• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1182-1194
• /
• 2018

The Dynamic Adaptive Streaming over HTTP(DASH) is envisioned to evolve to meet an increasing demand on providing seamless video streaming services in the near future. The DASH performance heavily depends on the client's adaptive quality selection algorithm that is not included in the standard. The existing conventional algorithms are basically based on a procedural algorithm that is not easy to capture and reflect all variations of dynamic network and traffic conditions in a variety of network environments. To solve this problem, this paper proposes a novel quality selection mechanism based on the Deep Q-Network(DQN) model, the DQN-based DASH Adaptive Bitrate(ABR) mechanism. The proposed mechanism adopts a new reward calculation method based on five major performance metrics to reflect the current conditions of networks and devices in real time. In addition, the size of the consecutive video segment to be downloaded is also considered as a major learning metric to reflect a variety of video encodings. Experimental results show that the proposed mechanism quickly selects a suitable video quality even in high error rate environments, significantly reducing frequency of quality changes compared to the existing algorithm and simultaneously improving average video quality during video playback.

• Journal of Korea Multimedia Society
• /
• v.20 no.1
• /
• pp.1-9
• /
• 2017

Explosive deployment of smart mobile devices such as smart phones, and tablets along with expansion of wireless internet bandwidth have enabled the deployment of mobile video streaming such that video traffic becomes the most important service in wireless networks. Recently, for more efficient video streaming services, the ISO MPEG group standardized a protocol called DASH (Dynamic Adaptive Streaming over HTTP) and the standard has been quickly adopted by many service providers such as YouTube and Netflix. Despite of the convenience of mobile streaming services, users also suffer from low QoE(Quality of Experience) due to dynamic channel fluctuations and unnecessary downloading due to high churning rates. This paper proposes a noble efficient video rate selection algorithm considering user buffer level, channel condition and churning rate. Computer simulation based performance study showed that the proposed algorithm improved the QoE significantly compared to a method that determines the video rate based on current channel conditions. Especially, the proposed method reduced the rebuffering rate, one of the most important performance factors of the QoE, to a nonnegligible level.

• Journal of Korean language education
• /
• v.29 no.2
• /
• pp.181-208
• /
• 2018

The aim of this study is to design a Real-time video Korean curriculum. Curriculum using real-time video, which is a variant of distance learning, teaches Korean to students studying in distant places through real-time video communication program. This is expected to supplement the lack of interaction in existing video classes and enable online simultaneous interaction, while increasing learning opportunities for Korean language students living in distance places. To find out the needs of the subjects for the curriculum design, this study conducted a one-on-one interview with 9 female married immigrants who are enrolled in the Cyber University which is opening a curriculum later. According to the survey, the students answered that they have a high intention of attending classes if the lack of interaction in existing distance classes are supplemented. Therefore, we could confirm the demand of a curriculum consisting of an overall real-time video education and multilateral individual connection. Also, we found out that there is a demand in performance rather than comprehension and a high demand for detailed feedback from the teacher. The result shows that the curriculum needs to establish performance-oriented contents to progress to an advanced level Korean Language, and include a study plain comprising of real-time interaction.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.329-346
• /
• 2022

Recently, as the market for short form videos (Instagram, TikTok, YouTube) on social media has gradually increased, research using them is actively being conducted in the artificial intelligence field. A representative research field is Video to Shop, which detects fashion products in videos and searches for product images. In such a video-based artificial intelligence model, product features are extracted using convolution operations. However, due to the limitation of computational resources, extracting features using all the frames in the video is practically impossible. For this reason, existing studies have improved the model's performance by sampling only a part of the entire frame or developing a sampling method using the subject's characteristics. In the existing Video to Shop study, when sampling frames, some frames are randomly sampled or sampled at even intervals. However, this sampling method degrades the performance of the fashion product search model while sampling noise frames where the product does not exist. Therefore, this paper proposes a sampling method MF (Missing Fashion items on frame) sampler that removes noise frames and improves the performance of the search model. MF sampler has improved the problem of resource limitations by developing a keyframe mechanism. In addition, the performance of the search model is improved through noise frame removal using the noise detection model. As a result of the experiment, it was confirmed that the proposed method improves the model's performance and helps the model training to be effective.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.986-1005
• /
• 2020

