPR 98 Definition XCombines eal and vitual wolds and objects XIt is inteactive and eal-time XThe inteaction

More information

Lecture Topics ECE 341. Lecture # 12. Control Signals. Control Signals for Datapath. Basic Processing Unit. Pipelining

Lecture Topics ECE 341. Lecture # 12. Control Signals. Control Signals for Datapath. Basic Processing Unit. Pipelining EE 341 Lectue # 12 Instucto: Zeshan hishti zeshan@ece.pdx.edu Novembe 10, 2014 Potland State Univesity asic Pocessing Unit ontol Signals Hadwied ontol Datapath contol signals Dealing with memoy delay Pipelining

More information

The Internet Ecosystem and Evolution

The Internet Ecosystem and Evolution The Intenet Ecosystem and Evolution Contents Netwok outing: basics distibuted/centalized, static/dynamic, linkstate/path-vecto inta-domain/inte-domain outing Mapping the sevice model to AS-AS paths valley-fee

More information

Extract Object Boundaries in Noisy Images using Level Set. Final Report

Extract Object Boundaries in Noisy Images using Level Set. Final Report Extact Object Boundaies in Noisy Images using Level Set by: Quming Zhou Final Repot Submitted to Pofesso Bian Evans EE381K Multidimensional Digital Signal Pocessing May 10, 003 Abstact Finding object contous

More information

Computer Graphics and Animation 3-Viewing

Computer Graphics and Animation 3-Viewing Compute Gaphics and Animation 3-Viewing Pof. D. Chales A. Wüthich, Fakultät Medien, Medieninfomatik Bauhaus-Univesität Weima caw AT medien.uni-weima.de Ma 5 Chales A. Wüthich Viewing Hee: Viewing in 3D

More information

Cellular Neural Network Based PTV

Cellular Neural Network Based PTV 3th Int Symp on Applications of Lase Techniques to Fluid Mechanics Lisbon, Potugal, 6-9 June, 006 Cellula Neual Netwok Based PT Kazuo Ohmi, Achyut Sapkota : Depatment of Infomation Systems Engineeing,

More information

Introduction To Pipelining. Chapter Pipelining1 1

Introduction To Pipelining. Chapter Pipelining1 1 Intoduction To Pipelining Chapte 6.1 - Pipelining1 1 Mooe s Law Mooe s Law says that the numbe of pocessos on a chip doubles about evey 18 months. Given the data on the following two slides, is this tue?

More information

A Novel Automatic White Balance Method For Digital Still Cameras

A Novel Automatic White Balance Method For Digital Still Cameras A Novel Automatic White Balance Method Fo Digital Still Cameas Ching-Chih Weng 1, Home Chen 1,2, and Chiou-Shann Fuh 3 Depatment of Electical Engineeing, 2 3 Gaduate Institute of Communication Engineeing

More information

Lecture 27: Voronoi Diagrams

Lecture 27: Voronoi Diagrams We say that two points u, v Y ae in the same connected component of Y if thee is a path in R N fom u to v such that all the points along the path ae in the set Y. (Thee ae two connected components in the

More information

COLOR EDGE DETECTION IN RGB USING JOINTLY EUCLIDEAN DISTANCE AND VECTOR ANGLE

COLOR EDGE DETECTION IN RGB USING JOINTLY EUCLIDEAN DISTANCE AND VECTOR ANGLE COLOR EDGE DETECTION IN RGB USING JOINTLY EUCLIDEAN DISTANCE AND VECTOR ANGLE Slawo Wesolkowski Systems Design Engineeing Univesity of Wateloo Wateloo (Ont.), Canada, NL 3G s.wesolkowski@ieee.og Ed Jenigan

More information

Visual Servoing from Deep Neural Networks

Visual Servoing from Deep Neural Networks Visual Sevoing fom Deep Neual Netwoks Quentin Bateux 1, Eic Machand 1, Jügen Leitne 2, Fançois Chaumette 3, Pete Coke 2 Abstact We pesent a deep neual netwok-based method to pefom high-pecision, obust

