• ETRI Journal
• /
• v.29 no.3
• /
• pp.353-362
• /
• 2007

In this paper, we propose a novel unsupervised video object extraction algorithm for individual images or image sequences with low depth of field (DOF). Low DOF is a popular photographic technique which enables the representation of the photographer's intention by giving a clear focus only on an object of interest (OOI). We first describe a fast and efficient scheme for extracting OOIs from individual low-DOF images and then extend it to deal with image sequences with low DOF in the next part. The basic algorithm unfolds into three modules. In the first module, a higher-order statistics map, which represents the spatial distribution of the high-frequency components, is obtained from an input low-DOF image. The second module locates the block-based OOI for further processing. Using the block-based OOI, the final OOI is obtained with pixel-level accuracy. We also present an algorithm to extend the extraction scheme to image sequences with low DOF. The proposed system does not require any user assistance to determine the initial OOI. This is possible due to the use of low-DOF images. The experimental results indicate that the proposed algorithm can serve as an effective tool for applications, such as 2D to 3D and photo-realistic video scene generation.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.646-654
• /
• 2007

In recent years, the use of text inserted into TV contents has grown to provide viewers with better visual understanding. In this paper, video text is defined as superimposed text region located of the bottom of video. Video text extraction is the first step for video information retrieval and video indexing. Most of video text detection and extraction methods in the previous work are based on text color, contrast between text and background, edge, character filter, and so on. However, the video text extraction has big problems due to low resolution of video and complex background. To solve these problems, we propose a method to extract text from videos using the Harris corner detector. The proposed algorithm consists of four steps: corer map generation using the Harris corner detector, extraction of text candidates considering density of comers, text region determination using labeling, and post-processing. The proposed algorithm is language independent and can be applied to texts with various colors. Text region update between frames is also exploited to reduce the processing time. Experiments are performed on diverse videos to confirm the efficiency of the proposed method.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.891-898
• /
• 2004

An effective video indexing is required to manipulate large video databases. Most algorithms for video indexing have been commonly used histograms, edges, or motion features. In this paper, we propose an efficient algorithm using the luminance projection for video retrieval. To effectively index the video sequences and to reduce the computational complexity, we use the key frames extracted by the cumulative measure, and compare the set of key frames using the modified Hausdorff distance. Experimental results show that the proposed video indexing and video retrieval algorithm yields the higher accuracy and performance than the conventional algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.6
• /
• pp.1175-1181
• /
• 2004

This paper proposes a system to analyze and summarize the video shots of baseball game TV program into fifteen categories. Our System consists of three modules: feature extraction, Hidden Markov Model (HMM) training, and video shot categorization. Video Shots belongs to the same class are not necessarily similar, so we require that the training set is large enough to include video shot with all possible variations to create a robust Hidden Markov Model. In the experiments, we have illustrated that our system can recognize the 15 different shot classes with a success ratio of 84.72%.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.747-759
• /
• 2018

In this paper, we implement viewport dependent tile partitioning for high quality 360 video transmission and rendering method to present a HMD (Head Mounted Display) screen for 360 video quality evaluation. As a method for high-quality video transmission based on a user's viewport, this paper introduces MCTS (Motion Constrained Tile Sets) technique for solving the motion reference problem and EIS (Extraction Information Sets) SEI including pre-configured tile information, and extractor that extracts tiles. In addition, it explains tile extraction method based on user's viewport and implementation contents of the method of expressing on an HMD. Therefore, if 360 video is transferred by the proposed implementation which only transfers video from the user viewport area, it is possible to express higher quality video with lower bandwidth while avoiding unnecessary image transmission.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.3
• /
• pp.103-110
• /
• 2008

This paper proposes an effective keyword extraction method for the Web videos. The proposed method classifies the Web video pages in one of 4 types. As such, we analyzed the structure of the Web pages based on the number of videos and the layout of the Web pages. And then we applied the keyword extraction algorithm fit to each page type. The experiment with 1,087 Web pages that have total 2,462 videos showed that the recall of the proposed extraction method is 18% higher than ImagerRover[2]. So, the proposed method could be used to build a powerful video search system for WWW.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.705-710
• /
• 2003

Recent years, as a rapid development of multimedia technology, video database system to retrieve video data efficiently seems to core technology in the oriented society. This thesis describes an efficient automatic frame detection and location method for content based retrieval of video. Frame extraction part is consist of incoming / outgoing car frame extraction and car number frame extraction stage. We gain star/end time of car video also car number frames. Frames are selected at fixed time interval from video and key frames are selected by color scale histogram and edge operation method. Car frame recognized can be searched by content based retrieval method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2006.11a
• /
• pp.257-260
• /
• 2006

In Video streaming environment, we must consider terminal and network characteristics, such as display resolution, frame rate, computational resource, network bandwidth, etc. The JVT (Joint Video Team) by ISO/IEC MPEG and ITU-TVCEG is currently standardizing Scalable Video Coding (SVC). This can represent video bitstreams in different sealable layers for flexible adaptation to terminal and network characteristics. This characteristic is very useful in video streaming applications. One fully scalable video can be extracted with specific target spatial resolution, temporal frame rate and quality level to match the requirements of terminals and networks. Besides, the extraction process is fast and consumes little computational resource, so it is possible to extract the partial video bitstream online to accommodate with changing network conditions etc. With all the advantages of SVC, we design and implement a network-adaptive SVC streaming system with an SVC extractor and a streamer to extract appropriate amounts of bitstreams to meet the required target bitrates and spatial resolutions. The proposed SVC extraction is designed to allow for flexible switching from layer to layer in SVC bitstreams online to cope with the change in network bandwidth. The extraction is made in every GOP unit. We present the implementation of our SVC streaming system with experimental results.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.75-81
• /
• 2023

Video platforms, including YouTube, have a structure in which the number of video views is directly related to the publisher's profits. Therefore, video publishers induce viewers by using provocative titles and thumbnails to garner more views. The conventional technique used to limit such harmful videos has low detection accuracy and relies on follow-up measures based on user reports. To address these problems, this study proposes a technique to improve the accuracy of filtering harmful media using thumbnails, titles, and audio data from videos. This study analyzed these three pieces of multimodal information; if the number of harmful determinations was greater than the set threshold, the video was deemed to be harmful, and its upload was restricted. The experimental results showed that the proposed multimodal information extraction technique used for harmfulvideo filtering achieved a 9% better performance than YouTube's Restricted Mode with regard to detection accuracy and a 41% better performance than the YouTube automation system.

• The KIPS Transactions:PartB
• /
• v.13B no.5 s.108
• /
• pp.515-524
• /
• 2006

Background extraction is an important technique to find the moving objects in video surveillance system. This paper proposes a new on-line background extraction method for color video using vector order statistics. In the proposed method, using the fact that background occurs more frequently than objects, the vector median of color pixels in consecutive frames Is treated as background at the position. Also, the objects of current frame are consisted of the set of pixels whose distance from background pixel is larger than threshold. In the paper, the proposed method is compared with the on-line multiple background extraction based on Gaussian mixture model(GMM) in order to evaluate the performance. As the result, its performance is similar or superior to the method based on GMM.