In this paper, we propose AnoVid, an automated video annotation tool based on deep neural networks, that automatically generates various meta data for each scene or shot in a long drama video containing rich elements. To this end, a novel meta data schema for drama video is designed. Based on this schema, the AnoVid video annotation tool has a total of six deep neural network models for object detection, place recognition, time zone recognition, person recognition, activity detection, and description generation. Using these models, the AnoVid can generate rich video annotation data. In addition, AnoVid provides not only the ability to automatically generate a JSON-type video annotation data file, but also provides various visualization facilities to check the video content analysis results. Through experiments using a real drama video, "Misaeing", we show the practical effectiveness and performance of the proposed video annotation tool, AnoVid.

• ETRI Journal
• /
• v.31 no.1
• /
• pp.10-20
• /
• 2009

In this paper, a video broadcasting system between a home-server-type device and a mobile device is proposed. The home-server-type device can automatically extract semantic information from video contents, such as news, a soccer match, and a baseball game. The indexing results are utilized to convert the original video contents to a digested or arranged format. From the mobile device, a user can make recording requests to the home-server-type devices and can then watch and navigate recorded video contents in a digested form. The novelty of this study is the actual implementation of the proposed system by combining the actual IT environment that is available with indexing algorithms. The implementation of the system is demonstrated along with experimental results of the automatic video indexing algorithms. The overall performance of the developed system is compared with existing state-of-the-art personal video recording products.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.1
• /
• pp.11-16
• /
• 2006

To manipulate large video databases, effective video indexing and retrieval are required. A large number of video indexing and retrieval algorithms have been presented for frame-w]so user query or video content query whereas a relatively few video sequence matching algorithms have been proposed for video sequence query. In this paper, we propose an efficient algorithm to extract key frames using color histograms and to match the video sequences using edge features. To effectively match video sequences with low computational load, we make use of the key frames extracted by the cumulative measure and the distance between key frames, and compare two sets of key frames using the modified Hausdorff distance. Experimental results with several real sequences show that the proposed video retrieval algorithm using color and edge features yields the higher accuracy and performance than conventional methods such as histogram difference, Euclidean metric, Battachaya distance, and directed divergence methods.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1318-1330
• /
• 2018

Video captioning refers to the process of extracting features from a video and generating video captions using the extracted features. This paper introduces a deep neural network model and its learning method for effective video captioning. In this study, visual features as well as semantic features, which effectively express the video, are also used. The visual features of the video are extracted using convolutional neural networks, such as C3D and ResNet, while the semantic features are extracted using a semantic feature extraction network proposed in this paper. Further, an attention-based caption generation network is proposed for effective generation of video captions using the extracted features. The performance and effectiveness of the proposed model is verified through various experiments using two large-scale video benchmarks such as the Microsoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.1
• /
• pp.17-32
• /
• 1996

In this paper, a model for two-layered video traffic is proposed. The performance analysis of the proposed model and the effects of two-layer coding scehemes in ATM networks are also studied. ATM-based networks give the possibility to support image codingat variable bit rate(VBR). Two layer coding is one of the very promising methods among many proposed methods to compensate the cell loss, the major drawback in ATM networks. From the experimental data of the 2-layer coded video traffics, it is observed that traffic patterns of base layer and enhanced layer are highly correlate to each other, when constant image quality is kept. With this observation, coded two layered video traffic can be modeled as 2-dimensional Markov chain. The model well fit the real experimental data. The model was used for the analysis of the performance of statistical multiplexer with priorites in ATM networks.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.611-614
• /
• 2002

In this paper, a novel error concealment, algorithm is proposed for the MPEG-4 video decoding. Apart from existing algorithms which fail to exhibit stable performance over various video sequences and error patterns, the proposed algorithm adopts a new hybrid scheme, which can achieve a consistent performance with reduced computational complexity. This algorithm is implemented on the basis of the MPEG-4 decoder, and the experimental results demonstrate that the new approach provides acceptable performance both subjectively and objectively at various bit error rates and video sequences.