跳到主要內容

臺灣博碩士論文加值系統

(44.211.117.197) 您好!臺灣時間:2024/05/22 01:13
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:胡莊群
研究生(外文):Chuang-Chun Hu
論文名稱:區塊式影像物件偵測之嵌入式系統
論文名稱(外文):Block-Based Image Object Detection for Embedded System
指導教授:許明華許明華引用關係
指導教授(外文):Ming-Hwa Sheu
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:電子與資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2010
畢業學年度:98
語文別:中文
論文頁數:66
中文關鍵詞:矽智產物件追蹤連接區域標籤化物件偵測智慧型影像監控系統
外文關鍵詞:Object deIntelligent video surveillance system
相關次數:
  • 被引用被引用:0
  • 點閱點閱:335
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
近年來,智慧型影像監控系統漸漸的被重視,也漸漸的取代了必須仰賴管理人員做即時監控的系統,不過許多的影像監控系統其方法過於複雜,且無法達到即時的效果,因此本論文將針對此問題,提出快速的物件偵測方式,有效的解決晃動的背景所造成的問題,並省下許多的記憶體空間,不僅可以在PC上面執行,更可以在TI TMS320DM6446 Davinci開發板上面執行。
本論文所提出的物件偵測方式,首先將影像分成諸多的區塊來執行,並且每個區塊裡有各自區塊的背景模型,我們透過與背景模型的比對,去判斷出前景物件出來,並更新背景模型,整體的執行速度在768*578的解析度下達到了12 fps,在320*240的解析度下40 fps,在160*120的解析度下130 fps。
而對於後續動作,如追蹤部份,我們還需要對於偵測出來的前景做連接物件標籤化處理,但由於此運算量相當龐大,因此本論文將此部分作成矽智產,提出了三點式影像物件標籤化的硬體架構,並做成CHIP,來增加系統處理速度並達到即時影像物件之偵測。
Intelligent video surveillance system has been paid much attention recently. It can improve the traditional monitoring system which is operated by human. However, many video surveillance systems are too complicated to be implemented in the embedded system. We propose a fast object detection method that will improve this problem in this thesis. An effective block-based approach is used to construct the background modeling, and save a lot of memory space. The input image is also divided into a number of blocks. Then we perform the object detection based on the block-based background. After judging the foreground and background block for the input image, our system use the foreground block to find the whole object and the background block to update the background modeling. Our approach is not only implemented in the PC, but also executed in TI TMS320DM6446 embedded platform. The processing frame rate depends on the input image resolution. In PC, the processing speech can achieve 12 fps for 768 * 578 frame size, and 40 fps for 320 * 240 frame size. In Davinci, the processing speech can achieve 25 fps for 320 * 240 frame size.
Besides, we develop 3-pixel parallel labeling to speed up the system performance. This parallel labeling is suitable for VLSI architecture design. After the Verilog simulation, this architecture has been synthesized based on TSMC 0.18 um CMOS processing. The chip layout is about 1580*1580 um2. Its working frequency is about 100 MHz to accelerate the labeling operation and achieve real-time object detection.
中文摘要 i
英文摘要 ii
誌謝 iii
目錄 v
表目錄 vi
圖目錄 vii
一、 序論 1
1.1 研究動機與背景 1
1.2 研究目的 1
1.3 論文架構 2
二、 相關背景 3
2.1 相關研究與簡介 3
2.2 背景註冊法Background Registration 5
2.3 Codebook 9
2.4 SACON 14
三、 區塊式影像物件偵測演算法設計 19
3.1 簡介 19
3.2 區塊式影像物件偵測演算法 19
3.2.1 背景模型建立 21
3.2.2 影像物件初步切割 23
3.2.3 條件式侵蝕(Conditional Fillter) 24
3.2.4 背景模型更新 25
3.2.5 後處理(Post Processing) 26
3.2.6 記憶體計算 26
四、 區塊式影像物件偵測之嵌入式系統應用與實現 27
4.1 在x86系統上的實現 27
4.2 在TI Davinci嵌入式平台上的實現 35
4.3 小結 38
五、 三點式影像物件標籤化 39
5.1 簡介 39
5.2 硬體演算法 40
5.2.1 標籤選擇和label equivalence說明 41
5.2.2 Label assignment 42
5.2.3 Label merge 43
5.3 硬體架構 45
5.4 電路功能驗證及VLSI實現 46
5.4.1 電路功能驗證 46
5.4.2 VLSI實現 49
5.5 效能比較 50
六、 結論 52
6.1 總結 52
6.2 未來方向 52
參考文獻 53
[1]Lo Presti, L.; La Cascia, M., “Real-time object detection in embedded video surveillance systems”, WIAMIS ''08. Ninth International Workshop on Image Analysis for Multimedia Interactive Services, pp. 151 - 154, 2008.
