CSE 237A: Final Project Report Object Tracking Willis Hoang & Shimona Carvalho November 27, 2006

Size: px
Start display at page:

Download "CSE 237A: Final Project Report Object Tracking Willis Hoang & Shimona Carvalho November 27, 2006"

Transcription

1 CSE 237A: Fnal Project Report Object Trackng Wlls Hoang & Shmona Carvalho November 27, Project Descrpton For ths project, we plan to mplement an object trackng applcaton usng the ntegrated vdeo camera on Intel's PXA27x embedded system platform. Our man goal s to track an object aganst a unform color backdrop. The relatve poston wll be dsplayed on the LCD. We also seek to optmze our applcaton to obtan the best possble rate and qualty of mage capture and analyss. If tme permts, we wll attempt to expand the scope to track more complex movng objects aganst a non-unform background. 2 Motvaton, Challenges and Lmtatons 2.1 Applcatons and challenges Moton trackng has many applcatons n today's dverse range of embedded systems. Ths type of trackng s frequently used for securty and survellance, medcal therapy, retal space nstrumentaton, traffc management and vdeo edtng. On cars, moton trackng could be used to montor other vehcles and alert the drver to dangers such as vehcles lurkng n the host vehcle's blnd spot. In the manufacturng ndustry, moton trackers are used for analyss of hgh-speed assembly lne producton. The man ssues n the development of such a system are the optmzng of the speed of capture and analyss of vdeo. Whle there are many pattern recognton algorthms avalable, care must be taken to select an optmal pattern recognton algorthm for each task. For example, n the manufacturng example, t would be easy to ensure that the robotc arm beng tracked was covered by an easly recognzable pattern. However, n the case of the blnd-spot trackng, the applcaton would need to dscern between the farly smlar mages of a car n the next lane a potental threat - and one two lanes over - not a threat [1]. The recognton algorthm also must be fast to provde useful real-tme response. The best car detecton algorthm would be worthless f the car was detected after t had gone by. Therefore, for a good embedded moton trackng system, an optmal balance between these varables should be mantaned. 2.2 State of the Art Current state of the art technques nvolve developng an unsupervsed, robust, computatonally effcent mult-object tracker. Key requrements of trackng algorthms are mnmum ntalzaton effort and fne-tunng for camera setups. MERL (Mtsubsh Electrc Research Laboratores) uses the methods descrbed below for most of ther survellance products [2]. One of the challenges presented by trackng algorthms s the desre for accurate mult-object trackng wth the constrant of low computatonal complexty. The two man algorthms use ether back-trackng or forward trackng. The back trackng based approach segments the foreground regons and attempts to fnd a correspondence of regons between the current and prevous mages. The forward trackng based approach estmates the postons n the current frame of the regons found n the prevous frame. To establsh correspondence, dfferent templates are needed to optmze for dfferent objects. For

2 example, trackng of humans wll requre a dfferent correspondence algorthm than that for factory equpment. 3 Implementng the Moton Tracker 3.1 Evaluaton of avalable camera code Our frst step was to evaluate the current c-capture code to decde whether t would be able to capture the vdeo we needed. Pror to capturng the stll mage, the program handled a few seconds of vdeo as a prevew. Ths was enough to base our code on. One ssue we ran nto at ths pont was that the vdeo s dsplayed only as 176 x 144. We researched on the web and attempted to make the program use 320 x 240 but found that the overlay2 devce returned fxed frame sze of 176 x 144. Any larger frame sze request resulted n the devce falng to open. We decded to stay wth 176 x 144. The vdeo captured by the camera s set to YCbCr planar format. Ths s because ths s the natve format of the LCD and therefore transfer from the camera to the screen s drect and needs no converson algorthm. Whle dealng wth RGB pxels mght have been more ntutve, we decded that the converson from YCbCr to RGB before the moton trackng algorthm would have hurt the effcency of the algorthm. Instead we researched the YCbCr format and used t drectly. 3.2 YUV format The YCbCr format separates the lumnance (or brghtness nformaton) from the chromnance (or color nformaton) of vdeo. Y s the luma component, and Cb and Cr the blue and red chroma components. YCbCr s the dgtal vdeo verson of the analog colorspace YUV. It more closely approxmates the human eye s response to lght, than RGB. Snce the human eye has farly small color senstvty, half the nformaton n the chroma components s dscarded. Whle there are as many Y values as there are pxels, there are half the amount of Cb and Cr values as there pxels. Ths s why the format s sometmes called YCbCr 4:2:2, the numbers representng the rato of Y values to Cb and Cr [3][4]. An example of an mage splt nto the three components s shown n Fgure 1. Fgure 1 YUV Image splt nto Lumnance, Red Chroma and Blue Chroma 3.3 Research of moton detecton algorthms Our ntal goal was to track a whte object aganst a unform black backdrop. We felt ths was farly easy to mplement so to challenge ourselves, we decded to mplement an algorthm that tracked a movng object regardless of the backdrop color. The algorthm mplemented conssts of three stages: dfference, threshold, and centrod [5]. Refer to Fgure 2 for an llustratve dagram.

