可重构的无线智能视频监控平台的研究
|
摘要
信息科技飞速发展的今天,在摩尔定律的引导下,超大规模集成电路生产技术的不断提高推动着以计算为中心的电子产业的前进。正是在这样的背景下,智能视频技术伴随着硬件能力的提升和计算机视觉科技的崛起,成为时下人们关注的热点。以智能化、网路化为特点的智能视频监控系统在安防监控、交通控制等领域应运而生。智能视频监控技术通过对前景与背景的分离,对特定区域或目标进行连续分析,从捕获的视频图像中发掘出隐藏的信息,避免了传统视频应用导致的信息爆炸。智能视频监控依赖于准确而可靠的视频分析算法,这些算法往往需要处理大量数据,消耗相当多的计算资源,给视频处理的实时性带来巨大挑战。基于DSP的视频监控系统,实现简单且具有很好的灵活性,但面对上百条视频流数据,性能往往会大打折扣；而以专用芯片作为视频分析引擎的分布式智能视频监控系统通常具有较好的实时性能,但灵活性又较差。本文综合考虑计算性能以及实现灵活两方面因素,利用FPGA的局部动态可重构技术,完成了可重构的无线智能视频监控平台的研究,主要分为以下几个方面的工作。
(1)研究了Xilinx FPGA的局部动态可重构技术,提出了一种基于FPGA的可重构视频处理硬件平台,平台可在不停止工作的情况下通过无线网络连接重新对重构区域进行配置。平台中使用一种高效的ICAP控制器作为重构引擎,仅需几毫秒甚至几十微秒即可完成硬件任务的重配。
(2)研究了智能视频监控的各类算法并在FPGA上一一实现,其中包括运动检测、目标识别以及目标跟踪,实现的各视频监控模块构成了可重构平台的智能视频监控IP库。其中,运动检测模块采用改进的相邻帧差算法,能够准确地标记出运动物体。目标识别模块采用改进的自映射神经网络算法,改进后的算法更加易于硬件实现,同时识别准确率与经典算法相当。目标跟踪模块采用改进的颜色粒子滤波算法,模块可在简单背景下对目标物体实现有效地跟踪。
(3)研究了面向视频处理应用的高性能片上通信架构,提出了一种4元树状片上网络架构及其线上可重构算法。4元树状片上网络架构具有良好的可扩展性,可针对不同应用快速的完成配置与搭建。提出的线上可重构算法可有效地减少片内数据通信量,减轻系统负载,降低功耗。
(4)提出了无线智能视频监控网络AdVision的实现,网络内支持IEEE802.11和IEEE802.15.4两种传输协议。设计了AdNode和AdBridge节点架构,并利用带有优先级的JPEG编码器,设计了低复杂度的视频压缩策略和传输机制,实现了无线网内实时、可靠地视频传输。
With the rapid development of information technology, VLSI manufacturing technology, guided by Moore's Law, is promoting electronics industry with booming computing capabilities. In this context, intelligent video technique becomes a hot issue along with the progress of computer vision technology. Intelligent video surveillance system came into being based on the application of security surveillance and traffic control. By separating foreground from background and continuous analysis in a specific area, intelligent video surveillance technology is able to get the obscure information from the captured video image and thus can avoid the explosion of information in traditional video applications. Intelligent video surveillance depends on accurate and reliable video analysis algorithms. These algorithms have to process large amounts of data and consume quite a lot of computing resources, which brings a huge challenge to real-time video processing. DSP-based video surveillance system is flexible and simple to implement, but the performance is not optimistic when processing hundreds of video streams. However, in distributed intelligent video surveillance system, ASIC chips as video analysis engine, guarantees good real-time performance, but suffers from the poor flexibility. In this thesis, considering both computing performance and flexibility, the author makes use of FPGA's partial dynamic reconfiguration technology to carry on the study of reconfigurable wireless intelligent video surveillance platform, which can be divided into following parts.
1) Xilinx FPGA partial dynamic reconfiguration technology has been studied. A FPGA-based reconfigurable video processing hardware platform which can be reconfigured through wireless connections in runtime has been proposed. The platform use an efficient ICAP controller as reconfiguration engine and only a few milliseconds or even tens of microseconds are needed to complete the process of reconfiguration.
2) Various algorithms on intelligent video surveillance have been studied and implemented in FPGA, including motion detection, object recognition and object tracking. These video processing modules form the library of hardware intelligent video processing IPs. In motion detection, an improved frame differing method is used; in object recognition, a simplified self-organizing map is presented; in object tracking, an improved color-based particle filter is proposed. All these intelligent video processing IPs perform well and are implemented on FPGA.
3) The high performance on-chip communication architecture for intelligent video processing has been studied. The author proposed a4-ary tree based network on chip with good scalability and flexibility which can save quite a lot of traffic load and consume less system power in communication.
4) A wireless intelligent video surveillance network named AdVision has been implemented, in which both IEEE802.11and IEEE802.15.4protocols are supported. In the wireless surveillance network, AdNode and AdBridge's hardware circuits are carefully designed to meet the requirements of both high performance and low power. To realize robust and real-time transferring, AdVision uses a low complexity compressing scheme through prioritized JPEG encoding.
