http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
박한엽,최연성 群山大學校 情報通信技術硏究所 1998 情報通信技術硏究論文集 Vol.2 No.-
Development of various multimedia applications depend on fast and efficient archiving, browsing, retrieval techniques. A number of techniques have approached about only pixel domain analysis until now. This approach brought about the costly overhead of decompressing because most of multimedia data is typically stored in compressed format. Generally given compressed video data, we can analyze the compressed data directly, and then avoid the costly overhead such as in pixel domain. In this paper, we analyze the information of compressed video stream directly, and then extract the available features for video indexing. We have derived the technique for cut detection using these features, and the stream is devided into shots. Also we propose new brief key frame selection technique and efficient video indexing method using spatial information(DCT cofficients) and temporal information(motion vectors).
MPEG 비디오 데이터를 이용한 움직이는 물체 추출 방법
김선우,최연성,박한엽 군산대학교 정보통신기술연구소 2000 情報通信技術硏究論文集 Vol.4 No.-
In this paper, we describe a method of moving object extraction directly using MPEG video data. Since motion information in MPEG coded data is determined in terms of coding efficiency point of view, it does not always provide real motion information of objects. We use a wide variety of coding information including motion vectors and DCT coefficients to estimate real object motion. Since such information can be directly obtained from coded bitstream, very fast operation can be expected. But, this bitstream have don't need noise because of illumination and H/W feature. In this paper, we proposed that the method is using median operator to exclude noise. Moving object are detected basically analyzing motion vectors and spatio-temporal correlation of motion in P- and B-Pictures. The simulation results show that successful moving object detection has been performed on MB level using several test sequences. Since proposed method is very simple and requires much less computational power than the conventional object detection methods, it has a significant advantage as motion analysis tool.