摘要
有別於傳統利用差異影像(difference image)，本文利用比率影像(ratio image)來偵測影像序列(image sequence)中的移動物體。由於利用比率影像比起傳統的差異影像較能排除因照度所產生之雜訊，因此利用它來偵測影像序列中的移動物體，將具有較高之準確性。除此之外，我們也運用了索貝爾運算子(Sobel operator)來增強比率影像。然後運用累計直方圖(cumulative histogram)單調遞增之特性來決定適當的門檻值。最後利用此門檻值來偵測影像序列中之移動物體。本論文所提出的方法相較於傳統利用影像相減之後，再從每張影像的直方圖決定門檻值的方法，具有更高品質及完整性，而且從實驗結果來看，偵測結果亦維持有一定之水準。
並列摘要
Motion detection is a useful method in many image processing and computer vision applications. Traditional background subtraction where the classification of pixels into motion pixels and background pixels is based on thresholding the difference image between background image and current image. However, background subtraction has easy been influenced by illumination especially in dark scene. In this paper, we present a simple and robust motion detection method based on ratio image. It can detect motion object not only in bright scene but also in dark scene. We also use of Sobel operator to enhance ratio image contrast that can easy refine motion object features and use of cumulative histogram to select a threshold. Experimental results show that the proposed method has efficiency and illumination tolerance in image sequence.