• Journal of the Korea Society of Computer and Information
• /
• v.18 no.11
• /
• pp.77-86
• /
• 2013

In this paper, we propose a fast video retargeting method which preserves the contents of a video and converts the image size. Since the conventional Seam Carving which is the well-known content-aware image retargeting technique uses the dynamic programming method, the repetitive update procedure of the accumulation energy is absolutely needed to obtain seam. The energy update procedure cannot avoid the processing time delay because of many operations by the image full-searching. By applying the proposed method, frames which have similar features in video are classified into a scene, and the first frame of a scene is resized by the modified Seam Carving where multiple seams are extracted from candidate seams to reduce the repetitive update procedure. After resizing the first frame of a scene, all continuous frames of the same scene are resized with reference to the seam information stored in the previous frame without the calculation of the accumulation energy. Therefore, although the fast processing is possible with reducing complexity and without analyzing all frames of scene, the quality of an image can be analogously maintained with an existing method. The experimental results show that the proposed method can preserve the contents of an image and can be practically applied to retarget the image on real time.

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.823-835
• /
• 2006

Multimedia is a very popular service in the Internet. But, we cannot provide multimedia service at a uniform content, because networks and devices are various. Thus, an adaptive service is needed for multimedia transmission. Video Transcoding is the good solution that can service multimedia adaptively. This paper proposes the streaming system that is composed of encoder, transcoder, decoder The encoder enhanced time complexity and PSNR in case of transcoding using PP(Prediction Period). The decoder is almost same as the traditional media player. Transcoder reduced time complexity through combination of prediction period in encoder and skipping period to control frame rate in transcoder. In simulation results, the performances of proposed scheme outperform the system with traditional transcoder in time complexity and PSNR.

• Journal of Broadcast Engineering
• /
• v.14 no.6
• /
• pp.661-675
• /
• 2009

The carelessly and illegally copied contents are raising serious social problem as internet and multimedia technologies are advancing. Therefore, development of video copy detection system must be settled without delay. In this paper, we propose the hierarchical video copy detection method that estimates similarity using statistical characteristics between original video and manipulated(transformed) copy video. We rank according to luminance value of video to be robust to spacial transformation, and choose similar videos categorized as candidate segments in huge amount of database to reduce processing time and complexity. The copy videos generally insert black area in the edge of the image, so we remove rig black area and decide copy or not by using statistical characteristics of original video and copied video with center part of frame that contains important information of video. Experiment results show that the proposed method has similar keyframe accuracy to reference method, but we use less memory to save feature information than reference's, because the number of keyframes is less 61% than that of reference's. Also, the proposed method detects if the video is copied or not efficiently despite expansive spatial transformations such as blurring, contrast change, zoom in, zoom out, aspect ratio change, and caption insertion.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.105-108
• /
• 2003

In the framework of universal multimedia access, one challenge for video transmission (communication) is to deliver video content through heterogeneous network channels matching the diversity of client devices. As one of the many adaptation methods, media transcoding is commonly considered. Particularly, FD (Frame Dropping)/CD Coefficient Dropping) transcoding is used due to the low computational complexity and simple implementation. In this scheme, CD is simply implemented by truncating the high frequency AC DCT coefficient bits. But, the CD error tends to be propagated within single GOV. In this paper, we derive the distortion relationships between CD error and propagation error, and investigate the error characteristics by computer simulations. The CD error characteristics can be effectively used in the FD/CD transcoding scheme.

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.3
• /
• pp.288-298
• /
• 2000

Digital assets denote multimedia information that exists in the form of digitized materials such as images, audio, and video. The management of digital assets demands much effort because of a huge amount of storage space requirement and multidimensional characteristics of the information needed to describe their contents. In this paper, we design and implement a Digital Asset Manager that stores and manages digital assets efficiently. Among the various types of digital assets, we focus on the video asset which has the highest complexity. Our Digital Asset Manager provides various facilities for digital contents authoring applications. In the Digital Asset Manager, video assets are managed by using a hierarchical model in order to ensure efficient accesses to any part of a video asset. Our system also guarantees the independence from the storage platform, and provides a fast content-based similarity search method on the digital assets.

