• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.242-243
• /
• 2022

코로나 팬데믹으로 세계가 큰 피해를 보고 있다. 기존 얼굴인식 보안시스템이 마스크 사용자 인식이 어려워 마스크 사용자를 인식할 수 있는 방안이 필요하다. 얼굴인식을 위한 영상처리 기술이 딥러닝에 의해 크게 발전하고 있으며, 여전히 전처리 기술 또한 중요하다. 본 논문에서는 영상처리 기술의 선명도 평가 함수와 YOLOv5를 사용해 학습 재학습 이후 변화하는 성능을 확인하였고, 비마스크 사용 시 분류정확도가 1%, 학습 손실률에서 0.2% 정도의 성능 개선을 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1311-1314
• /
• 2022

DNN을 사용하여 객체 인식 과정에서 객체를 잘 분류하기 위해서는 시각적 설명성이 요구된다. 시각적 설명성은 object class에 대한 예측을 pixel-wise attribution으로 표현해 예측 근거를 해석하기 위해 제안되었다, Scale-invariant한 특징을 제공하도록 설계된 pyramidal features 기반 backbone 구조는 object detection 및 classification 등에서 널리 쓰이고 있으며, 이러한 특징을 갖는 feature pyramid를 trainable attention mechanism에 적용하고자 할 때 계산량 및 메모리의 복잡도가 증가하는 문제가 있다. 본 논문에서는 일반적인 FPN에서 객체 인식 성능과 설명성을 높이기 위한 피라미드-주의집중 계층네트워크 (FPN-Attention Layered Network) 방식을 제안하고, 실험적으로 그 특성을 평가하고자 한다. 기존의 FPN만을 사용하였을 때 객체 인식 과정에서 설명성을 향상시키는 방식이 객체 인식에 미치는 정도를 정량적으로 평가하였다. 제안된 모델의 적용을 통해 낮은 computing 오버헤드 수준에서 multi-level feature를 고려한 시각적 설명성을 개선시켜, 결괴적으로 객체 인식 성능을 향상 시킬 수 있음을 실험적으로 확인할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1195-1198
• /
• 2022

홀로그램은 빛의 세기와 위상 정보를 모두 기록함으로써 3차원 영상 정보를 기록 및 재현할 수 있는 차세대 영상 시스템이다. 홀로그램은 부동 소수점의 복소 데이터로 실수, 허수 또는 진폭, 위상 신호로 분리되어 압축된다. 본 논문에서는 복소 홀로그램 영상의 표현방식에 따른 압축성능을 비교해보고, 진폭-위상 압축에 대해 압축 친화적인 복소 홀로그램 변환 방식을 제안한다. 이후, 각 표현방식의 압축에서 효율적인 비트량 할당 방법을 제시한다. 본 논문은 제안방식인 QS 진폭-위상 표현이 실수-허수 표현만큼 높은 압축성능을 갖는 것을 확인하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.4B
• /
• pp.165-173
• /
• 2008

In this paper, we propose a new reliable broadcast protocol referred to as timer-based reliable broadcast (TRB) for wireless sensor networks (WSNs). The proposed TRB scheme exploits (1) bitmap based explicit ACK to effectively reduce the unnecessary error control messages and (2) randomized timer for ACK transmission to substantially reduce the possibility of contentions. Although it has been argued that 100% reliability is not necessary in WSNs, there should be messages (such as mission-critical message, task assignment, software updates, etc.) that need to be reliably delivered to the entire sensor field. We propose to use the TRB algorithm for such cases. Performance evaluation shows that the TRB scheme achieves 100 % reliability significantly better than other schemes with expense of slightly increased energy consumption.

• Journal of Digital Convergence
• /
• v.12 no.5
• /
• pp.501-515
• /
• 2014

The enforcement of the digital switch been two years, but more than half of the viewers are still not enjoying the benefits of it. Therefore, the government proposed that 8VSB transmission method so that majority of the viewer is able to enjoy the benefits of a digital switch. However, the claim has been suggested that 8VSB transmission method will have negative impacts on broadcast market feedback. In this regard, this study verified the effect of 8VSB and the method of minimization on the broadcast market. This study has conducted in-depth interviews concerned experts to achieve this purpose. Results of an interview revealed that the negative impact on the market of content and platforms, network is very small. In other words, the majority of the experts argued that the policy of government about 8VSB transmission are inadequate and it is improved to broaden the choice of the broadcast consumer.

