• 대한임베디드공학회논문지
• /
• 제11권3호
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• 대한전자공학회논문지SP
• /
• 제47권1호
• /
• pp.169-174
• /
• 2010

이 논문은 잡음환경에서 음성인식률 향상을 위한 끝점 검출 방법에 대해 소개한다. 제안된 방법은 엔트로피와 음성의 하모닉 검출을 이용해 음성 구간과 비음성 구간을 검출한다. 음성의 스펙트럴 에너지에 대한 엔트로피를 사용하여 끝점검출을 하게 되면 비교적 높은 SNR 환경(SNR 15dB)에서는 성능이 우수하나 잡음환경의 변화에 따라 음성과 비음성의 문턱값이 변화 하여 낮은 SNR환경(SNR 0dB)에서는 정확한 끝점 검출이 어렵다. 본 논문은 낮은 SNR 환경(0dB)에서도 정확한 끝점을 검출할 수 있도록 음성의 스펙트럴 엔트로피와 하모닉 성분을 검출하여 끝점을 검출하는 방법을 제안한다. 실험결과 기존의 엔트로피만을 이용한 방법보다 개선된 성능을 보였다.

• 제어로봇시스템학회논문지
• /
• 제21권1호
• /
• pp.21-27
• /
• 2015

A conventional fire detection has been developed based on images captured from a fixed camera. However, It is difficult to apply current algorithms to a flying Quad-rotor to detect fire. To solve this problem, we propose that the fire detection algorithm can be modified for Quad-rotor using Ego-motion compensation. The proposed fire detection algorithm consists of color detection, motion detection, and fire determination using a randomness test. Color detection and randomness test are adapted similarly from an existing algorithm. However, Ego-motion compensation is adapted on motion detection for compensating the degree of Quad-rotor's motion using Planar Projective Transformation based on Optical Flow, RANSAC Algorithm, and Homography. By adapting Ego-motion compensation on the motion detection step, it has been proven that the proposed algorithm has been able to detect fires 83% of the time in hovering mode.

• 한국군사과학기술학회지
• /
• 제9권1호
• /
• pp.24-32
• /
• 2006

This paper is to analyze the effectiveness of multistatic sonar network based on detection performance. The multistatic sonar network is a distributed detection system that places a source and multi-receivers apart. So it needs a detection technique that relates to decision rule and optimization of sonar system to improve the detection performance. For this we propose a data fusion procedure using Bayesian decision and optimal sensor arrangement by optimizing a bistatic sonar. Also, to analyze the detection performance effectively, we propose the environmental model that simulates a propagation loss and target strength suitable for multistatic sonar networks in real surroundings. The effectiveness analysis on the multistatic sonar network confirms itself as a promising tool for effective allocation of detection resources in multistatic sonar system.

• Journal of Power Electronics
• /
• 제16권2호
• /
• pp.760-768
• /
• 2016

Three-phase grid-connected inverters are widely applied in the fields of new energy power generation, electric vehicles and so on. Islanding detection is necessary to ensure the stability and safety of such systems. In this paper, feature recognition technology is applied and a novel islanding detection method is proposed. It can identify the features of inverter systems. The theoretical values of these features are defined as codebooks. The difference between the actual value of a feature and the codebook is defined as the quantizing distortion. When islanding happens, the sum of the quantizing distortions exceeds the threshold value. Thus, islanding can be detected. The non-detection zone can be avoided by choosing reasonable features. To accelerate the speed of detection and to avoid miscalculation, an active islanding detection method based on feature recognition technology is given. Compared to the active frequency or phase drift methods, the proposed active method can reduce the distortion of grid-current when the inverter works normally. The principles of the islanding detection method based on the feature recognition technology and the improved active method are both analyzed in detail. An 18 kVA DSP-based three-phase inverter with the SVPWM control strategy has been established and tested. Simulation and experimental results verify the theoretical analysis.

