與亮度無關之即時移動偵測系統

Real Time Change Detection Method under Time-Varying Illumination

黃國烜(Kuo-Hsuan Huang)

指導教授 ： 林啟芳

元智大學/資訊學院/資訊工程學系/碩士(2006年)

https://doi.org/10.6838/YZU.2006.00212

摘要

科技日新月異，對傳統攝影機監控系統的影響，也漸漸的數位電腦化，資訊數位化的好處在於可以很容易的對影片分析，例如移動物體的偵測、物體辨識等。
本論文的主要目的是在攝影監控系統中提出一套與亮度無關物件追蹤的方法，可以在光線昏暗不足的環境下做移動偵測，其中目的在於發展一個更聰明的監控機制，在有限的環境下得到更多的資訊，本論文的移動偵測的方法，是把影像分割成小區塊，分別計算各區塊質心來偵測移動物體，我們以影像動差(Moment)的特性，有效的克服光線不足下的移動偵測。

關鍵字

移動偵測 ； 動差

並列摘要

With increasing advancing of pervasive computer and information technology, the traditional surveillance system is moving toward to digitization. The benefit of the digitization of surveillance system are analyzing image data easily and fast for some purposes such as "Change Detection" and " Recognition of object" in image.
The goal of this study is to provide a method for tracking object regardless of luminance, in other words, the proposed method will detect the moving object in the circumstance with insufficient light and dim, and by retrieve additional information under the light limited environment then we can develop a more smart mechanism for surveillance system usage. We cut single image frame in several small blocks for computing corresponding "Moment value" to each block. We leverage the characteristic of "Image Moment" to approach an effective moving detecting method under insufficient light environment. Finally, we an application to prove our method can detect moving object fast and precisely under the insufficient light environment.

並列關鍵字

Change Detection ； Moment

參考文獻

[2] Yakoub Bazi, Lorenzo Bruzzone, and Farid Melgani, “An unsupervised approach based on the generalized gaussian model to automatic change detection in multitemporal SAR images,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 43, No. 4, pp. 874-887, April 2005.

[4] Daniel J. Dailey and L. Li, “An algorithm to estimate vehicle speed using un-calibrated cameras, intelligent transportation systems,” in Proceedings 1999 IEEE/IEEJ/JSAI International Conference, pp. 441-446, 1999.

[5] Çi˘gdem Ero˘glu Erdem, Bülent Sankur, and A. Murat Tekalp, “Performance measures for video object segmentation and tracking,” IEEE Transactions on Image Processing, Vol. 13, No. 7, pp. 937-951, July 2004.

[6] Aishy Amer, “Voting-Based simultaneous tracking of multiple video objects,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 15, No. 11, pp. 1448-1462, November 2005.

[7] Emrullah Duruca and touradj Ebrahimi, “Change detection and background extraction by linear algebr,” Proceedings of the IEEE, Vol. 89, No. 10, pp. 1368-1381, October 2001.