(1)研究了Xilinx FPGA的局部动态可重构技术,提出了一种基于FPGA的可重构视频处理硬件平台,平台可在不停止工作的情况下通过无线网络连接重新对重构区域进行配置。平台中使用一种高效的ICAP控制器作为重构引擎,仅需几毫秒甚至几十微秒即可完成硬件任务的重配。
(2)研究了智能视频监控的各类算法并在FPGA上一一实现,其中包括运动检测、目标识别以及目标跟踪,实现的各视频监控模块构成了可重构平台的智能视频监控IP库。其中,运动检测模块采用改进的相邻帧差算法,能够准确地标记出运动物体。目标识别模块采用改进的自映射神经网络算法,改进后的算法更加易于硬件实现,同时识别准确率与经典算法相当。目标跟踪模块采用改进的颜色粒子滤波算法,模块可在简单背景下对目标物体实现有效地跟踪。
(3)研究了面向视频处理应用的高性能片上通信架构,提出了一种4元树状片上网络架构及其线上可重构算法。4元树状片上网络架构具有良好的可扩展性,可针对不同应用快速的完成配置与搭建。提出的线上可重构算法可有效地减少片内数据通信量,减轻系统负载,降低功耗。
(4)提出了无线智能视频监控网络AdVision的实现,网络内支持IEEE802.11和IEEE802.15.4两种传输协议。设计了AdNode和AdBridge节点架构,并利用带有优先级的JPEG编码器,设计了低复杂度的视频压缩策略和传输机制,实现了无线网内实时、可靠地视频传输。
With the rapid development of information technology, VLSI manufacturing technology, guided by Moore's Law, is promoting electronics industry with booming computing capabilities. In this context, intelligent video technique becomes a hot issue along with the progress of computer vision technology. Intelligent video surveillance system came into being based on the application of security surveillance and traffic control. By separating foreground from background and continuous analysis in a specific area, intelligent video surveillance technology is able to get the obscure information from the captured video image and thus can avoid the explosion of information in traditional video applications. Intelligent video surveillance depends on accurate and reliable video analysis algorithms. These algorithms have to process large amounts of data and consume quite a lot of computing resources, which brings a huge challenge to real-time video processing. DSP-based video surveillance system is flexible and simple to implement, but the performance is not optimistic when processing hundreds of video streams. However, in distributed intelligent video surveillance system, ASIC chips as video analysis engine, guarantees good real-time performance, but suffers from the poor flexibility. In this thesis, considering both computing performance and flexibility, the author makes use of FPGA's partial dynamic reconfiguration technology to carry on the study of reconfigurable wireless intelligent video surveillance platform, which can be divided into following parts.
1) Xilinx FPGA partial dynamic reconfiguration technology has been studied. A FPGA-based reconfigurable video processing hardware platform which can be reconfigured through wireless connections in runtime has been proposed. The platform use an efficient ICAP controller as reconfiguration engine and only a few milliseconds or even tens of microseconds are needed to complete the process of reconfiguration.
2) Various algorithms on intelligent video surveillance have been studied and implemented in FPGA, including motion detection, object recognition and object tracking. These video processing modules form the library of hardware intelligent video processing IPs. In motion detection, an improved frame differing method is used; in object recognition, a simplified self-organizing map is presented; in object tracking, an improved color-based particle filter is proposed. All these intelligent video processing IPs perform well and are implemented on FPGA.
3) The high performance on-chip communication architecture for intelligent video processing has been studied. The author proposed a4-ary tree based network on chip with good scalability and flexibility which can save quite a lot of traffic load and consume less system power in communication.
4) A wireless intelligent video surveillance network named AdVision has been implemented, in which both IEEE802.11and IEEE802.15.4protocols are supported. In the wireless surveillance network, AdNode and AdBridge's hardware circuits are carefully designed to meet the requirements of both high performance and low power. To realize robust and real-time transferring, AdVision uses a low complexity compressing scheme through prioritized JPEG encoding.
引文
[1]Clarence R C, LESLIE P G. An Investigation Of Closed-Circuit Television For Teaching University Courses. Instructional Television Research, Project Number One.1955.
[2Information Security Today. http://infosectoday.com/
[3]JL Crowley, S Pesnel, P Reignier, A Lux. Context Aware Vision using Image-based Active Recognition.
[4]ISCAPS(Integrated Surveillance of Crowded Areas for Public Security).2004. http://iscaps.net
[5]I Haritaoglu, D Harwood, L S Davis. W4:Real-Time Surveillance Of People And Their Activities. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000.22. (8).809-830.
[6]Hu Weiming, Tan Tieniu, Wang Liang, S Maybank. A Survey on Visual Surveillance of Object Motion and Behaviors. IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews.2004.34. (3).334-352.
[7]Brian Leininger, Jonathan Edwards, John Antoniades, David Chester, Dan Haas, Eric Liu, Mark Stevens, Charlie Gershfield, Mike Braun, James D Targove. Autonomous Real-time Ground Ubiquitous Surveillance-imaging System (ARGUS-IS).2008.69810H--69810H.