More information

XFVHDL: A Tool for the Synthesis of Fuzzy Logic Controllers

XFVHDL: A Tool for the Synthesis of Fuzzy Logic Controllers XFVHDL: A Tool fo the Synthesis of Fuzzy Logic Contolles E. Lago, C. J. Jiménez, D. R. López, S. Sánchez-Solano and A. Baiga Instituto de Micoelectónica de Sevilla. Cento Nacional de Micoelectónica, Edificio

More information

High performance CUDA based CNN image processor

High performance CUDA based CNN image processor High pefomance UDA based NN image pocesso GEORGE VALENTIN STOIA, RADU DOGARU, ELENA RISTINA STOIA Depatment of Applied Electonics and Infomation Engineeing Univesity Politehnica of Buchaest -3, Iuliu Maniu

More information

Motion Estimation. Yao Wang Tandon School of Engineering, New York University

Motion Estimation. Yao Wang Tandon School of Engineering, New York University Motion Estimation Yao Wang Tandon School of Engineeing, New Yok Univesity Outline 3D motion model 2-D motion model 2-D motion vs. optical flow Optical flow equation and ambiguity in motion estimation Geneal

More information

3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach

3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach 3D Hand Tajectoy Segmentation by Cuvatues and Hand Oientation fo Classification though a Pobabilistic Appoach Diego R. Faia and Joge Dias Abstact In this wok we pesent the segmentation and classification

More information

Approximating Euclidean Distance Transform with Simple Operations in Cellular Processor Arrays

Approximating Euclidean Distance Transform with Simple Operations in Cellular Processor Arrays 00 th Intenational Wokshop on Cellula Nanoscale Netwoks and thei Applications (CNNA) Appoximating Euclidean Distance Tansfom with Simple Opeations in Cellula Pocesso Aas Samad Razmjooei and Piot Dudek

More information

Structured Light Stereoscopic Imaging with Dynamic Pseudo-random Patterns

Structured Light Stereoscopic Imaging with Dynamic Pseudo-random Patterns Stuctued Light Steeoscopic Imaging with Dynamic Pseudo-andom Pattens Piee Payeu and Danick Desjadins Univesity of Ottawa, SITE, 800 King Edwad, Ottawa, ON, Canada, K1N 6N5 {ppayeu,ddesjad}@site.uottawa.ca

More information

Dense pointclouds from combined nadir and oblique imagery by object-based semi-global multi-image matching

Dense pointclouds from combined nadir and oblique imagery by object-based semi-global multi-image matching Dense pointclouds fom combined nadi and oblique imagey by object-based semi-global multi-image matching Y X Thomas Luhmann, Folkma Bethmann & Heidi Hastedt Jade Univesity of Applied Sciences, Oldenbug,

More information

Obstacle Avoidance of Autonomous Mobile Robot using Stereo Vision Sensor

Obstacle Avoidance of Autonomous Mobile Robot using Stereo Vision Sensor Obstacle Avoidance of Autonomous Mobile Robot using Steeo Vision Senso Masako Kumano Akihisa Ohya Shin ichi Yuta Intelligent Robot Laboatoy Univesity of Tsukuba, Ibaaki, 35-8573 Japan E-mail: {masako,

More information

HISTOGRAMS are an important statistic reflecting the

HISTOGRAMS are an important statistic reflecting the JOURNAL OF L A T E X CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 1 D 2 HistoSketch: Disciminative and Dynamic Similaity-Peseving Sketching of Steaming Histogams Dingqi Yang, Bin Li, Laua Rettig, and Philippe

More information

User Specified non-bonded potentials in gromacs

User Specified non-bonded potentials in gromacs Use Specified non-bonded potentials in gomacs Apil 8, 2010 1 Intoduction On fist appeaances gomacs, unlike MD codes like LAMMPS o DL POLY, appeas to have vey little flexibility with egads to the fom of

