結論 - 利用時空域分析與背景相減法作視訊移動物偵測

本研究主要結合了時域、空間域以及色彩資訊等概念，以背景相減法來擷取完整的移動物，並解決偵測時最常遇到的非前景物移動物與動態背景雜訊的問題。由實驗結果顯示，本研究方法在室內環境下其正確偵測率為 92.91%，室外環境下為 91.81%，可有效地去除如陰影等前景雜訊與動態的背景雜訊，擷取出正確的動態前景。

首先利用修正時序式統計法來建構可隨時間更新的初始背景，來達到擷取完整前景物資訊與計算簡單且不易受光線影響的目的。而在前景擷取的部份則利用色彩值域座標轉換的概念，將三維 RGB 座標利用 Angle-module 方法直接轉換成更能代表前景物資訊的二維色相變化以及色彩強度資訊，經由自適應閥值來擷取前景移動物，並利用背景與前景的色彩差異性濾除前景雜訊(陰影、變化微小的雜訊)，取得更完整前景物，也增添系統本身的環境適應性。加上以時空域的概念，建立區域相關係數遮罩，由此遮罩將動態背景去除，最後得到濾除前景雜訊以及動態背景雜訊的移動物影像。除此之外，

本研究發現區域相關係數遮罩對攝影機因外力輕微搖晃所產生的誤測，有著很好的濾除性。

在實驗測試結束後，本研究歸納及分析了所提出的移動物擷取法方法。

得此演算法之特點，以下將一一加以列舉。

特點：

1. 不需要有事先存在的背景圖就能建構快速自適應性的背景，且由於利用直方圖統計的方式建立背景，僅需記憶體空間來從儲存背景資料，不需複雜的統計運算

2. 能有效地去除陰影雜訊。

3. 可用於較複雜的動態背景情況之移動物偵測。

4. 可快速的適應光線變化所造成的影響；由光線變化的關燈實驗可知，其適應速度為約經過 10 張影像格數後(#179~#189)，就能開始正確的擷取前景移動物。

5. 可降低因攝影機晃動之誤差，如圖 4.11；以及鬼影所造成之誤差，如圖 3.18。

6. 可以擷取較為完整前景移動物體。

總結來說，本研究的方法在不管在室內或室外環境下，都有著良好的偵測率以及環境適應性。未來可以更進一步結合其他偵測演算法，例如人臉偵測等來整合成更有效的智慧監控系統。此外，本文動態背景去除的方式，與初始設定的遮罩大小以及相關性閥值的設定有著絕對的關係，因此可進一步研究加入自適應學習法，將遮罩大小設計成可隨著動態雜訊的多寡做更新，

相信能更增強系統的強健性。本系統每秒大致可以處理 9 張影像，未來可以 試著對程式架構進行最佳化的動作，來更增進系統的效能。

參考資料

1. Wikipedia: public editor, “RGB color model”, available at:

http://en.wikipedia.org/wiki/RGB.

2. Colantoni, P., “Cours-Couleur.Org”, available at:

http://www.couleur.org/index.php?page=transformations.

3. 鐘國亮，「影像處理與電腦視覺」，台灣東華書局股份有限公司，2006 4. Lipton, A.J., Fujiyoshi, H., and Patil, R.S., “Moving Target Classification

and Tracking from Real-time Video”, IEEE Workshop on Applications of Computer Vision, pp. 8-14, 1998.

5 Wixson, L., and Hansen, M., “Detecting Salient Motion by Accumulating Directionally-consistent Flow”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 774-780, 2000.

6. Tian, Y.L., and Hampapur, A., “Robust Salient Motion Detection with Complex Background for Real-time Video Surveillance”, IEEE Workshop on Motion and Video Computing, vol. 2, pp. 30-35, 2005.

7. Huang, K., Wang, L., Tan, T., and Steve, M., “A Real-time Object Detecting and Tracking System for Outdoor Night Surveillance”, Pattern Recognition, vol. 41, pp. 432-444, 2008.

8. Wren, C., Azarbayejani, A., Darrel, T., and Pentland, A.P., “Pfinder:

Real-time Tracking of Human Body”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, pp. 780-785, 1997.