[8]ObjectVideo. www.objectvideo.com/
[9]DVTEL.www.dvtel.com/
[10]NiceVision. www.nice.com/video
[11]Citilog.www.citilog.com
[12]Huawei.www.huawei.com/
[13]S. FleckW. Strasser. Smart Camera Based Monitoring System and Its Application to Assisted Living. Proceedings of the IEEE.2008.96. (10).1698-1714.
[14]Wang Youlu, S. VelipasalarM. Casares. Cooperative Object Tracking and Composite Event Detection With Wireless Embedded Smart Cameras. IEEE Transactions on Image Processing.2010.19. (10).2614-2633.
[15]K. Sato, B. L. EvansJ. K. Aggarwal. Designing an embedded video processing camera using a 16-bit microprocessor for surveillance system.2002.151-158.
[16]DaVinciTM Video Processors. http://www.ti.com/lsds/ti/dsp/video_processors/
[17]UG190:Virtex-5 FPGA User Guide.2012.
[18]Xilinx Spartan-3A DSP DaVinci Development Kit. http://www.em.avnet.com//en-us/design/drc/Pages/Xilinx-Spartan-3A-DSP-DaVi nci-Development-Kit.aspx
[19]Eutecus, Inc. Multi-core Video Analytics Engine. http://www.eutecus.com/
[20]Michael IsardAndrew Blake. Condensation-conditional density propagation for visual tracking. International journal of computer vision.1998.29. (1).5--28.
[21]M. Sanjeev Arulampalam, Simon Maskell, Neil GordonTim Clapp. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing.2002.50. (2).174-188.
[22]Arnaud Doucet, Neil J. GordonVikram Krishnamurthy. Particle filters for state estimation of jump Markov linear systems. IEEE Transactions on Signal Processing.2001.49. (3).613--624.
[23]Simon BakerIain Matthews. Lucas-kanade 20 years on:A unifying framework. International Journal of Computer Vision.2004.56. (3).221--255.
[24]Zuren Feng, Na LuPing Jiang. Posterior probability measure for image matching. Pattern Recognition.2008.41. (7).2422--2433.
[25]K. VipinS. A. Fahmy. Efficient region allocation for adaptive partial reconfiguration.2011.1-6.
[26]Kizheppatt VipinSuhaibA. Fahmy. Architecture-A ware Reconfiguration-Centric Floorplanning for Partial Reconfiguration.2012.7199.13-25.
[27]Li ZhiyuanS. Hauck. Configuration Compression for Virtex FPGAs.2001. 147-159.
[28]DS280:OPB HWICAP.2006.
[29]DS586:XPS HWICAP.2010.
[30]C. Claus, F. H. Muller, J. ZeppenfeldW. Stechele. A new framework to accelerate Virtex-II Pro dynamic partial self-reconfiguration.2007.1-7.
[31]Liu Ming, W. Kuehn, Lu ZhonghaiA. Jantsch. Run-time Partial Reconfiguration speed investigation and architectural design space exploration.2009.498-502.
[32]Richard Neil Pittman Alessandro Shaoshan Liu. Minimizing Partial Reconfiguration Overhead with Fully Streaming DMA Engines and Intelligent ICAP Controller.2009.
[33]Kyprianos Papadimitriou, Apostolos DollasScott Hauck. Performance of partial reconfiguration in FPGA systems:A survey and a cost model. ACM Transaction on Reconfigurable Technology System.2011.4. (4).36:1--36:24.
[34]Lei FeiZhao Xiaoxia. Adaptive background estimation of underwater using Kalman-Filtering.2010.64-67.
[35]C. R. Wren, A. Azarbayejani, T. DarrellA. P. Pentland. Pfinder:real-time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence.1997.19. (7).780-785.
[36]Chris StaufferW. E. L. Grimson. Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000. 22. (8).747-757.
[37]Pakorn KaewTraKulPongRichard Bowden. An improved adaptive background mixture model for real-time tracking with shadow detection.2002.135-144.
[38]Roland MechM. Wollborn. A noise robust method for segmentation of moving objects in video sequences.1997.2657-2660 vol.4.
[39]A. Neri, S. Colonnese, G. RussoP. Talone. Automatic moving object and background separation. Signal Processing.1998.66. (2).219--232.
[40]Alan J. Lipton, Hironobu FujiyoshiRaju S. Patil. Moving target classification and tracking from real-time video.1998.8--14.
[41]Jeff Chase, Brent Nelson, John Bodily, Zhaoyi WeiDah-Jye Lee. Real-time optical flow calculations on FPGA and GPU architectures:a comparison study. 2008.173-182.
[42]Deqing Sun, Stefan Roth, J. P. LewisMichael J. Black. Learning optical flow. 2008.83-97.
[43]Toby LowGordon Wyeth. Obstacle detection using optical flow.2005.
[44]Michael Harville. A framework for high-level feedback to adaptive, per-pixel, mixture-of-gaussian background models.2002.543-560.
