A User-Attention Based Focus Detection Framework and Its Applications
|
|
- Nathaniel Davidson
- 5 years ago
- Views:
Transcription
1 A Uer-Attention Baed Focu Detection Framework and It Application Chia-Chiang Ho, Wen-Huang Cheng, Ting-Jian Pan, Ja-Ling Wu Communication and Multimedia Laboratory, Department of Computer Science and Information Engineering, National Taiwan Univerity, No. 1, Roovelt Rd. Sec. 4, Taipei, Taiwan Abtract In thi paper, a generic uer-attention baed focu detection framework i developed to capture uer focu point for video frame. The propoed framework conider both bottom-up and top-down attention, and integrate both image-baed and video-baed viual feature for aliency map computation. For efficiency purpoe, the number of adopted feature i kept a few a poible. The realized framework i extenible and flexible in integrating more feature with a variety of fuion cheme. One application of the propoed framework, the uer-aited patial reolution reduction, ha alo been addreed. 1. Introduction Attention refer to the ability of one human to focu and concentrate upon ome viual or auditory object, by carefully watching or litening. Auming limited proceing reource of one human, attention alo refer to the allocation of thee reource. Here, the reource can refer to either neurological or cognitive reource. The former i often referred a bottom-up attention and the later top-down attention. We can roughly ay that bottom-up attention model what people are attracted to ee, and topdown attention model what people are willing to ee. In hort, thee two model can be ummarized briefly a follow: Bottom-up attention: The bottom-up attention can be modeled a an integration of different meaurable, lowlevel image feature [1]. Koch and Ullman propoed the firt neurally plauible computational architecture of bottom-up attention model in 1985 [2]. Later reearche on bottom-up attention generally followed thi pioneering architecture. Nowaday, the bottom-up attention model propoed by Itti et al. draw great attention [3]. Top-down attention: Although the bottom-up attention model may capture the deployment of attention within the firt few hundred of milliecond after preenting the viual cene, a complete attention model mut conider top-down, tak-oriented influence a well. Baed on bottom-up attention model, there are reearche that integrated the concept of top-down attention for object recognition tak [4][5][6]. For general purpoe, top-down attention i uually modeled by detecting ome meaningful (emantic) object or video feature. For example, in [7], top-down attention wa modeled by face detection and camera motion detection. In thi paper, we integrate both bottom-up and top-down feature in our uer attention model. Then, we propoe a general uer-attention baed framework to detect uer focue in video frame. Our work may provide another point of view for olving ome content-aware problem. We preent one application and related experimental reult of the propoed focu detection framework: the uer-aited patial reolution reduction which aim at obtaining better patial reolution reduction of the input video intead of direct ub-ampling. Modeling Uer attention may alo benefit other application, uch a video encoding, urveillance, watermarking, and video ummarization [7]. The ret of thi paper i organized a follow: Section 2 introduce the propoed uer-attention baed focu detection framework. Section 3 dicue the uer-aited patial reolution reduction. Section 4 report ome experimental reult. Finally, Section 5 preent the concluion and future work. 2. The Propoed Uer-Attention Baed Focu Detection Framework In thi ection, we propoe a uer-attention baed focu detection framework, which combine both bottom-up and top-down attention feature, uch a intenity, color, motion and face. Without fully emantic undertanding of video content, the propoed framework provide u another way to benefit many content-baed application. Meanwhile, the ytem i carefully deigned to deal with peed iue which real-time application concerned about. Fig. 1 how the naphot and illutration of the implemented focu detection framework.
2 The lat thing to do i to combine all feature map belonging to one feature into one integrated map. All map are re-caled into the ame ize, and a pixel-by-pixel maximum operation i performed among all thee re-caled map. Thi reemble a winner-take-all competition among different feature map. An additional maximum operation i performed to combine Cb and Cr feature map into one color aliency map. Thu the computation of low-level feature yield two aliency map, i.e., the intenity aliency map and the color aliency map. Figure 1. The operational naphot of the propoed uerattention baed focu detection framework. 2.1 Attentional Viual Feature Calculation We model computable attentional viual feature into three level, ay, low level, medium level and high level. Low-level feature (intenity and color): Feature belonging to thi level correpond to the o-called early viual feature in the biological viion, including but not limited to intenity contrat, color opponency, and orientation. Speed i a major concern in our ytem, o only intenity and color are ued in our attention model. It i worthy of mentioning that in our obervation, mot of alient region (or object) found through computation of different early viual feature might actually be imilar. In our ytem, intenity and color feature are calculated in the YCbCr color pace, which i ued by mot of video coding tandard. The generation of adopted feature map i imilar to that of the Itti method [8]. A map normalization operation i then applied to each feature map, which globally promote map in which a mall number of trong peak are preented and globally uppree thoe map with many peak. Another effect of normalization operation i to let all feature map hare a common dynamic range. The normalization operation i performed by: a) Finding out the maximal and minimum value, MinVal and MaxVal, of the feature map, and then calculate a threhold value δ, which i defined a MinVal + ( MaxVal MinVal)/10. (1) b) Counting the average value of pixel with value larger than δ, V. δ c) Calculating the map caling factor a MaxVal Vδ 255 F =, (2) MaxVal MinVal MaxVal and multiplying the feature map with thi caling factor. The dynamic range after map normalization operation i [0,255], for all feature map. Medium-level feature (motion): In our thought, motion preent not only bottom-up but alo top-down attention information. Some baic obervation can be drawn: a) Image egment with patially conitent motion field are more likely to be part of foreground moving object and receive more uer attention than thoe in the background do. b) The uer i more aware of object with temporally conitent motion. c) Object with larger motion draw more attention than thoe with maller motion do. d) People can pay attention to a very limited number of object in a cene. When there are many different object (poibly with different motion), people lo the ability of attention. In thi paper, block motion vector are ued for motion analyi and uer-attention modeling. Though ometime motion vector don t reflect the true motion field well, but utilizing motion vector can greatly help for reducing more computation complexity than that of the fine-grained optical flow. An approach imilar to [7] i adopted to deal with our motion aliency map. For one macroblock i, we define the intenity of it motion vector ( dx, dy) a I ( i) + dy By computing motion vector intenitie of all macroblock in a frame, we get an intenity map I. Let W (i) be the et of motion vector of all macroblock until a redefined window, W. The phae of one motion vector ( dx, dy) i defined a dy Phae = arctan( ). (4) dx 2 2 = dx. (3) The range of a phae i [ 0,2π ]. We calculate an eight-bin phae hitogram of W (i) and meaure the patial-temporal conitency a H p ( h)log( p ( h)) h= 1 C( i) = 1+, (5) log( H )
