• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권10호
• /
• pp.3520-3537
• /
• 2014

Video copy detection methods have emerged in recent years for a variety of applications. However, the lack of efficiency in the usual retrieval systems restricts their use. In this paper, we propose a parallel implementation strategy for content based video copy detection (CBCD) by using a multi-core processor. This strategy can support video copy detection effectively, and the processing time tends to decrease linearly as the number of processors increases. Experiments have shown that our approach is successful in speeding up computation and as well as in keeping the performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1334-1337
• /
• 2004

This paper presents a novel method to speed up neural network (NN) based face detection systems. NN-based face detection can be viewed as a classification and search problem. The proposed method formulates the search problem as an integer nonlinear optimization problem (INLP) and expands the basic particle swarm optimization (PSO) to solve it. PSO works with a population of particles, each representing a subwindow in an input image. The subwindows are evaluated by how well they match a NN-based face filter. A face is indicated when the filter response of the best particle is above a given threshold. To achieve better performance, the influence of PSO parameter settings on the search performance was investigated. Experiments show that with fine-adjusted parameters, the proposed method leads to a speedup of 94 on 320${\times}$240 images compared to the traditional exhaustive search method.

• 대한교통학회지
• /
• 제20권5호
• /
• pp.163-174
• /
• 2002

최근 국내에 확대 설치되고 있는 자동과속단속시스템의 핵심은 주행차량의 지점속도를 측정하는 속도검지부의 정확도라 할 수 있다. 우리나라 속도검지부의 경우 대부분 2중 루프검지기를 이용하여 속도를 측정하고 있는 데 속도측정정확도는 루프검지기의 하드웨어 성능뿐 아니라 루프검지기 발생신호를 처리하는 알고리즘에 상당부분 의존한다. 따라서 본 연구에서는 2중 루프검지기의 속도측정 정확도를 높이기 위한 신호처리 알고리즘을 개발하고 이를 현장에서 평가하였다. 먼저 이론 및 현장실험에서 밝혀진 문제점들을 분석하여 원인별로 개선방향을 분류한 뒤 알고리즘을 개발하였다. 이를 위해서 첫째, 검지기의 2개의 진입시점 신호 뿐 아니라 진출시점 신호까지 포함시켜 정확도를 높이는 2중 처리 알고리즘을 개발하였다. 둘째, 속도측정 오차의 허용범위인 $\pm$5%를 초과하는 원인이 되는 검지영역내 비정상적인 주행궤적차량 즉, 대자선주행과 동시진입차량을 걸러내는 필터링알고리즘을 개발하였다. 현장실험을 통하여 개발 알고리즘의 정확성을 평가한 결과 속도측정정확도가 대폭적으로 개선됨을 확인할 수 있었다. 또한 패각선 주행차량, 동시진입차량 등 검지영역 내에서 비정상적 주행궤적을 발생시켜 심각한 오차를 발생시키는 차량들을 성공적으로 제거할 수 있었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.593-596
• /
• 2018

The speed of vehicles has remained a significant factor that influences the severity of accidents and traffic accident rate in many parts of the world including South Korea. This behavior where drivers drive at speeds which exceed a posted safe threshold is known as 'speeding'. Over the past twenty years, the Korean National Police Agency (NPA) has become aware of an increased frequency of drivers who are speeding. Therefore, fixed-type ASE systems [1] have been installed on hazardous road sections of many highways. These system monitor vehicle speeds using a camera. However, the use of ASE systems has changed the behavior of the drivers. Specifically, drivers reduce speed or avoid the route where the cameras are mounted. It is not practical to install cameras at every possible location. Therefore, it is challenging to thoroughly explore the location where speeding occurs. In view of these problems, the author of this paper designed and implemented a prototype visualization system in which point and color are used to show vehicle location and associated over-speed information. All of this information was used to create a comprehensive visualization application to show information about vehicle driving. In this paper, we present an approach detecting vehicles moving at speeds which exceed a threshold and visualizing the points those violations occur on a map. This was done using vehicle trajectory data collected in Daegu city. We propose steps for exploring the data collected from those sensors. The resulting mapping has two layers. The first layer contains the dynamic vehicle trajectory data. The second underlying layer contains the static road networks. This allows comparing the speed of vehicles on roads with the known maximum safe speed of those roads, and presents the results with a visualization tool. We also compared data about people who drive over threshold safe speeds on each road on days and weekends based on vehicle trajectories. Finally, our study suggests improved times and locations where law enforcement should use monitoring with speed cameras, and where they should be stricter with traffic law enforcement. We learned that people will drive over the speed limit at midnight more than 1.9 times as often when compared with rush hour traffic at 8 o'clock in the morning, and 4.5 times as often when compared with traffic at 7 o'clock in the evening. Our study can benefit the government by helping them select better locations for installation of speed cameras. This would ultimately reduce police labor in traffic speed enforcement, and also has the potential to improve traffic safety in Daegu city.

