以環場攝影機網及其資料融合從事一室內停車場內車輛追蹤

Omni-Directional Camera Networks and Data Fusion for Vehicle Tracking in an Indoor Parking Lot

蔡慶廷(Tsai Ching-Ting)

指導教授 ： 陳世旺

國立臺灣師範大學/理學院/資訊工程研究所/碩士(2004年)

摘要

一座智慧型停車場須具有快速引導車輛到空位停放、方便管理者管理、安全監控等等功能。其中車輛快速引導系統最能有效且直接的增加停車場的使用效率。然而，完整的車輛引導系統，必須建構一個完善的車輛追蹤系統之上，如何在停車場中建構出一個完善的車輛追蹤系統，便是本論文最主要的討論重點。
我們提出了一個以視訊為基礎的室內停車場追蹤系統，其中使用多個單一類型的三百六十度環場攝影機為視訊來源，同時監控整座停車場內車輛的移動路徑。並以分散式的架構，來達到即時追蹤車輛的目標。另外，利用接圖技術與相鄰攝影機畫面重疊所提供的資訊，調整攝影機在設置時，所產生的誤差。
本系統可以藉由增加環場攝影機的數目，擴大我們的監控範圍，相較於其他大範圍追蹤系統，有著更大的擴充彈性。實驗結果顯示，本系統能夠在模擬車場的環境中，正確的追蹤車輛，並紀錄車輛移動路徑。

關鍵字

環場攝影機 ； 大範圍追蹤系統 ； 停車場 ； 智慧型停車場

並列摘要

The vehicle guiding system is an important part of an intelligent parking lot system. It helps vehicles find a parking space more efficiently. In this paper, a vision-based tracking system designed for such a guiding system is purposed. This system can track vehicles over a wide space, and is easy to extend because only one kind of cameras is used.
This tracking system consists of a back-end element and many front-end elements. Foreground vehicles captured by the cameras are extracted by the front-end elements, and integrated by the back-end element. The whole monitoring image is constructed from the front-end elements by applying mosaicing, which also helps to adjust the setting of all cameras at the same time.
Compared with the other kinds of tracking systems, our system can more easily enlarge the monitoring area by adding cameras. The experimental results show that those vehicles moving in our parking system can be tracked exactly and can be integrated with the guiding system very well.

參考文獻

[Alt98] Y. Altunbasak, P. E. Eren and A. M. Tekalp, Region-Based Parametric Motion Segmentation Using Color Information, Graphical Models and Images Processing, vol. 60, no.1, pp.13-23, 1998.

[Cuc00] R. Cucchiara, M. Piccardi and P. Mello, Image Analysis and Rule-Based Reasoning for a Traffic Monitoring System, IEEE Trans. on Intelligent Transportation Systems, vol. 1, no. 2, pp. 119-130, June 2000.

[Ell02] T. Ellis, "Multi-camera Video Surveillance", Proceedings 36th Annual 2002 International Carnahan Conference on, Security Technology, pp. 228 – 233 Oct. 2002.

[Fat95] M. Fathy, M. Y. Siyal, Real-Time Image Processing Approach to Measure Traffic Queue Parameters, Proc. of IEE Conf. on Vision, Image and Signal Processing, vol. 142, no. 5, pp. 297-303, Oct. 1995.

[Fer98] J. M. Ferryman, S. J. Maybank and A. D. Worrall, Visual Surveillance for Moving Vehicles, Proc. of IEEE Workshop on Visual Surveillance, pp. 73 -80, 1998.