• The KIPS Transactions:PartC
• /
• v.9C no.6
• /
• pp.919-926
• /
• 2002

In this paper, new multicast scheduling algorithms are proposed for the WDM single-hop broadcast-and-select networks. The existing multicast scheduling algorithms are focused on the partitioning a multicast group into several subgroups to reduce the delay time of each receiver. These partitioning algorithms are grouping method of the receivers already tuned to the transmitter's wavelength. However, these algorithms ignore the state of receivers, which leads to increase the number of subgroups and the delay time. Therefore, 1 propose two new multicast scheduling algorithms called H_EAR and PGM that partition a multicast group to subgroups using the tunable transmitter, state information of receivers, and pseudo group concept. The performance of proposed algorithms are evaluated through the computer simulation. They show the better performance comparing with the existing multicast scheduling algorithm.

• Journal of Internet Computing and Services
• /
• v.13 no.4
• /
• pp.95-102
• /
• 2012

The development of applications for vehicular ad hoc networks (VANETs) has very specific and clear goals such as providing intellectual safe transport systems. An emergency warning technic for public safety is one of the applications which requires an intelligent broadcast mechanism to transmit warning messages quickly and efficiently against the time restriction. The broadcast storm problem causing several packet collisions and extra delay has to be considered to design a broadcast protocol for VANETs, when multiple nodes attempt transmission simultaneously at the access control layer. In this paper, we propose an early intelligent alert broadcasting (EI-CAST) algorithm to resolve effectively the broadcast storm problem and meet time-critical requirement. The proposed algorithm uses not only the early alert technic on the basis of time to collision (TTC) but also the intelligent broadcasting technic on the basis of fuzzy logic, and the performance of the proposed algorithm was compared and evaluated through simulation with the existing broadcasting algorithms. It was demonstrated that the proposed algorithm shows a vehicle can receive the alert message before a collision and have no packet collision when the distance of alert region is less than 4 km.

• Journal of Broadcast Engineering
• /
• v.18 no.2
• /
• pp.196-203
• /
• 2013

The importance of Digital Rights Protection technologies, especially the forensic marking, is getting larger and larger as the demand for the digital contents is increased. But the technologies for the evaluation of forensic marking is not set up properly due to the conflicts between interested parties and technical difficulties. Therefore to evaluate the performance of forensic marking objectively, image and video modification items/levels and evaluation criteria are essential. This paper suggests the quantitative system for evaluating the performance of forensic marking objectively. By providing the opportunity to evaluate the Digital Rights Protection product in objective and quantitative manner, forensic marking industry can expedite its technology development and consumer can get objective and universally validated performance result. It is expected this technology could help revitalizing the related industries and help expediting the development of forensic mark technologies.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.723-733
• /
• 2020

In this paper, MPEG-I Immersive Audio Standardization and related trends are presented. MPEG-I Immersive Audio, which is under the development of standard documents at the exploration stage, can make a user interact with a virtual scene in 6 DoF manner and perceive sounds realistic and matching the user's spatial audio experience in the real world, in VR/AR environments that are expected as killer applications in hyper-connected environments such as 5G/6G. In order to do this, MPEG Audio Working Group has discussed the system architecture and related requirements for the spatial audio experience in VR/AR, audio evaluation platform (AEP) and encoder input format (EIF) for assessing the performance of submitted proponent technologies, and evaluation procedures.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.775-784
• /
• 2019

Image stitching is a technique for solving the problem of narrow field of view of a camera by composing multiple images. Recently, as the use of content such as Panorama, Super Resolution, and 360 VR increases, the need for faster and more accurate image stitching technology is increasing. So far, many algorithms have been proposed to satisfy the required performance, but the objective evaluation method for measuring the accuracy has not been standardized. In this paper, we present the problems of PSNR and SSIM(Structural similarity index method) measurement methods and propose a Local Differential Pixel Mean method. The LDPM evaluation method that includes geometric similarity and brightness measurement information is proved through a test, and the advantages of the evaluation method are revealed through comparison with SSIM.