[45]Ahmed Elgammal, Ramani Duraiswami, David HarwoodLarry S. Davis. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE.2002.90. (7). 1151-1163.
[46]Shengcai Liao, Guoying Zhao, Vili Kellokumpu, Matti PietikainenStan Z. Li. Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes.2010.1301-1306.
[47]Gian Luca Foresti. Object recognition and tracking for remote video surveillance. IEEE Transactions on Circuits and Systems for Video Technology.1999.9. (7). 1045-1062.
[48]Wei Niu, Jiao Long, Dan Han Yuan-Fang Wang. Human activity detection and recognition for video surveillance.2004.719-722.
[49]Weiyao Lin, Ming-Ting Sun, Radha PoovendranZhengyou Zhang. Activity recognition using a combination of category components and local models for video surveillance. IEEE Transactions on Circuits and Systems for Video Technology.2008.18. (8).1128--1139.
[50]Marian Stewart Bartlett, Javier R. MovellanTerrence J. Sejnowski. Face recognition by independent component analysis. IEEE Transactions on Neural Networks.2002.13. (6).1450--1464.
[51]Daniel TranelAntonio R. Damasio. Knowledge without awareness:An autonomic index of facial recognition by prosopagnosics. Science.1985.228. (4706). 1453-1454.
[52]Roberto BrunelliTomaso Poggio. Face recognition:Features versus templates. IEEE Transactions on Pattern Analysis and Machine Intelligence.1993.15. (10). 1042--1052.
[53]Wenyi Zhao, Rama Chellappa, P. Jonathon PhillipsAzriel Rosenfeld. Face recognition:A literature survey. Acm Computing Surveys (CSUR).2003.35. (4). 399--458.
[54]S. Impedovo, L. OttavianoS. Occhinegro. Optical character recognition-a survey. International Journal of Pattern Recognition and Artificial Intelligence.1991.5. (01n02).1--24.
[55]Shunji Mori, Hirobumi NishidaHiromitsu Yamada. Optical character recognition. John Wiley & Sons, Inc.,1999,
[56]James M. WhiteGene D. Rohrer. Image thresholding for optical character recognition and other applications requiring character image extraction. IBM Journal of Research and Development.1983.27. (4).400-411.
[57]Massimo Pacella, Quirico SemeraroAlfredo Anglani. Manufacturing quality control by means of a Fuzzy ART network trained on natural process data. Engineering Applications of Artificial Intelligence.2004.17. (1).83-96.
[58]Christian Demant, Bernd Streicher-AbelPeter Waszkewitz. Industrial image processing:visual quality control in manufacturing. Springer Verlag,1999,
[59]T. Kohonen. The self-organizing map. Proceedings of the IEEE.1990.78. (9). 1464-1480.
[60]T. Kohonen, S. Kaski, K. Lagus, J. Salojarvi, J. Honkela, V. PaateroA. Saarela. Self organization of a massive document collection. IEEE Transactions on Neural Networks.2000.11. (3).574-585.
[61]Olli Silv E N, Matti Niskanen, Hannu Kauppinen. Wood inspection with non-supervised clustering. Machine Vision and Applications.2003.13. (5-6). 275-285.
[62]Stefan R U Ping, Ulrich R U CkertKarl Goser. Hardware Design for Self-Organizing Feature Maps with Binary Input Vectors.1993.488--493.
[63]T. Yamakawa, K. HorioT. Hiratsuka. Advanced self-organizing maps using binary weight vector and its digital hardware design.2002.1330-1335 vol.3.
[64]J. Pena, M. VanegasA. Valencia. Digital Hardware Architectures of Kohonen's Self Organizing Feature Maps with Exponential Neighboring Function.2006.1-8.
[65]K. Appiah, A. Hunter, Meng Hongying, Yue Shigang, M. Hobden, N. Priestley, P. HobdenC. Pettit. A binary Self-Organizing Map and its FPGA implementation. 2009.164-171.
[66]Suhap Sahin, Yasar BecerikliSuleyman Yazici. Neural Network Implementation in Hardware Using FPGAs.2006.1105-1112.
[67]Chip-Hong Chang, Menon ShibuRui Xiao. Self Organizing Feature Map for Color Quantization on FPGA.2006.225-245.
[68]Mario Porrmann, Ulf WitkowskiUlrich Ruckert. Implementation of Self-Organizing Feature Maps in Reconfigurable Hardware.2006.247-269.
[69]Agust I. N. Ram Agundis, Rafael Gadea Girones, Ricardo Colom PaleroJavier D. I. Az Carmona. A mixed hardware/software sofm training system. Computaciny Sistemas.2008.11. (4).349--356.
[70]K. Appiah, A. Hunter, P. DickinsonMeng Hongying. Implementation and Applications of Tri-State Self-Organizing Maps on FPGA. IEEE Transactions on Circuits and Systems for Video Technology.2012.22. (8).1150-1160.
[71]C. Cortes Y. LeCun. The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/
[72]David Exner, Erich Bruns, Daniel Kurz, Anselm Grundh O FerOliver Bimber. Fast and reliable CAMShift tracking.2005.