More information

Topological Characteristic of Wireless Network

Topological Characteristic of Wireless Network Topological Chaacteistic of Wieless Netwok Its Application to Node Placement Algoithm Husnu Sane Naman 1 Outline Backgound Motivation Papes and Contibutions Fist Pape Second Pape Thid Pape Futue Woks Refeences

More information

Feature Extraction Technique for Neural Network Based Pattern Recognition

Feature Extraction Technique for Neural Network Based Pattern Recognition Ashoka H.N et al. / Intenational Jounal on Compute Science and Engineeing (IJCSE) Featue Extaction Technique fo Neual Netwok Based Patten Recognition Ashoka H.N. Depatment of Electical and Electonics Engineeing,

More information

High Performance Computing on GPU for Electromagnetic Logging

High Performance Computing on GPU for Electromagnetic Logging Intenational Confeence "Paallel and Distiuted Computing Systems" High Pefomance Computing on GPU fo lectomagnetic Logging Glinskikh V.N. Kontoovich A.. pov M.I. Tofimuk Institute of Petoleum Geology and

More information

EE 168 Handout #32 Introduction to Digital Image Processing March 7, 2012 HOMEWORK 7 SOLUTIONS

EE 168 Handout #32 Introduction to Digital Image Processing March 7, 2012 HOMEWORK 7 SOLUTIONS EE 168 Handout #32 Intoduction to Diital Imae Pocessin Mach 7, 2012 HOMEWORK 7 SOLUTIONS Polem 1: Colo Wheels We can epesent an N x N colo imae y a thee-dimensional aay such that the fist two dimensions

More information

4.2. Co-terminal and Related Angles. Investigate

4.2. Co-terminal and Related Angles. Investigate .2 Co-teminal and Related Angles Tigonometic atios can be used to model quantities such as

More information

ADDING REALISM TO SOURCE CHARACTERIZATION USING A GENETIC ALGORITHM

ADDING REALISM TO SOURCE CHARACTERIZATION USING A GENETIC ALGORITHM ADDING REALISM TO SOURCE CHARACTERIZATION USING A GENETIC ALGORITHM Luna M. Rodiguez*, Sue Ellen Haupt, and Geoge S. Young Depatment of Meteoology and Applied Reseach Laboatoy The Pennsylvania State Univesity,

More information

Spiral Recognition Methodology and Its Application for Recognition of Chinese Bank Checks

Spiral Recognition Methodology and Its Application for Recognition of Chinese Bank Checks Spial Recognition Methodology and Its Application fo Recognition of Chinese Bank Checks Hanshen Tang 1, Emmanuel Augustin 2, Ching Y. Suen 1, Olivie Baet 2, Mohamed Cheiet 3 1 Cente fo Patten Recognition

More information

A Hybrid DWT-SVD Image-Coding System (HDWTSVD) for Color Images

A Hybrid DWT-SVD Image-Coding System (HDWTSVD) for Color Images A Hybid DWT-SVD Image-Coding System (HDWTSVD) fo Colo Images Humbeto Ochoa a,b, K.R. Rao a a Univesity of Texas at Alington, Box 906 46 ates Steet, Neddeman Hall, Rm 530 Alington, TX 7609 hdo594@exchange.uta.edu

More information

Improved Utility-based Congestion Control for Delay-Constrained Communication

Improved Utility-based Congestion Control for Delay-Constrained Communication Impoved Utility-based Congestion Contol fo Delay-Constained Communication Stefano D Aonco, Laua Toni, Segio Mena, Xiaoqing Zhu, and Pascal Fossad axiv:5.2799v3 [cs.ni] 2 Jan 27 Abstact Due to the pesence

More information

Effective Data Co-Reduction for Multimedia Similarity Search

Effective Data Co-Reduction for Multimedia Similarity Search Effective Data Co-Reduction fo Multimedia Similaity Seach Zi Huang Heng Tao Shen Jiajun Liu Xiaofang Zhou School of Infomation Technology and Electical Engineeing The Univesity of Queensland, QLD 472,