3 In the dfference stage, we subtract the current vdeo frame wth the prevous vdeo frame. Let us denote I c as the current vdeo frame, I p as the prevous vdeo frame, and as the resultng dfference. Mathematcally, ths s gven as I = I I. By d c! dong so, we are able to detect movement between the current and prevous vdeo frames. Areas wthout sgnfcant movement wll be approxmately zero and areas wth sgnfcant movement wll be approxmate one. Effectvely, ths removes the background and statonary objects. p I d Fgure 2. Moton Detecton Algorthm To make processng easer, we threshold the pxel values n the second stage producng a bnary mage. Dong ths "exaggerates" the detected movements. Ths s mathematcally gven as I = { 1 f I d < t, 0 f I d! t where t s the threshold value. The last stage s centrod, ths can be thought of as calculatng the "center of mass" of I t. Center of mass s genercally gven as =! system, r s the poston, and sum of the pxels n I t, calculated twce, once for x and once for y. CM 1 m r where M s the total mass of the M m s the weghted mass [6]. For our applcaton, M s the total m s the pxel value, and r s the pxel locaton. The centrod s Ths process s calculated for each frame where the centrod denotes the moton tracked object. To clearly represent ths and denote relatve poston, we overlay a frame surroundng the centrod coordnates on the LCD of our embedded platform. 3.4 Problems and Solutons The ntegrated camera sensor was very senstve to slght changes and nose such as the flckerng of the ambent lght. Ths nose would show up as dfference after the subtracton stage. To avod ths, a threshold mass was used whch requred a certan mass of moved pxels to accumulate before regsterng as actual moton. Ths successfully fltered out the effects of sensor nose and flcker. Snce the FPS of the vdeo capture s very hgh, takng the dfference between two consecutve dd not result n much change. To extract more meanngful nformaton, we used a sldng wndow method wheren we compared the current buffer to one several frames before t. The dfference between these two frames was more sgnfcant as more tme had elapsed between them. Another ssue we found was that the centrod had no nerta and jumped around very quckly. Whle accurate, t reduced the qualty of the trackng movement as vewed by the human eye. To solve ths ssue we used a weghtng system to pull the new centrod closer to old centrod. By expermentng wth dfferent weghts, we found an deal weght whch stopped the tracker from appearng too jumpy wthout causng too much lag f the object moved quckly. t

4 3.5 Possble Extensons We found that multple movng objects cause the algorthm to pck a pont at the centrod of the dfferent movng objects. Ths s because the algorthm could not detect that there were multple movng objects and assumed one large movng object. Wth more tme, an algorthm could be developed to detect and separate multple movng objects, and track them ndvdually, but t was beyond our scope at ths tme. Algorthms are currently beng developed that employ occluson detecton methods such as merge-splt and straght-through [7] to track multple objects. 4 Optmzng the Moton Tracker 4.1 Box Frame Drawng One optmzaton we added n the mplementaton phase was the statc frame drawng. When we frst calculated the FPS before any trackng was turned on, we got an average FPS of We then tred our software wth the trackng turned on and had an FPS of Ths was a large drop n the FPS, but we suspected the code that overlad a box marker around the movng object. Our orgnal soluton was to determne the box pxels usng a dynamc algorthm that took the centrod locaton as an nput. Ths was too computaton ntensve as t needed to be done per frame, so we desgned a more effcent, alternate algorthm. The new algorthm used a predefned array of relatve postons to map out the box pxels. Ths statc array reduced our computaton tme to a fracton of the orgnal and resulted n an FPS rate of 43.79, very close to the orgnal FPS before trackng. 4.2 The Camera Capture Bottleneck Our frst attempts to measure performance led us to an nterestng result. Our bggest bottleneck was not the algorthm but the speed of camera capture. Reducng the amount of analyss we dd per frame was not havng a sgnfcant effect on our FPS, so we decded to measure the tme taken for the camera to capture 1000 frames, compared to the tme taken to capture and analyze 1000 frames. The results are tabulated n Table 1. Frequency (MHz) DVFM FPS Capture (sec) Capture + Analyze (sec) Vdeo Qualty good good poor Table 1. Comparson of Camera Capture tme and Capture + Analyss tme As you can see, at the hghest two frequences, the tme taken to capture + analyze s only slghtly greater than the tme taken to capture. Ths s because the software spends a sgnfcant amount of tme suspended, watng for the camera hardware to return a frame of vdeo data. The camera operates parallel to software except when the software s transferrng a frame of captured vdeo over. The algorthm proceeds as follows. On recept of a frame of vdeo from the camera, the processor analyzes t, transfers t onto the LCD and requests another frame of data. Then, t suspends untl t receves t. Thus, at the hgher frequences, where the trackng algorthm takes less tme than the capture tme of the camera, no optmzatons of the algorthm tself wll mprove the FPS. Also