[73]Juan Liang, Jianhua Hou, Jun Xiang, Bangyou DaShaobo Chen. An effective automatic tracking algorithm based on Camshift and Kalman filter.2011. 800316--800316.
[74]Xia Liu, Hongxia ChuPingjun Li. Research of the improved camshift tracking algorithm.2007.968--972.
[75]Ivana Mikic, Slawomir KrucinskiJames D. Thomas. Segmentation and tracking in echocardiographic sequences:Active contours guided by optical flow estimates. IEEE Transactions on Medical Imaging.1998.17. (2).274--284.
[76]Jeffrey F. Cohn, Adena J. Zlochower, J. J. LienTakeo Kanade. Feature-point tracking by optical flow discriminates subtle differences in facial expression. 1998.396--401.
[77]M. S. Arulampalam, S. Maskell, N. GordonT. Clapp. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing.2002.50. (2).174-188.
[78]A. Doucet, N. J. GordonV. Krishnamurthy. Particle filters for state estimation of jump Markov linear systems. IEEE Transactions on Signal Processing.2001.49. (3).613-624.
[79]洪少华,史治国,陈抗生,Hong Shao-hua, Shi Zhi-guoChen Kang-sheng.用于纯方位跟踪的简化粒子滤波算法及其硬件实现.电子与信息学报.2009.31.(1).
[80]P. Perez, C. Hue, J. VermaakM. Gangnet. Color-based probabilistic tracking. Computer Vison-ECCV 2002, PT 1.2002.2350.661-675.
[81]H. Medeiros, J. ParkA. Kak. A parallel color-based particle filter for object tracking.2008.1-8.
[82]Wang Tzu-Heng, Chang Jing-YingChen Liang-Gee. Algorithm and architecture for object tracking using particle filter.2009.1374-1377.
[83]Arnaud Doucet, Nando De FreitasNeil Eds. Gordon. Sequential Monte Carlo Methods in Practice. New York:Springer Verlag,2001,
[84]M. Bolic, A. Athalye, S. HongP. M. Djuric. Study of Algorithmic and Architectural Characteristics of Gaussian Particle Filters. Journal of Signal Processing Systems.2009.1-14.
[85]E. A. LehmannR. C. Williamson. Experimental comparison of particle filtering algorithms for acoustic source localization in a reverberant room.2003.147.
[86]Gerald Estrin. Organization of computer systems:the fixed plus variable structure computer.1960.33--40.
[87]Vu-Duc Ngo, Huy-Nam NguyenHae-Wook Choi. Analyzing the Performance of Mesh and Fat-Tree Topologies for Network on Chip Design.2005.300-310.
[88]P. P. Pande, C. Grecu, M. Jones, A. IvanovR. Saleh. Performance evaluation and design trade-offs for network-on-chip interconnect architectures. IEEE Transactions on Computers.2005.54. (8).1025-1040.
[89]D. Ludovici, F. Gilabert, S. Medardoni, C. Gomez, M. E. Gomez, P. Lopez, G. N. GaydadjievD. Bertozzi. Assessing fat-tree topologies for regular network-on-chip design under nanoscale technology constraints.2009.562-565.
[90]Michael R. GareyDavid S. Johnson. Computers and Intractability; A Guide to the Theory of NP-Completeness. New York, NY, USA:W. H. Freeman Co.,1990,
[91]Richard E. Korf. From approximate to optimal solutions:a case study of number partitioning.1995.266--272.
[92]Richard E. Korf. Multi-way number partitioning.2009.538--543.
[93]Richard E. Korf. A complete anytime algorithm for number partitioning. Artificial Intelligence.1998.106. (2).181--203.
[94]Benjamin Yakir. The differencing algorithm LDM for partitioning:a proof of a conjecture of Karmarkar and.1996.21. (1).85--99.
[95]Y. E. Krasteva, J. Portilla, E. De la TorreT. Riesgo. Embedded Runtime Reconfigurable Nodes for Wireless Sensor Networks Applications. Sensors Journal, IEEE.2011.11. (9).1800-1810.
[96]A. Nahapetian, P. Lombardo, A. Acquaviva, L. BeniniM. Sarrafzadeh. Dynamic Reconfiguration in Sensor Networks with Regenerative Energy Sources.2007. 1-6.
[97]A. Dunkels, B. GronvallT. Voigt. Contiki-a lightweight and flexible operating system for tiny networked sensors.2004.455-462.
[98]Jin Tao, G. NoubirSheng Bo. WiZi-Cloud:Application-transparent dual ZigBee-WiFi radios for low power internet access.2011.1593-1601.
[99]Wei LiJia Ke-Bin. Implementation of embedded Web Server based on uIP TCP/IP stack.2007.668-671.
[2Information Security Today. http://infosectoday.com/
[3]JL Crowley, S Pesnel, P Reignier, A Lux. Context Aware Vision using Image-based Active Recognition.
[4]ISCAPS(Integrated Surveillance of Crowded Areas for Public Security).2004. http://iscaps.net
[5]I Haritaoglu, D Harwood, L S Davis. W4:Real-Time Surveillance Of People And Their Activities. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000.22. (8).809-830.