More information

A Recommender System for Online Personalization in the WUM Applications

A Recommender System for Online Personalization in the WUM Applications A Recommende System fo Online Pesonalization in the WUM Applications Mehdad Jalali 1, Nowati Mustapha 2, Ali Mamat 2, Md. Nasi B Sulaiman 2 Abstact foeseeing of use futue movements and intentions based

More information

Prioritized Traffic Recovery over GMPLS Networks

Prioritized Traffic Recovery over GMPLS Networks Pioitized Taffic Recovey ove GMPLS Netwoks 2005 IEEE. Pesonal use of this mateial is pemitted. Pemission fom IEEE mu be obtained fo all othe uses in any cuent o futue media including epinting/epublishing

More information

Development and Analysis of a Real-Time Human Motion Tracking System

Development and Analysis of a Real-Time Human Motion Tracking System Development and Analysis of a Real-Time Human Motion Tacking System Jason P. Luck 1,2 Chistian Debunne 1 William Hoff 1 Qiang He 1 Daniel E. Small 2 1 Coloado School of Mines 2 Sandia National Labs Engineeing

More information

MULTI-TEMPORAL AND MULTI-SENSOR IMAGE MATCHING BASED ON LOCAL FREQUENCY INFORMATION

MULTI-TEMPORAL AND MULTI-SENSOR IMAGE MATCHING BASED ON LOCAL FREQUENCY INFORMATION Intenational Achives of the Photogammety Remote Sensing and Spatial Infomation Sciences Volume XXXIX-B3 2012 XXII ISPRS Congess 25 August 01 Septembe 2012 Melboune Austalia MULTI-TEMPORAL AND MULTI-SENSOR

More information

Tissue Classification Based on 3D Local Intensity Structures for Volume Rendering

Tissue Classification Based on 3D Local Intensity Structures for Volume Rendering 160 IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, VOL. 6, NO., APRIL-JUNE 000 Tissue Classification Based on 3D Local Intensity Stuctues fo Volume Rendeing Yoshinobu Sato, Membe, IEEE, Cal-Fedik

More information

CLUSTERED BASED TAKAGI-SUGENO NEURO-FUZZY MODELING OF A MULTIVARIABLE NONLINEAR DYNAMIC SYSTEM

CLUSTERED BASED TAKAGI-SUGENO NEURO-FUZZY MODELING OF A MULTIVARIABLE NONLINEAR DYNAMIC SYSTEM Asian Jounal of Contol, Vol. 7, No., pp. 63-76, June 5 63 -Bief Pape- CLUSTERED BASED TAKAGI-SUGENO NEURO-FUZZY MODELING OF A MULTIVARIABLE NONLINEAR DYNAMIC SYSTEM E. A. Al-Gallaf ABSTRACT This eseach

More information

Dynamic Topology Control to Reduce Interference in MANETs

Dynamic Topology Control to Reduce Interference in MANETs Dynamic Topology Contol to Reduce Intefeence in MANETs Hwee Xian TAN 1,2 and Winston K. G. SEAH 2,1 {stuhxt, winston}@i2.a-sta.edu.sg 1 Depatment of Compute Science, School of Computing, National Univesity

More information

A Memory Efficient Array Architecture for Real-Time Motion Estimation

A Memory Efficient Array Architecture for Real-Time Motion Estimation A Memoy Efficient Aay Achitectue fo Real-Time Motion Estimation Vasily G. Moshnyaga and Keikichi Tamau Depatment of Electonics & Communication, Kyoto Univesity Sakyo-ku, Yoshida-Honmachi, Kyoto 66-1, JAPAN

More information

Configuring RSVP-ATM QoS Interworking

Configuring RSVP-ATM QoS Interworking Configuing RSVP-ATM QoS Intewoking Last Updated: Januay 15, 2013 This chapte descibes the tasks fo configuing the RSVP-ATM QoS Intewoking featue, which povides suppot fo Contolled Load Sevice using RSVP

More information

Input Layer f = 2 f = 0 f = f = 3 1,16 1,1 1,2 1,3 2, ,2 3,3 3,16. f = 1. f = Output Layer

