• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06a
• /
• pp.3-8
• /
• 1998

The conversion of monoscopic video to 3D stereoscopic video has been studied by some pioneering researchers. In spite of the commercial of potential of the technology, two problems have bothered the progress of this research area: vertical motion parallax and high computational complexity. The former causes the low 3D perception, while the hardware complexity is required by the latter. The previous research has dealt with NTSC video, thur requiring complex processing steps, one of which is motion estimation. This paper proposes 3D stereoscopic conversion method of MPGE encoded data. Our proposed method has the advantage that motion estimation can be avoided by processing MPEG compressed data for the extraction of motion data as well as that camera and object motion in random in random directions can be handled.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.192-195
• /
• 2011

본 연구에서는 SVC 기반의 HTTP 스트리밍 서비스에서 스케일러블 임의 접근 (random access) 기능을 가능하게 하는 방법을 제안한다. ISO MPEG에서는 DASH (Dynamic Adaptive Streaming over HTTP) 기술을 표준화 하고 있는데, H.264/AVC 비디오에 대한 임의 접근 기능을 지원하는 구문론 (syntax)과 의미론 (semantics)은 현재 표준의 범위에 포함되어 있는 상황이지만 SVC 비디오에 대한 임의 접근 기능에 대한 기술은 포함되어 있지 않다. 본 연구에서는 SVC의 계층적 구조(layered structure)를 고려한 스케일러블 (scalable) 임의 접근 기능을 지원하기 위한 구문론 (syntax)과 의미론 (semantics)에 대해 제안한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.3
• /
• pp.209-215
• /
• 2014

Sequence tagging is the task of predicting frame-wise labels for a given input sequence and has important applications to diverse domains. Conventional methods such as maximum likelihood (ML) learning matches global features in empirical and model distributions, rather than local features, which directly translates into frame-wise prediction errors. Recent probabilistic sequence models such as conditional random fields (CRFs) have achieved great success in a variety of situations. In this paper, we introduce a novel discriminative CRF learning algorithm to minimize local feature mismatches. Unlike overall data fitting originating from global feature matching in ML learning, our approach reduces the total error over all frames in a sequence. We also provide an efficient gradient-based learning method via gradient forward-backward recursion, which requires the same computational complexity as ML learning. For several real-world sequence tagging problems, we empirically demonstrate that the proposed learning algorithm achieves significantly more accurate prediction performance than standard estimators.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.4
• /
• pp.1-6
• /
• 1999

When continuous media are transmitted over the communication networks, asynchrony which can not maintain temporal relationships among packets my occur due to a random transit delay. There exist two types of synchronization schemes ; for guaranteed or non-guaranteed resource networks. The former which applies a resource reservation technique maintains delay characteristics however, the latter supply a best-effort service. In this paper, I propose a intra-media synchronization scheme to transmit continuous media on general networks not guaranteeing a bounded delay time. The scheme controls transmission times of the packets by estimating next delay time with the delay distribution So, the arriving packets my be maintained within a limited delay boundary, and playout will be performed after buffering to smoothen small delay variations. To prevent network congestion and maintain minimum quality of service the transmitter performs media scaling-down by dropping the current packet when informed excessive delay from the receiver.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.23 no.11
• /
• pp.1307-1314
• /
• 2012

To reduce the effects of clutters with subsurface inhomogenities in ground-penetrating radar(GPR) images, an eigenimage based signal-processing technique is presented. If the conventional eigenimage filtering technique is applied to B-scan images of a GPR survey, relatively homogeneous clutters such as antenna ringing, direct coupling between transmitting and receiving antennas, and soil-surface reflection, can be removed sufficiently. However, since random clutters of subsurface inhomogenities still remain in the images, target signals are distorted and obscured by the clutters. According to a comparison of the eigenimage filtering results, there is different coherency between subsurface clutters and target signals. To reinforce the pixels with high coherency and reduce the pixels with low coherency, the pixel-by-pixel geometric-mean process after the eigenimage filtering is proposed here. For the validity of the proposed approach, GPR survey for detection of a metal target in a randomly inhomogeneous soil is numerically simulated by using a random media generation technique and the finite-difference time-domain(FDTD) method. And the proposed signal processing is applied to the B-scan data of the GPR survey. We show that the proposed approach provides sufficient enhancement of target signals as well as remarkable reduction of subsurface inhomogeneous clutters in comparison with the conventional eigenimage filtering.