• ETRI Journal
• /
• 제37권2호
• /
• pp.212-221
• /
• 2015

As the amount of re-sequencing genome data grows, minimizing the execution time of an analysis is required. For this purpose, recent computing systems have been adopting both high-performance coprocessors and host processors. However, there are few applications that efficiently utilize these heterogeneous computing resources. This problem equally refers to the work of single nucleotide polymorphism (SNP) detection, which is one of the bottlenecks in genome data processing. In this paper, we propose a method for speeding up an SNP detection by enhancing the utilization of heterogeneous computing resources often used in recent high-performance computing systems. Through the measurement of workload in the detection procedure, we divide the SNP detection into several task groups suitable for each computing resource. These task groups are scheduled using a window overlapping method. As a result, we improved upon the speedup achieved by previous open source applications by a magnitude of 10.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2003년도 Proceeding
• /
• pp.197-206
• /
• 2003

With the growing usage of the networks, the world-wide Internet has become the main means to exchange data and carry out transactions. It has also become the main means to attack hosts. To solve the security problems which occur in the network such as Internet, we import software products of network security elements like an IDS (Intrusion Detection System) and a firewall. In this paper, we have designed and constructed the General Simulation Environment of Network Security model composed of multiple IDSes and a firewall which coordinate by CNP (Contract Net Protocol) for the effective detection of the intrusion. The CNP, the methodology for efficient integration of computer systems on heterogeneous environment such as distributed systems, is essentially a collection of agents, which cooperate to resolve a problem. Command console in the CNP is a manager who controls tie execution of agents or a contractee, who performs intrusion detection. In the Network Security model, each model of simulation environment is hierarchically designed by DEVS (Discrete EVent system Specification) formalism. The purpose of this simulation is to evaluate the characteristics and performance of CNP architecture with rete pattern matching algorithm and the application of rete pattern matching algorithm for the speeding up the inference cycle phases of the intrusion detection expert system.

• 한국ITS학회 논문지
• /
• 제16권2호
• /
• pp.105-115
• /
• 2017

루프 검지기, 영상 검지기 등의 기존 교통 검지기들은 설치와 유지보수에 드는 비용이 크고, 밤과 낮에 따라 상이한 검지 알고리즘이 필요하거나 날씨에 따라 검지율의 편차가 크다는 단점을 가지고 있다. 반면에 밀리미터파 레이더는 악천후에 의한 영향을 받지 않고, 주야간에 관계없이 일정한 검지 성능을 얻을 수 있다. 덧붙여 설치와 유지보수를 위하여 교통 통제의 필요가 없고, 다수의 차량을 동시에 검지 가능하다. 본 연구는 이러한 장점을 가진 레이더 센서를 활용한 다중 물체 검지 알고리즘을 기존의 단일 물체 검지 알고리즘을 응용하여 구현하였으며 이에 대한 평가를 수행하여 의미 있는 결과를 얻었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.692-712
• /
• 2022

Buoys used for Aid to Navigation systems are widely used to guide the sea paths and are powered by batteries, requiring continuous battery replacement. However, since human labor is required to replace the batteries, humans can be exposed to dangerous situation, including even collision with shipping vessels. In addition, Maritime sensors are installed on the route signs, so that these are often damaged by collisions with small and medium-sized ships, resulting in significant financial loss. In order to prevent these accidents, maritime object detection technology is essential to alert ships approaching buoys. Existing studies apply a number of filters to eliminate noise and to detect objects within the sea image. For this process, most studies directly access the pixels and process the images. However, this approach typically takes a long time to process because of its complexity and the requirements of significant amounts of computational power. In an emergent situation, it is important to alarm the vessel's rapid approach to buoys in real time to avoid collisions between vessels and route signs, therefore minimizing computation and speeding up processes are critical operations. Therefore, we propose Fast Connected Component Labeling (FCCL) which can reduce computation to minimize the processing time of filter applications, while maintaining the detection performance of existing methods. The results show that the detection performance of the FCCL is close to 30 FPS - approximately 2-5 times faster, when compared to the existing methods - while the average throughput is the same as existing methods.

• 한국ITS학회 논문지
• /
• 제12권6호
• /
• pp.108-115
• /
• 2013

영상취득 장치를 이용한 지능화된 감시 장치의 개발 기술 또한 발전하고 있다. 이 분야의 기술 영역은 감시하고 있는 장소에 어떤 사람이나 물체를 탐지하는 전경 분리 기술과 사람이나 물체의 이동 경로를 파악하는 추적 기술로 나뉜다. 본 논문에서는 이동체를 탐지하는 기술로서 잡음이나 조도의 변화에 비교적 안정적인 엔진개발을 위한 개선된 알고리즘을 제안한다. 논문의 제안 알고리즘은 사람이나, 동물, 또는 비교적 저속 운행 중인 차량 등의 탐지에 적합한 모델로서, 조도의 변화나 잡음에 안정적이면서 실시간 처리가 가능한 방법을 고안하는 데 주안점을 두고 있다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 추계학술대회
• /
• pp.78-81
• /
• 2012

본 논문에서는 차량 출입통제, 주정차 단속, 과속 차량 단속 등 다양한 분야에서 사용가능한 신형 차량번호판 검출 방법을 제안한다. 먼저 가우시안 차이를 이용한 필터링을 사용하여 번호판의 연속적인 주요 숫자가 잘 나타나도록 이진화를 수행한다. 이후 번호판의 형태학적 특징을 이용한 반복 레이블링 기법을 이용하여 번호판 영역을 결정한다. 마지막으로 투영 변환을 통한 번호판의 정형화 과정을 거쳐 카메라나 차량의 위치에 따라 발생하는 기울어짐과 같은 왜곡을 보정한다.