[6]Hu Weiming, Tan Tieniu, Wang Liang, S Maybank. A Survey on Visual Surveillance of Object Motion and Behaviors. IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews.2004.34. (3).334-352.
[7]Brian Leininger, Jonathan Edwards, John Antoniades, David Chester, Dan Haas, Eric Liu, Mark Stevens, Charlie Gershfield, Mike Braun, James D Targove. Autonomous Real-time Ground Ubiquitous Surveillance-imaging System (ARGUS-IS).2008.69810H--69810H.
[8]ObjectVideo. www.objectvideo.com/
[9]DVTEL.www.dvtel.com/
[10]NiceVision. www.nice.com/video
[11]Citilog.www.citilog.com
[12]Huawei.www.huawei.com/
[13]S. FleckW. Strasser. Smart Camera Based Monitoring System and Its Application to Assisted Living. Proceedings of the IEEE.2008.96. (10).1698-1714.
[14]Wang Youlu, S. VelipasalarM. Casares. Cooperative Object Tracking and Composite Event Detection With Wireless Embedded Smart Cameras. IEEE Transactions on Image Processing.2010.19. (10).2614-2633.
[15]K. Sato, B. L. EvansJ. K. Aggarwal. Designing an embedded video processing camera using a 16-bit microprocessor for surveillance system.2002.151-158.
[16]DaVinciTM Video Processors. http://www.ti.com/lsds/ti/dsp/video_processors/
[17]UG190:Virtex-5 FPGA User Guide.2012.
[18]Xilinx Spartan-3A DSP DaVinci Development Kit. http://www.em.avnet.com//en-us/design/drc/Pages/Xilinx-Spartan-3A-DSP-DaVi nci-Development-Kit.aspx
[19]Eutecus, Inc. Multi-core Video Analytics Engine. http://www.eutecus.com/
[20]Michael IsardAndrew Blake. Condensation-conditional density propagation for visual tracking. International journal of computer vision.1998.29. (1).5--28.
[21]M. Sanjeev Arulampalam, Simon Maskell, Neil GordonTim Clapp. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing.2002.50. (2).174-188.
[22]Arnaud Doucet, Neil J. GordonVikram Krishnamurthy. Particle filters for state estimation of jump Markov linear systems. IEEE Transactions on Signal Processing.2001.49. (3).613--624.
[23]Simon BakerIain Matthews. Lucas-kanade 20 years on:A unifying framework. International Journal of Computer Vision.2004.56. (3).221--255.
[24]Zuren Feng, Na LuPing Jiang. Posterior probability measure for image matching. Pattern Recognition.2008.41. (7).2422--2433.
[25]K. VipinS. A. Fahmy. Efficient region allocation for adaptive partial reconfiguration.2011.1-6.
[26]Kizheppatt VipinSuhaibA. Fahmy. Architecture-A ware Reconfiguration-Centric Floorplanning for Partial Reconfiguration.2012.7199.13-25.
[27]Li ZhiyuanS. Hauck. Configuration Compression for Virtex FPGAs.2001. 147-159.
[28]DS280:OPB HWICAP.2006.
[29]DS586:XPS HWICAP.2010.
[30]C. Claus, F. H. Muller, J. ZeppenfeldW. Stechele. A new framework to accelerate Virtex-II Pro dynamic partial self-reconfiguration.2007.1-7.
[31]Liu Ming, W. Kuehn, Lu ZhonghaiA. Jantsch. Run-time Partial Reconfiguration speed investigation and architectural design space exploration.2009.498-502.
[32]Richard Neil Pittman Alessandro Shaoshan Liu. Minimizing Partial Reconfiguration Overhead with Fully Streaming DMA Engines and Intelligent ICAP Controller.2009.
[33]Kyprianos Papadimitriou, Apostolos DollasScott Hauck. Performance of partial reconfiguration in FPGA systems:A survey and a cost model. ACM Transaction on Reconfigurable Technology System.2011.4. (4).36:1--36:24.
[34]Lei FeiZhao Xiaoxia. Adaptive background estimation of underwater using Kalman-Filtering.2010.64-67.
[35]C. R. Wren, A. Azarbayejani, T. DarrellA. P. Pentland. Pfinder:real-time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence.1997.19. (7).780-785.
[36]Chris StaufferW. E. L. Grimson. Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000. 22. (8).747-757.
[37]Pakorn KaewTraKulPongRichard Bowden. An improved adaptive background mixture model for real-time tracking with shadow detection.2002.135-144.
[38]Roland MechM. Wollborn. A noise robust method for segmentation of moving objects in video sequences.1997.2657-2660 vol.4.
[39]A. Neri, S. Colonnese, G. RussoP. Talone. Automatic moving object and background separation. Signal Processing.1998.66. (2).219--232.
[40]Alan J. Lipton, Hironobu FujiyoshiRaju S. Patil. Moving target classification and tracking from real-time video.1998.8--14.
[41]Jeff Chase, Brent Nelson, John Bodily, Zhaoyi WeiDah-Jye Lee. Real-time optical flow calculations on FPGA and GPU architectures:a comparison study. 2008.173-182.
