臺灣博碩士論文加值系統

智慧型影像監控與辨識系統依其功能不同，分別被運用在日常生活的各式範疇。例如：運用於交通管理方面的影像式車輛偵測系統、一般安全警戒方面的大樓入侵偵測系統及安全辨識方面的人臉辨識系統…等。而本論文研究的主要重點，為設計演算法與搭配國產低價位攝影機，以取代目前進口高價位的影像式車輛偵測系統。
本論文利用國產低價位固定攝影機擷取即時連續影像，並設計一套有效的漸進式背景分類擷取演算法，在短時間內將背景影像分離。後續進入系統之影像，除利用影像與背景的差異將移動物件切割出來外，並同時利用所切割出之移動物件來更新原背景影像，使系統背景能長時穩定與適應光線的變化。移動物件自輸入影像中被切割出來後，再以視覺車長及車寬的計算對其特徵進行交疊切割與辨識。本論文所提出的演算法，能有效克服系統長時運行所遇之光線變化及複雜的交疊切割問題，大大降低系統硬體建置成本，同時藉由各種道路環境的長時實測結果，驗證了所提之方法的強健性、準確性與即時性。

Capabilities of a video-based monitoring and recognizing system can be applied to many categories, for example vision-based vehicle detection system of traffic management, intrusion detection system of security and face recognition access control system of biometrics etc. This thesis proposes an algorithm with a low-cost camera by Taiwan to replace high-priced imports of vision-based vehicle detection system.
We propose an algorithm to extract initial color backgrounds from surveillance videos using a probability-based background extraction algorithm. With the proposed algorithm, the initial background can be extracted accurately and quickly, while using relatively little memory. The intrusive objects can then be segmented quickly and correctly by a robust object segmentation algorithm. The segmentation algorithm analyzes the threshold values of the background subtraction from the prior frame to obtain good quality and update while minimizing execution time and maximizing detection accuracy. The segmentation and recognition method uses the length, width, and roof size to classify vehicles, even when occlusive vehicles are continuously merging from one frame to the next. The segmented objects can be recognized and counted in accordance with their varying features, via the proposed recognition and tracking methods. The color background images can be extracted efficiently and quickly from color image sequences and updated in real time to overcome any variation in illumination conditions. Experimental results for various environmental sequences and weather conditions are provided to demonstrate the robustness, accuracy, effectiveness, and memory economy of the proposed algorithm.

誌謝 ii
摘要 iii
ABSTRACT iv
目錄 v
表目錄 vii
圖目錄 viii
1、 緒論 1
1.1 研究背景與目的 1
1.2 影像式車輛偵測系統的發展現況 2
1.3 論文架構 16
2、 系統概述 17
2.1 硬體架構 17
2.2 硬體設備 18
2.3 系統流程 19
3、 文獻回顧 20
4、 移動物件偵測 24
4.1 機率式背景擷取 24
4.2 物件切割與背景更新 33
5、 移動車輛辨識 38
5.1 視覺長度計算 38
5.2 車輛辨識 42
5.2.1 水平邊緣偵測與量化分析 42
5.2.2 車輛外型量測 43
5.3 車輛追蹤演算法 45
6、 交疊車輛偵測與切割 47
7、 實驗結果與討論 53
7.1 長時測試實驗環境介紹 53
7.2 系統移動物件偵測效能比較 59
7.2.1 記憶體需求與運算時間 59
7.2.2 不同環境適應性 63
7.2.3 切割品質評估 67
7.3 系統長時測試 68
7.4 未來研究方向 75
參考文獻 76
附錄A 80

參考文獻
[1] http://www.autoscope.com/。
[2] http://www.iteris.com/。
[3] http://www.keona.co.kr。
[4] http://www.peek-traffic.com/index.html。
[5] http://www.citilog.fr/index_en.php & http://www.sunsky.com.tw/。
[6] http://www.traficonasia.com/。
[7] Hi, A. H. S. and Yung, N. H. C., “A Fast and Accurate Scoreboard Algorithm for Estimating Stationary Backgrounds in an Image Sequence,” Proceedings of the IEEE Symp. Circuits and Systems, Vol. 4, No. 31, pp. 241–244, June 1998.
