臺灣博碩士論文加值系統

近年來，智慧型影像監控系統漸漸被重視，也漸漸取代必須仰賴管理人員做即時監控的系統。隨著科技不斷演進，現今的智慧型監控系統都是藉由網路來傳輸即時影像，傳統上的做法都是在監控中心接收到網路封包，再進行封包拆解與解壓縮後所得到的原始影像，來進行物件偵測。因此針對此問題，本論文提出了兩套新穎的演算法，一開始會介紹所我們所提出區塊式時域紋理分析的方法，進而推導至頻域影像的分析，由於頻域影像演算法能實現並嵌入於監控中心的解壓端，最後實現於PC的速度會比一般傳統式的方法快上2倍，而在準確度方面，平均都可以達到60%的精準度，最後不僅可在PC上執行，於PC模擬768*576的影像解碼速度都可以達到遠大於Real-time的速度，記憶體消耗跟MoG比起來少了5倍以上，更可以在TI TMS320DM6446 DavinCi開發板上面執行，模擬於DavinCi開發版的速度可以達到20 fps以上，增加的將來產品化的可能。

Intelligent surveillance system has been gradually becoming an important role lately. It replaces the regular surveillance system which is monitored by manpower. As high technology keeps evolving, the surveillance system nowadays transfers real-time video by network instead of NTSC cable. In conventional way, surveillance center receives the network packets from remote network camera then being parsed into series compressed video data. After decoding the compressed video which is normally called as raw data of video, the algorithm of object detection and segmentation would be developed beneath it. The thesis proposed two novel methods for the object detection. At the beginning, we proposed our object detecting method with block-based texture at Spatial Domain, and then prove it is possible to translate into frequency domain for detection, with the advantage that the detection method of frequency domain analysis can implant into the MPEG Decoder at surveillance center. Our approach can achieve two times of processing speed than the conventional approach in spatial domain. Besides, it can also reach average 60% accuracy. The proposed approach is not only used for the dynamic background, but also implemented on embedded system “TI TMS320DM6446 DaVinci”. The performance on PC has exceeded real-time operation of 40 fps with frame size 768*576. Similarly, the performance on DaVinci embedded system can achieve 20 fps.

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
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 2
1.3 論文架構 2
1.4 相關背景研究 3
1.4.1 Spatial Domain的相關研究介紹 4
1.4.2 Compressed Domain的相關研究介紹 7
二、 頻域紋理影像物件偵測演算法設計 10
2.1 時域區塊式紋理分析物件偵測演算法 10
2.1.1區塊式紋理影像分析 12
2.1.2區塊式多重門檻值的訓練 14
2.1.3區塊式紋理影像背景模型建立 16
2.1.4紋理影像物件區塊切割與背景模型更新 17
2.1.5移動物件細緻化 18
2.2 頻域影像物件偵測演算法 19
2.2.1時域紋理影像與頻域影像之探討 20
2.2.2移動物件細緻化 31
三、 頻域影像物件偵測演算法之嵌入式系統應用與實現 34
3.1 在Linux系統上的實現 34
3.1.1以像素為基準做比較 34
3.1.2以區塊為基準做比較 45
3.1.3判斷前景運算複雜度比較 56
3.2 在TI DavinCi嵌入式平台上的實現 58
四、 結論 63
4.1 總結 63
4.2 未來方向 63
4.3 Q & A 63
參考文獻 65
附錄：英文論文 68