5 note that the frequency of the processor has no effect on the speed of capture, whch appears to be entrely hardware-dependent. 4.3 Skp A Frame or Fve We then turned our attenton to the lower frequences. In the 208MHz example n Table 1, the tme taken for analyss has now exceeded the tme taken to capture. Ths means, by the tme the algorthm s ready to receve a new frame of vdeo data, t has already mssed one and needs to wat a whole new capture cycle to get the next one. As a result the tme taken s more than twce that of the capture tme, and the vdeo qualty s poor. Hence we realzed, t was possbly to optmze n the lower frequency cases. One technque would be to run the trackng algorthm only once every n frames nstead of each tme. In frames where no algorthm s run, the data s stll transferred from the camera to the screen. Ths would reduce the total tme spent runnng the moton detecton algorthm. We would probably stll mss a frame of vdeo data but only once every n tmes. 4.4 Results Whle the frame skppng method gave us large energy savngs, we also notced that the more frames, we skpped the more the trackng box would lag behnd the movng object, especally f the object moved at a hgh speed. By balancng out both these factors, we found that we could acheve 75% energy savngs runnng at 208MHz skppng 5 frames. Ths s a good result gven that pror to our optmzatons, we were unable to run at ths power mode wth acceptable vdeo qualty. Freq (MHz) DVFM Skp Frames FPS Qualty Total Energy (mj) % Energy Saved good % good % poor % poor % good % good % good % bad % good % bad % bad % bad % bad % bad % bad % bad % Table 2. Comparson of Energy Savngs usng Power Modes and Frame-Skppng

6 5 Concluson and Outlook On the whole, the algorthm mplementaton was farly straghtforward. From the very begnnng, we attempted to wrte the code mndful of effcency and number of cycles used per teraton. Ths helped us mantan a hgh frames-per-second rate, and opened up possbltes for the power consumpton optmzatons. At the same tme, we attempted to keep the vdeo qualty at an acceptably smooth level as perceved by the human eye. The result of the optmzatons was a 75% energy savngs on the orgnal measurement. Ths rather large dfference would mprove the potental of usng ths applcaton n more portable settngs, for example n stuatons where the camera communcates wrelessly wth a server. Further extensons of the applcaton would nvolve detectng several movng objects and dstngushng between them. Multple cameras could also be used to obtan 3D nformaton. Moton trackng s an exctng tool n the development of ncreasngly reactve technologes. Ths wll save humans from constantly havng to montor ther applances and electroncs, and allow some decsons to be made autonomously, such as montorng of manufacturng equpment. It can also be used to help humans make decsons by provdng them wth pre-measured useful nformaton prevously unavalable, such as n blnd spot detecton. Wth technques lke ths, embedded systems can move away from more needy nteractve models, toward more convenent and speeder reactve models.

7 References [1] Bourbaks, N.; Fndler, M., "Smart cars as autonomous ntellgent agents," Tools wth Artfcal Intellgence, Proceedngs of the 13th Internatonal Conference on, vol., no.pp.25-32, 7-9 Nov 2001 [2] MERL, "Object Trackng and Understandng," Mtsubsh Electrc Research Laboratores, July 15, 2004 < [3] "Ycbcr." Wkpeda, The Free Encyclopeda. 28 Oct 2006, 07:29 UTC. Wkmeda Foundaton, Inc. 14 Nov 2006 < [4] Kovacevc, Mjo. "Color n Image and Vdeo." Nov < [5] Han, Xu; Sun, Yng, "Algorthm for the Actve Image Moton Seekng (AIMS) Camera System." Unversty of Rhode Island. 13 Nov < [6] Center of mass." Wkpeda, The Free Encyclopeda. 10 Nov 2006, 10:04 UTC. Wkmeda Foundaton, Inc. 14 Nov 2006 < [7] P. F. Gabrel, J. G. Verly, J. H. Pater, and A. Genon. "The state of the art n multple object trackng under occluson n vdeo sequences." In Advanced Concepts for Intellgent Vson Systems (ACIVS), 2003

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

Face Detection with Deep Learning

Face Detection with Deep Learning Face Detecton wth Deep Learnng Yu Shen Yus122@ucsd.edu A13227146 Kuan-We Chen kuc010@ucsd.edu A99045121 Yzhou Hao y3hao@ucsd.edu A98017773 Mn Hsuan Wu mhwu@ucsd.edu A92424998 Abstract The project here

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

Simulation Based Analysis of FAST TCP using OMNET++

Simulation Based Analysis of FAST TCP using OMNET++ Smulaton Based Analyss of FAST TCP usng OMNET++ Umar ul Hassan 04030038@lums.edu.pk Md Term Report CS678 Topcs n Internet Research Sprng, 2006 Introducton Internet traffc s doublng roughly every 3 months

More information

The Codesign Challenge

The Codesign Challenge ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.

More information

Active Contours/Snakes

Active Contours/Snakes Actve Contours/Snakes Erkut Erdem Acknowledgement: The sldes are adapted from the sldes prepared by K. Grauman of Unversty of Texas at Austn Fttng: Edges vs. boundares Edges useful sgnal to ndcate occludng

More information

Efficient Distributed File System (EDFS)

Efficient Distributed File System (EDFS) Effcent Dstrbuted Fle System (EDFS) (Sem-Centralzed) Debessay(Debsh) Fesehaye, Rahul Malk & Klara Naherstedt Unversty of Illnos-Urbana Champagn Contents Problem Statement, Related Work, EDFS Desgn Rate

More information

Real-time Motion Capture System Using One Video Camera Based on Color and Edge Distribution

Real-time Motion Capture System Using One Video Camera Based on Color and Edge Distribution Real-tme Moton Capture System Usng One Vdeo Camera Based on Color and Edge Dstrbuton YOSHIAKI AKAZAWA, YOSHIHIRO OKADA, AND KOICHI NIIJIMA Graduate School of Informaton Scence and Electrcal Engneerng,

