使用樣板比對做進出口行人數量統計

A Passing People Counting System using Template Matching Technique

彭振軒(Chen-Hsuan Peng)

指導教授 ： 范國清

國立中央大學/資訊電機學院/資訊工程學系/碩士(2006年)

摘要

隨著取像設備價格大幅的降低，以及電腦科學的進步，以視覺為基礎的智慧型監控系統成為近年來熱門的研究主題。利用電腦視覺的方法，在不需要人為的操作之下，讓監控系統能夠自動對攝影機所擷取的影像進行分析，以具有偵測、追蹤及辨識的功能。而其好處，包括節省人力資源、降低成本和提供多樣化的服務。
本篇論文提出一個進出口人數統計的系統，是利用樣版比對的方式，判斷進出的物體是否為行人。首先利用背景相減法來找出前景物，接下來偵測部分，利用特徵比對的方式，辨識進出的行人，過濾其他的物體。最後則是利用追蹤來判定行人進出的方向，並統計各個方向的行人總數。
實驗部分是採用數段不同的行人進出影像，實驗結果顯示論文所提出的方法能準確且有效率的偵測並追蹤行人，達到統計進出人數的目的。

關鍵字

樣板比對 ； 行人統計 ； 距離轉換

並列摘要

With the price declining of capturing devices and the advancement of computer technologies recently, the topics of vision-based intelligent surveillance system have become more and more popular. Using the technique of computer vision without the needing of manual intervention, surveillance system can automatically analyze images captured by video camera to embed the functionalities of detection, tracking and identification. The advantages include saving human resources, saving cost and providing variety of services.
This thesis presents a passing people counting system using the method of template matching to identify whether the object moving into or out of the entrance is a pedestrian or not. Firstly, background subtraction is employed to find out moving objects. Secondly, feature matching is used to identify pedestrian and filter non-pedestrian objects in detection process. Lastly, tracking method is applied to recognize the direction of moving pedestrians, and the total numbers of two ways passing people is counted simultaneously.
Experiments were conducted on several passing people sequences. The results reveal that the proposed method can accurately and effectively detect and track pedestrians so as to successfully achieve the purpose of people counting.

並列關鍵字

template matching ； distance transform ； people counting

參考文獻

[2] T. Horprasert, D. Harwood and L.S. Davis, “A statistical approach for real-time robust background subtraction and shadow detection,” in Proc. IEEE Frame-Rate Workshop, 1999.

[3] B. Chen and Y. Lei, “Indoor and outdoor people detection and shadow suppression by exploiting HSV color information,” in Proc. IEEE Conf. Computer and Information Technology, pp.137-142, 2004.

[4] C. Stauffer and W.E.L. Grimson, “Adaptive background mixture models for real-time tracking,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, VOL. 2, pp.246-252, 1999.

[5] A.J. Lipton, H. Fujiyoshi and R.S. Patil, “Moving target classification and tracking from real-time video,” in Proc. IEEE Workshop Applications of Computer Vision, pp.8-14, 1998.

[6] G. Welch and G. Bishop, “An introduction to the Kalman Filter”.