3 where H i the number of hitogram bin and p (h) i the probability of one particular bin h. The larger C (i) mean the more conitent motion field. By computing the patialtemporal conitency value of all macroblock, we get a motion conitency map C. The motion intenity map, I, and the motion conitency map, C, are combined to yield a ingle value of motion attention. That i, M = I C. (6) We call M a the motion aliency map, and a normalization operation i performed to yield a dynamic range of [0, 255]. High-level feature (face): Dominant face in video frame certainly attract uer attention. In fact, we can aume that people naturally locate face in video frame with priority over other type of object. In our implementation, two kind of face detection cheme are invetigated. Traditional face detection i baed on template matching. We invetigate an object detector pecifically trained for face detection. The idea ha been initially propoed by Paul Viola [9] and improved by Rainer Lienhart [10]. Thi cheme provide comparably good reult for frontal face; however, it uffer from non-frontal face and tilted face. The alternative cla of face detection i baed on kinregion detection. We implemented the kin color model given in [11]. Thi cheme can find mot of face region in video frame. While mi detection rate i very low, uing kin-color detection only ometime uffer from high fale alarm rate. It i our experience that uing the morphological opening operation and impoing ome ize and apect ratio contraint on the detected region can help to reduce fale alarm. Finally, after face region detection, we get a face aliency map. 2.2 The Fuion Stage and the Focu Point Detection The fuion tage: After four aliency map (intenity, color, motion and face map) are available, a fuion tage i required to integrate all map into a final aliency map. In our implementation, we ue a particular fuion cheme, called priority-baed competition. Feature map in the ame level are combined uing the maximal operation. Then the integrated map in the lower level i caled down by a pre-defined factor, and then compete with the integrated map in the higher level. The block diagram of the priority-baed competition i hown in Fig. 2. Focu point detection: Once the final aliency map i generated through the fuion tage, we are now ready to detect a ingle focu point for each video frame. Following tep accomplih thi work: a) Threholding and binarization. Let MIN and MAX be the minimal and the maximal value of the final aliency map. The threhold BinThr i determined a: BinThr = MAX ( MAX MIN) / ThrFactor, (7) where ThrFactor i an adjutable parameter. b) Connected component analyi i then performed and the larget component i found. The center of the larget connected component i et a the candidate of focu point. If no connected component i found, or the area of the larget component i maller than a pre-defined threhold, the candidate focu point i et to be the center of the frame. c) To avoid poible fale alarm, we retrict the ditance between focu point of two neighboring frame. d) To maintain a mooth locu of focu point, a Gauianlike filter i applied to ucceive detected focue. Figure 2. The priority-baed fuion cheme for final aliency map calculation. 3. Uer-Aited Spatial Reolution Reduction Spatial reolution reduction i neceary for ome content repurpoing related application. For example, adapting video with higher patial reolution to device with maller diplay. The eaiet way to perform patial reolution reduction i through direct ub-ampling, however, thi may be undeirable becaue the intereting ubject() may be too mall to view. For better uer atifaction of patial reolution reduction, we propoe the o-called uer-aited patial reolution reduction. Firt, we perform the attention focu detection baed on the precribed uer-attention modeling ytem. Then we let the uer pecify the wanted patial ub-ampling factor and the patial cropping factor. Let thee two value be repectively denoted a r and r c, and the valid range of them i (0,1). Finally, we perform the required ubampling and cropping operation by etting the detected focu point a the center of the operational region. Then we can adjut the patial reolution of image or video by
4 cropping the operational region intead of jut down ampling the entire image or video. 4. Experimental Reult In thi ection, we preent ome experimental reult of the propoed uer-attention baed focu point detection framework, the uer-aited patial reolution reduction, and the attentional focu-point ubjective experiment. We tet the propoed focu detection framework by uing ome well-known equence. Fig. 4 and Fig. 5 how ome focu detection reult for the equence foreman and mobile, repectively. In Fig. 4, the foreman ha conpicuou motion activitie and explicit face, which are uccefully detected through motion and face aliency calculation, and the detected focu point perform reaonably and atifactorily. (a) (b) Figure 4. Reult of aliency map and focu point detection for the equence foreman : (a) the 9 th frame, (b) the 80 th frame. Fig. 5 how aliency map and detected focu point for the intereted frame of the mobile equence. Although thee frame have a lot of intenity or color aliency pot (it can be een that the background i complex), motion map are popped out becaue (1) there i only one conpicuou region exit and (2) motion map are with larger weighting in the fuion tage. The reult are atifactory. different characteritic. In different categorie, we have different weighting factor in combining aliency map of the focu detection framework. Then, we invited 20 oberver to participate in the tet. Every oberver give a core from 1 to 5 (larger value mean better quality in perception) according to hi or her intuition. The ubjective reult are hown in Table 1. In each category, the core mean i atifactory and the core variance i mall. We find from that by chooing proper parameter et, the detected focu point in different kind of video content i repreentative. In concluion, the focu-point detection framework uccefully model the oberver attention. Category Score mean Score var. Home Video High Motion Nature Sport TV & Movie Other Table 1. Reult of the focu-point ubjective experiment The econd kind of our experiment i about patial reolution reduction. Fig. 6 how different patial reolution reduction reult of the equence horn by uing different parameter but with the ame final image ize. The cropping region hown in Fig. 6 are determined by the aitance of the uer attention modeling ytem. The difference of emantic information revealed by different patial reolution reduction parameter i obviou to ee, and the uer-attention modeling ytem do help for revealing more emantic information when the final image ize i very mall a compared to the original one. (a) (b) (c) Figure 6. Spatial reolution reduction with parameter: (a) r = 0.25 and r c = 1.0, (b) r = 0.5 and r c = 0.5, and (c) r = 1.0 and r c = The Concluion and Future Work The following concluion can be made for the propoed framework of focu detection: (a) (b) Figure 5. Reult of aliency map and focu point detection for the equence mobile : (a) the 15 th frame, and (b) the 73 rd frame. To further validate the propoed framework of focu finding, we performed ubjective experiment. Teting video clip are claified into ix categorie according to a) A general uer attention baed focu detection framework i developed to capture uer focu point on video frame. The propoed framework conider both bottom-up and top-down attention, and i extenible and flexible for integrating more feature with a variety of fuion cheme.