[2]Apewokin, S.; Valentine, B.; Wills, L.; Wills, S.; Gentile, A., “Multimodal Mean Adaptive Backgrounding for Embedded Real-Time Video Surveillance”, IEEE Conference on Computer Vision and Pattern Recognition, 2007. CVPR ''07., pp. 1 - 6, 2007.
[3]Lin Zhu, Jie Zhou, and Jingyan Song, “Tracking multiple objects through occlusion with online sampling and position estimation”, 2008 Elsevier Pattern Recognition, Volume 41, Issue 8, pp. 2447 - 2460, August 2008.
[4]Luis M. Fuentes, Sergio A. Velastin, "Foreground segmentation using luminance contrast", Proceedings of the WSES/IEEE conference on speech, signal and image processing (SSIP 2001), pp 2231 - 2235, September 2001.
[5]Spirito, M, Regazzoni, C.S.; Marcenaro, L., “Automatic detection of dangerous events for underground surveillance”, IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2005, pp. 195 - 200, 2005
[6]Luis M. Fuentes, Sergio A. Velastin, “People tracking in surveillance applications”, Performance Evaluation of Tracking and Surveillance Image and Vision Computing, Volume 24, Issue 11, pp. 1165 - 1171, 1 November 2006.
[7]Hsien-Huang P. Wu, Jen-Hung Chang, Ping-Kuo Weng, Ying-Yih Wu, “Improved moving object segmentation by multiresolution and variable thresholding”, 2006 Society of Photo-Optical Instrumentation Engineers Image Processing, Volume 45 Issue 11, 27 November 2006.
[8]Patwardhan, K.A.; Sapiro, G.; Morellas, V., “Robust Foreground Detection in Video Using Pixel Layers”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 30, Issue 4, pp.746 - 751, 2008.
[9]Xiaoshi Zheng; Yanling Zhao; Na Li; Huimin Wu, “An Automatic Moving Object Detection Algorithm for Video Surveillance Applications”, International Conference on Embedded Software and Systems, 2009. ICESS ''09, pp. 541 - 543, 2009.
[10]Yu-Ting Chen, Chu-Song Chen, Chun-Rong Huang and Yi-Ping Hung, “Efficient hierarchical method for background subtraction”, Pattern Recognition Society Published by Elsevier B.V., Volume 40, Issue 10, pp. 2706 - 2715, October 2007.
[11]Tianci Huang, Jingbang Qiu, Sakayori, T., Goto, S., Ikenaga, T., “Motion Detection Based On Background Modeling And Performance Analysis For Outdoor Surveillance”, International Conference on Computer Modeling and Simulation, 2009. ICCMS ''09, pp. 38 - 42, 2009.
[12]Heikkila, M., Pietikainen, M.,”A Texture-Based Method for Modeling the Background and Detecting Moving Objects”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 28 , Issue 4, pp.657 - 662, 2006.
[13]Jian Yao, Odobez, J.-M., “Multi-Layer Background Subtraction Based on Color and Texture”, IEEE Conference on Computer Vision and Pattern Recognition, 2007. CVPR ''07, pp. 1 - 8, 2007.
[14]Nigam, C., Babu, R.V., Raja, S.K., Ramakrishnan, K.R., “Feature Fusion for Robust Object Tracking Using Fragmented Particles”, First ACM/IEEE International Conference on Distributed Smart Cameras, 2007. ICDSC ''07., pp. 283 - 290, 2007.
[15]Stauffer, C., Grimson, W.E.L., “Learning Patterns of Activity Using Real-Time Tracking”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 22 , Issue 8, pp. 747 - 757, 2000.
[16]Kyungnam Kim , Thanarat H. Chalidabhongse, David Harwoodand Larry Davis, “Real-time foreground-background segmentation using Codebook model”, Special Issue on Video Object Processing Real-Time Imaging, Volume 11 Issue 3 pp. 172 - 185, June 2005.
[17]Arth, C., Bischof, H., Leistner, C., “TRICam - An Embedded Platform for Remote Traffic Surveillance”, Conference on Computer Vision and Pattern Recognition Workshop, 2006. CVPRW ''06., pp. 125 - 125, 2006.
[18]Qiu Tu, Yiping Xu, Manli Zhou, “Box-based Codebook Model for Real-time Object Detection”, 7th World Congress on Intelligent Control and Automation, 2008. WCICA 2008., pp. 7621 - 7625, 2008.
[19]ZhaoHui Zhang, RuiQing Chen, HanQing Lu, YuKun Yan, HuiQing Cui, “Moving Foreground Detection based on Modified Codebook”, International Congress on Image and Signal Processing, 2009. CISP ''09. 2nd, pp. 1 - 5, 2009.
