即時多重移動物體追蹤系統之設計

Design of Real-time Multiple-Object Tracking System

盧晨皓(Chen-Hao Lu)

指導教授 ： 王永鐘

國立臺北科技大學/電資學院/電機工程系所/碩士(2009年)

https://doi.org/10.6841/NTUT.2009.00191

摘要

在本論文我們提出可同時驅動多台攝影機之低運算量即時性移動物體追蹤系統。為了使系統適用於多雜訊之低階攝影設備，我們提出的方法以種抑制雜訊為首要考慮要件，同時為了即時追蹤移動物件，我們提出濾波型連續影像相減法（Filtering Temporal Differencing）和靜態彩色影像背景相減法（Static Color Background Subtraction），並以此兩種相差法進行交叉比對，另加上前遞式低通濾波器（One-Step Recursive Low-Pass Filter）與標記（Label）分類器進行多重移動物體追蹤。藉由實驗的結果證明我們所提的方法不但能有效抑制雜訊，同時能即時追蹤移動的物件。

關鍵字

時間差異法 ； 彩色背景相減法 ； 移動偵測 ； 動態追蹤

並列摘要

In this thesis, we proposed a real-time moving object tracking system which can simultaneously drive multiple cameras. As to used of low quality photographic equipments which have more noise, we presented several methods for noise suppression. In order to effectively search a real-time images of moving objects, the proposed tracking multiple moving objects system included Filtering Temporal Differencing, Static Color Background Subtraction, One-Step Recursive Low-Pass Filter, and Label classifier. The experiment results showed that the proposed tracking multiple moving objects system not only suppressed noise but also real-time tracking multiple moving object.

並列關鍵字

Temporal Differencing ； Static Color Background Subtraction ； Motion Detector ； Dynamic Tracking

參考文獻

[1] 許倫維，即時性連續手勢追蹤與辨識，碩士論文，國立臺北科技大學研究所，台北，2006。

[2] T. K. Kuo, A Robust Visual Servo Based Headtracker with Auto-Zooming in Cluttered Environment, Master's thesis, National Taiwan University, Taiwan, 2002.

[3] S. L. Dockstader and N. S. Imennov, "Prediction for Human Motion Tracking Failures," IEEE Transactions on Image Processing, vol. 15, no.2, 2006, pp. 411-421.

[5] I. Haritaoglu, D. Harwood and L. Davis, "W4: Who, When, Where, What: A Realtime System for Detecting and Tracking People," IEEE International Conference on Automatic Face and Gesture Recognition, 1998, pp. 222–227.

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