• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1434-1449
• /
• 2019

Video object segmentation is a significant task in computer vision, but its performance is not very satisfactory. A method of video object segmentation using weakly temporal information is presented in this paper. Motivated by the phenomenon in reality that the motion of the object is a continuous and smooth process and the appearance of the object does not change much between adjacent frames in the video sequences, we use a feed-forward architecture with motion estimation to predict the mask of the current frame. We extend an additional mask channel for the previous frame segmentation result. The mask of the previous frame is treated as the input of the expanded channel after processing, and then we extract the temporal feature of the object and fuse it with other feature maps to generate the final mask. In addition, we introduce multi-mask guidance to improve the stability of the model. Moreover, we enhance segmentation performance by further training with the masks already obtained. Experiments show that our method achieves competitive results on DAVIS-2016 on single object segmentation compared to some state-of-the-art algorithms.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.609-612
• /
• 2010

최근 스마트 폰을 이용한 사용자들이 생성하는 사진 데이터의 양이 급속히 증가하였다. 폭발적인 사진 데이터 양의 증가는 사용자가 원하는 사진에 대한 접근을 어렵게 하였다. 때문에 본 연구에서는 사진의 접근 및 관리의 효율을 높이기 위한 폭소노미를 통한 태그 추천 시스템을 안드로이드 모바일 플랫폼과 서버의 연계로 구현하였다. 구현된 애플리케이션은 25,000 장의 사진을 기반으로 하는 폭소노미를 통해 태그 추천을 하며, 태그 추천에 평균적으로 5.5 초의 시간이 걸렸다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.321-340
• /
• 2016

The Compressive Video Sensing (CVS) is a useful technology for wireless systems requiring simple encoders but handling more complex decoders, and its rate-distortion performance is highly affected by the quantization of measurements and reconstruction of video frame, which motivates us to presents the Space-Time Quantization (ST-Q) and Motion-Aligned Reconstruction (MA-R) in this paper to both improve the performance of CVS system. The ST-Q removes the space-time redundancy in the measurement vector to reduce the amount of bits required to encode the video frame, and it also guarantees a low quantization error due to the fact that the high frequency of small values close to zero in the predictive residuals limits the intensity of quantizing noise. The MA-R constructs the Multi-Hypothesis (MH) matrix by selecting the temporal neighbors along the motion trajectory of current to-be-reconstructed block to improve the accuracy of prediction, and besides it reduces the computational complexity of motion estimation by the extraction of static area and 3-D Recursive Search (3DRS). Extensive experiments validate that the significant improvements is achieved by ST-Q in the rate-distortion as compared with the existing quantization methods, and the MA-R improves both the objective and the subjective quality of the reconstructed video frame. Combined with ST-Q and MA-R, the CVS system obtains a significant rate-distortion performance gain when compared with the existing CS-based video codecs.

• Journal of Information Technology Services
• /
• v.14 no.1
• /
• pp.99-113
• /
• 2015

Adaptive bitrate (ABR) streaming technology has become an important and prevalent feature in many multimedia delivery systems, with content providers such as Netflix and Amazon using ABR streaming to increase bandwidth efficiency and provide the maximum user experience when channel conditions are not ideal. Where such systems could see improvement is in the delivery of live video with a closed loop cognitive control of video encoding. In this paper, we present streaming camera system which provides spatially and temporally adaptive video streams, learning the user's preferences in order to make intelligent scaling decisions. The system employs a hardware based H.264/AVC encoder for video compression. The encoding parameters can be configured by the user or by the cognitive system on behalf of the user when the bandwidth changes. A cognitive video client developed in this study learns the user's preferences (i.e. video size over frame rate) over time and intelligently adapts encoding parameters when the channel conditions change. It has been demonstrated that the cognitive decision system developed has the ability to control video bandwidth by altering the spatial and temporal resolution, as well as the ability to make scaling decisions

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.2
• /
• pp.156-160
• /
• 2012

In this paper, we investigate the effect of asynchronous haptic and video feedback on the performance of teleoperation. To analyze the effect, a tele-manipulation experiment is specially designed, which operator moves square objects from one place to another place by using master/slave telerobotic system. Task completion time and total number of falling of the object are used for evaluating the performance. Subjective study was conducted with 10 subjects in 16 different combinations of video and haptic feedback while participants didn't have any prior information about the amount of each delay. Initially we assume that synchronized haptic and video feedback would give best performance. However as a result, we found that the accuracy was increased when haptic and video feedback was synchronized, and the completion time was decreased when one of the feedback (either haptic or video) was decreased. Another interesting fact that we found in this experiment is that it showed even better accuracy when haptic information arrives little bit earlier than video information, than the case when those are synchronized.

