• 전자공학회논문지S
• /
• 제36S권8호
• /
• pp.88-100
• /
• 1999

얼굴과 얼굴 구성 요소를 자동으로 검출하는 것은 얼굴 인식 시스템에서 반드시 필요한 과정이다. 본 논문에서는 얼굴의 크기와 회전 변화가 동시에 존재하는 영상에서 log-polar 사상(mapping)에 기반한 단일 log-polar 얼굴 탬플릿(template)을 사용하는 밝기 기반 템플릿 정합(matching)으로 얼굴과 눈을 자동으로 검출하는 새로운 방법을 제안한다. 템플릿 정합에서는 입력 영상의 크기와 회전 변화를 템플릿의 크기와 회전 각도에 대하여 정규화시키는 과정이 필요하다. 그런데 인간 시각 시스템의 space-variant 특성과 유사한 구조를 가지는 log-polar 사상은 입력 영상의 크기와 회전 변화를 log-polar 평면상에서 수평과 수직 순환 이동으로 변화시키는 특성을 갖는다. 이러한 특성을 이용하여 입력 상반신 영상의 fixation point들에서 사상된 후보 log-polar 얼굴들은 log-polar 얼굴들을 log-polar 평면상에서 수평과 수직 이동시켜 템플릿과 정합한다. 따라서 제안한 방법은 얼굴의 크기와 회전 변화에 대응하기 위하여 계산량이 증대되는 multitemplate와 multiresolution 기법들은 적용할 필요성이 없게된다. 이러한 크기와 회전 불변 정합을 이용하여 제안된 방법은 얼굴과 눈을 동시에 검출할 수 있다. 얼굴의 크기와 회전 변화가 존재하는 상반신 영상 795장에 제안한 방법을 적용하여 98.7%의 얼굴과 눈의 검출율을 달성하였다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.43-48
• /
• 2011

Cooling system's operation ratio shall be controlled automatically by the internal external temperature sensors in rolling stock. The Cooling System shall be the automatic operation ratio control system which automatically controlling the rotation speed of condenser, evaporator etc. using temperature detection from outside and inside of cabin. This paper will examine the cooling system that can be provide comfortable cooling service for passenger in summer.

• 방송공학회논문지
• /
• 제24권4호
• /
• pp.580-591
• /
• 2019

본 논문의 목적은 자율주행을 위하여 카메라와 라이다를 이용하여 객체를 검출하고 각 센서에서 검출된 객체를 late fusion 방식으로 융합을 하여 성능을 향상하는 것을 목적으로 한다. 카메라를 이용한 객체 검출은 one-stage 검출인 YOLOv3을, 검출된 객체의 거리 추정은 perspective matrix를, 라이다의 객체 검출은 K-means 군집화 기반 객체 검출을 각각 이용하였다. 카메라와 라이다 calibration은 PnP-RANSAC을 이용하여 회전, 변환 행렬을 구하였다. 센서 융합은 라이다에서 검출된 객체를 이미지 평면에 옮겨 Intersection over union(IoU)을 계산하고, 카메라에서 검출된 객체를 월드 좌표에 옮겨 거리, 각도를 계산하여 IoU, 거리 그리고 각도 세 가지 속성을 로지스틱 회귀를 이용하여 융합을 하였다. 융합을 통하여 각 센서에서 검출되지 않은 객체를 보완해주어 성능이 약 5% 증가하였다.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권2호
• /
• pp.101-111
• /
• 2023

Many spoofing detection studies have been conducted to cope with the most difficult types of deception among various disturbances of GPS, such as jamming, spoofing, and meaconing. In this paper, we propose a spoofing detection scheme based on elevation masked-relative received power between GPS L1 and L2 signals in a system using a multi-band array antenna. The proposed scheme focuses on enabling spoofing to be normally detected and minimizes the possibility of false detection in an environment where false alarms may occur due to pattern distortion among elements of an array antenna. The pattern distortion weakens the GPS signal strength at low elevation. It becomes confusing to detect a spoofing signal based on the relative power difference between GPS L1 and L2, especially when GPS L2 has weak signal strength. We propose design parameters for the relative power threshold including beamforming gain, the minimum received power difference between L1 and L2, and the patch antenna gain difference between L1 and L2. In addition, in order to eliminate the weak signal strength of GPS L2 in the spoofing detection process, we propose a rotation matrix that sets the elevation mask based on platform coordinates. Array antennas generally do not have high usefulness in commercial areas where receivers are operated alone, but are considered essential in military areas where GPS receivers are used together with signal processing for beamforming in the direction of GPS satellites. Through laboratory and live sky tests using the device under test, the proposed scheme with an elevation mask detects spoofing signals well and reduces the probability of false detection relative to that without the elevation mask.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.617-625
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.123-125
• /
• 2005

