- 學位論文
與亮度無關之即時影像移動偵測與追蹤方法
A Real Time Motion Detection and Target Tracking Methods under Time-Varying Illumination
若您是本文的作者，可授權文章由華藝線上圖書館中協助推廣。
摘要
本論文的目的在於利用固定背景下的即時影像，建立一個與亮度無關的移動物影像追蹤系統。首先分成移動物件的偵測與物件追蹤兩部分，在移動偵測方面，運用影像處理的技術建立目前影像環境的背景影像，利用影像處理動差（Moment）的特性及統計檢定的法則處理目前影像與背景影像的差異，消除雜訊，及門檻值的求取，將移動物件與背景分離；在物件追蹤方面，利用卡門濾波器（Kalman Filter）的特性追蹤及預測移動物件。本論文所提出方法之特色：是在影像經過任何前置處理之前先進行移動偵測的好處在於可減少所處理原始影像資料的數量；再利用簡化的卡門濾波器更有效率的追蹤及預測移動物件。實驗結果將顯示所提方法之可行性。
並列摘要
The purpose of this thesis is using the real-time image of fixed background to build up a motion object tracking system which is not related with the variation of illumination. This system consists of two phases, i.e., the phase of motion object detection and the phase of tracking. In the first phase, the motion object is extracted by noticing the differences between the current and the background images. The techniques involved include the calculation of the moment and the statistical hypothesis testing. In the second phase, the method of Kalman Filter is adopted to track and predict the positions of moving object. In addition, the process of the Kalman Filter is simplified so as to greatly reduce the processing time and satisfy the requirement of real-time process. Finally, the experimental results reveals the feasibility of the proposed method.
參考文獻
[6] D. Han, C. Y. Shih, S. J. Choi, and J. S. Park, “A motion adaptive 3-D de-interlacing algorithm based on the brightness profile pattern difference,” IEEE Transactions on Consumer Electronics, Vol. 45, No. 3, pp. 690-696, 1999.
[8] 游世豪,與陳永盛博士 “交通監控系統之研究, ”元智大學電機工程研究所碩士論文, 2002.
[10] S. N. Jayaramamurthy and R. Jain, “An approach to the segmentation of textured dynamic scenes,” Computer Vision, Graphics and Image Processing, Vol. 21, pp. 239-261, 1983.
[12] Y. Z. Hsu, H. H. Nagel, and G. Refers, “New likelihood test methods for change detection in image sequence,” Computer Vision, Graphics and Image Processing, Vol. 26, pp. 73-106, 1984.
[13] K. Skifstad and R. Jain, “Illumination independent change detection from real world image sequences,” Computer Vision, Graphics and Image Processing, Vol. 46, pp. 387-399, 1989.