Input Layer f = 2 f = 0 f = f = 3 1,16 1,1 1,2 1,3 2, ,2 3,3 3,16. f = 1. f = Output Layer Using the Gow-And-Pune Netwok to Solve Poblems of Lage Dimensionality B.J. Biedis and T.D. Gedeon School of Compute Science & Engineeing The Univesity of New South Wales Sydney NSW 2052 AUSTRALIA bbiedis@cse.unsw.edu.au

More information

ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS

ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS Daniel A Menascé Mohamed N Bennani Dept of Compute Science Oacle, Inc Geoge Mason Univesity 1211 SW Fifth

More information

ANN Models for Coplanar Strip Line Analysis and Synthesis

ANN Models for Coplanar Strip Line Analysis and Synthesis 200 IJCSNS Intenational Jounal of Compute Science and Netwok Secuity, VOL.8 No.10, Octobe 2008 Models fo Coplana Stip Line Analysis and J.Lakshmi Naayana D.K.Si Rama Kishna D.L.Patap Reddy Chalapathi Institute

More information

Robust Object Detection at Regions of Interest with an Application in Ball Recognition

Robust Object Detection at Regions of Interest with an Application in Ball Recognition Robust Object Detection at Regions of Inteest with an Application in Ball Recognition Saa Miti, Simone Fintop, Kai Pevölz, Hatmut Sumann Faunhofe Institute fo Autonomous Intelligent Systems (AIS) Schloss

More information

arxiv: v5 [cs.cv] 29 Sep 2018

arxiv: v5 [cs.cv] 29 Sep 2018 Bi-Real Net: Enhancing the Pefomance of 1-it CNNs With Impoved Repesentational Capaility and Advanced Taining Algoithm axiv:1808.00278v5 [cs.cv] 29 Sep 2018 Zechun Liu 1, Baoyuan Wu 2, Wenhan Luo 2, Xin

More information

EYE DIRECTION BY STEREO IMAGE PROCESSING USING CORNEAL REFLECTION ON AN IRIS

EYE DIRECTION BY STEREO IMAGE PROCESSING USING CORNEAL REFLECTION ON AN IRIS EYE DIRECTION BY STEREO IMAGE PROCESSING USING CORNEAL REFLECTION ON AN IRIS Kumiko Tsuji Fukuoka Medical technology Teikyo Univesity 4-3-14 Shin-Katsutachi-Machi Ohmuta Fukuoka 836 Japan email: c746g@wisdomcckyushu-uacjp

More information

9-2. Camera Calibration Method for Far Range Stereovision Sensors Used in Vehicles. Tiberiu Marita, Florin Oniga, Sergiu Nedevschi

9-2. Camera Calibration Method for Far Range Stereovision Sensors Used in Vehicles. Tiberiu Marita, Florin Oniga, Sergiu Nedevschi 9-2 Camea Calibation Method fo Fa Range Steeovision Sensos Used in Vehicles ibeiu Maita, Floin Oniga, Segiu Nedevschi Compute Science Depatment echnical Univesity of Cluj-Napoca Cluj-Napoca, 400020, ROMNI

More information

Accelerating Storage with RDMA Max Gurtovoy Mellanox Technologies

Accelerating Storage with RDMA Max Gurtovoy Mellanox Technologies Acceleating Stoage with RDMA Max Gutovoy Mellanox Technologies 2018 Stoage Develope Confeence EMEA. Mellanox Technologies. All Rights Reseved. 1 What is RDMA? Remote Diect Memoy Access - povides the ability

More information

Fifth Wheel Modelling and Testing

Fifth Wheel Modelling and Testing Fifth heel Modelling and Testing en Masoy Mechanical Engineeing Depatment Floida Atlantic Univesity Boca aton, FL 4 Lois Malaptias IFMA Institut Fancais De Mechanique Advancee ampus De lemont Feand Les

More information

Output Primitives. Ellipse Drawing

Output Primitives. Ellipse Drawing Output Pimitives Ellipse Dawing Ellipses. An ellipses is an elongated cicle and can be dawn with modified cicle dawing algoithm.. An ellipse has set of fied points (foci) that will have a constant total