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes SPH3UW Unt 7.3 Sphercal Concave Mrrors Page 1 of 1 Notes Physcs Tool box Concave Mrror If the reflectng surface takes place on the nner surface of the sphercal shape so that the centre of the mrror bulges

More information

Virtual Memory. Background. No. 10. Virtual Memory: concept. Logical Memory Space (review) Demand Paging(1) Virtual Memory

Virtual Memory. Background. No. 10. Virtual Memory: concept. Logical Memory Space (review) Demand Paging(1) Virtual Memory Background EECS. Operatng System Fundamentals No. Vrtual Memory Prof. Hu Jang Department of Electrcal Engneerng and Computer Scence, York Unversty Memory-management methods normally requres the entre process

More information

An Efficient Background Updating Scheme for Real-time Traffic Monitoring

An Efficient Background Updating Scheme for Real-time Traffic Monitoring 2004 IEEE Intellgent Transportaton Systems Conference Washngton, D.C., USA, October 3-6, 2004 WeA1.3 An Effcent Background Updatng Scheme for Real-tme Traffc Montorng Suchendra M. Bhandarkar and Xngzh

More information

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research

More information

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 A mathematcal programmng approach to the analyss, desgn and

More information

Edge Detection in Noisy Images Using the Support Vector Machines

Edge Detection in Noisy Images Using the Support Vector Machines Edge Detecton n Nosy Images Usng the Support Vector Machnes Hlaro Gómez-Moreno, Saturnno Maldonado-Bascón, Francsco López-Ferreras Sgnal Theory and Communcatons Department. Unversty of Alcalá Crta. Madrd-Barcelona

More information

Complex Numbers. Now we also saw that if a and b were both positive then ab = a b. For a second let s forget that restriction and do the following.

Complex Numbers. Now we also saw that if a and b were both positive then ab = a b. For a second let s forget that restriction and do the following. Complex Numbers The last topc n ths secton s not really related to most of what we ve done n ths chapter, although t s somewhat related to the radcals secton as we wll see. We also won t need the materal

More information

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION 1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute

More information

Lecture 5: Multilayer Perceptrons

Lecture 5: Multilayer Perceptrons Lecture 5: Multlayer Perceptrons Roger Grosse 1 Introducton So far, we ve only talked about lnear models: lnear regresson and lnear bnary classfers. We noted that there are functons that can t be represented

More information

Wishing you all a Total Quality New Year!

Wishing you all a Total Quality New Year! Total Qualty Management and Sx Sgma Post Graduate Program 214-15 Sesson 4 Vnay Kumar Kalakband Assstant Professor Operatons & Systems Area 1 Wshng you all a Total Qualty New Year! Hope you acheve Sx sgma

More information

Assignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009.

Assignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009. Farrukh Jabeen Algorthms 51 Assgnment #2 Due Date: June 15, 29. Assgnment # 2 Chapter 3 Dscrete Fourer Transforms Implement the FFT for the DFT. Descrbed n sectons 3.1 and 3.2. Delverables: 1. Concse descrpton

More information

Fitting: Deformable contours April 26 th, 2018

Fitting: Deformable contours April 26 th, 2018 4/6/08 Fttng: Deformable contours Aprl 6 th, 08 Yong Jae Lee UC Davs Recap so far: Groupng and Fttng Goal: move from array of pxel values (or flter outputs) to a collecton of regons, objects, and shapes.

More information

Related-Mode Attacks on CTR Encryption Mode

Related-Mode Attacks on CTR Encryption Mode Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory

More information

Robust Classification of ph Levels on a Camera Phone

Robust Classification of ph Levels on a Camera Phone Robust Classfcaton of ph Levels on a Camera Phone B.Y. Loh, N.K. Vuong, S. Chan and C.. Lau AbstractIn ths paper, we present a new algorthm that automatcally classfes the ph level on a test strp usng color

More information

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Proceedngs of the Wnter Smulaton Conference M E Kuhl, N M Steger, F B Armstrong, and J A Jones, eds A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Mark W Brantley Chun-Hung

More information

Reducing Frame Rate for Object Tracking

Reducing Frame Rate for Object Tracking Reducng Frame Rate for Object Trackng Pavel Korshunov 1 and We Tsang Oo 2 1 Natonal Unversty of Sngapore, Sngapore 11977, pavelkor@comp.nus.edu.sg 2 Natonal Unversty of Sngapore, Sngapore 11977, oowt@comp.nus.edu.sg

More information

Optimized Region Competition Algorithm Applied to the Segmentation of Artificial Muscles in Stereoscopic Images

Optimized Region Competition Algorithm Applied to the Segmentation of Artificial Muscles in Stereoscopic Images Vol. 2, No. 3, Page 185-195 Copyrght 2008, TSI Press Prnted n the USA. All rghts reserved Optmzed Regon Competton Algorthm Appled to the Segmentaton of Artfcal Muscles n Stereoscopc Images Rafael Verdú-Monedero,

More information

Efficient Video Coding with R-D Constrained Quadtree Segmentation

Efficient Video Coding with R-D Constrained Quadtree Segmentation Publshed on Pcture Codng Symposum 1999, March 1999 Effcent Vdeo Codng wth R-D Constraned Quadtree Segmentaton Cha-Wen Ln Computer and Communcaton Research Labs Industral Technology Research Insttute Hsnchu,

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User Authentication Based On Behavioral Mouse Dynamics Biometrics User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA

More information

Sorting Review. Sorting. Comparison Sorting. CSE 680 Prof. Roger Crawfis. Assumptions

Sorting Review. Sorting. Comparison Sorting. CSE 680 Prof. Roger Crawfis. Assumptions Sortng Revew Introducton to Algorthms Qucksort CSE 680 Prof. Roger Crawfs Inserton Sort T(n) = Θ(n 2 ) In-place Merge Sort T(n) = Θ(n lg(n)) Not n-place Selecton Sort (from homework) T(n) = Θ(n 2 ) In-place

More information

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated.