[8] Pang, C. C. C., Lam, W. W. L., and Yung, N. H. C., “A Novel Method for Resolving Vehicle Occlusion in a Monocular Traffic-Image Sequence,” IEEE Trans. Intelligent Transportation Systems, Vol. 5, No. 3, pp. 129–141, Sept. 2004.
[9] Pang, C. C. C., Lam, W. W. L., and Yung, N. H. C., “A Method for Vehicle Count in the Presence of Multiple-Vehicle Occlusions in Traffic Images,” IEEE Trans. on Intelligent Transportation Systems, Vol. 8, No. 3, pp. 441–459, Sept. 2007.
[10] Pang, C. C. C., Lam, W. W. L., and Yung, N. H. C., “Vehicle-Component Identification Based on Multiscale Textural Couriers,” IEEE Trans. on Intelligent Transportation Systems, Vol. 8, No. 4, pp. 681–694, December 2007.
[11] Ikeda, H., Kaneko, Y., Matsuo, T., and Tsuji, K., “Abnormal Incident Detection System Employing Image Processing Technology,” Proceedings of the IEEE/IEEJ/JSAI Conf. Intelligent Transportation Systems, pp. 748–752, October 1999.
[12] Kamijo, S., Matsushita, Y., Ikeuchi, K., and Sakauchi, M., “Traffic Monitoring and Accident Detection at Intersections,” IEEE Trans. Intelligent Transportation Systems, Vol. 1, No. 2, pp. 108–118, June 2000.
[13] Arth, C., Bischof, H., and Leistner, C., “TRICam—An Embedded Platform for Remote Traffic Surveillance,” Proceedings of the Computer Vision and Pattern Recognition Workshop Conf. Digital Object Identifier, pp. 125–133, June 2006.
[14] Tseng, B. L., Lin, C. Y., and Smith, J. R., “Real-Time Video Surveillance for Traffic Monitoring Using Virtual Line Analysis,” IEEE International Conference on Multimedia and Expo, Vol. 2, pp. 541- 544, August, 2002.
[15] Kim, Z. and Malik, J., “Fast Vehicle Detection with Probabilistic Feature Grouping and Its Application to Vehicle Tracking,” Proceedings of the IEEE Conf. Computer Vision, Vol. 1, pp. 524–531, 2003.
[16] Hsieh, J. W., Yu, S. H., Chen, Y. S., and Hu, W. F., “Automatic Traffic Surveillance System for Vehicle Tracking and Classification,” IEEE Trans. Intelligent Transportation Systems, Vol. 7, No. 2, pp. 175–187, June 2006.
[17] Wixson, L., “Detecting Salient Motion by Accumulating Directionary-Consistent Flow,” IEEE Trans. Pattern Anal. Machine Intell., Vol. 22, pp.774–780, Aug. 2000.
[18] Dailey, D. J., Cathey, F. W., and Pumrin, S., “An Algorithm to Estimate Mean Traffic Speed Using Uncalibrated Cameras,” IEEE Trans. Intelligent Transportation Systems, Vol. 1, No. 2, pp. 98–107, June 2000.
[19] Cucchiara, R., Piccardi, M., and Mello, P., “Image Analysis and Rule-Based Reasoning for a Traffic Monitoring System,” IEEE Trans. Intelligent Transportation Systems, Vol. 1, No. 2, pp. 119–130, June 2000.
[20] Stauffer, C. and Grimson, W. E. L., “Adaptive Background Mixture Models for Real-Time Tracking,” Proceedings of Computer Vision and Pattern Recognition, Vol. 2, pp.246–252, 1999.
[21] Stauffer, C. and Grimson, W. E. L., “Learning Patterns of Activity Using Real-Time Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 22, No. 8, pp.747–757, Aug. 2000.
[22] Vceraraghavan, H., Masoud, O., and Papanikolopoulos, N., “Vision-Based Monitoring of Intersections,” Proceedings of the IEEE Conf. Intelligent Transportation System, pp.7–12, 2002.