Many researchers conducted the effort for improving the classification accuracy of satellite image. Most of the study has used optical spectrum information of each pixel for image classification. By applying this method for high resolution satellite image, number of class becomes increase. This situation is remarkable for house, because the roof of house has variety of many colors. Even if the classification is carried out for many classes, roof color information of each house is not necessary. Most of the case, we need the information that object is house or not. In this study, we propose the method for detecting the object by using Genetic Algorithms (GA). Aircraft was selected as object. It is easy for this object to detect in the airport. An aircraft was taken as a template. Object image was taken from QuickBird. Target image includes an aircraft and Haneda Airport. Chromosome has four or five parameters which are composed of number of template, position (x,y), rotation angle, rate of enlarge. Good results were obtained in the experiment.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1302-1312
• /
• 2015

Recent research has been devoted and focused on detecting pedestrian and vehicle in intelligent vehicles except for the vulnerable road user(VRUS). In this paper suggest a new projection method which has robustness for rotation invariant and reducing dimensionality for each cell from original image to detect two-wheeler. We applied new weighting values which are calculated by maximum curvature containing very important object shape features and uniform local binary pattern to remove the noise. This paper considered the Adaboost algorithm to make a strong classification from weak classification. Experiment results show that the new approach gives higher detection accuracy than of the conventional method.

• 전기학회논문지P
• /
• 제64권3호
• /
• pp.187-192
• /
• 2015

Detecting human in images is a challenging task owing to their variable appearance and the wide range of poses the they can adopt. The first need is a robust feature set that allows the human form to be discriminated cleanly, even in cluttered background under difficult illumination. A large number of vision application rely on matching keypoints across images. These days, the deployment of vision algorithms on smart phones and embedded device with low memory and computation complexity has even upped the ante: the goal is to make descriptors faster compute, more compact while remaining robust scale, rotation and noise. In this paper we focus on improving the speed of pedestrian(walking person) detection using Histogram of Oriented Gradient(HOG) descriptors provide excellent performance and tracking using kalman filter.

• 한국멀티미디어학회논문지
• /
• 제7권12호
• /
• pp.1639-1649
• /
• 2004

In this paper, a method for detection of forged signatures based on spectral analysis of directional gradient density function and a weighted fuzzy classifier is proposed. The well defined outline of an incoming signature image is extracted in a preprocessing stage which includes noise reduction, automatic thresholding, image restoration and erosion process. The directional gradient density function derived from extracted signature outline is highly related to the overall shape of signature image, and thus its frequency spectrum is used as a feature set. With this spectral feature set, having a property to be invariant in size, shift, and rotation, a weighted fuzzy classifier is evaluated for the verification of freehand and random forgeries. Experiments show that less than 5% averaged error rate can be achieved on a database of 500 signature samples.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 전기.전자공학 학술대회 논문집
• /
• pp.709-712
• /
• 1988

Ultrasonic Doppler Diagnostic System utilizes the Doppler effect for measurement of blood velocity. The sign of the Doppler frequency shift represents blood flow direction. CW(Continuous-Wave) Doppler System uses quadrature detection and phase rotation method to produce simultaneous independent audio and velocity signals for forward and reverse blood flow direction in the time-domain, had been fabricated. But time-domain analyzing such as audio evaluation and zero- crossing detection for instantaneous and mean frequnecy measurement do not provide both an accurate and quantitative result. Therefore, it is necessary to adopt frequency-domain technique to improve system performance. In this paper, we describe a unit which is composed of CW Doppler System and real-time spectrum analyzer (installed TMS 32010 DSP Chip). This unit shows time-dependent spectrum variation and mean velocity of Blood signal.