動態視訊之即時接圖系統

A real time image registration system for video sequences

鄒雯姍(Wen-Shan Tsou)

指導教授 ： 林啟芳

元智大學/資訊學院/資訊工程學系/碩士(2002年)

摘要

本論文擬提出一個影像接圖技術，來即時接合不同視訊來源之連續影像，成為一完整之視訊影像。此系統將可應用在大型監控系統即建立即時環場顯像系統。我們提出一種具有高接合效果的無特徵點影像接圖方法，對兩個具重疊區域之攝影機所拍攝支連續影像進行數次接圖並利用統計方式針對每次接圖所得之特徵點，過濾不夠穩定的特徵點，再利用所得之穩定的特徵點轉換成一精確的轉換矩陣，最後利用所得之轉換矩陣對此二部攝影機所設影像進行快速接圖，以達到即時接圖的效果。最後我們以實景影像來驗證所提方法的可行性。

關鍵字

影像接圖 ； 監視系統

並列摘要

An automatic registering system is presented in the paper, which can be utilized to register two sequences of video images. In a traditional security system, operators must pay their great attention on viewing scenes captured by cameras and displayed on monitors. The task is very hard especially when the number of cameras is large due to the discontinuity of the monitoring views. Another problem of the traditional system is that there will be places where the cameras cannot reach if the number of the camera installed in the system is few. In the paper, we develop methods to solve the above problems by registering the monitoring views together. The cameras used in this study are limited to two, but the concept can be easily modified to registering more than two camera views. The proposed method consists of the learning stage as well as the operation stage. In the first stage, the registering parameters and the transformation matrix are learned and stored in the table. In the latter stage, the registering process is in progress for registering the image sequences of the two cameras using the matrix created before. Experiments are arranged for demonstrating the feasibility of the proposed approach.

並列關鍵字

Image Registration ； Monitoring System ； Powell Search

參考文獻

[3] R. D. T. Janssen, and A. M. Vossepoel, “Compilation of mosaics from separately scanned line drawings,” Proceedings of the Second IEEE Workshop on Applications of Computer Vision, Netherlands, pp. 36-43, 1994.

[4] H. Li, B. S. Manjunath, and S. K. Mitra, “A contour-based approach to multisensor image registration,” IEEE Trans. Image Processing, Vol. 4, No. 3, pp. 320-334, March 1995.

[5] J. Flusser and T. Suk, “A moment-based approach to registration of images with affine geometric distortion,” IEEE Trans. on Geoscience and Remote Sensing, Vol. 32, No. 2, March, pp. 382-387, 1994.

[6] Q. Zheng and R. Chellapa, “A computational vision approach to image registration,” IEEE Trans. Image Processing, Vol. 2, No. 3, pp. 311-326, 1993.

[8] J. Flusser and T. Suk, “Affine moment invariants: a new tool for character recognition,” Pattern Recognition Letters, Vol. 4, pp. 433-436, April 1994.