• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.153-156
• /
• 2000

동영상 정보는 영상정보뿐만 아니라 음성정보, 문자정보 및 각종 의미있는 정보들을 포함하고 있어서 기존의 검색방법으로는 사용자가 원하는 이미지를 찾는데 어려움이 따른다. 따라서, 본 연구에서는 동영상 정보의 효율적인 활용을 위한 색인방법으로 칼라 임계값을 이용한 컷 검출 방법을 제안하였다. 이것은 frame 간의 유사도를 측정해서 이 값이 주어진 임계값보다 작을 경우, 장면의 전환이 일어나는 곳을 컷 지점으로 검출하는 것인데, 동영상의 장면에 따른 유사도가 다를 수 있기 때문에, 컷을 구성하는 프레임들간의 칼라 임계값에 변동을 주어 최적의 컷 검출율을 구하고자 했다. 초기의 칼라 임계값은 '80'을 사용했고, 이후 frame 의 유사도가 임계값보다 클 경우, 즉 장면전환이 일어나지 않았을 경우일정한 상수 값을 초기 임계값에서 감산토록 하였다. 이러한, 과정을 거쳐 추출된 frame을 가지고 원하는 이미지를 검색하게 되면 사용자의 노력 및 검색 시간이 단축되고, 동영상 정보의 관리가 용이해진다.

• International Journal of Contents
• /
• v.4 no.2
• /
• pp.24-28
• /
• 2008

In this paper, we propose a new approach for content-based video retrieval using non-parametric based motion classification in the shot-based video indexing structure. Our system proposed in this paper has supported the real-time video retrieval using spatio-temporal feature comparison by measuring the similarity between visual features and between motion features, respectively, after extracting representative frame and non-parametric motion information from shot-based video clips segmented by scene change detection method. The extraction of non-parametric based motion features, after the normalized motion vectors are created from an MPEG-compressed stream, is effectively fulfilled by discretizing each normalized motion vector into various angle bins, and by considering the mean, variance, and direction of motion vectors in these bins. To obtain visual feature in representative frame, we use the edge-based spatial descriptor. Experimental results show that our approach is superior to conventional methods with regard to the performance for video indexing and retrieval.

• Proceedings of the KSME Conference
• /
• 2000.04a
• /
• pp.67-72
• /
• 2000

Demand for now nondestructive evaluation are growing to detect fatigue crack growth behavior to predict long term performance of materials and structure in aggressive environments especially when they are In non-visible area. Acoustic emission technique is well suited to these problems and has drawn a keen interests because of its dynamic detection ability, extreme sensitivity and location of growing defects. In this study, we analysed acoustic emission signals obtained in fatigue and tensile test of high strength fire resistance steel for frame structure with time-frequency analysis methods. The main frequency range is different in the noise and the fatigue crack propagation. It could be classified that it were also generated by composite fracture mechanics of cleavage, dimple, inclusion separation etc.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2000.11a
• /
• pp.113-117
• /
• 2000

침입 탐지 시스템은 네트워크나 호스트에 대한 오용, 남용, 또는 허가되지 않은 접근을 탐지하는 기능을 갖는 시스템이다. 최근 침입들은 그 종류가 매우 다양화되고, 탐지하기가 매우 어려운 형태로 나타나고 있다. 이러한 침입으로 대표적인 것이 분산 공격과 스텔시 공격(Stealthy Attack)이 있다. 분산 공격은 침입자가 공간적으로 분산되어 이를 탐지하기 어렵게 하는 공격을 말하며, 스텔시 공격은 시간적으로 분산되어 이를 탐지하기 어려운 경우를 말한다. 침입 탐지 시스템의 모델링 및 시뮬레이션을 위해서는 침입 탐지 시스템 모델에 필요한 침입을 제공하고, 침입에 대한 탐지 능력을 평가하기 위한 experimental frame을 디자인 해야한다. 본 연구에서는 분산 공격과 스텔시 공격 기능을 갖는 침입 생성 모델링 방법을 소개하며, 침입 생성을 위해 요구되는 침입 정보 베이스의 역할 및 저장 정보를 소개한다. 또한, 침입에 대한 탐지 능력 평가를 위한 Transducer 모델의 디자인을 소개한다.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.1
• /
• pp.39-47
• /
• 2016

In this paper, we propose vehicle SoC fault diagnosis platform using FlexRay protocol in order to detect the faults of semiconductor control chip even after vehicle production. Before FlexRay protocol by sending NFI (Null Frame Indicator) bit among the header segment and a specific identifier in the payload segment of FlexRay frame, this technique can be distinguishable from normal mode and test mode. By using this technique, it is possible to detect the faults such as performance degradation of vehicle network system caused by the aging or several problems of vehicle semiconductor chip. Also high reliability and safety of vehicle can be maintained by using structural test for vehicle SoC fault detection.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.420-423
• /
• 1999

In this paper, we propose the method which efficiently obtain information through edit and retrieval of video data easily and rapidly. To support this method, extract the candidate representative frame using existing scene change detection method and the user selects representative frame for video segmentation at his desire, and then visualization indexing methods supported by logical-links enable users to freely merge and split each scene.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.1
• /
• pp.50-56
• /
• 2016

This paper is about the implementation of the OFDM-based border guard/reconnaissance communication terminal systems. We have implemented Real-time Dynamic DL/UL symbol rate control function using the DL-MAP message, and proposed error detection method caused by malfunctioning and timing optimization method. The proposed scheme detects the variable rate symbol decoding timing without increasing additional physical layer logic, and also provides a wide variety of DL/UL data transfer rate. Furthermore, the proposed scheme applies to the current border guard/reconnaissance equipment and confirms a operation performance through field tests and demonstration at home and abroad.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1538-1552
• /
• 2021

Machine learning models are vulnerable to adversarial examples generated by adding a deliberately designed perturbation to a benign sample. Particularly, for automatic speech recognition (ASR) system, a benign audio which sounds normal could be decoded as a harmful command due to potential adversarial attacks. In this paper, we focus on the countermeasures against audio adversarial examples. By analyzing the characteristics of ASR systems, we find that frame offsets with silence clip appended at the beginning of an audio can degenerate adversarial perturbations to normal noise. For various scenarios, we exploit frame offsets by different strategies such as defending, detecting and hybrid strategy. Compared with the previous methods, our proposed method can defense audio adversarial example in a simpler, more generic and efficient way. Evaluated on three state-of-the-arts adversarial attacks against different ASR systems respectively, the experimental results demonstrate that the proposed method can effectively improve the robustness of ASR systems.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.2
• /
• pp.183-189
• /
• 1987

The performance of frame synchronization can be represented by the values of three characteristic variables-average misframe interval, average syncloss detection time, average reframe time. In this paper, we have analyzed the performance of frame synchronization of the standardized 90Mb/s optical transmission system by Markov chain method, with the suggestion of an extended algorithm for performance improvement. Maximum average reframe time of 1.18 ms can be obtained by the suggested algorithm, which is compared with that of 2.28 ms for the existing algorithm.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.497-502
• /
• 2003

Content-based video copy detection is a complementary approach to watermarking. As opposed to watermarking, which relies on inserting a distinct pattern into the video stream, video copy detection techniques match content-based signatures to detect copies of video. Existing typical content-based copy detection schemes have relied on image matching which is based on key frame detection. This paper proposes a motion directional histogram, which is quantized and accumulated the direction of motion, for video copy detection. The video clip is represented by a motion directional histogram as a 1-dimensional graph. This method is suitable for real time indexing and counting the TV CF verification that is high motion video clips.