[42]Deqing Sun, Stefan Roth, J. P. LewisMichael J. Black. Learning optical flow. 2008.83-97.
[43]Toby LowGordon Wyeth. Obstacle detection using optical flow.2005.
[44]Michael Harville. A framework for high-level feedback to adaptive, per-pixel, mixture-of-gaussian background models.2002.543-560.
[45]Ahmed Elgammal, Ramani Duraiswami, David HarwoodLarry S. Davis. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE.2002.90. (7). 1151-1163.
[46]Shengcai Liao, Guoying Zhao, Vili Kellokumpu, Matti PietikainenStan Z. Li. Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes.2010.1301-1306.
[47]Gian Luca Foresti. Object recognition and tracking for remote video surveillance. IEEE Transactions on Circuits and Systems for Video Technology.1999.9. (7). 1045-1062.
[48]Wei Niu, Jiao Long, Dan Han Yuan-Fang Wang. Human activity detection and recognition for video surveillance.2004.719-722.
[49]Weiyao Lin, Ming-Ting Sun, Radha PoovendranZhengyou Zhang. Activity recognition using a combination of category components and local models for video surveillance. IEEE Transactions on Circuits and Systems for Video Technology.2008.18. (8).1128--1139.
[50]Marian Stewart Bartlett, Javier R. MovellanTerrence J. Sejnowski. Face recognition by independent component analysis. IEEE Transactions on Neural Networks.2002.13. (6).1450--1464.
[51]Daniel TranelAntonio R. Damasio. Knowledge without awareness:An autonomic index of facial recognition by prosopagnosics. Science.1985.228. (4706). 1453-1454.
[52]Roberto BrunelliTomaso Poggio. Face recognition:Features versus templates. IEEE Transactions on Pattern Analysis and Machine Intelligence.1993.15. (10). 1042--1052.
[53]Wenyi Zhao, Rama Chellappa, P. Jonathon PhillipsAzriel Rosenfeld. Face recognition:A literature survey. Acm Computing Surveys (CSUR).2003.35. (4). 399--458.
[54]S. Impedovo, L. OttavianoS. Occhinegro. Optical character recognition-a survey. International Journal of Pattern Recognition and Artificial Intelligence.1991.5. (01n02).1--24.
[55]Shunji Mori, Hirobumi NishidaHiromitsu Yamada. Optical character recognition. John Wiley & Sons, Inc.,1999,
[56]James M. WhiteGene D. Rohrer. Image thresholding for optical character recognition and other applications requiring character image extraction. IBM Journal of Research and Development.1983.27. (4).400-411.
[57]Massimo Pacella, Quirico SemeraroAlfredo Anglani. Manufacturing quality control by means of a Fuzzy ART network trained on natural process data. Engineering Applications of Artificial Intelligence.2004.17. (1).83-96.
[58]Christian Demant, Bernd Streicher-AbelPeter Waszkewitz. Industrial image processing:visual quality control in manufacturing. Springer Verlag,1999,
[59]T. Kohonen. The self-organizing map. Proceedings of the IEEE.1990.78. (9). 1464-1480.
[60]T. Kohonen, S. Kaski, K. Lagus, J. Salojarvi, J. Honkela, V. PaateroA. Saarela. Self organization of a massive document collection. IEEE Transactions on Neural Networks.2000.11. (3).574-585.
[61]Olli Silv E N, Matti Niskanen, Hannu Kauppinen. Wood inspection with non-supervised clustering. Machine Vision and Applications.2003.13. (5-6). 275-285.
[62]Stefan R U Ping, Ulrich R U CkertKarl Goser. Hardware Design for Self-Organizing Feature Maps with Binary Input Vectors.1993.488--493.
[63]T. Yamakawa, K. HorioT. Hiratsuka. Advanced self-organizing maps using binary weight vector and its digital hardware design.2002.1330-1335 vol.3.
[64]J. Pena, M. VanegasA. Valencia. Digital Hardware Architectures of Kohonen's Self Organizing Feature Maps with Exponential Neighboring Function.2006.1-8.
[65]K. Appiah, A. Hunter, Meng Hongying, Yue Shigang, M. Hobden, N. Priestley, P. HobdenC. Pettit. A binary Self-Organizing Map and its FPGA implementation. 2009.164-171.
[66]Suhap Sahin, Yasar BecerikliSuleyman Yazici. Neural Network Implementation in Hardware Using FPGAs.2006.1105-1112.
[67]Chip-Hong Chang, Menon ShibuRui Xiao. Self Organizing Feature Map for Color Quantization on FPGA.2006.225-245.
[68]Mario Porrmann, Ulf WitkowskiUlrich Ruckert. Implementation of Self-Organizing Feature Maps in Reconfigurable Hardware.2006.247-269.
[69]Agust I. N. Ram Agundis, Rafael Gadea Girones, Ricardo Colom PaleroJavier D. I. Az Carmona. A mixed hardware/software sofm training system. Computaciny Sistemas.2008.11. (4).349--356.