[1].P.-M. Jodoin, M. Mignotte, J. Konrad, “Statistical Background Subtraction Using Spatial Cues, ”IEEE Trans. Circuits and Systems, vol. 17, Issue 12, pp. 1758-1763, 2007.
[2].L. Li, W. Huang, Y.-H. Gu, Q. Tian, “Statistical Modeling of Complex Backgrounds for Foreground Object Detection”, IEEE Trans. Image. Processing, vol. 11, Issue 11, pp. 1459-1472, 2004.
[3].C. Stauffer, W. Eric L. Grimson, “Learning Patterns of Activity Using Real-Time Tracking, ”IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, NO. 8, pp. 747-757, 2000.
[4].C. Kim, J.-N. Hwang, “Object Based Video Abstraction for Video Surveillance Systems”, IEEE Trans. Circuits and Systems for Video Technology, vol. 12, NO.12, pp. 1128-1138, 2002.
[5].S.-Y. Chien, S.-Y. Ma and L.-G. Chen, “Efficient Moving Object Segmentation Algorithm Using Background Registration Technique,” IEEE Trans. Circuits and Systems for Video Technology, vol. 12, No. 7, pp.577-586, 2002.
[6].K. Kim, T.-H. Chalidabhongse, D. Harwood, and L.-S. Davis, “Real-Time Foreground-Background Segmentation using Codebook Model,” Real-Time Imaging, pp.172-185, 2005.
[7].M. Heikkila, M. Pietikainen, ”A Texture-Based Method for Modeling the Background and Detecting Moving Objects,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.28, Issue 4, pp. 657-662, April 2006.
[8].A. Cavallaro, O. Steiger, T. Ebrahimi, “Tracking Video Objects in Cluttered Background, ”IEEE Trans. Circuits and Systems, vol. 15, Issue 4, pp. 575-584, 2005.
[9].P. Spagnolo, T.D. Orazio, M. Leo, A. Distante, “Moving Object Segmentation by Background Subtraction and Temporal Analysis,” Image Vision Computing, vol. 24, pp. 411-423, 2006.
[10].H.-H. Paul, J.-H. Chang, P.-K. Weng, and Y.-Y. Wu, “Improved Moving Object Segmentation by Multi-Resolution and Variable Thresholding, ”Optical Engineering. vol. 45, No.11, pp. 117-123, 2006.
[11].H.-L. Eng, J. Wang, A. Harvey K.-S Wah, W.-Y. Yau, “Robust Human Detection Within a Highly Dynamic Aquatic Environment in Real Time, ” IEEE Trans. Image Processing, vol. 15, NO. 15, pp. 1583-1600, 2006.
[12].Hanzi Wang, David Suter, “ A Consensus-Based Method for Tracking Modelling Background Scenario and Foreground Appearance,” Pattern Recognition, pp. 1091-1105, 2006.
[13].E.-J. Carmona, M.-C. Javier, J. Mira, ”A New Video Segmentation Method of Moving Objects Based on Blob-Level Knowledge”, Pattern Recognition Letters, vol.29, pp. 272-285, 2008.
[14].C.-C. Chiu, M.-Yu. Ku, and L.-W. Liang, “A Robust Object Segmentation System Using a Probability-Based Background Extraction Algorithm”, IEEE Trans. Circuits and Systems for Video Technology, vol. 20, pp. 518-528, 2010.
[15].D.-M. Tsai, W.-Y. Chiu, “Motion Detection Using Fourier Image Reconstruction, ”Pattern Recognition Letters, vol. 29, Issue 16, pp. 2145-2155, 2008.
[16].Y. Sheikh, M. Shah, “Bayesian Modeling of Dynamic Scenes for Object Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence,vol.27, NO. 11, pp.1778-1792,2005.
[17].H.-L. Li, K.-N. Ngan, “Unsupervized Video Segmentation with Low Depth of Field,” IEEE Trans. Circuits and Systems for Video Technology, vol.17,NO. 12,pp.1742-1751,2007.
[18].B. Zhang, O’Neill. K, J.-A. Kong; Grzegorczyk. T.M, “Support Vector Machine and Neural Network Classification of Metallic Objects Using Coefficients of the Spheroidal MQS Response Modes,” IEEE Trans. Geo science and Remote Sensing,vol.46, Issue 1, pp.159-171,2007.
[19].Y. Liu, Y.-F. Zheng, “Soft SVM and Its Application in Video-Object Extraction,” IEEE Trans. Signal, vol.55, Issue 7, pp. 3272-3282, 2007.
[20].L. Maddalena, A. Petrosino, “A Self-Organizing Approach to Background subtraction for Visual Surveillance Applications,” IEEE Trans. Image Processing, vol. 17, NO. 7, pp. 1168–1177, 2008.
[21].Z. Wang, G. Liu. and L. Liu, “A Fast and Accurate Video Object Detection and Segmentation Method in the Compressed Domain”, IEEE Neural Networks & Signal Processing, pp. 1209–1212, 2003.
[22].L. Long, F. Xingle, J. Ruirui, D. Yi, “A Moving Object Segmentation in MPEG Compressed Domain Based on Motion Vectors and DCT Coefficients”, IEEE Congress on Image and Signal Processing, pp.605–609, 2008.
[23].W. Wang, J.Yang, W. Gao, ”Modeling Background and Segmenting Moving Objects from Compressed Video”, IEEE Trans. Circuits and Systems for Video Technology, vol. 18, NO. 5, pp. 670-681, 2008.
[24].M. Fujiyoshi, K. Kuroiwa, H. Kiya, “A Scrambling Method for Motion JPEG Videos Enabling Moving Objects Detections From Scrambling Videos”, IEEE. ICIP, pp. 773-776, 2008.
[25].M. Fujiyoshi, K. Kuroiwa, H. Kiya, “A DCT Coefficient Sign-Based Background Model for Moving Objects Detection from Motion JPEG Coded Movies”, IEEE. ISPACS, pp. 37-40, 2009.
[26].C. Poppe*, S. De Bruyne, T. Paridaens, P. Lambert, R.-Van. Walle, “ Moving object detection in the H.264/AVC compressed domain for video surveillance applications”,Elsvier Vison. Communication Image, pp.428-437, 2009.
[27].W. Zhang, X. Zhong, “Detection of Moving Cast Shadows Using Image Orthogonal Transform”, IEEE ICPR, pp. 232-240, 2006.