• The Journal of the Korea Contents Association
• /
• v.7 no.12
• /
• pp.311-321
• /
• 2007

For fast and robust face detection, this paper proposes an approach for face detection using fusion of heterogeneous template matching. First, we detect skin regions using a model of skin color which covers various illumination and races. After reducing a search space by region labelling and filtering, we apply template matching with skin color and edge to the detected regions. Finally, we detect a face by finding the best choice of template fusion. Experimental results show the proposed approach is more robust in skin color-like environments than with a single template matching and is fast by reducing a search space to face candidate regions. Also, using a global accumulator can reduce excessive space requirements of template matching.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.8
• /
• pp.5263-5268
• /
• 2014

This paper suggests a fast human detection algorithm that can be applied to a high-resolution CCTV camera. Human detection algorithms, which used a HOG detector show high performance in the region of image processing. On the other hand, it is difficult to apply to real-time high resolution imaging because of its slow processing speed in the extracting figures of HOG. To resolve this problems, we suggest how to detect humans into two stages. First, candidates of a human region are found using background subtraction, and humans and non-humans are distinguished using a HOG detector only. This process increases the detection speed by approximately 2.5 times without any degradation in performance.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.473-474
• /
• 2007

본 연구는 체내 이식형 Pacemaker를 연구하면서 심장 질환을 Therapy 해 주는 방법에 대해 저전력 및 성능향상에 중점을 두고 연구 및 실험을 하였다. 우선적으로 심장의 심박동을 연산량이 적은 Peak_detection에서 체크하여 전력소모를 줄이고 나오는 각 심실 및 심방의 Interval을 Disease_episode 에서 받는다. 여기서 5가지 심실 및 심방에 관한 질환들 (VF : Ventricular Fibrillation, VT : Ventricular Tachycardia, FVT : Fast Ventricular Tachycardia, FAT_AF : Fast Atrial Tachycardia/Atrial Fibrillation, AT_AF : Atrial Tachycardia AT_AF : Atrial Fibrillation)을 판별한 후 각 병증에 맞는 Therapy 값을 출력하게 하였다. 그 외에 남아있는 병증에 대해서도 Therapy가 저전력 및 성능향상 되도록 설계하였다. 기존에 적용되어 있는 Detection 기법에서는 각각의 병증에 대해서 각 Detection이 있어 VF와 VT 사이에 있는 FVT와 같은 병증을 치료할 때 FVT 같은 경우에는 VF와 VT사이에 있는 질병이기 때문에 FVT_VF 및 FVT_VT와 같이 각각의 Detection을 두어 전력 소모가 있었다. 심장에서는 여러 질병이 한번에 나을 수 없다는 것에 착안하여 (심박동 Interval에 의해 질병이 판단되므로) 다른 병증이지만 같은 진단 기준을 쓰는 Detection을 통합함으로써 하나의 모듈로 구성하여 Gate수를 줄이고 저전력을 구현하였다. 또한 병증을 판별하는 진단 기준 모듈 중 Onset_Criterion 재설계하여 좀더 성능 향상에 중점을 두었다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.5_6
• /
• pp.257-267
• /
• 2004

Most algorithms for handling distributed deadlock problem in the generalized request model use the diffusing computation technique where propagation of probes and backward propagation of replies carrying dependency information between processes are both required to detect deadlock Since fast deadlock detection is critical, we propose an algorithm that lets probes rather than replies carry the information required for deadlock detection. This helps to remove the backward propagation of replies and reduce the time cost for deadlock detection to almost half of that of the existing algorithms. Moreover, the proposed algorithm is extended to deal with concurrent executions, which achieves further improvement of deadlock detection time, whereas the current algorithms deal only with a single execution. We compare the performance of the proposed algorithm with that of the other algorithms through simulation experiments.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.14 no.4
• /
• pp.111-121
• /
• 2004