• 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.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.6
• /
• pp.130-136
• /
• 2016

HEVC (High Efficiency Video Coding) extension considers screen content as one of its main candidate sources for encoding. Among the tools already included in HEVC version 1, the technique of using transform skip mode allows transform to be skipped and to perform quantization process only. It is known to improve video coding efficiency for screen contents which are characterized to have much high frequency energy. But encoding complexity increases since its encoder should decide whether transform should be used or not in each $4{\times}4$ transform block. Based on statistical correlation between IBC (Intra block copy) and transform skip modes both of which are known effective in screen contents, this paper proposes a combined method of the fast transform skip mode decision and a modified transform skip signaling which signals transform_skip_flag at CU level as a representative transform skip signal. By simulation, the proposed method is shown to reduce encoding time of $4{\times}4$ transform blocks by about 32%.

• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.35-49
• /
• 2024

Video captioning technology, as a significant outcome of the integration between computer vision and natural language processing, has emerged as a key research direction in the field of artificial intelligence. This technology aims to achieve automatic understanding and language expression of video content, enabling computers to transform visual information in videos into textual form. This paper provides an initial analysis of the research trends in deep learning-based video captioning and categorizes them into four main groups: CNN-RNN-based Model, RNN-RNN-based Model, Multimodal-based Model, and Transformer-based Model, and explain the concept of each video captioning model. The features, pros and cons were discussed. This paper lists commonly used datasets and performance evaluation methods in the video captioning field. The dataset encompasses diverse domains and scenarios, offering extensive resources for the training and validation of video captioning models. The model performance evaluation method mentions major evaluation indicators and provides practical references for researchers to evaluate model performance from various angles. Finally, as future research tasks for video captioning, there are major challenges that need to be continuously improved, such as maintaining temporal consistency and accurate description of dynamic scenes, which increase the complexity in real-world applications, and new tasks that need to be studied are presented such as temporal relationship modeling and multimodal data integration.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4B
• /
• pp.713-720
• /
• 2010

Lately, IPTV is in the limelight using a broadband information service to provide video content and broadcast services. Current IPTV system is combining CAS and DRM system for VOD contents to protect transmitting contents and authentication, but it has drawbacks such as system's complexity and high construction costs. Multicast DRM system emerged as a method to improve them, but, in the multicast DRM system, if the key is intercepted by a malicious user, it can be viewed by an unauthorized user of illegal broadcasting which can be a problem. In this paper, we suggest to protect content from a malicious user by applying the techniques using user authentication in the multicast DRM system.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.560-568
• /
• 2020

In recent years, as network technology develops, the usage of streaming services by users is increasing. However, the complexity of streaming services is also increasing due to various terminal environments. Even when streaming the same content, it is necessary to re-encode the content according to the type of service. In order to solve the complexity and latency of the streaming service, Moving Picture Experts Group (MPEG) has standardized the Common Media Application Format (CMAF). In addition, as content transmission using a communication network becomes possible, the Republic of Korea's Ultra High Definition (UHD) broadcasting standard has been enacted as a hybrid standard using a broadcasting network and a communication network. The hybrid service enables various services such as transmitting additional information of contents or providing user-customized contents through a communication network. The Republic of Korea's UHD transmission standard utilizes MPEG Media Transport (MMT), and Mobile MMT is an extension of MMT to provide mobile network-specific functions. This paper proposes a method of inserting CMAF contents suitable for various streaming services using signaling messages of MMT and Mobile MMT. In addition, this paper proposes a model for content insertion system in heterogeneous network environment using broadcasting and communication networks, and verifies the validity of the proposed technology by checking the result of content insertion.