• Journal of information and communication convergence engineering
• /
• v.11 no.1
• /
• pp.62-68
• /
• 2013

This paper proposes a method for identification of harmful video images based on the degree of harmfulness in the video content. To extract harmful candidate frames from the video effectively, we used a video color extraction method applying a projection map. The procedure for identifying the harmful video has five steps, first, extract the I-frames from the video and map them onto projection map. Next, calculate the similarity and select the potentially harmful, then identify the harmful images by comparing the similarity measurement value. The method estimates similarity between the extracted frames and normative images using the critical value of the projection map. Based on our experimental test, we propose how the harmful candidate frames are extracted and compared with normative images. The various experimental data proved that the image identification method based on the 2-dimensional projection map is superior to using the color histogram technique in harmful image detection performance.

• Journal of Broadcast Engineering
• /
• v.7 no.2
• /
• pp.79-87
• /
• 2002

The fast advances in digital video processing and multimedia processing technology over the last decade enabled various non-linear video browsing techniques. Based on the machine-understanding of the video content, non-linear video brows ing interfaces such as key-frame based content summarization have been introduced. The key-frame based user interfaces, such as storyboard or table of content, however, are still very hard for conventional TV users to use, and are very hard to implement without the service providers providing additional information for the construction of the key-frame based interfaces. In this paper, non-linear video browsing techniques, which not only overcome previously described drawbacks but also are easy-to-use, and real-time video indexing technology to support the proposed browsing techniques are proposed. The structure-based skipping and skimming help users easily find interesting scene and understand the content in a very short time, using real-time video indexing technology.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.261-266
• /
• 2020

As pioneers of the early video art, Steina Vasulka(1940-) and Woody Vasulka(1937-2019) had lead not only their own experimental arts, but also entire changes of contemporary avant-garde performance, music, and visual art. Two artists invented and developed electronic machines for video image-processing by collaborating with engineers, and performed creative experiment on transformation of digital image. For them, video art is not just a means of documentation. The Vasulkas' artistic practices were not bounded by conventional canons and rules in art world, and preferably were parts of active aesthetic strategies for coexistence of vision of human and vision of machine. Particularly, their video art recognized the video as the key medium in an era where media technology began to dominate the system of communication, and established artist's authority over manipulation of moving image electronically without depending on video camera. In that regard, we can value on their video art. Therefore, the paper reflects on the Vasulkas' art and life which have not yet been studied, and suggests academic interests in the context of their artistic activities and aesthetic strategies.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.691-701
• /
• 2010

We propose a haptic rendering technology for touchable video. Our touchable video technique allows users for feeling the sense of touch while probing directly on 2D objects in video scenes or manipulating 3D objects brought out from video scenes using haptic devices. In our technique, a server sends video and haptic data as well as the information of 3D model objects. The clients receive video and haptic data from the server and render 3D models. A video scene is divided into small grids, and each cell has its tactile information which corresponds to a specific combination of four attributes: stiffness, damping, static friction, and dynamic friction. Users can feel the sense of touch when they touch directly cells of a scene using a haptic device. Users can also examine objects by touching or manipulating them after bringing out the corresponding 3D objects from the screen. Our touchable video technique proposed in this paper can lead us to feel maximum satisfaction the haptic-audio-vidual effects directly on the video scenes of movies or home-shopping video contents.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2793-2803
• /
• 2013

In H.264, three different data partition types are used, which have unequal importance to the reconstructed video quality. To improve the performance of H.264 video streaming transmission over IEEE 802.11e Wireless Local Area Networks, a prioritization mechanism that categorizes different partition types to different priority classes according to the calculated distortion within one Group of Pictures. In the proposed scheme, video streams have been encoded based on the H.264 codec with its data partition enabled. The dynamic scheduling scheme based on Enhanced Distributed Channel Access has been configured to differentiate the data partitions according to their distortion impact and the queue utilization ratio. Simulation results show that the proposed scheme improves the received video quality by 1dB in PSNR compared with the existing Enhanced Distributed Channel Access static mapping scheme.