[23] Zang, Q. and Klette, R., “Robust Background Subtraction and Maintenance,” Proceedings of the IEEE Conf. on Pattern Recognition, Vol. 2, pp. 90–93, Aug. 2004.
[24] Tian, Y. L., Lu, M., and Hampapur, A., “Robust and Efficient Foreground Analysis for Real-Time Video Surveillance,” Proceedings of the IEEE Computer Vision and Pattern Recognition, Vol. 1, pp. 1182–1187, 2005.
[25] Wang, H. and Suter, D., “A Re-Evaluation of Mixture-of-Gaussian Background Modeling,” Proceedings of the IEEE Conf. on Acoustics, Speech, and Signal Processing, Vol. 2, pp. 1017–1020, Mar. 2005.
[26] Dickinson, P. and Hunter, A., “Scene Modelling Using an Adaptive Mixture of Gaussians in Colour and Space,” Proceedings of the IEEE Advanced Video and Signal Based Surveillance, pp. 64–69, Sept. 2005.
[27] Teixeira, L. F. and Corte-Real, L., “Cascaded Change Detection for Foreground Segmentation,” Proceedings of the IEEE Workshop Motion and Video Computing, pp. 6–13, Feb. 2007.
[28] Li, L., Huang, W., Gu, I. Y. H., and Tian, Q., “Statistical Modeling of Complex Backgrounds for Foreground Object Detection,” IEEE Trans. Image Processing, Vol. 13, No. 11, pp. 1459–1472, Nov. 2004.
[29] Huang, S. S., Fu, L. C., and Hsiao, P. Y., “Region-Level Motion-Based Background Modeling and Subtraction Using MRFs,” IEEE Trans. Image Processing, Vol. 16, No. 5, pp. 1446–1456, May 2007.
[30] Chien, S. Y., Ma, S. Y., and Chen, L. G., “Efficient Moving Object Segmentation Algorithm Using Background Registration Technique,” IEEE Trans. Circuits and System for Video Technology, Vol. 12, No. 7, pp. 577–586, July 2002.
[31] Chien, S. Y., Huang, Y. W., Hsieh, B. Y., Ma, S. Y., and Chen, L. G., “Fast Video Segmentation Algorithm with Shadow Cancellation, Global Motion Compensation, and Adaptive Threshold Techniques,” IEEE Trans. Multimedia, Vol. 6, No. 5, pp. 732–748, Oct. 2004.
[32] Foresti, G. L., Murino, V., and Regazzoni, C., “Vehicle Recognition and Tracking from Road Image Sequences,” IEEE Transactions on Vehicular Technology, Vol. 48, No. 1, pp. 301–318, Jan. 1999.
[33] Limin, X., “Vehicle Shape Recovery and Recognition Using Generic Models,” Proceedings of the 4th World Congress on Intelligent Control and Automation, pp. 1055–1059, Feb. 2002.
[34] Wei, W., Zhang, Q., and Wang, M., “A Method of Vehicle Classification Using Models and Neural Networks,” Proceedings of the IEEE Conf. on Vehicular Technology, Vol. 4, pp. 3022–3026, 2001.
[35] Song, X. and Nevatia, R., “A Model-Based Vehicle Segmentation Method for Tracking,” Proceedings of the IEEE International Conference on Computer Vision, Vol. 2, pp. 1124–1131, 2005.
[36] Wren, C. R., Azarbayejani, A., Darrell, T., and Pentland, A. P., “Pfinder: Real-Time Tracking of the Human Body,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 780–785, July 1997.
[37] Bevilacqua, A., “Effective Shadow Detection in Traffic Monitoring Applications,” Journal of WSCG, Vol. 11, No. 1, pp. 57–64, Feb. 2004.
[38] Canny, J., “Finding Edges and Lines in Images,” Technical Report, AITR-720, M.I.T Artificial Intelligence Laboratory, 1983.
[39] http://perception.i2r.a-star.edu.sg/bk_model/bk_index.html。
[40] http://www.cipr.rpi.edu/resource/sequences/qcif.html。