5 b) Combining other perceptual model with our framework, the ytem can have many application, uch a uerattention baed video encoding, and the uer-aited patial reolution reduction, which have alo been addreed in thi write-up. In the future, more tak mut be done to enlarge the capability of the propoed framework, e.g., uing more complex modeling cheme to improve adopted feature, integrating more robut face detection cheme and adopting more complex fuion cheme to the fuion tage. A for application of focu detection, one intereting application i the o-called uer-attention baed video encoding, which aim at reducing bitrate requirement, without acrificing perceived quality for typical encoding cheme. The uer-attention baed video encoding can be done through dicarding unimportant viual information a much a poible, under the guideline of the foveation model [12]. It alo electively preerve higher quality for thoe focued region, in trade of wore quality for thoe periphery region, to maximally match uer expectation. Thee cenario can alo be applied to generate the bae layer bittream of a calable video, when the bitrate contraint i very trict. Fig 3 how the propoed architecture of the uer-attention baed video encoding. Some reearch iue and experimental reult are addreed in [13]. Imaging, Special Iue on Human Viion and Electronic Imaging, Vol. 10, No. 1, pp , [5] I. A. Rybak, V. I. Guakova, A. Golovan, L. N. Podladchikova, and N. A. Shevtova, A model of attention-guided viual perception and recognition, Viion Reolution, Vol. 38, pp , [6] G. Deco and J. Zihl, A neurodynamical model of viual attention: Feedback enhancement of patial reolution in a hierarchical ytem, Journal of Computational Neurocience, Vol. 10, pp , [7] Y.-F. Ma, L. Lu, H.-J. Zhang, and M. Li, A uer attention model for video ummarization, in Proc. ACM Multimedia (ACMMM 02), pp , Dec [8] L. Itti, C. Koch, and E. Niebur, A model of aliencybaed viual attention for rapid cene analyi, IEEE Tran. Pattern Anal. Machine Intell., Vol. 20, No. 11, pp , Nov [9] P. Viola and M. Jone, Robut real-time object detection, in Second Intl, Workhop on Statitical and Computational Theorie of Viion: Modeling, Learning, Computing and Sampling, July [10] R. Lienhart and J. Maydt, An extended et of haarlike feature for rapid object detection, in Proc. IEEE Intl. Conf. Image Proceing (ICIP 02), pp , Sept [11] C. Garcia and G. Tzirita, Face detection uing quantized kin color region merging and wavelet packet analyi, IEEE Tran. Multimedia, Vol. 1, No. 3, pp , Sept Figure 3. The propoed architecture of the uer-attention baed video encoding. Reference [1] A. M. Treiman and G. Gelade, A feature integration theory of attention, Cognitive Pychology, Vol. 12, No. 1, pp , [12] C.-C. Ho and J.-L. Wu, "A foveation-baed rate haping mechanim for MPEG video," in Proc. 3th IEEE Pacific-Rim Conference on Multimedia (PCM'02), Springer-Verlag (LNCS 2532), pp , Hinchu, Taiwan, Dec [13] Ho, C.-C. A Study of Effective Technique for Uer- Centric Video Streaming, Ph.D. diertation, National Taiwan Univerity, Taipei, Taiwan, June, [2] C. Koch and S. Ullman, Shift in elective viual attention: toward the underlying neural circuitry, Human Neurobiology, Vol. 4, pp , [3] L. Itti and C. Koch, Computational modeling of viual attention, Nature Review Neurocience, Vol. 2, No. 3, pp , Mar [4] K. Schill, E. Umkehrer, S. Beinlich, G. Krieger, and C. Zetzche, Scene analyi with accadic eye movement: top-down and bottom-up modeling, Journal of Electronic
Performance of a Robust Filter-based Approach for Contour Detection in Wireless Sensor Networks
Performance of a Robut Filter-baed Approach for Contour Detection in Wirele Senor Network Hadi Alati, William A. Armtrong, Jr., and Ai Naipuri Department of Electrical and Computer Engineering The Univerity
More informationLaboratory Exercise 6
Laboratory Exercie 6 Adder, Subtractor, and Multiplier The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each type of circuit will be implemented in two
More informationUniversität Augsburg. Institut für Informatik. Approximating Optimal Visual Sensor Placement. E. Hörster, R. Lienhart.
