• 한국멀티미디어학회논문지
• /
• 제20권6호
• /
• pp.893-910
• /
• 2017

In this paper, we propose a simple online multiple object (human) tracking method, LKDeep (Lucas-Kanade feature and Detection based Simple Online Multiple Object Tracker), which can run in fast online enough on CPU core only with acceptable tracking performance for embedded surveillance purpose. The proposed LKDeep is a pragmatic hybrid approach which tracks multiple objects (humans) mainly based on LK features but is compensated by detection on periodic times or on necessity times. Compared to other state-of-the-art multiple object tracking methods based on 'Tracking-By-Detection (TBD)' approach, the proposed LKDeep is faster since it does not have to detect object on every frame and it utilizes simple association rule, but it shows a good object tracking performance. Through experiments in comparison with other multiple object tracking (MOT) methods using the public DPM detector among online state-of-the-art MOT methods reported in MOT challenge [1], it is shown that the proposed simple online MOT method, LKDeep runs faster but with good tracking performance for surveillance purpose. It is further observed through single object tracking (SOT) visual tracker benchmark experiment [2] that LKDeep with an optimized deep learning detector can run in online fast with comparable tracking performance to other state-of-the-art SOT methods.

• Journal of Communications and Networks
• /
• 제12권4호
• /
• pp.375-381
• /
• 2010

A flooding attack, such as DoS or Worm, can be easily created or even downloaded from the Internet, thus, it is one of the main threats to servers on the Internet. This paper presents an online real-time network response system, which can determine whether a LAN is suffering from a flooding attack within a very short time unit. The detection engine of the system is based on the incremental mining of fuzzy association rules from network packets, in which membership functions of fuzzy variables are optimized by a genetic algorithm. The incremental mining approach makes the system suitable for detecting, and thus, responding to an attack in real-time. This system is evaluated by 47 flooding attacks, only one of which is missed, with no false positives occurring. The proposed online system belongs to anomaly detection, not misuse detection. Moreover, a mechanism for dynamic firewall updating is embedded in the proposed system for the function of eliminating suspicious connections when necessary.

• ETRI Journal
• /
• 제34권2호
• /
• pp.288-291
• /
• 2012

In this letter, a new online anomaly detection approach for software systems is proposed. The novelty of the proposed approach is to apply a new semantic kernel function for a support vector machine (SVM) classifier to detect fault-suspicious execution paths at runtime in a reasonable amount of time. The kernel uses a new sequence matching algorithm to measure similarities among program execution paths in a customized feature space whose dimensions represent the largest common subpaths among the execution paths. To increase the precision of the SVM classifier, each common subpath is given weights according to its ability to discern executions as correct or anomalous. Experiment results show that compared with the known kernels, the proposed SVM kernel will improve the time overhead of online anomaly detection by up to 170%, while improving the precision of anomaly alerts by up to 140%.

• Nuclear Engineering and Technology
• /
• 제53권9호
• /
• pp.2899-2908
• /
• 2021

The laser transport system of the high power laser facility is mainly composed of large-aperture laser transport mirrors (TMs). Obtaining the high-resolution online damage images during the operation, which is of great significance for operating safely of the mirrors and the facility. Based on wavefront coding, pan-tilt scanning and image stitching technologies, an online laser-damage images detection system is designed, and it can achieve high-precision detection of surface characteristics of large-aperture laser transport mirrors. The preliminary simulation proves that the system can solve the depth of field matching problem caused by pan-tilt tilt imaging and achieve higher resolution.

• 한국음향학회지
• /
• 제41권2호
• /
• pp.199-209
• /
• 2022

일반적인 비정상 탐지 알고리즘은 사전 데이터를 이용하여 학습된다. 따라서 시간에 따른 정상 데이터의 특징이 변화되는 경우에 기존의 배치 학습 기반 알고리즘의 성능 저하가 불가피하다. 본 논문에서는 정상 데이터의 점진적 특징 변화를 고려할 수 있는 온라인 비정상 탐지 알고리즘을 제안한다. 제안하는 알고리즘은 단일 클래스 분류 모델에 기반하며 오프라인 및 온라인 단계의 학습 과정을 포함한다. 제안된 알고리즘의 오프라인 학습 단계에서는 사전 데이터가 잠재 공간의 중심에 근접하도록 학습하고, 이후 온라인 학습단계에서는 신규 데이터에 의한 점진적 잠재 공간의 중심을 갱신하고, 갱신된 중심을 기준으로 계속 학습을 진행한다. 공개된 수중 음향 데이터를 이용한 실험결과 제안된 온라인 비정상 탐지 알고리즘은 점진적 중심 갱신 및 학습을 위해 단지 2 % 정도의 추가 학습시간이 소요되는 것으로 확인되었다. 반면에 시변 정상데이터가 수신되는 경우에 오프라인 학습 모델과 비교하여 19.10 % 개선된 Area Under the receiver operating characteristic Curve(AUC) 성능을 보였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.677-679
• /
• 1999