[70]K. Appiah, A. Hunter, P. DickinsonMeng Hongying. Implementation and Applications of Tri-State Self-Organizing Maps on FPGA. IEEE Transactions on Circuits and Systems for Video Technology.2012.22. (8).1150-1160.
[71]C. Cortes Y. LeCun. The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/
[72]David Exner, Erich Bruns, Daniel Kurz, Anselm Grundh O FerOliver Bimber. Fast and reliable CAMShift tracking.2005.
[73]Juan Liang, Jianhua Hou, Jun Xiang, Bangyou DaShaobo Chen. An effective automatic tracking algorithm based on Camshift and Kalman filter.2011. 800316--800316.
[74]Xia Liu, Hongxia ChuPingjun Li. Research of the improved camshift tracking algorithm.2007.968--972.
[75]Ivana Mikic, Slawomir KrucinskiJames D. Thomas. Segmentation and tracking in echocardiographic sequences:Active contours guided by optical flow estimates. IEEE Transactions on Medical Imaging.1998.17. (2).274--284.
[76]Jeffrey F. Cohn, Adena J. Zlochower, J. J. LienTakeo Kanade. Feature-point tracking by optical flow discriminates subtle differences in facial expression. 1998.396--401.
[77]M. S. Arulampalam, S. Maskell, N. GordonT. Clapp. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing.2002.50. (2).174-188.
[78]A. Doucet, N. J. GordonV. Krishnamurthy. Particle filters for state estimation of jump Markov linear systems. IEEE Transactions on Signal Processing.2001.49. (3).613-624.
[79]洪少华,史治国,陈抗生,Hong Shao-hua, Shi Zhi-guoChen Kang-sheng.用于纯方位跟踪的简化粒子滤波算法及其硬件实现.电子与信息学报.2009.31.(1).
[80]P. Perez, C. Hue, J. VermaakM. Gangnet. Color-based probabilistic tracking. Computer Vison-ECCV 2002, PT 1.2002.2350.661-675.
[81]H. Medeiros, J. ParkA. Kak. A parallel color-based particle filter for object tracking.2008.1-8.
[82]Wang Tzu-Heng, Chang Jing-YingChen Liang-Gee. Algorithm and architecture for object tracking using particle filter.2009.1374-1377.
[83]Arnaud Doucet, Nando De FreitasNeil Eds. Gordon. Sequential Monte Carlo Methods in Practice. New York:Springer Verlag,2001,
[84]M. Bolic, A. Athalye, S. HongP. M. Djuric. Study of Algorithmic and Architectural Characteristics of Gaussian Particle Filters. Journal of Signal Processing Systems.2009.1-14.
[85]E. A. LehmannR. C. Williamson. Experimental comparison of particle filtering algorithms for acoustic source localization in a reverberant room.2003.147.
[86]Gerald Estrin. Organization of computer systems:the fixed plus variable structure computer.1960.33--40.
[87]Vu-Duc Ngo, Huy-Nam NguyenHae-Wook Choi. Analyzing the Performance of Mesh and Fat-Tree Topologies for Network on Chip Design.2005.300-310.
[88]P. P. Pande, C. Grecu, M. Jones, A. IvanovR. Saleh. Performance evaluation and design trade-offs for network-on-chip interconnect architectures. IEEE Transactions on Computers.2005.54. (8).1025-1040.
[89]D. Ludovici, F. Gilabert, S. Medardoni, C. Gomez, M. E. Gomez, P. Lopez, G. N. GaydadjievD. Bertozzi. Assessing fat-tree topologies for regular network-on-chip design under nanoscale technology constraints.2009.562-565.
[90]Michael R. GareyDavid S. Johnson. Computers and Intractability; A Guide to the Theory of NP-Completeness. New York, NY, USA:W. H. Freeman Co.,1990,
[91]Richard E. Korf. From approximate to optimal solutions:a case study of number partitioning.1995.266--272.
[92]Richard E. Korf. Multi-way number partitioning.2009.538--543.
[93]Richard E. Korf. A complete anytime algorithm for number partitioning. Artificial Intelligence.1998.106. (2).181--203.
[94]Benjamin Yakir. The differencing algorithm LDM for partitioning:a proof of a conjecture of Karmarkar and.1996.21. (1).85--99.
[95]Y. E. Krasteva, J. Portilla, E. De la TorreT. Riesgo. Embedded Runtime Reconfigurable Nodes for Wireless Sensor Networks Applications. Sensors Journal, IEEE.2011.11. (9).1800-1810.
[96]A. Nahapetian, P. Lombardo, A. Acquaviva, L. BeniniM. Sarrafzadeh. Dynamic Reconfiguration in Sensor Networks with Regenerative Energy Sources.2007. 1-6.
[97]A. Dunkels, B. GronvallT. Voigt. Contiki-a lightweight and flexible operating system for tiny networked sensors.2004.455-462.
[98]Jin Tao, G. NoubirSheng Bo. WiZi-Cloud:Application-transparent dual ZigBee-WiFi radios for low power internet access.2011.1593-1601.
[99]Wei LiJia Ke-Bin. Implementation of embedded Web Server based on uIP TCP/IP stack.2007.668-671.