Univerität Augburg à ÊÇÅÍÆ ËÀǼ Approximating Optimal Viual Senor Placement E. Hörter, R. Lienhart Report 2006-01 Januar 2006 Intitut für Informatik D-86135 Augburg Copyright c E. Hörter, R. Lienhart Intitut
More informationMulti-Target Tracking In Clutter
Multi-Target Tracking In Clutter John N. Sander-Reed, Mary Jo Duncan, W.B. Boucher, W. Michael Dimmler, Shawn O Keefe ABSTRACT A high frame rate (0 Hz), multi-target, video tracker ha been developed and
More informationBuilding a Compact On-line MRF Recognizer for Large Character Set using Structured Dictionary Representation and Vector Quantization Technique
202 International Conference on Frontier in Handwriting Recognition Building a Compact On-line MRF Recognizer for Large Character Set uing Structured Dictionary Repreentation and Vector Quantization Technique
More informationHassan Ghaziri AUB, OSB Beirut, Lebanon Key words Competitive self-organizing maps, Meta-heuristics, Vehicle routing problem,
COMPETITIVE PROBABIISTIC SEF-ORGANIZING MAPS FOR ROUTING PROBEMS Haan Ghaziri AUB, OSB Beirut, ebanon ghaziri@aub.edu.lb Abtract In thi paper, we have applied the concept of the elf-organizing map (SOM)
More informationChapter 13 Non Sampling Errors
Chapter 13 Non Sampling Error It i a general aumption in the ampling theory that the true value of each unit in the population can be obtained and tabulated without any error. In practice, thi aumption
More informationANALYSIS OF THE FIRST LAYER IN WEIGHTLESS NEURAL NETWORKS FOR 3_DIMENSIONAL PATTERN RECOGNITION
ANALYSIS OF THE FIRST LAYER IN WEIGHTLESS NEURAL NETWORKS FOR 3_DIMENSIONAL PATTERN RECOGNITION A. Váque-Nava * Ecuela de Ingeniería. CENTRO UNIVERSITARIO MEXICO. DIVISION DE ESTUDIOS SUPERIORES J. Figueroa
More informationComparison of Methods for Horizon Line Detection in Sea Images
Comparion of Method for Horizon Line Detection in Sea Image Tzvika Libe Evgeny Gerhikov and Samuel Koolapov Department of Electrical Engineering Braude Academic College of Engineering Karmiel 2982 Irael
More informationDAROS: Distributed User-Server Assignment And Replication For Online Social Networking Applications
DAROS: Ditributed Uer-Server Aignment And Replication For Online Social Networking Application Thuan Duong-Ba School of EECS Oregon State Univerity Corvalli, OR 97330, USA Email: duongba@eec.oregontate.edu
More informationA reduced reference image quality metric based on feature fusion and neural networks
Univerity of Wollongong Reearch Online Faculty of Engineering and Information Science - Paper: Part A Faculty of Engineering and Information Science 2011 A reduced reference image quality metric baed on
More informationIMPROVED JPEG DECOMPRESSION OF DOCUMENT IMAGES BASED ON IMAGE SEGMENTATION. Tak-Shing Wong, Charles A. Bouman, and Ilya Pollak
IMPROVED DECOMPRESSION OF DOCUMENT IMAGES BASED ON IMAGE SEGMENTATION Tak-Shing Wong, Charle A. Bouman, and Ilya Pollak School of Electrical and Computer Engineering Purdue Univerity ABSTRACT We propoe
More informationLecture 14: Minimum Spanning Tree I
COMPSCI 0: Deign and Analyi of Algorithm October 4, 07 Lecture 4: Minimum Spanning Tree I Lecturer: Rong Ge Scribe: Fred Zhang Overview Thi lecture we finih our dicuion of the hortet path problem and introduce
More informationMAT 155: Describing, Exploring, and Comparing Data Page 1 of NotesCh2-3.doc
MAT 155: Decribing, Exploring, and Comparing Data Page 1 of 8 001-oteCh-3.doc ote for Chapter Summarizing and Graphing Data Chapter 3 Decribing, Exploring, and Comparing Data Frequency Ditribution, Graphic
More informationDistributed Packet Processing Architecture with Reconfigurable Hardware Accelerators for 100Gbps Forwarding Performance on Virtualized Edge Router
Ditributed Packet Proceing Architecture with Reconfigurable Hardware Accelerator for 100Gbp Forwarding Performance on Virtualized Edge Router Satohi Nihiyama, Hitohi Kaneko, and Ichiro Kudo Abtract To
More informationMarkov Random Fields in Image Segmentation
Preented at SSIP 2011, Szeged, Hungary Markov Random Field in Image Segmentation Zoltan Kato Image Proceing & Computer Graphic Dept. Univerity of Szeged Hungary Zoltan Kato: Markov Random Field in Image
More informationTrainable Context Model for Multiscale Segmentation
Trainable Context Model for Multicale Segmentation Hui Cheng and Charle A. Bouman School of Electrical and Computer Engineering Purdue Univerity Wet Lafayette, IN 47907-1285 {hui, bouman}@ ecn.purdue.edu
More informationMulticlass Road Sign Detection using Multiplicative Kernel
Proceeding of the Croatian Computer Viion Workhop, Year 1 Multicla Road Sign Detection uing Multiplicative Kernel Valentina Zadrija Mireo d. d. Zagreb, Croatia valentina.zadrija@mireo.hr Siniša Šegvić
More informationService and Network Management Interworking in Future Wireless Systems
Service and Network Management Interworking in Future Wirele Sytem V. Tountopoulo V. Stavroulaki P. Demeticha N. Mitrou and M. Theologou National Technical Univerity of Athen Department of Electrical Engineering
More informationxy-monotone path existence queries in a rectilinear environment
CCCG 2012, Charlottetown, P.E.I., Augut 8 10, 2012 xy-monotone path exitence querie in a rectilinear environment Gregory Bint Anil Mahehwari Michiel Smid Abtract Given a planar environment coniting of
More informationGray-level histogram. Intensity (grey-level) transformation, or mapping. Use of intensity transformations:
Faculty of Informatic Eötvö Loránd Univerity Budapet, Hungary Lecture : Intenity Tranformation Image enhancement by point proceing Spatial domain and frequency domain method Baic Algorithm for Digital
More informationTracking High Speed Skater by Using Multiple Model
Vol. 2, No. 26 Tracing High Speed Sater by Uing Multiple Model Guojun Liu & Xianglong Tang School of Computer Science & Engineering Harbin Intitute of Technology Harbin 5000, China E-mail: hitliu@hit.edu.cn
More informationAn Image Edge Detection Algorithm using Wavelet Transform and Fuzzy Techniques
An Image Edge Detection Algorithm uing Wavelet Tranform and Fuzzy Technique Bin Huang 1*, Jiaofeng Wang,Xiaomei Jin 3 1.College of Teacher Education, Quzhou Univerity, Zheiang Quzhou, china. Quzhou Vocational
More informationAUTOMATIC TEST CASE GENERATION USING UML MODELS
Volume-2, Iue-6, June-2014 AUTOMATIC TEST CASE GENERATION USING UML MODELS 1 SAGARKUMAR P. JAIN, 2 KHUSHBOO S. LALWANI, 3 NIKITA K. MAHAJAN, 4 BHAGYASHREE J. GADEKAR 1,2,3,4 Department of Computer Engineering,
More information3D SMAP Algorithm. April 11, 2012
3D SMAP Algorithm April 11, 2012 Baed on the original SMAP paper [1]. Thi report extend the tructure of MSRF into 3D. The prior ditribution i modified to atify the MRF property. In addition, an iterative
