李忠謀顏百璋2019-09-052009-7-202019-09-052009http://etds.lib.ntnu.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=id=%22GN0696470318%22.&%22.id.&http://rportal.lib.ntnu.edu.tw:80/handle/20.500.12235/106726本研究提出一個適用於教學影片結構化與分析的方法，來提供使用者有效率地取得教學上的內容與知識，在不使用color-based 或 histogram-based的方法下，本研究提出一個edge-based的片段變化偵測演算法，來建立投影片切換時的結構，且可成功抵禦來自光線的影響，以及當影像中出現人或其他物體遮蔽投影片內容時，也可免於錯誤偵測的發生；當片段偵測階段完畢，本研究更進一步利用影片中講者的手勢以及聲音的資訊，來找尋講者欲強調內容在影像上的位置，分析探勘出教學重點，讓使用者更方便的學習。We present a lecture video structuring and analysis scheme to provide students an efficient way to access the lecture content. Instead of using color-based or histogram-based methodologies, we propose a new edge-based shot change detection algorithm to accurately rebuild the slide structure. The proposed approach can successfully resist the unwanted influences induced from the variant illumination condition and occlusions. Furthermore, the teaching focus is analyzed according to the location which the instructor points and the audio information so that this system becomes more useful for learning.教學影片片段變化偵測遮蔽物體偵測lecture videoshot change detectionocclusion object detection