9. Koller, D., Weber, J., Hung, T., Malik, J., Ogasawara, G., Rao, B., and Russel, S., “Towards Robust Automatic Traffic Scene Analysis in Real-time”, Computer Vision & Image Processing, vol. 1, pp. 126-131, 1994.

10. Haritaoglu, I., Harwood, D., and Davis, L.S., “W4: Real-time Surveillance of People and Their activities”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 809-830, 2000.

11. Stauffer, C., and Grimson, W.E.L., “Adaptive Background Mixture Models for Real-time Tracking”, Computer Vision and Pattern Recognition, vol. 2, pp. 246-252, 1999.

12. Elgammal, A., Harwood, D., and Davis, L.S., “Non-Parametric Model for Background Subtraction”, Computer Vision ECCV 2000, pp. 751-764, 2000.

13. Ekinci, M., and Gedikli, E., “Silhouette Based Human Motion Detection and Analysis for Real-time Automated Video Surveillance”, Turkish Journal of Electrical Engineering & Computer Sciences, vol.13, pp. 199-229, 2005.

14. Kumar, P., Sengupta, K., and Lee, A., “A Comparative Study of Different Color Spaces for Foreground and Shadow Detection for Traffic Monitoring System”, The IEEE 5th International Conference on Intelligent Transportation Systems, pp. 100-105, 2002.

15. Enrique, J., Martínez, J., and Mira, J., “A new Video Segmentation Method of Moving Objects Based on Blob-Level Knowledge”, Pattern Recognition Letters, vol. 29, pp. 272-285, 2008.

16. Jabri, S., Duric, Z., and Wechsler, H., Tracking Groups of People”, Computer Vision and Image Understanding, vol. 80, pp. 42-56, 2000.

17. Javed, O., Shafique, K., and Shah, M., “A Hierarchical Approach to Robust Background Subtraction Using Color and Gradient Information”, Workshop on Motion and Video Computing, pp. 22-27, 2002.

18. Wardhani, A., and Thomson, T., “Content Based Image Retrieval Using Category-based Indexing”, 2004 IEEE International Conference on Multimedia and Expo (ICME), vol. 2, pp. 783-786, 2004.

19. Doshi, A., “highwayI”, database available at:

http://cvrr.ucsd.edu/aton/shadow/index.html.

20. 李振(金昇)，「非靜態背景條件下之移動性人物偵測」，國立中正大學電機工程研究所碩士論文，民國96年7月。

21. Tai, J.C., and Song, K.T., “Background Segmentation and Its Application to Traffic Monitoring Using Modified Histogram”, IEEE International

Conference on Networking, Sensing and Control, vol. 1, pp. 13-18, 2004.

22. Prati, A., Mikic, I., Trivedi, M.M., and Cucchiara, R., “Detecting Moving Shadows: Algorithms and Evaluation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.25, pp. 918-923, 2003.

23. Prati, A., Mikic, I., Crana, C., Trivedi, M.M., “Shadow Detection Algorithms for Traffic Flow Analysis: a Comparative Study”, IEEE Intelligent Transportation Systems Conference Proceedings, pp. 25-29, 2001.

24. Spagnolo, P., OrazioM, T.D., Leo, M., and Distante, A., “Moving Object Segmentation by Background Subtraction and Temporal Analysis”, Image and Vision Computing, vol. 24, pp. 411-423, 2006.

25. Li, G., Wang, Y., and Shu, W., “Real-time Moving Object Detection for Video Monitoring Systems”, Second International Symposium on Intelligent Information Technology Application, vol. 3, pp. 163-166, 2008.

26. Sijun, L., Jian, Z., Feng, D., “An Efficient Method for Detecting Ghost and Left Objects in Surveillance Video”, IEEE Conference on Advanced Video and Signal Based Surveillance, pp.540-545, 2007.

27. Fisher, R., “Browse1”, database available at:

http://groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/

28. Liyuan, L., “Campus with wavering tree branches”, database available at:

http://perception.i2r.a-star.edu.sg/bk_model/bk_index.html.

在文檔中利用時空域分析與背景相減法作視訊移動物偵測 (頁 89-93)