More informationAnalyzing Hydra Historical Statistics Part 2
Analyzing Hydra Hitorical Statitic Part Fabio Maimo Ottaviani EPV Technologie White paper 5 hnode HSM Hitorical Record The hnode i the hierarchical data torage management node and ha to perform all the
More informationHow to. write a paper. The basics writing a solid paper Different communities/different standards Common errors
How to write a paper The baic writing a olid paper Different communitie/different tandard Common error Reource Raibert eay My grammar point Article on a v. the Bug in writing Clarity Goal Conciene Calling
More informationAalborg Universitet. Published in: Proceedings of the Working Conference on Advanced Visual Interfaces
Aalborg Univeritet Software-Baed Adjutment of Mobile Autotereocopic Graphic Uing Static Parallax Barrier Paprocki, Martin Marko; Krog, Kim Srirat; Kritofferen, Morten Bak; Krau, Martin Publihed in: Proceeding
More informationRouting Definition 4.1
4 Routing So far, we have only looked at network without dealing with the iue of how to end information in them from one node to another The problem of ending information in a network i known a routing
More informationPlanning of scooping position and approach path for loading operation by wheel loader
22 nd International Sympoium on Automation and Robotic in Contruction ISARC 25 - September 11-14, 25, Ferrara (Italy) 1 Planning of cooping poition and approach path for loading operation by wheel loader
More information/06/$ IEEE 364
006 IEEE International ympoium on ignal Proceing and Information Technology oie Variance Etimation In ignal Proceing David Makovoz IPAC, California Intitute of Technology, MC-0, Paadena, CA, 95 davidm@ipac.caltech.edu;
More informationUSING ARTIFICIAL NEURAL NETWORKS TO APPROXIMATE A DISCRETE EVENT STOCHASTIC SIMULATION MODEL
USING ARTIFICIAL NEURAL NETWORKS TO APPROXIMATE A DISCRETE EVENT STOCHASTIC SIMULATION MODEL Robert A. Kilmer Department of Sytem Engineering Unite State Military Acaemy Wet Point, NY 1996 Alice E. Smith
More informationMotion Control (wheeled robots)
3 Motion Control (wheeled robot) Requirement for Motion Control Kinematic / dynamic model of the robot Model of the interaction between the wheel and the ground Definition of required motion -> peed control,
More informationOn combining Learning Vector Quantization and the Bayesian classifiers for natural textured images
On combining Learning Vector Quantization and the Bayeian claifier for natural textured image María Guiarro Dept. Ingeniería del Software e Inteligencia Artificial Facultad Informática Univeridad Complutene
More informationSee chapter 8 in the textbook. Dr Muhammad Al Salamah, Industrial Engineering, KFUPM
Goal programming Objective of the topic: Indentify indutrial baed ituation where two or more objective function are required. Write a multi objective function model dla a goal LP Ue weighting um and preemptive
More informationOperational Semantics Class notes for a lecture given by Mooly Sagiv Tel Aviv University 24/5/2007 By Roy Ganor and Uri Juhasz
Operational emantic Page Operational emantic Cla note for a lecture given by Mooly agiv Tel Aviv Univerity 4/5/7 By Roy Ganor and Uri Juhaz Reference emantic with Application, H. Nielon and F. Nielon,
More informationComputer Aided Drafting, Design and Manufacturing Volume 25, Number 3, September 2015, Page 10
Computer Aided Drafting, Deign and Manufacturing Volume 5, umber 3, September 015, Page 10 CADDM Reearch of atural Geture Recognition and Interactive Technology Compatible with YCbCr and SV Color Space
More informationAdvanced Encryption Standard and Modes of Operation
Advanced Encryption Standard and Mode of Operation G. Bertoni L. Breveglieri Foundation of Cryptography - AES pp. 1 / 50 AES Advanced Encryption Standard (AES) i a ymmetric cryptographic algorithm AES
More informationSLA Adaptation for Service Overlay Networks
SLA Adaptation for Service Overlay Network Con Tran 1, Zbigniew Dziong 1, and Michal Pióro 2 1 Department of Electrical Engineering, École de Technologie Supérieure, Univerity of Quebec, Montréal, Canada
More informationEdits in Xylia Validity Preserving Editing of XML Documents
dit in Xylia Validity Preerving diting of XML Document Pouria Shaker, Theodore S. Norvell, and Denni K. Peter Faculty of ngineering and Applied Science, Memorial Univerity of Newfoundland, St. John, NFLD,
More informationCENTER-POINT MODEL OF DEFORMABLE SURFACE
CENTER-POINT MODEL OF DEFORMABLE SURFACE Piotr M. Szczypinki Iintitute of Electronic, Technical Univerity of Lodz, Poland Abtract: Key word: Center-point model of deformable urface for egmentation of 3D
More informationImage authentication and tamper detection using fragile watermarking in spatial domain
International Journal of Advanced Reearch in Computer Engineering & Technology (IJARCET) Volume 6, Iue 7, July 2017, ISSN: 2278 1323 Image authentication and tamper detection uing fragile watermarking
More informationelse end while End References
621-630. [RM89] [SK76] Roenfeld, A. and Melter, R. A., Digital geometry, The Mathematical Intelligencer, vol. 11, No. 3, 1989, pp. 69-72. Sklanky, J. and Kibler, D. F., A theory of nonuniformly digitized
More informationModeling of underwater vehicle s dynamics
Proceeding of the 11th WEA International Conference on YTEM, Agio Nikolao, Crete Iland, Greece, July 23-25, 2007 44 Modeling of underwater vehicle dynamic ANDRZEJ ZAK Department of Radiolocation and Hydrolocation
More informationDevelopment of an atmospheric climate model with self-adapting grid and physics
Intitute of Phyic Publihing Journal of Phyic: Conference Serie 16 (2005) 353 357 doi:10.1088/1742-6596/16/1/049 SciDAC 2005 Development of an atmopheric climate model with elf-adapting grid and phyic Joyce
More informationOn successive packing approach to multidimensional (M-D) interleaving
On ucceive packing approach to multidimenional (M-D) interleaving Xi Min Zhang Yun Q. hi ankar Bau Abtract We propoe an interleaving cheme for multidimenional (M-D) interleaving. To achieved by uing a
More informationLinkGuide: Towards a Better Collection of Hyperlinks in a Website Homepage
Proceeding of the World Congre on Engineering 2007 Vol I LinkGuide: Toward a Better Collection of Hyperlink in a Webite Homepage A. Ammari and V. Zharkova chool of Informatic, Univerity of Bradford anammari@bradford.ac.uk,
More informationTexture-Constrained Active Shape Models
107 Texture-Contrained Active Shape Model Shuicheng Yan, Ce Liu Stan Z. Li Hongjiang Zhang Heung-Yeung Shum Qianheng Cheng Microoft Reearch Aia, Beijing Sigma Center, Beijing 100080, China Dept. of Info.
