臺灣博碩士論文加值系統

最近於公共安全環境監控領域中，監控攝影機時常被使用於紀錄社會安全、犯罪事件等之用途，像是走失人口、追蹤嫌疑犯等事件，然而當監控人員於事後調閱其影像進行查證時，往往所要調閱之攝影機數目過於龐大，逐一搜索會花費大量時間與人力，導致其搜索效率過低。故本論文針對上述問題，設計一套於多攝影機環境下多目標物追蹤系統，使用者可以於影像片段中框選欲追蹤目標物，此系統即會以此所框選之目標物進行跟蹤，以達到監控人員所需花費大量時間與人力之目的。
在此，本論文之貢獻有以下三點：第一，提出一套特徵調變機制，輔助系統追蹤不同目標物，使其更為準確。第二，提出一套攝影機追蹤權切換機制，透過追蹤目標物最後消失之位置，以及多攝影機網路之架構，判斷出下次追蹤目標物會出現之攝影機，進而提高系統追蹤效率；第三，完成一個多攝影機環境下多目標物追蹤系統之雛形，整合目標物與攝影機相關資訊於一監控畫面，使監控人員能有效地減輕事後調閱影像之負擔。

Nowadays, in the field of the public security surveillance environment, surveillance cameras are often used to record the societal security and criminal events. However, there are more surveillance cameras when the supervisors browse the video after events happen. It will cause a lot of times and human resources. According to the above-mentioned problems, this thesis designs a system which tracks the multi-object in a multi-camera network. The users can choose the objects from the video chips and the system will track them across different cameras.
There are three contributions in this thesis. First, this thesis proposes a feature modulation mechanism. It can help the system track different objects accurately. Second, this thesis proposes a switching multi-camera mechanism. Though the architecture of the multi-camera network, the system determines the next camera which the objects will appear to improve the tracking efficiency. Third, this thesis completes the prototype of the multi-object in a multi-camera network. Then the system integrates the information of objects and cameras into the monitor system and reduces the burden which supervisors investigate video afterwards.

摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
圖目錄 vi
表目錄 xi
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 相關研究之探討 2
1.4 論文貢獻與架構 4
第二章 相關技術與原理 5
2.1 前景擷取 5
2.1.1 背景相減法 5
2.1.2 陰影抑制 7
2.1.3 形態學 9
2.1.4 連通元件標記法 13
2.2 均值漂移演算法 15
2.2.1 顏色特徵機率 15
2.2.2 平均位移量 16
2.2.3 多組特徵融合 18
2.3 方向梯度直方圖 20
第三章 系統流程 23
3.1 整體系統架構 23
3.2 影像前處理 24
3.3 單攝影機追蹤 26
3.3.1 追蹤條件 27
3.3.2 追蹤演算法 29
3.3.3 位置偏移修正 31
3.3.4 多目標物追蹤 32
3.3.5 目標物自動更新 34
3.4 多攝影機網路 35
3.5 距離比例轉換 42
第四章 實驗結果與分析 46
4.1 實驗機制 46
4.1.1 實驗設備介紹 46
4.1.2 實驗場景介紹 47
4.2 實驗結果分析與討論 49
4.2.1 單攝影機追蹤實驗結果之分析與討論 50
4.2.2 多攝影機網路實驗結果之分析與討論 63
4.2.3 實驗結果比較 82
第五章 結論與未來工作 86
參考資料 87

[1] R. K. Sadykhov and S. A. Kuchuk, “Background Substraction in Grayscale Images Algorythm,” in Proceedings of IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems, Berlin, Germany, vol. 1, pp. 425-428, Sep. 2013.
[2] C. Stauffer and W. E. L. Grimson, “Adaptive Background Mixture Models for Real-Time Tracking,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, USA, vol. 2, pp. 252, Jun. 1999.
[3] S. Denman, V. Chandran, and S. Sridharan, “Adaptive Optical Flow for Person Tracking,” in Proceedings of Digital Image Computing: Techniques and Applications, Queensland, Australia, pp. 6-8, Dec. 2005.
[4] S. Feng, Q. Guan, S. Xu, and F. Tan, “Human Tracking Based on Mean Shift and Kalman Filter,” in Proceedings of IEEE International Conference on Artificial Intelligence and Computational Intelligence, Shanghai, China, vol. 3, pp. 518-522, Nov. 2009.
[5] D. Comaniciu, V. Ramesh, and P. Meer, “Kernel-Based Object Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 5, pp. 564-577, May 2003.
[6] Y. Zhao, B. Zhang, and X. Zhang, “Meanshift Blob Tracking with Target Model Adaptive Update,” in Proceedings of Chinese Conference on Control, Nanjing, China, pp. 4831-4835, Jul. 2014.
[7] D. Comaniciu, V. Ramesh, and P. Meer, “Real-Time Tracking of Non-Rigid Objects using Mean Shift,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head Island, USA, vol. 2, pp. 142-149, Jun. 2000.
[8] H. Rajabi and M. Nahvi, “Modified Contour-Based Algorithm for Multiple Objects Tracking and Detection,” in Proceedings of IEEE International Conference on Computer and Knowledge Engineering, Mashhad, Iran, pp. 235-239, Oct. 2013.
[9] S. C and K. Tieu, “Automated Multi-Camera Planar Tracking Correspondence Modeling,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 259-266, Jun. 2003.
[10] C. H. Chen, T. Y. Chen, J. C. Lin, and D. J. Wang, “People Tracking in the Multi-Camera Surveillance System,” in Proceedings of IEEE International Conference on Innovations in Bio-inspired Computing and Applications, Shenzhen, China, pp. 1-4, Dec. 2011.
[11] S. Khan, O. Javed, Z. Rasheed, and M. Shah, “Human Tracking in Multiple Cameras,” in Proceedings of IEEE International Conference on Computer Vision, Vancouver, Canada, vol. 1, pp. 331-336, Jul. 2001.
[12] H. H. Hsu, W. M. Yang, and T. K. Shih, “People Tracking in a Multi-Camera Environment,” in Proceedings of IEEE Conference on Anthology, China, pp. 1-4, Jan. 2013.
[13] D. T. Lin and K. Y. Huang, “Collaborative Pedestrian Tracking with Multiple Cameras: Data Fusion and Visualization,” in Proceedings of Joint International Conference on Neural Networks, Barcelona, Spain, pp. 1-8, Jul. 2010.
[14] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd ed., Prentice Hall, Upper Saddle River, New Jersey, 2007.
[15] K. Yang, Y. Xiao, E. Wang, and J. Feng, “Mean-Shift Tracking Algorithm Based on Adaptive Fusion of Multi-Feature,” in Proceedings of SPIE Conference on Image Processing and Analysis, China, vol. 9675, Oct. 2015.
[16] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proceedings of Computer Vision and Pattern Recognition, San Diego, USA, vol. 1, pp. 886-893, June, 2005.
[17] H. Wu and Q. Zheng, “Self-Evaluation of Visual Tracking Systems,” in Proceedings of ASC Conference, Orlando, USA, Nov. 2004.