• The Journal of Engineering Research
• /
• v.3 no.1
• /
• pp.107-116
• /
• 1998

Video data are retrieved and stored in various compressed forms according to their characteristics. In this paper, we present a generic data model that captures the structure of a video document and that provides a means for indexing a video stream. Using this model, we design and implement CVIMS (the MPEG-2 Compressed Video Information Management System) to store and retrieve video documents. CVIMS extracts I-frames from MPEG-2 TS files, selects key-frames from the I-frames, and stores in database the index information such as thumbnails, captions, and picture descriptors of the key-frames. And, CVIMS retrieves MPEG-2 video data using the thumbnails of key-frames and various labels of queries. And also, the system is accessible by a web interface.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1023-1026
• /
• 2002

In this paper, we propose an efficient transcoding of MPEG video. Transcoding is the process of converting a compressed video format to another different compressed video format. We propose an simple and efficient transcoding by requantization in which MPEG coded video at high bit-rate is converted into MPEG bitstream at lower bit-rate. To reduce a image quality degradation, we use HVS(Human Visual System) that is the effect that visibility of noise is less in high activity regions than in low activity regions. By using the effect, the part of image in high activity region is coarsely quantized without seriously degrading the image quality. Experimental results show that the proposed method can provide good performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.8A
• /
• pp.836-845
• /
• 2002

Video summary is one of the tools which can provide the fast and effective browsing for a lengthy video. Video summary consists of many key-frames that could be defined differently depending on the video genre it belongs to. Consequently, the video summary constructed by the uniform manner might lead into inadequate result. Therefore, identifying the video genre is the important first step in generating the meaningful video summary. We propose a new method that can classify the genre of the video data in MPEC compressed bit-stream domain. Since the proposed method operates directly on the compressed bit-stream without decoding the frame, it has merits such as simple calculation and short processing time. In the proposed method, only the visual information is utilized through the spatial-temporal analysis to classify the video genre. Experiments are done for 6 genres of video: Cartoon, commercial, Music Video, News, Sports, and Talk Show. Experimental result shows more than 90% of accuracy in genre classification for the well -structured video data such as Talk Show and Sports.

• Journal of KIISE:Information Networking
• /
• v.27 no.2
• /
• pp.109-122
• /
• 2000

As the full-motion videos in MPEG are widely available nowadays, an editor that could easily edit such kind of media data is required to develop various multimedia applications. In order to concatenate and apply a transition effect to two video streams encoded in MPEG, they should be decoded first since there are dependencies in the frames in MPEG-encoded video stream. Since this decode-edit-encode process requires a huge amount of computing/storage resources, a new editing scheme that could apply various transition effects to MPEG video streams directly while keeping the quality of video data is strongly required. This paper proposes a new editing scheme that could apply three transition effects (such as fade-in, fade-out, and dissolve) to MPEG video streams in a compressed domain. In the proposed scheme, an extension of previous method in which the frames are partially decompressed and transition effects are applied is adopted for I- and P-frames. In addition, a new processing scheme for B-frame that could apply the transition effects in DCT domain directly using an approximation of motion compensation based on the motion vector to reference frames. Since this processing scheme could apply the transition effects in a compressed domain directly, the editing process could be speed-up about $3{\sim}4$ times faster than previous decode-edit-encoding method while keeping the quality of video data as good as the source data. The proposed scheme could be used to build a software-only MPEG video editing system that helps to edit MPEG video data even on a low-cost desk-top computer.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.157-160
• /
• 2002

Scene change detection is the fundamental process of automatic video indexing and retrieving. In this paper we propose a method which utilizes both compressed and uncompressed domain methods to detect scene change in a video. Candidate locations for scene change are estimated from DC images and motion vector information in compressed domain. And candidate frames are verified using edge histogram distance and color histogram distance, in uncompressed domain. The experimental results show that scene change can be detected fast and correctly by proposed method.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.10
• /
• pp.156-165
• /
• 1998

In this paper, the hybrid algorithm for the scene change detection of MPEG-based compressed video data is proposed. There have been two methods to detect scene changes of video data compressed using algorithms such as MPEG or motion-JPEG: analyzing the compressed data directly, and analyzing from the retrieved data. The former has the advantage of taking less time, while the latter can obtain detail results at the expense of time and memory. Thus by combining each algorithm we detect cuts from compressed sequence, retrieve data for some selected region, and detect gradual scene changes. Simulation results verify the superiorities of the proposed algorithm in analyzing time and accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.6
• /
• pp.1370-1378
• /
• 1996

A subjective video quality assessment methods are proposed based on CCIR Rec. 500-5 for an evaluation and testing of compressed video quality and performance of video codec to be designed in accordance with the MPEG-2 MP ML specification which is adapted as a DTV standard for Korea digital DBS. Video sequence compressed in compliance with MPEG-2 MP ML encoding parameterswastested by the proposed video quality evaluation procedure. Test sequence were compressed at the bit rate 6Mbps, 7.5Mbps and 9Mbps, repectively. Test results of the 7.5Mbps bitrate showed a satisfactory picture quality at about 4.0 on the 5.0 absolute scale of ITU-R 500-5.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.859-862
• /
• 1998

Many playback methods of MPEG-1 video were developed and are have beendeveloped now. But nomal playback method demands great time. In this paper we designed and implemented the scene transition playback method of the MPEG-1 video data. The previous studies of scene transition playback have used to the DC or edge information after decoding process of picture. In this paper, scene transition is detected by macroblock information from MPEG-1 compressed area, then decodes and playbacks the only scene transition picture. This MPEG-1 video player was implemented by decoding control. So it is possible to add special playback method to MPEG-1 video player. As the result, which is proposed in this paper the scene transition method can minimize to decoding calculation and decrease to playback time of the MPEG-1 video data.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.11
• /
• pp.3566-3575
• /
• 2000

In this paper, we propose an simple and efficient method to estunate the camera operation by using compressed information, which is extracted diracily from MPEG2 stream without complete decoding. In the method, the motion vector is converted into approximate optical flow by using the feature of predicted frame, because the motion vector in MPEG2 video stream is not regular sequene. And they are used to estimate the camera operation, which consist of pan, and zoom by Hough transform technique. The method provided better results than the least square method for video stream of basketball and socer games. The proposed method can have a reduced computational complexity because the information is directiv abtained in compressed domain. Additionally it can be a useful technology in content-based searching and analysis of video information. Also, the estimatd cameral operationis applicable in searching or tracking objects in MPEG2 video stream without decoding.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.27-34
• /
• 2004

This paper proposes a method to trace and interpret a moving object based on the information which can be directly obtained from MPEG-2 compressed video stream without decoding process. In the proposed method, the motion flow is constructed from the motion vectors included in compressed video. We calculate the amount of pan, tilt, and zoom associated with camera operations using generalized Hough transform. The local object motion can be extracted from the motion flow after the compensation with the parameters related to the global camera motion. Initially, a moving object to be traced is designated by user via bounding box. After then automatic tracking Is performed based on the accumulated motion flows according to the area contributions. Also, in order to reduce the cumulative tracking error, the object area is reshaped in the first I-frame of a GOP by matching the DCT coefficients. The proposed method can improve the computation speed because the information can be directly obtained from the MPEG-2 compressed video, but the object boundary is limited by macro-blocks rather than pixels. Also, the proposed method is proper for approximate object tracking rather than accurate tracing of an object because of limited information available in the compressed video data.