This paper introduces a implementation of fault detection for national highway line 3. Fault detection system was installed and operated on national highway line 3, environmental elements caused by abnormal status or faults has often happened. Therefore, the function of fault detection system is to speedy notify fault site, cause as well as scale of fault to manager. Though the fault detection and diagnosis system has been imported in the field of process of water and electric power, it is just beginning step in the field of ITS(Intelligent Transportation Systems). In general, Maintenance system is performed the online/offline process of detection, diagnosis and measure. This paper is studied online detection process, which is realtime remote detection.

• 한국게임학회 논문지
• /
• 제11권6호
• /
• pp.81-93
• /
• 2011

온라인상에서 사용자의 개인정보를 불법적으로 취득, 악용하는 계정도용 문제는 금전적인 이득을 얻을 수 있는 MMORPG(Massively Multi-player Online Role Playing Games)에서 특히 빈번하게 발생하고 있다. 많은 사람들이 게임을 이용하여 심각한 피해로 이어질 수 있기 때문에 이에 대한 대책마련이 시급함에도 불구하고, 이를 예방하거나 탐지하는 기법에 대한 연구가 많이 부족한 실정이다. 본 연구에서는 온라인게임에서 발생했던 실제 계정도용 사례 분석을 통해 계정도용의 유형을 체계적으로 정의하고, 유형별로 계정도용을 분류하는 자동화된 탐지모델을 제안한다. 실 계정도용 사례를 분석한 결과 속전속결형, 신중형, 대담무쌍형의 3가지로 구분되었으며 이 분류 체계와 탐지모델을 국내 주요 온라인게임회사 중 한 곳에 적용하였다. 본 연구에서 제시한 유형별 탐지모델은 해킹의 유무만을 판정하던 기존의 모델보다 탐지에 있어서 향상된 성능을 보였다.

• 전자통신동향분석
• /
• 제36권2호
• /
• pp.75-82
• /
• 2021

Online action detection (OAD) in a streaming video is an attractive research area that has aroused interest lately. Although most studies for action understanding have considered action recognition in well-trimmed videos and offline temporal action detection in untrimmed videos, online action detection methods are required to monitor action occurrences in streaming videos. OAD predicts action probabilities for a current frame or frame sequence using a fixed-sized video segment, including past and current frames. In this article, we discuss deep learning-based OAD models. In addition, we investigated OAD evaluation methodologies, including benchmark datasets and performance measures, and compared the performances of the presented OAD models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.600-619
• /
• 2015

We propose a cost-efficient hybrid algorithm for online location updates that efficiently combines feature point detection with the online trajectory-based sampling algorithm. Our algorithm is designed to minimize the average trajectory error with the minimal number of sample points. The algorithm is composed of 3 steps. First, we choose corner points from the map as sample points because they will most likely cause fewer trajectory errors. By employing the online trajectory sampling algorithm as the second step, our algorithm detects several missing and important sample points to prevent unwanted trajectory errors. The final step improves cost efficiency by eliminating redundant sample points on straight paths. We evaluate the proposed algorithm with real GPS trajectory data for various bus routes and compare our algorithm with the existing one. Simulation results show that our algorithm decreases the average trajectory error 28% compared to the existing one. In terms of cost efficiency, simulation results show that our algorithm is 29% more cost efficient than the existing one with real GPS trajectory data.

• 정보보호학회논문지
• /
• 제25권5호
• /
• pp.1097-1114
• /
• 2015

빠르게 성장한 게임 시장의 규모에 따라 게임봇, 게임핵, 골드파밍, 사설서버, 시스템 해킹, 네트워크 해킹, 계정도용 등과 같은 게임을 이용한 여러 불법 행위가 증가해 왔다. 이러한 불법 행위를 예방 및 탐지하기 위해 게임 보안 솔루션들이 존재하지만 각 게임마다의 특징이 존재하기 때문에 부정행위로부터 보호하는 것에는 어려움이 있다. 또한 게임 보안은 게임의 기획과 조화되는 게임 보안 솔루션 및 탐지 방법들이 필요하다. 본 연구에서는 최근 온라인 게임에서의 보안 관련 연구에 대한 동향을 조사하였다. 온라인 게임에서의 부정행위를 분류하였고, 온라인 게임에서의 각 특징에 따른 부정행위 예방 및 탐지 방법을 분류하였다.