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated. Some Advanced SP Tools 1. umulatve Sum ontrol (usum) hart For the data shown n Table 9-1, the x chart can be generated. However, the shft taken place at sample #21 s not apparent. 92 For ths set samples,

More information

TN348: Openlab Module - Colocalization

TN348: Openlab Module - Colocalization TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages

More information

Dynamic Camera Assignment and Handoff

Dynamic Camera Assignment and Handoff 12 Dynamc Camera Assgnment and Handoff Br Bhanu and Ymng L 12.1 Introducton...338 12.2 Techncal Approach...339 12.2.1 Motvaton and Problem Formulaton...339 12.2.2 Game Theoretc Framework...339 12.2.2.1

More information

Efficient Content Representation in MPEG Video Databases

Efficient Content Representation in MPEG Video Databases Effcent Content Representaton n MPEG Vdeo Databases Yanns S. Avrths, Nkolaos D. Doulams, Anastasos D. Doulams and Stefanos D. Kollas Department of Electrcal and Computer Engneerng Natonal Techncal Unversty

More information

Implementation of a Dynamic Image-Based Rendering System

Implementation of a Dynamic Image-Based Rendering System Implementaton of a Dynamc Image-Based Renderng System Nklas Bakos, Claes Järvman and Mark Ollla 3 Norrköpng Vsualzaton and Interacton Studo Lnköpng Unversty Abstract Work n dynamc mage based renderng has

More information

Contours Planning and Visual Servo Control of XXY Positioning System Using NURBS Interpolation Approach

Contours Planning and Visual Servo Control of XXY Positioning System Using NURBS Interpolation Approach Inventon Journal of Research Technology n Engneerng & Management (IJRTEM) ISSN: 2455-3689 www.jrtem.com olume 1 Issue 4 ǁ June. 2016 ǁ PP 16-23 Contours Plannng and sual Servo Control of XXY Postonng System

More information

CSCI 104 Sorting Algorithms. Mark Redekopp David Kempe

CSCI 104 Sorting Algorithms. Mark Redekopp David Kempe CSCI 104 Sortng Algorthms Mark Redekopp Davd Kempe Algorthm Effcency SORTING 2 Sortng If we have an unordered lst, sequental search becomes our only choce If we wll perform a lot of searches t may be benefcal

More information

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

More information

Multiple Frame Motion Inference Using Belief Propagation

Multiple Frame Motion Inference Using Belief Propagation Multple Frame Moton Inference Usng Belef Propagaton Jang Gao Janbo Sh The Robotcs Insttute Department of Computer and Informaton Scence Carnege Mellon Unversty Unversty of Pennsylvana Pttsburgh, PA 53

More information

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents

More information

Pictures at an Exhibition

Pictures at an Exhibition 1 Pctures at an Exhbton Stephane Kwan and Karen Zhu Department of Electrcal Engneerng Stanford Unversty, Stanford, CA 9405 Emal: {skwan1, kyzhu}@stanford.edu Abstract An mage processng algorthm s desgned

More information

Multi-view 3D Position Estimation of Sports Players

Multi-view 3D Position Estimation of Sports Players Mult-vew 3D Poston Estmaton of Sports Players Robbe Vos and Wlle Brnk Appled Mathematcs Department of Mathematcal Scences Unversty of Stellenbosch, South Afrca Emal: vosrobbe@gmal.com Abstract The problem

More information

Classification Based Mode Decisions for Video over Networks

Classification Based Mode Decisions for Video over Networks Classfcaton Based Mode Decsons for Vdeo over Networks Deepak S. Turaga and Tsuhan Chen Advanced Multmeda Processng Lab Tranng data for Inter-Intra Decson Inter-Intra Decson Regons pdf 6 5 6 5 Energy 4

More information

Collaborative Tracking of Objects in EPTZ Cameras

Collaborative Tracking of Objects in EPTZ Cameras Collaboratve Trackng of Objects n EPTZ Cameras Fasal Bashr and Fath Porkl * Mtsubsh Electrc Research Laboratores, Cambrdge, MA, USA ABSTRACT Ths paper addresses the ssue of mult-source collaboratve object

More information

RAP. Speed/RAP/CODA. Real-time Systems. Modeling the sensor networks. Real-time Systems. Modeling the sensor networks. Real-time systems:

RAP. Speed/RAP/CODA. Real-time Systems. Modeling the sensor networks. Real-time Systems. Modeling the sensor networks. Real-time systems: Speed/RAP/CODA Presented by Octav Chpara Real-tme Systems Many wreless sensor network applcatons requre real-tme support Survellance and trackng Border patrol Fre fghtng Real-tme systems: Hard real-tme:

More information

METRIC ALIGNMENT OF LASER RANGE SCANS AND CALIBRATED IMAGES USING LINEAR STRUCTURES

METRIC ALIGNMENT OF LASER RANGE SCANS AND CALIBRATED IMAGES USING LINEAR STRUCTURES METRIC ALIGNMENT OF LASER RANGE SCANS AND CALIBRATED IMAGES USING LINEAR STRUCTURES Lorenzo Sorg CIRA the Italan Aerospace Research Centre Computer Vson and Vrtual Realty Lab. Outlne Work goal Work motvaton

More information

Adaptive Silhouette Extraction and Human Tracking in Dynamic. Environments 1

Adaptive Silhouette Extraction and Human Tracking in Dynamic. Environments 1 Adaptve Slhouette Extracton and Human Trackng n Dynamc Envronments 1 X Chen, Zhha He, Derek Anderson, James Keller, and Marjore Skubc Department of Electrcal and Computer Engneerng Unversty of Mssour,

More information

A NEW FUZZY C-MEANS BASED SEGMENTATION STRATEGY. APPLICATIONS TO LIP REGION IDENTIFICATION

A NEW FUZZY C-MEANS BASED SEGMENTATION STRATEGY. APPLICATIONS TO LIP REGION IDENTIFICATION A NEW FUZZY C-MEANS BASED SEGMENTATION STRATEGY. APPLICATIONS TO LIP REGION IDENTIFICATION Mhaela Gordan *, Constantne Kotropoulos **, Apostolos Georgaks **, Ioanns Ptas ** * Bass of Electroncs Department,

More information

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr)

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr) Helsnk Unversty Of Technology, Systems Analyss Laboratory Mat-2.08 Independent research projects n appled mathematcs (3 cr) "! #$&% Antt Laukkanen 506 R ajlaukka@cc.hut.f 2 Introducton...3 2 Multattrbute

More information

A fast algorithm for color image segmentation

A fast algorithm for color image segmentation Unersty of Wollongong Research Onlne Faculty of Informatcs - Papers (Arche) Faculty of Engneerng and Informaton Scences 006 A fast algorthm for color mage segmentaton L. Dong Unersty of Wollongong, lju@uow.edu.au

More information

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

Resolving Ambiguity in Depth Extraction for Motion Capture using Genetic Algorithm

Resolving Ambiguity in Depth Extraction for Motion Capture using Genetic Algorithm Resolvng Ambguty n Depth Extracton for Moton Capture usng Genetc Algorthm Yn Yee Wa, Ch Kn Chow, Tong Lee Computer Vson and Image Processng Laboratory Dept. of Electronc Engneerng The Chnese Unversty of

More information

A ROBUST FEATURE TRACKER FOR ACTIVE SURVEILLANCE OF OUTDOOR SCENES

A ROBUST FEATURE TRACKER FOR ACTIVE SURVEILLANCE OF OUTDOOR SCENES Electronc Letters on Computer Vson and mage Analyss 1(1):21-34, 2003 A ROBUST FEATURE TRACKER FOR ACTVE SURVELLANCE OF OUTDOOR SCENES G. L. Forest and C. Mchelon Departement of Mathematcs and Computer

More information

A Background Subtraction for a Vision-based User Interface *

A Background Subtraction for a Vision-based User Interface * A Background Subtracton for a Vson-based User Interface * Dongpyo Hong and Woontack Woo KJIST U-VR Lab. {dhon wwoo}@kjst.ac.kr Abstract In ths paper, we propose a robust and effcent background subtracton

More information

A Gradient Difference based Technique for Video Text Detection

A Gradient Difference based Technique for Video Text Detection A Gradent Dfference based Technque for Vdeo Text Detecton Palaahnakote Shvakumara, Trung Quy Phan and Chew Lm Tan School of Computng, Natonal Unversty of Sngapore {shva, phanquyt, tancl }@comp.nus.edu.sg

More information

Mathematics 256 a course in differential equations for engineering students

Mathematics 256 a course in differential equations for engineering students Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

Feature Reduction and Selection

Feature Reduction and Selection Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components

More information

A Gradient Difference based Technique for Video Text Detection

A Gradient Difference based Technique for Video Text Detection 2009 10th Internatonal Conference on Document Analyss and Recognton A Gradent Dfference based Technque for Vdeo Text Detecton Palaahnakote Shvakumara, Trung Quy Phan and Chew Lm Tan School of Computng,

More information

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 An Iteratve Soluton Approach to Process Plant Layout usng Mxed

More information

Feature-Area Optimization: A Novel SAR Image Registration Method

Feature-Area Optimization: A Novel SAR Image Registration Method Feature-Area Optmzaton: A Novel SAR Image Regstraton Method Fuqang Lu, Fukun B, Lang Chen, Hao Sh and We Lu Abstract Ths letter proposes a synthetc aperture radar (SAR) mage regstraton method named Feature-Area

More information

Load-Balanced Anycast Routing

Load-Balanced Anycast Routing Load-Balanced Anycast Routng Chng-Yu Ln, Jung-Hua Lo, and Sy-Yen Kuo Department of Electrcal Engneerng atonal Tawan Unversty, Tape, Tawan sykuo@cc.ee.ntu.edu.tw Abstract For fault-tolerance and load-balance