More informationA Multi-objective Genetic Algorithm for Reliability Optimization Problem
International Journal of Performability Engineering, Vol. 5, No. 3, April 2009, pp. 227-234. RAMS Conultant Printed in India A Multi-objective Genetic Algorithm for Reliability Optimization Problem AMAR
More informationA PROBABILISTIC NOTION OF CAMERA GEOMETRY: CALIBRATED VS. UNCALIBRATED
A PROBABILISTIC NOTION OF CAMERA GEOMETRY: CALIBRATED VS. UNCALIBRATED Jutin Domke and Yianni Aloimono Computational Viion Laboratory, Center for Automation Reearch Univerity of Maryland College Park,
More informationCutting Stock by Iterated Matching. Andreas Fritsch, Oliver Vornberger. University of Osnabruck. D Osnabruck.
Cutting Stock by Iterated Matching Andrea Fritch, Oliver Vornberger Univerity of Onabruck Dept of Math/Computer Science D-4909 Onabruck andy@informatikuni-onabrueckde Abtract The combinatorial optimization
More informationKinematics Programming for Cooperating Robotic Systems
Kinematic Programming for Cooperating Robotic Sytem Critiane P. Tonetto, Carlo R. Rocha, Henrique Sima, Altamir Dia Federal Univerity of Santa Catarina, Mechanical Engineering Department, P.O. Box 476,
More informationKey Terms - MinMin, MaxMin, Sufferage, Task Scheduling, Standard Deviation, Load Balancing.
Volume 3, Iue 11, November 2013 ISSN: 2277 128X International Journal of Advanced Reearch in Computer Science and Software Engineering Reearch Paper Available online at: www.ijarce.com Tak Aignment in
More informationA SIMPLE IMPERATIVE LANGUAGE THE STORE FUNCTION NON-TERMINATING COMMANDS
A SIMPLE IMPERATIVE LANGUAGE Eventually we will preent the emantic of a full-blown language, with declaration, type and looping. However, there are many complication, o we will build up lowly. Our firt
More informationPerformance Evaluation of an Advanced Local Search Evolutionary Algorithm
Anne Auger and Nikolau Hanen Performance Evaluation of an Advanced Local Search Evolutionary Algorithm Proceeding of the IEEE Congre on Evolutionary Computation, CEC 2005 c IEEE Performance Evaluation
More informationA Practical Model for Minimizing Waiting Time in a Transit Network
A Practical Model for Minimizing Waiting Time in a Tranit Network Leila Dianat, MASc, Department of Civil Engineering, Sharif Univerity of Technology, Tehran, Iran Youef Shafahi, Ph.D. Aociate Profeor,
More informationA Load Balancing Model based on Load-aware for Distributed Controllers. Fengjun Shang, Wenjuan Gong
4th International Conference on Machinery, Material and Computing Technology (ICMMCT 2016) A Load Balancing Model baed on Load-aware for Ditributed Controller Fengjun Shang, Wenjuan Gong College of Compute
More informationAn Intro to LP and the Simplex Algorithm. Primal Simplex
An Intro to LP and the Simplex Algorithm Primal Simplex Linear programming i contrained minimization of a linear objective over a olution pace defined by linear contraint: min cx Ax b l x u A i an m n
More information3D MODELLING WITH LINEAR APPROACHES USING GEOMETRIC PRIMITIVES
MAKARA, TEKNOLOGI, VOL. 9, NO., APRIL 5: 3-35 3D MODELLING WITH LINEAR APPROACHES USING GEOMETRIC PRIMITIVES Mochammad Zulianyah Informatic Engineering, Faculty of Engineering, ARS International Univerity,
More informationThe Implementation of an Adaptive Mechanism in the RTP Packet in Mobile Video Transmission
2011 International Conference on Information Management and Engineering (ICIME 2011) IPCSIT vol. 52 (2012) (2012) IACSIT Pre, Singapore DOI: 10.7763/IPCSIT.2012.V52.91 The Implementation of an Adaptive
More informationLaboratory Exercise 2
Laoratory Exercie Numer and Diplay Thi i an exercie in deigning cominational circuit that can perform inary-to-decimal numer converion and inary-coded-decimal (BCD) addition. Part I We wih to diplay on
More informationData Mining with Linguistic Thresholds
Int. J. Contemp. Math. Science, Vol. 7, 22, no. 35, 7-725 Data Mining with Linguitic Threhold Tzung-Pei Hong Department of Electrical Engineering National Univerity of Kaohiung Kaohiung, Taiwan, R.O.C.