With rapid growth of the Internet, network intrusions have greatly increased and damage of attacks has become more serious. Recently some kinds of Internet attacks cause significant damage to overall network performance. Current Intrusion Detection Systems are not capable of performing the real-time detection on the backbone network In this paper, we propose the broadband network intrusion detection system using the exponential smoothing method. We made an experiment with real backbone traffic data for 8 days. The results show that our proposed system detects big jumps of traffic volume well.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.254-257
• /
• 2014

Recently, various applications using real-time face detection have been developed as face recognition technology and hardware grows. While network service is developing and video instruments costs lower, it is needed that smart surveillance camera and service using network camera based on IP and face detection technology. However, videos should be compressed for reducing network bandwidth and storage capacity in surveillance system. As it requires high-level improvement of system performance when all the compressed frames are processed in a face detection program, fast face detection method is needed. In this paper, not only a fast way of algorithm using Haar like features and adaboost learning and motion information but also an application on broadcast system is suggested.

• Nuclear Engineering and Technology
• /
• v.56 no.3
• /
• pp.893-899
• /
• 2024

In a secondary cooling system of a sodium-cooled fast reactor (SFR), rapid detection of hydrogen due to sodium-water reaction (SWR) caused by water leakage from a heat exchanger tube of a steam generator (SG) is important in terms of safety and property protection of the SFR. For hydrogen detection, the hydrogen detectors using atomic transmission phenomenon of hydrogen within Ni-membrane were used in Japanese proto-type SFR "Monju". However, during the plant operation, detection signals of water leakage were observed even in the situation without SWR concerning temperature up and down in the cooling system. For this reason, the study of a new hydrogen detector has been carried out to improve stability, accuracy and reliability. In this research, the authors focus on the difference in composition of hydrogen and the difference between the background hydrogen under normal plant operation and the one generated by SWR and theoretically estimate the hydrogen behavior in liquid sodium by using ultra-accelerated quantum chemical molecular dynamics (UA-QCMD). Based on the estimation, dissolved H or NaH, rather than molecular hydrogen (H₂), is the predominant form of the background hydrogen in liquid sodium in terms of energetical stability. On the other hand, it was found that hydrogen molecules produced by the sodium-water reaction can exist stably as a form of a fine bubble concerning some confinement mechanism such as a NaH layer on their surface. At the same time, we observed experimentally that the fine H₂ bubbles exist stably in the liquid sodium, longer than previously expected. This paper describes the comparison between the theoretical estimation and experimental results based on hydrogen form in sodium in the development of the new hydrogen detector in Japan.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.1
• /
• pp.49-55
• /
• 2015

In this paper, we propose a fast interest point detection method using SURF algorithm. Since the SURF algorithm needs a great computations to detect the interest points and obtain the corresponding descriptors, it is not suitable for real-time based applications. In order to overcome this problem, the interest point detection step is parallelized by OpenMP and SIMD based on analysis of the scale space representation process and localization one in the step. The simulation results demonstrate that processing speed is enhanced about 55% by applying the proposed method.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.216-224
• /
• 2017

Abnormal situation caused by aggressive behavior of pigs adversely affects the growth of pigs, and comes with an economic loss in intensive pigsties. Therefore, IT-based video surveillance system is needed to monitor the abnormal situations in pigsty continuously in order to minimize the economic demage. Recently, some advances have been made in pig monitoring; however, detecting each pig is still challenging problem. In this paper, we propose a new color image-based monitoring system for the detection of the individual pig using a fast region-based convolution neural network with consideration of detecting touching pigs in a crowed pigsty. The experimental results with the color images obtained from a pig farm located in Sejong city illustrate the efficiency of the proposed method.

• Journal of KIISE:Software and Applications
• /
• v.32 no.12
• /
• pp.1157-1163
• /
• 2005

In this paper, an efficient and fast method to segment a video in the MPEG(motion picture expert group) video stream is proposed. For the real time processing of large amount of broadcasting data, we use DC images of I-frames in an MPEG compressed video with minimal decoding. Using the modified histogram comparison which counts on not only luminance but also chrominance information, the scene change detection was performed in the fast and accurate way Also, to discriminate anchorperson frame from non-anchor frame, a neural network method was introduced.