More information

Assessment of Track Sequence Optimization based on Recorded Field Operations

Assessment of Track Sequence Optimization based on Recorded Field Operations Assessment of Tack Sequence Optimization based on Recoded Field Opeations Matin A. F. Jensen 1,2,*, Claus G. Søensen 1, Dionysis Bochtis 1 1 Aahus Univesity, Faculty of Science and Technology, Depatment

More information

Slotted Random Access Protocol with Dynamic Transmission Probability Control in CDMA System

Slotted Random Access Protocol with Dynamic Transmission Probability Control in CDMA System Slotted Random Access Potocol with Dynamic Tansmission Pobability Contol in CDMA System Intaek Lim 1 1 Depatment of Embedded Softwae, Busan Univesity of Foeign Studies, itlim@bufs.ac.k Abstact In packet

More information

OPTIMAL KINEMATIC SYNTHESIS OF CRANK & SLOTTED LEVER QUICK RETURN MECHANISM FOR SPECIFIC STROKE & TIME RATIO

OPTIMAL KINEMATIC SYNTHESIS OF CRANK & SLOTTED LEVER QUICK RETURN MECHANISM FOR SPECIFIC STROKE & TIME RATIO OPTIMAL KINEMATIC SYNTHESIS OF CRANK & SLOTTED LEVER QUICK RETURN MECHANISM FOR SPECIFIC STROKE & TIME RATIO Zeeshan A. Shaikh 1 and T.Y. Badguja 2 1,2 Depatment of Mechanical Engineeing, Late G. N. Sapkal

More information

Modeling a shared medium access node with QoS distinction

Modeling a shared medium access node with QoS distinction Modeling a shaed medium access node with QoS distinction Matthias Gies, Jonas Geutet Compute Engineeing and Netwoks Laboatoy (TIK) Swiss Fedeal Institute of Technology Züich CH-8092 Züich, Switzeland email:

More information

A Mathematical Implementation of a Global Human Walking Model with Real-Time Kinematic Personification by Boulic, Thalmann and Thalmann.

A Mathematical Implementation of a Global Human Walking Model with Real-Time Kinematic Personification by Boulic, Thalmann and Thalmann. A Mathematical Implementation of a Global Human Walking Model with Real-Time Kinematic Pesonification by Boulic, Thalmann and Thalmann. Mashall Badley National Cente fo Physical Acoustics Univesity of

More information

View Synthesis using Depth Map for 3D Video

View Synthesis using Depth Map for 3D Video View Synthesis using Depth Map fo 3D Video Cheon Lee and Yo-Sung Ho Gwangju Institute of Science and Technology (GIST) 1 Oyong-dong, Buk-gu, Gwangju, 500-712, Republic of Koea E-mail: {leecheon, hoyo}@gist.ac.k

More information

A VECTOR PERTURBATION APPROACH TO THE GENERALIZED AIRCRAFT SPARE PARTS GROUPING PROBLEM

A VECTOR PERTURBATION APPROACH TO THE GENERALIZED AIRCRAFT SPARE PARTS GROUPING PROBLEM Accepted fo publication Intenational Jounal of Flexible Automation and Integated Manufactuing. A VECTOR PERTURBATION APPROACH TO THE GENERALIZED AIRCRAFT SPARE PARTS GROUPING PROBLEM Nagiza F. Samatova,

More information

A Shape-preserving Affine Takagi-Sugeno Model Based on a Piecewise Constant Nonuniform Fuzzification Transform

A Shape-preserving Affine Takagi-Sugeno Model Based on a Piecewise Constant Nonuniform Fuzzification Transform A Shape-peseving Affine Takagi-Sugeno Model Based on a Piecewise Constant Nonunifom Fuzzification Tansfom Felipe Fenández, Julio Gutiéez, Juan Calos Cespo and Gacián Tiviño Dep. Tecnología Fotónica, Facultad

More information