More informationThe Association of System Performance Professionals
The Aociation of Sytem Performance Profeional The Computer Meaurement Group, commonly called CMG, i a not for profit, worldwide organization of data proceing profeional committed to the meaurement and
More informationAn Active Stereo Vision System Based on Neural Pathways of Human Binocular Motor System
Journal of Bionic Engineering 4 (2007) 185 192 An Active Stereo Viion Sytem Baed on Neural Pathway of Human Binocular Motor Sytem Yu-zhang Gu 1, Makoto Sato 2, Xiao-lin Zhang 2 1. Department of Advanced
More informationAn Algebraic Approach to Adaptive Scalable Overlay Network Monitoring
An Algebraic Approach to Adaptive Scalable Overlay Network Monitoring ABSTRACT Overlay network monitoring enable ditributed Internet application to detect and recover from path outage and period of degraded
More informationAudio-Visual Voice Command Recognition in Noisy Conditions
Audio-Viual Voice Command Recognition in Noiy Condition Joef Chaloupka, Jan Nouza, Jindrich Zdanky Laboratory of Computer Speech Proceing, Intitute of Information Technology and Electronic, Technical Univerity
More informationAN ALGORITHM FOR RESTRICTED NORMAL FORM TO SOLVE DUAL TYPE NON-CANONICAL LINEAR FRACTIONAL PROGRAMMING PROBLEM
RAC Univerity Journal, Vol IV, No, 7, pp 87-9 AN ALGORITHM FOR RESTRICTED NORMAL FORM TO SOLVE DUAL TYPE NON-CANONICAL LINEAR FRACTIONAL PROGRAMMING PROLEM Mozzem Hoain Department of Mathematic Ghior Govt
More informationA METHOD OF REAL-TIME NURBS INTERPOLATION WITH CONFINED CHORD ERROR FOR CNC SYSTEMS
Vietnam Journal of Science and Technology 55 (5) (017) 650-657 DOI: 10.1565/55-518/55/5/906 A METHOD OF REAL-TIME NURBS INTERPOLATION WITH CONFINED CHORD ERROR FOR CNC SYSTEMS Nguyen Huu Quang *, Banh
More informationVariable Resolution Discretization in the Joint Space
Variable Reolution Dicretization in the Joint Space Chritopher K. Monon, David Wingate, and Kevin D. Seppi {c,wingated,keppi}@c.byu.edu Computer Science, Brigham Young Univerity Todd S. Peteron peterto@uvc.edu
More informationManeuverable Relays to Improve Energy Efficiency in Sensor Networks
Maneuverable Relay to Improve Energy Efficiency in Senor Network Stephan Eidenbenz, Luka Kroc, Jame P. Smith CCS-5, MS M997; Lo Alamo National Laboratory; Lo Alamo, NM 87545. Email: {eidenben, kroc, jpmith}@lanl.gov
More informationComputer Arithmetic Homework Solutions. 1 An adder for graphics. 2 Partitioned adder. 3 HDL implementation of a partitioned adder
Computer Arithmetic Homework 3 2016 2017 Solution 1 An adder for graphic In a normal ripple carry addition of two poitive number, the carry i the ignal for a reult exceeding the maximum. We ue thi ignal
More informationA New Approach to Pipeline FFT Processor
A ew Approach to Pipeline FFT Proceor Shouheng He and Mat Torkelon Department of Applied Electronic, Lund Univerity S- Lund, SWEDE email: he@tde.lth.e; torkel@tde.lth.e Abtract A new VLSI architecture
More informationMinimum congestion spanning trees in bipartite and random graphs
Minimum congetion panning tree in bipartite and random graph M.I. Otrovkii Department of Mathematic and Computer Science St. John Univerity 8000 Utopia Parkway Queen, NY 11439, USA e-mail: otrovm@tjohn.edu
More informationKeywords: Defect detection, linear phased array transducer, parameter optimization, phased array ultrasonic B-mode imaging testing.
Send Order for Reprint to reprint@benthamcience.ae 488 The Open Automation and Control Sytem Journal, 2014, 6, 488-492 Open Acce Parameter Optimization of Linear Phaed Array Tranducer for Defect Detection
More informationTesting Structural Properties in Textual Data: Beyond Document Grammars
Teting Structural Propertie in Textual Data: Beyond Document Grammar Felix Saaki and Jen Pönninghau Univerity of Bielefeld, Germany Abtract Schema language concentrate on grammatical contraint on document
More informationUC Berkeley International Conference on GIScience Short Paper Proceedings
UC Berkeley International Conference on GIScience Short Paper Proceeding Title A novel method for probabilitic coverage etimation of enor network baed on 3D vector repreentation in complex urban environment
More informationMirror shape recovery from image curves and intrinsic parameters: Rotationally symmetric and conic mirrors. Abstract. 2. Mirror shape recovery
Mirror hape recovery from image curve and intrinic parameter: Rotationally ymmetric and conic mirror Nuno Gonçalve and Helder Araújo Λ Intitute of Sytem and Robotic Univerity of Coimbra Pinhal de Marroco
More informationAn Approach to a Test Oracle for XML Query Testing
An Approach to a Tet Oracle for XML Query Teting Dae S. Kim-Park, Claudio de la Riva, Javier Tuya Univerity of Oviedo Computing Department Campu of Vieque, /n, 33204 (SPAIN) kim_park@li.uniovi.e, claudio@uniovi.e,
More informationContents. shortest paths. Notation. Shortest path problem. Applications. Algorithms and Networks 2010/2011. In the entire course:
Content Shortet path Algorithm and Network 21/211 The hortet path problem: Statement Verion Application Algorithm (for ingle ource p problem) Reminder: relaxation, Dijktra, Variant of Dijktra, Bellman-Ford,
More informationIncreasing Throughput and Reducing Delay in Wireless Sensor Networks Using Interference Alignment
Int. J. Communication, Network and Sytem Science, 0, 5, 90-97 http://dx.doi.org/0.436/ijcn.0.50 Publihed Online February 0 (http://www.scirp.org/journal/ijcn) Increaing Throughput and Reducing Delay in
More informationTHE EXPLOSIVE growth of multimedia applications such
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 21, NO. 11, NOVEMBER 2011 1667 Perceptually Scalable Extenion of H.264 Hojin Ha, Jincheol Park, Sanghoon Lee, Member, IEEE, Alan Conrad