More information

Detection of an Object by using Principal Component Analysis

Detection of an Object by using Principal Component Analysis Detecton of an Object by usng Prncpal Component Analyss 1. G. Nagaven, 2. Dr. T. Sreenvasulu Reddy 1. M.Tech, Department of EEE, SVUCE, Trupath, Inda. 2. Assoc. Professor, Department of ECE, SVUCE, Trupath,

More information

K-means and Hierarchical Clustering

K-means and Hierarchical Clustering Note to other teachers and users of these sldes. Andrew would be delghted f you found ths source materal useful n gvng your own lectures. Feel free to use these sldes verbatm, or to modfy them to ft your

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

More information

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and

More information

IP Camera Configuration Software Instruction Manual

IP Camera Configuration Software Instruction Manual IP Camera 9483 - Confguraton Software Instructon Manual VBD 612-4 (10.14) Dear Customer, Wth your purchase of ths IP Camera, you have chosen a qualty product manufactured by RADEMACHER. Thank you for the

More information

Newton-Raphson division module via truncated multipliers

Newton-Raphson division module via truncated multipliers Newton-Raphson dvson module va truncated multplers Alexandar Tzakov Department of Electrcal and Computer Engneerng Illnos Insttute of Technology Chcago,IL 60616, USA Abstract Reducton n area and power

More information

Theodoros Alexandropoulos, Vassili Loumos, Eleftherios Kayafas

Theodoros Alexandropoulos, Vassili Loumos, Eleftherios Kayafas Estmaton of ambent llumnaton varaton between colour mages n the presence of content changes for real-tme llumnaton-nvarant change detecton Theodoros Alexandropoulos, Vassl Loumos, Eleftheros Kayafas atonal

More information

Conditional Speculative Decimal Addition*

Conditional Speculative Decimal Addition* Condtonal Speculatve Decmal Addton Alvaro Vazquez and Elsardo Antelo Dep. of Electronc and Computer Engneerng Unv. of Santago de Compostela, Span Ths work was supported n part by Xunta de Galca under grant

More information

S1 Note. Basis functions.

S1 Note. Basis functions. S1 Note. Bass functons. Contents Types of bass functons...1 The Fourer bass...2 B-splne bass...3 Power and type I error rates wth dfferent numbers of bass functons...4 Table S1. Smulaton results of type

More information

Shape-adaptive DCT and Its Application in Region-based Image Coding

Shape-adaptive DCT and Its Application in Region-based Image Coding Internatonal Journal of Sgnal Processng, Image Processng and Pattern Recognton, pp.99-108 http://dx.do.org/10.14257/sp.2014.7.1.10 Shape-adaptve DCT and Its Applcaton n Regon-based Image Codng Yamn Zheng,

More information

Smoothing Spline ANOVA for variable screening

Smoothing Spline ANOVA for variable screening Smoothng Splne ANOVA for varable screenng a useful tool for metamodels tranng and mult-objectve optmzaton L. Rcco, E. Rgon, A. Turco Outlne RSM Introducton Possble couplng Test case MOO MOO wth Game Theory

More information

Classifier Swarms for Human Detection in Infrared Imagery

Classifier Swarms for Human Detection in Infrared Imagery Classfer Swarms for Human Detecton n Infrared Imagery Yur Owechko, Swarup Medasan, and Narayan Srnvasa HRL Laboratores, LLC 3011 Malbu Canyon Road, Malbu, CA 90265 {owechko, smedasan, nsrnvasa}@hrl.com

More information

SAO: A Stream Index for Answering Linear Optimization Queries

SAO: A Stream Index for Answering Linear Optimization Queries SAO: A Stream Index for Answerng near Optmzaton Queres Gang uo Kun-ung Wu Phlp S. Yu IBM T.J. Watson Research Center {luog, klwu, psyu}@us.bm.com Abstract near optmzaton queres retreve the top-k tuples

More information

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS ARPN Journal of Engneerng and Appled Scences 006-017 Asan Research Publshng Network (ARPN). All rghts reserved. NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS Igor Grgoryev, Svetlana

More information

Fast Feature Value Searching for Face Detection

Fast Feature Value Searching for Face Detection Vol., No. 2 Computer and Informaton Scence Fast Feature Value Searchng for Face Detecton Yunyang Yan Department of Computer Engneerng Huayn Insttute of Technology Hua an 22300, Chna E-mal: areyyyke@63.com

More information

SVM Based Forest Fire Detection Using Static and Dynamic Features

SVM Based Forest Fire Detection Using Static and Dynamic Features DOI: 10.2298/CSIS101012030Z SVM Based Forest Fre Detecton Usng Statc and Dynamc Features Janhu Zhao, Zhong Zhang, Shzhong Han, Chengzhang Qu Zhyong Yuan, and Dengy Zhang Computer School, Wuhan Unversty,

More information

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces Range mages For many structured lght scanners, the range data forms a hghly regular pattern known as a range mage. he samplng pattern s determned by the specfc scanner. Range mage regstraton 1 Examples

More information

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms Course Introducton Course Topcs Exams, abs, Proects A quc loo at a few algorthms 1 Advanced Data Structures and Algorthms Descrpton: We are gong to dscuss algorthm complexty analyss, algorthm desgn technques