• Journal of IKEEE
• /
• v.19 no.2
• /
• pp.237-243
• /
• 2015

Recently, eight out of ten people have smartphone in Korea. Also, many applications of smartphone have increased. So, smartphone addiction has become a social issue. Especially, many people in smartphone addiction can't control themselves. Sometimes they don't realize that they are smartphone addiction. Many studies, mostly surveys, have been conducted to diagnose smartphone addiction, e.g. S-measure. In this paper, we suggest how to detect smartphone addiction based on ECG and Eye Gaze. We measure the signals of ECG from the Shimmer and the signals of Eye Gaze from the smart eye when the subjects see the emotional video. In addition, we extract features from the S-transform of ECG. Using Eye Gaze signals(pupil diameter, Gaze distance, Eye blinking), we extract 12 features. The classifier is trained using Random Forest. The classifiers detect the smartphone addiction using the ECG and Eye Gaze signals. We compared the detection results with S-measure results that surveyed before test. It showed 87.89% accuracy in ECG and 60.25% accuracy in Eye Gaze.

• Journal of applied mathematics & informatics
• /
• v.25 no.1_2
• /
• pp.315-327
• /
• 2007

Mathematical aspects of the electromagnetic surface-wave propagation are examined for the dielectric core consisting of multiple sub-layers, which are embedded in the gap between the two bounding cladding metals. For this purpose, the linear problem with a partial differential wave equation is formulated into a nonlinear eigenvalue problem. The resulting eigenvalue is found to exist only for a certain combination of the material densities and the number of the multiple sub-layers. The implications of several limiting cases are discussed in terms of electromagnetic characteristics.

• Journal of Mechanical Science and Technology
• /
• v.17 no.4
• /
• pp.545-561
• /
• 2003

We use the first-passage-time formulation by Torquato, Kim and Cule ［J. Appl. Phys., Vol. 85, pp. 1560∼1571 (1999) ］, which makes use of the first-passage region in association with the diffusion tracer's Brownian movement, and develop a new efficient Brownian motion simulation method to compute the effective conductivity of digitized composite media. By using the new method, one can remarkably enhance the speed of the Brownian walkers sampling the medium and thus reduce the computation time. In the new method, we specifically choose the first-passage regions such that they coincide with two, four, or eight digitizing units according to the dimensionality of the composite medium and the local configurations around the Brownian walkers. We first obtain explicit solutions for the relevant first-passage-time equations in two-and three-dimensions. We then apply the new method to solve the illustrative benchmark problem of estimating the effective conductivities of the checkerboard-shaped composite media. for both periodic and random configurations. Simulation results show that the new method can reduce the computation time about by an order of magnitude.

• Journal of Korea Multimedia Society
• /
• v.19 no.3
• /
• pp.531-538
• /
• 2016

In this paper, we propose a novel post-processing method of semantic segmentation from indoor scenes with RGBD inputs. For accurate segmentation, various post-processing methods such as superpixel from color edges or Conditional Random Field (CRF) method considering neighborhood connectivity have been used, but these methods are not efficient due to high complexity and computational cost. To solve this problem, we maximize the efficiency of post processing by using depth superpixel extracted from disparity image to handle object silhouette. Our experimental results show reasonable performances compared to previous methods in the post processing of semantic segmentation.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.9-17
• /
• 2020

Hippocampus is a complex brain structure embedded deep into the temporal lobe. Studies have shown that this structure gets affected by neurological and psychiatric disorders and it is a significant landmark for diagnosing neurodegenerative diseases. Hippocampus features play very significant roles in region-of-interest based analysis for disease diagnosis and prognosis. In this study, we have attempted to learn the embeddings of this important biomarker. As conventional metric learning methods for feature embedding is known to lacking in capturing semantic similarity among the data under study, we have trained deep Siamese convolutional neural network for learning metric of the hippocampus. We have exploited Gwangju Alzheimer's and Related Dementia cohort data set in our study. The input to the network was pairs of three-view patches (TVPs) of size 32 × 32 × 3. The positive samples were taken from the vicinity of a specified landmark for the hippocampus and negative samples were taken from random locations of the brain excluding hippocampi regions. We have achieved 98.72% accuracy in verifying hippocampus TVPs.