More informationReporting Checklist for Nature Neuroscience
Correponding Author: Manucript Number: Manucript Type: Jeremy Elman NNBC48172A Brief Communication Reporting Checklit for Nature Neurocience # Figure: 2 # Figure: 5 # Table: 6 # Video: 0 Thi checklit i
More informationAnisotropic filtering on normal field and curvature tensor field using optimal estimation theory
Aniotropic filtering on normal field and curvature tenor field uing optimal etimation theory Min Liu Yuhen Liu and Karthik Ramani Purdue Univerity, Wet Lafayette, Indiana, USA Email: {liu66 liu28 ramani}@purdue.edu
More informationAnalysis of the results of analytical and simulation With the network model and dynamic priority Unchecked Buffer
International Reearch Journal of Applied and Baic Science 218 Available online at www.irjab.com ISSN 2251-838X / Vol, 12 (1): 49-53 Science Explorer Publication Analyi of the reult of analytical and imulation
More informationInternational Journal of Engineering Research & Technology (IJERT) ISSN: Vol. 2 Issue 5, May
Intertage Pipeline VLI Architecture for 2-D DWT Ajinkya. Bankar 1,Bhavika. haha 2, P.K. Kadbe 3 E&TC Department, Pune Univerity 1,2,3 VPCOE Baramati Abtract In thi paper, a cheme for the deign of a high-pd
More informationx y z Design variable positions A
COMMUNICATIONS IN NUMERICAL METHODS IN ENGINEERING Commun. Numer. Meth. Engng 2001 00:1{7 [Verion: 2000/03/22 v1.0] A tabilied peudo-hell approach for urface parametriation in CFD deign problem O. Soto,R.Lohner
More informationHow to Select Measurement Points in Access Point Localization
Proceeding of the International MultiConference of Engineer and Computer Scientit 205 Vol II, IMECS 205, March 8-20, 205, Hong Kong How to Select Meaurement Point in Acce Point Localization Xiaoling Yang,
More informationA Linear Interpolation-Based Algorithm for Path Planning and Replanning on Girds *
Advance in Linear Algebra & Matrix Theory, 2012, 2, 20-24 http://dx.doi.org/10.4236/alamt.2012.22003 Publihed Online June 2012 (http://www.scirp.org/journal/alamt) A Linear Interpolation-Baed Algorithm
More informationNearly Constant Approximation for Data Aggregation Scheduling in Wireless Sensor Networks
Nearly Contant Approximation for Data Aggregation Scheduling in Wirele Senor Network Scott C.-H. Huang, Peng-Jun Wan, Chinh T. Vu, Yinghu Li and France Yao Computer Science Department, City Univerity of
More informationFocused Video Estimation from Defocused Video Sequences
Focued Video Etimation from Defocued Video Sequence Junlan Yang a, Dan Schonfeld a and Magdi Mohamed b a Multimedia Communication Lab, ECE Dept., Univerity of Illinoi, Chicago, IL b Phyical Realization
More informationResearch on Star Image Noise Filtering Based on Diffusion Model of Regularization Influence Function
016 Sith International Conference on Intrumentation & Meaurement Computer Communication and Control Reearch on Star Image Noie Filtering Baed on Diffuion Model of Regularization Influence Function SunJianming
More informationM 4 CD: A Robust Change Detection Method for Intelligent Visual Surveillance
1 M 4 CD: A Robut Change Detection Method for Intelligent Viual Surveillance Kunfeng Wang, Member, IEEE, Chao Gou, and Fei-Yue Wang, Fellow, IEEE Abtract In thi paper, we propoe a robut change detection
More informationRefining SIRAP with a Dedicated Resource Ceiling for Self-Blocking
Refining SIRAP with a Dedicated Reource Ceiling for Self-Blocking Mori Behnam, Thoma Nolte Mälardalen Real-Time Reearch Centre P.O. Box 883, SE-721 23 Väterå, Sweden {mori.behnam,thoma.nolte}@mdh.e ABSTRACT
More informationImplementation of a momentum-based distance metric for motion graphs. Student: Alessandro Di Domenico (st.no ), Supervisor: Nicolas Pronost
Implementation of a momentum-baed ditance metric for motion graph Student: Aleandro Di Domenico (t.no 3775682), Supervior: Nicola Pronot April 3, 2014 Abtract Thi report preent the procedure and reult
More informationDrawing Lines in 2 Dimensions
Drawing Line in 2 Dimenion Drawing a traight line (or an arc) between two end point when one i limited to dicrete pixel require a bit of thought. Conider the following line uperimpoed on a 2 dimenional
More informationAspects of Formal and Graphical Design of a Bus System
Apect of Formal and Graphical Deign of a Bu Sytem Tiberiu Seceleanu Univerity of Turku, Dpt. of Information Technology Turku, Finland tiberiu.eceleanu@utu.fi Tomi Weterlund Turku Centre for Computer Science
More informationTopics. Lecture 37: Global Optimization. Issues. A Simple Example: Copy Propagation X := 3 B > 0 Y := 0 X := 4 Y := Z + W A := 2 * 3X
Lecture 37: Global Optimization [Adapted from note by R. Bodik and G. Necula] Topic Global optimization refer to program optimization that encompa multiple baic block in a function. (I have ued the term
More informationAN INTELLIGENT SCHEME FOR FACIAL EXPRESSION RECOGNITION
AN INTELLIGENT SCHEME FOR FACIAL EXPRESSION RECOGNITION A. Raouzaiou, S. Ioannou, K. Karpouzi, N. Tapatouli, S. Kollia 1, R. Cowie 2 1 Department of Electrical and Computer Engineering National Technical
More informationImage Morphing Using Deformation Techniques
Image Morphing Uing Deformation Technique Seung-Yong Lee, Kyung-Yong Chwa, Jame Hahn, and Sung Yong Shin Department of Computer Science Korea Advanced Intitute of Science and Technology 373-1 Kuong-dong
More informationKeywords Cloud Computing, Service Level Agreements (SLA), CloudSim, Monitoring & Controlling SLA Agent, JADE
Volume 5, Iue 8, Augut 2015 ISSN: 2277 128X International Journal of Advanced Reearch in Computer Science and Software Engineering Reearch Paper Available online at: www.ijarce.com Verification of Agent
More information