More information

Intro. Iterators. 1. Access

Intro. Iterators. 1. Access Intro Ths mornng I d lke to talk a lttle bt about s and s. We wll start out wth smlartes and dfferences, then we wll see how to draw them n envronment dagrams, and we wll fnsh wth some examples. Happy

More information

SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB

SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB V. Hotař, A. Hotař Techncal Unversty of Lberec, Department of Glass Producng Machnes and Robotcs, Department of Materal

More information

CHAPTER 3 ENCODING VIDEO SEQUENCES IN FRACTAL BASED COMPRESSION. Day by day, the demands for higher and faster technologies are rapidly

CHAPTER 3 ENCODING VIDEO SEQUENCES IN FRACTAL BASED COMPRESSION. Day by day, the demands for higher and faster technologies are rapidly 65 CHAPTER 3 ENCODING VIDEO SEQUENCES IN FRACTAL BASED COMPRESSION 3.1 Introducton Day by day, the demands for hgher and faster technologes are rapdly ncreasng. Although the technologes avalable now are

More information

DLK Pro the all-rounder for mobile data downloading. Tailor-made for various requirements.

DLK Pro the all-rounder for mobile data downloading. Tailor-made for various requirements. DLK Pro the all-rounder for moble data downloadng Talor-made for varous requrements www.dtco.vdo.com Smply brllant, brllantly smple Always the rght soluton The DLK Pro s the VDO product famly, whch sets

More information

Virtual Machine Migration based on Trust Measurement of Computer Node

Virtual Machine Migration based on Trust Measurement of Computer Node Appled Mechancs and Materals Onlne: 2014-04-04 ISSN: 1662-7482, Vols. 536-537, pp 678-682 do:10.4028/www.scentfc.net/amm.536-537.678 2014 Trans Tech Publcatons, Swtzerland Vrtual Machne Mgraton based on

More information

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines A Modfed Medan Flter for the Removal of Impulse Nose Based on the Support Vector Machnes H. GOMEZ-MORENO, S. MALDONADO-BASCON, F. LOPEZ-FERRERAS, M. UTRILLA- MANSO AND P. GIL-JIMENEZ Departamento de Teoría

More information

SUMMARY... I TABLE OF CONTENTS...II INTRODUCTION...

SUMMARY... I TABLE OF CONTENTS...II INTRODUCTION... Summary A follow-the-leader robot system s mplemented usng Dscrete-Event Supervsory Control methods. The system conssts of three robots, a leader and two followers. The dea s to get the two followers to

More information

Support Vector Machines

Support Vector Machines Support Vector Machnes Decson surface s a hyperplane (lne n 2D) n feature space (smlar to the Perceptron) Arguably, the most mportant recent dscovery n machne learnng In a nutshell: map the data to a predetermned

More information

An optimized workflow for coherent noise attenuation in time-lapse processing

An optimized workflow for coherent noise attenuation in time-lapse processing An optmzed workflow for coherent nose attenuaton n tme-lapse processng Adel Khall 1, Hennng Hoeber 1, Steve Campbell 2, Mark Ibram 2 and Dan Daves 2. 1 CGGVertas, 2 BP 75 th EAGE Conference & Exhbton ncorporatng

More information

MOTION PANORAMA CONSTRUCTION FROM STREAMING VIDEO FOR POWER- CONSTRAINED MOBILE MULTIMEDIA ENVIRONMENTS XUNYU PAN

MOTION PANORAMA CONSTRUCTION FROM STREAMING VIDEO FOR POWER- CONSTRAINED MOBILE MULTIMEDIA ENVIRONMENTS XUNYU PAN MOTION PANORAMA CONSTRUCTION FROM STREAMING VIDEO FOR POWER- CONSTRAINED MOBILE MULTIMEDIA ENVIRONMENTS by XUNYU PAN (Under the Drecton of Suchendra M. Bhandarkar) ABSTRACT In modern tmes, more and more

More information

An Image Fusion Approach Based on Segmentation Region

An Image Fusion Approach Based on Segmentation Region Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua

More information

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15 CS434a/541a: Pattern Recognton Prof. Olga Veksler Lecture 15 Today New Topc: Unsupervsed Learnng Supervsed vs. unsupervsed learnng Unsupervsed learnng Net Tme: parametrc unsupervsed learnng Today: nonparametrc

More information

CS 534: Computer Vision Model Fitting

CS 534: Computer Vision Model Fitting CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust

More information

Real time depth mapping performed on an autonomous stereo vision module

Real time depth mapping performed on an autonomous stereo vision module 1 Real tme depth mappng performed on an autonomous stereo vson module Jeroen Smt 1, Rchard Klehorst 2, Anteneh Abbo 2, Jan Meuleman 1 and Gerard van Wllgenburg 1 1 Wagenngen Unversty, Bornsesteeg 59, 6708

More information

A Study on the Application of Spatial-Knowledge-Tags using Human Motion in Intelligent Space

A Study on the Application of Spatial-Knowledge-Tags using Human Motion in Intelligent Space A Study on the Applcaton of Spatal-Knowledge-Tags usng Human Moton n Intellgent Space Tae-Seok Jn*, Kazuyuk Moroka**, Mhoko Ntsuma*, Takesh Sasak*, and Hdek Hashmoto * * Insttute of Industral Scence, the

More information