[20]Ilyas, A., Scuturici, M., Miguet, S., “Real Time Foreground-Background Segmentation Using a Modified Codebook Model”, IEEE International Conference on Advanced Video and Signal Based Surveillance, 2009. AVSS ''09. Sixth, pp. 454 - 459, 2009.
[21]Yong Chu, Hong Zhu, Dong Wang, “A Codebook-based Video Moving Objects Detecting Method”, IEEE International Conference on Information Acquisition, pp 43 - 47, 2006.
[22]Yu Wu, Delong Zeng, Hongbo Li, “Layered Video Objects Detection Based on LBP and Codebook”, First International Workshop on Education Technology and Computer Science, 2009. ETCS ''09., Volume 1 pp. 207 - 213, 2009.
[23]Piccardi, M., Cheng, E.D., “Multi-Frame Moving Object Track Matching Based on an Incremental Major Color Spectrum Histogram Matching Algorithm”, IEEE Computer Society Conference Computer Vision and Pattern Recognition - Workshops, 2005. CVPR Workshops., pp. 19 - 19, 2005.
[24]Hanzi Wang, David Suter, “A consensus-based method for tracking: Modelling background scenario and foreground appearance”, 2006 Pattern Recognition Society Published by Elsevier B.V., Volume 40, Issue 3, pp. 1091-1105, March 2007.
[25]Du-Ming Tsai, Wei-Yao Chiu, “Motion detection using Fourier image reconstruction”, 2008 Pattern Recognition Letters by Elsevier B.V., Volume 29, Issue 16, pp. 2145 - 2155, 1 December 2008.
[26]Weiqiang Wang; Jie Yang; Wen Gao, “Modeling Background and Segmenting Moving Objects from Compressed Video”, IEEE Transactions on Circuits and Systems for Video Technology, Volume 18, Issue 5, pp. 670 - 681, 2008.
[27]Shao-Yi Chien; Shyh-Yih Ma; Liang-Gee Chen, “Efficient Moving Object Segmentation Algorithm Using Background Registration Technique”, IEEE Transactions on Circuits and Systems for Video Technology, Volume 12, Issue 7, pp. 577 - 586, 2002.
[28]Wei-Kai Chan; Shao-Yi Chien, “Real-Time Memory-Efficient Video Object Segmentation in Dynamic Background with Multi-Background Registration Technique”, IEEE 9th Workshop on Multimedia Signal Processing, 2007. MMSP 2007., pp. 219 - 222, 2007.
[29]R.E. Cypher, J.L.C. Sanz, and L. Snyder, “Algorithms for image component labeling on SIMD mesh-connected computers”, IEEE Transactions on Computers, Volume 39, Issue 2, pp. 276 - 281, Feb. 1990.
[30]H.M. Alnuweiri, and V.K. Prasanna, “Parallel architectures and algorithms for image component labeling”, IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 14, Issue 10, pp. 1024 - 1034, Oct. 1992.
[31]T. Hattori, “A high-speed pipeline processor for regional labeling based on a new algorithm”, 10th International Cinference on Pattern Recognition, Volume 2, pp. 494 - 496, June 1990.
[32]S.D. Jean, C.M. Liu, C.C. Chang, and Z. Chen, “A new algorithm and its VLSI architecture design for connected component labeling”, Internetional Symposium on Circuits and Systems, Volume 2, pp. 565 - 568, 1994.
[33]R.M. Haralick, “Some neighborhood operations”, In real time/parallel computing image analysis, Plenum Press, New York, pp.11 - 35, 1981.
[34]C.J. Nicol, “A systolic approach for real time connected component labeling”, Computer Vision and Image Understanding, Volume 61, Issue 1, pp. 17 - 31, Jan. 1995.
[35]N. Ranganathan, R. Mehrotra, and S. Subramanian, “A high speed systolic architecture for labeling connected components in an image”, IEEE Transactions on Systems, Man and Cybernetics, Volume 25, Issue 3, pp. 415 - 423, 1995.
[36]K.B. Wang, T.L. Chia, and Z. Chen, “Parallel execution of a connected component labeling operation on a linear array architecture”, Journal of Information science and engineering, vol. 19, pp.353-370, 2003.
[37]H. Flatt, S. Blume, S. Hesselbarth, T. Schuemann, and P. Pirsch, “A parallel hardware architecture for connected component labeling based on fast label merging,” International Conference on Application-Specific Systems, Architectures and Processors, pp. 144 - 149, July 2008.
[38]朱元昌,06 2008,在混沌背景下以多成背景模型為基礎之物件切割與追蹤,碩士論文,電子工程系碩士班 國立雲林科技大學。
[39]葉欣錩,06 2009,嵌入式即時影像物件切割之軟硬體協同設計,碩士論文,電子工程系碩士班 國立雲林科技大學。
[40]陳思穎,06 2009,即時多重移動物件追蹤與計數之影像監控系統,碩士論文,電子工程系碩士班 國立雲林科技大學。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top