• 디지털산업정보학회논문지
• /
• 제13권3호
• /
• pp.19-25
• /
• 2017

Nowadays, networked computer systems play an increasingly important role in our society and its economy. They have become the targets of a wide array of malicious attacks that invariably turn into actual intrusions. This is the reason computer security has become an essential concern for network administrators. Recently, a number of Detection/Prevention System schemes have been proposed based on various technologies. However, the techniques, which have been applied in many systems, are useful only for the existing patterns of intrusion. Therefore, probe detection has become a major security protection technology to detection potential attacks. Probe detection needs to take into account a variety of factors ant the relationship between the various factors to reduce false negative & positive error. It is necessary to develop new technology of probe detection that can find new pattern of probe. In this paper, we propose an hybrid probe detection using Fuzzy Cognitive Map(FCM) and Self Adaptive Module(SAM) in dynamic environment such as Cloud and IoT. Also, in order to verify the proposed method, experiments about measuring detection rate in dynamic environments and possibility of countermeasure against intrusion were performed. From experimental results, decrease of false detection and the possibilities of countermeasures against intrusions were confirmed.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 추계학술대회
• /
• pp.328-330
• /
• 2015

에지는 영상에 포함된 물체의 크기, 방향, 위치 등을 쉽게 획득할 수 있는 특징 정보이며, 에지 검출은 물체 검출, 물체 인식 등의 여러 영상 처리 응용 분야에서 전처리 과정으로 활용되고 있다. 기존의 에지 검출 방법에는 Sobel, Prewitt, Roberts 에지 검출 방법 등이 있다. 이러한 기존의 에지 검출 방법들은 구현이 간단하며, 고정 가중치 마스크를 적용하므로 에지 검출 특성이 다소 미흡하다. 따라서 기존의 에지 검출 방법들의 문제점을 보완하기 위하여, 본 논문에서는 국부 마스크 내의 평균 및 표준편차에 따라 가중치를 적용한 후 에지를 검출하는 알고리즘을 제안하였다.

• 한국통신학회논문지
• /
• 제31권6A호
• /
• pp.586-592
• /
• 2006

대역확산 시스템에서 나머지 도플러 주파수 오프셋이 (residual Doppler frequency offset, RDFO) 있으면 부호 동기가 정확히 맞을 때에도 표본화된 최고 상관값은 실제 상관값의 꼭지값보다 낮다. 이로 말미암아 기존 단일 주파수 셀 (single frequency cell, SFC) 검파기법의 성능은 떨어진다. 이 논문에서는 RDFO가 있을 때 실제 꼭지값 근처에 상관값이 큰 여러 표본이 존재하는 것에 착안하여 새로운 탐색기법을 제안한다. 이를 위해 먼저 대역 확산 시스템에서 RDFO가 성능을 떨어뜨리는지 분석한다. 그 뒤, 기존 기법과 제안한 기법의 검파확률과 오경보확률을 얻고, 모의실험을 수행하여 RDFO가 있을 때 제안한 기법이 기존 기법보다 성능이 뛰어남을 보인다.

• Journal of Information Processing Systems
• /
• 제7권1호
• /
• pp.173-186
• /
• 2011

Due to the disadvantages of signature-based computer virus detection techniques, behavior-based detection methods have developed rapidly in recent years. However, current popular behavior-based detection methods only take API call sequences as program behavior features and the difference between API calls in the detection is not taken into consideration. This paper divides virus behaviors into separate function modules by introducing DLLs into detection. APIs in different modules have different importance. DLLs and APIs are both considered program calling resources. Based on the calling relationships between DLLs and APIs, program calling resources can be pictured as a tree named program behavior resource tree. Important block structures are selected from the tree as program behavior features. Finally, a virus detection model based on behavior the resource tree is proposed and verified by experiment which provides a helpful reference to virus detection.

• 제어로봇시스템학회논문지
• /
• 제21권11호
• /
• pp.989-995
• /
• 2015

Due to the recent increase of the importance and demand of security services, the importance of a surveillance monitor system that makes an automatic security system possible is increasing. As the market for surveillance monitor systems is growing, price competitiveness is becoming important. As a result of this trend, surveillance monitor systems based on an embedded system are widely used. In this paper, an object detection algorithm based on an embedded system for a surveillance monitor system is introduced. To apply the object detection algorithm to the embedded system, the most important issue is the efficient use of resources, such as memory and processors. Therefore, designing an appropriate algorithm considering the limit of resources is required. The proposed algorithm uses two background models; therefore, the embedded system is designed to have two independent processors. One processor checks the sub-background models for if there are any changes with high update frequency, and another processor makes the main background model, which is used for object detection. In this way, a background model will be made with images that have no objects to detect and improve the object detection performance. The object detection algorithm utilizes one-dimensional histogram distribution, which makes the detection faster. The proposed object detection algorithm works fast and accurately even in a low-priced embedded system.