多相機環境下之車輛監控與停車管理系統

Vision-based Vehicle Surveillance and Parking Management using Multiple Cameras

吳智軒(Chih-Hauan Wu)

指導教授 ： 賴薇如

共同指導教授 ： 謝君偉

元智大學/電機通訊學院/電機工程學系/碩士(2009年)

摘要

監控系統已經廣泛地被應用在許多地方，例如：停車場、校園、住宅區等。在這些大範圍的環境之中，要追踨物體是沒辦法用單一攝影機就完成的，必須要聯結不同相機之間的對應關係，才能取得足夠的場景資訊。
在本系統建立在四個靜止不動的攝影機下，由於每台攝影機都有與其他攝影機重疊的地方，所以透過仿射變換來聯結四個攝影機所擷取的畫面，形成一個大場景。特別是本論文探討當照片資料是由網路監控攝影機取得的情況下，因為每台攝影機的畫面擷取速率不一樣，要如何進行同步的動作。本論文主要分成兩部份，包括車輛監控與停車管理，在車輛監控方面，我們先針對攝影機內的畫面透過背景相減取得前景物。記錄每個前景物的資訊，如顏色、位置、移動方面等，再於每張影像中，比較每個前景物的相似度，依此做追踨。在停車管理方面，我們記錄地板顏色的資訊，針對停車格內屬於地板的部份進行比對，並依據邊緣的數量來判斷停車格內是否有車。
由實驗結果得知，我們的系統可以適用於許多不同條件底下，並且有很好的表現。

關鍵字

停車場 ； 車輛監控 ； 多相機

並列摘要

Surveillance system has been used in many places, such as parking lots, campuses and residential areas. In these big environments, it is impossible to track objects by one single camera. So, several cameras are necessary to catch pictures and we should connect the relation among these cameras. In this system, there are four static cameras. The affine transform can be used to connect the four cameras which have overlap regions between cameras. Therefore, it can be wide scene. The data is obtained by internet protocol cameras. Because the frame rates are different in each camera, it should do the camera synchronization. There are two parts, vehicle surveillance and parking managed, studied in this thesis. In vehicle surveillance, the background subtraction is applied to extract different foreground objects from images. Then, the color, position and motion information of the objects are recorded. It can track objects by comparing with the similarity of objects in every image. In parking management, the information of floor color are recorded and compared with the parking spaces. By judging the quantity of edge, we can determine whether the parking spaces are vacant. Experimental results reveal that our system works well in several different conditions.

並列關鍵字

parking lot ； vehicle surveillance ； multiple cameras

參考文獻

[1]Jun-Wei Hsieh, “Fast Stitching Algorithm for Moving Object Detection and Mosaic Construction,” Proceedings of International Conference on Multimedia and Expo, pp.I-85-8, Jul. 2003.

[2]Q. Wu, C. C. Huang, S. Y. Wang, W. C. Chiu, and T. H. Chen, “Robust Parking Space Detection Considering Inter-Space Correlation,” IEEE International Conference on Multimedia and Expo, pp. 659-662, Jul. 2007.

[3]C.C. Huang, S. J. Wang, Y. J. Chang, and T. Chen, “A Bayesian Hierarchical Detection Framework for Parking Space Detection,” IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2097-2100, Apr. 2008

[4]Y. Wang, “Real-Time Moving Vehicle Detection With Cast Shadow Removal in Video Based on Conditional Random Field,” IEEE transactions on Circuits and Systems for Video Technology, vol. 19, no. 3, pp. 437-441, Mar. 2009.

[7]B. Leibe, K. Schindler, N. Cornelis, and L. V. Gool, “Coupled Object Detection and Tracking from static cameras and moving vehicles,” IEEE transactions on Pattern Analysis and Machine intelligence, vol. 30, no. 10, pp1683-1698, Oct. 2008.