• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2007년도 추계학술대회 학술발표 논문집
• /
• pp.427-430
• /
• 2007

기존의 LVQ(Learning Vector Quantization) 방법을 이용하여 물체를 분류하면 데이터의 학습이 빠르고 연산량이 적어 실시간으로 물체를 분류할 수 있는 장점이 있다. 하지만 데이터의 훈련시 output neuron의 개수를 정확히 예측할 수 없고 output neuron의 개수에 따라 물체를 분류하는 정확도가 매우 달라질 수 있다. 그러므로 본 논문에서는 output neuron의 개수를 데이터의 특성에 맞게 결정해주는 알고리즘을 제시한다. DLVQ(Dynamic Learning Vector Quantization) 알고리즘은 승자로 결정된 가중치 벡터의 부류가 샘플 데이터의 부류와 같으면 업데이트하고 다르면 새로운 가중치 벡터로 생성한다. 제한한 알고리즘의 가장 다른 부분은 미리 output neuron의 개수를 정하는 것이 아니라 훈련 과정에서 동적으로 output neuron의 개수를 생성하는 것이다. 그리고 클러터의 구분 방법을 제시하여 사람, 차, 클러터를 구분할 수 있다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2007년도 춘계학술대회 학술발표 논문집 제17권 제1호
• /
• pp.353-356
• /
• 2007

본 논문은 비정형 객체를 추적함에 있어서 다른 객체와 겹쳐진 후 계속 추적할 수 있는 방법을 제시한다. 기본적으로 색 정보 기반의 CAMshift 알고리즘을 바탕으로 각 프레임마다 color template를 업데이트하여 현재의 객체와 template를 비교하고, 업데이트 된 color template를 바탕으로 색 분포를 사용하여 CAMshift 결과를 비교하여 추적하는 물체를 보다 정확하게 판별할 수 있도록 한다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.567-570
• /
• 2003

A color restoration algorithm for dynamic images under multiple luminance conditions is proposed by using correction vectors, defined for sub regions that the original target is divided into and calculated from color information given in well-illuminated regions. These vectors restore chromatic information of the restored image obtained by the color restoration algorithm in a low luminance condition. Under the condition that the size of dynamic color images in multiple luminance conditions is $320\times240$, experimental results show that the restored image by the proposed algorithm decreases the color-difference about 30％ than that of the restoration algorithm with color change vectors in a low luminance condition. The proposed algorithm aims to construct the surveillance system with a low cost CCD camera in the real world.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권4호
• /
• pp.246-252
• /
• 2017

Non-invasive and non-restrictive methods for measuring the physiological functions of the human body are useful for health care, security, and surveillance. In this paper, a new method that extracts human heartbeat information by utilizing ultra-wideband (UWB) impulse radar is proposed. The amplitude spectra of received radar pulses reflected from the human body are accumulated at specific time intervals, and chirp z-transform (CZT) is used to extract the heartbeat frequency from the amplitude spectra. The heartbeat frequency can be extracted with high-frequency resolution in the frequency band of the heartbeat of interest using CZT. Experimental results to verify the performance of the proposed method show that a highly accurate extraction of the heartbeat frequency is possible using this method.

• 한국지능시스템학회논문지
• /
• 제17권3호
• /
• pp.349-354
• /
• 2007

물체를 추적하는데 있어서 추적하고자 하는 물체를 검출하여 템플릿을 만드는 것과 두 물체가 겹쳐지거나 다른 배경에 가려진 물체를 구분하여 추적하는 것은 물체 추적에 있어서 중요한 문제이다. 물체를 검출하여 템플릿을 만드는 방법으로 Frame Difference를 이용하면 천천히 움직이는 물체를 잘 구분할 수 없는 문제점이 있다. 이를 해결하기 위하여 본 논문에서는 Adaptive 3-Frame Difference를 이용하여 정확한 물체의 템플릿을 생성하는 알고리즘을 제안한다.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1494-1507
• /
• 2018

Intelligent human identification using face information has been the research hotspot ranging from Internet of Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligent access control. Since 2D face images are usually captured from a long distance in an unconstrained environment, to fully exploit this advantage and make human recognition appropriate for wider intelligent applications with higher security and convenience, the key difficulties here include gray scale change caused by illumination variance, occlusion caused by glasses, hair or scarf, self-occlusion and deformation caused by pose or expression variation. To conquer these, many solutions have been proposed. However, most of them only improve recognition performance under one influence factor, which still cannot meet the real face recognition scenario. In this paper we propose a multi-scale parallel convolutional neural network architecture to extract deep robust facial features with high discriminative ability. Abundant experiments are conducted on CMU-PIE, extended FERET and AR database. And the experiment results show that the proposed algorithm exhibits excellent discriminative ability compared with other existing algorithms.

• 한국멀티미디어학회논문지
• /
• 제15권4호
• /
• pp.449-471
• /
• 2012

In intelligent surveillance systems, it is required to robustly track multiple people. Most of the previous studies adopted a Gaussian mixture model (GMM) for discriminating the object from the background. However, it has a weakness that its performance is affected by illumination variations and shadow regions can be merged with the object. And when two foreground objects overlap, the GMM method cannot correctly discriminate the occluded regions. To overcome these problems, we propose a new method of tracking and identifying multiple people. The proposed research is novel in the following three ways compared to previous research: First, the illuminative variations and shadow regions are reduced by an illumination normalization based on the median and inverse filtering of the L*a*b* image. Second, the multiple occluded and overlapped people are tracked by combining the GMM in the still image and the Lucas-Kanade-Tomasi (LKT) method in successive images. Third, with the proposed human tracking and the existing face detection & recognition methods, the tracked multiple people are successfully identified. The experimental results show that the proposed method could track and recognize multiple people with accuracy.

• 한국컴퓨터정보학회논문지
• /
• 제22권12호
• /
• pp.79-85
• /
• 2017

In this paper, we propose a CNN-based swimmer detection algorithm. Every year, water safety accidents have been occurred frequently, and accordingly, intelligent video surveillance systems are being developed to prevent accidents. Intelligent video surveillance system is a real-time system that detects objects which users want to do. It classifies or detects objects in real-time using algorithms such as GMM (Gaussian Mixture Model), HOG (Histogram of Oriented Gradients), and SVM (Support Vector Machine). However, HOG has a problem that it cannot accurately detect the swimmer in a complex and dynamic environment such as a beach. In other words, there are many false positives that detect swimmers as waves and false negatives that detect waves as swimmers. To solve this problem, in this paper, we propose a swimmer detection algorithm using CNN (Convolutional Neural Network), specialized for small object sizes, in order to detect dynamic objects and swimmers more accurately and efficiently in complex environment. The proposed CNN sets the size of the input image and the size of the filter used in the convolution operation according to the size of objects. In addition, the aspect ratio of the input is adjusted according to the ratio of detected objects. As a result, experimental results show that the proposed CNN-based swimmer detection method performs better than conventional techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1043-1064
• /
• 2020

A kind of Subjective Imaging Effect Assessment (SIEA) method and its applications on intelligent imaging terminal design in engineering site are presented. First, some visual assessment indices are used to characterize the imaging effect: the image brightness, the image brightness uniformity, the color image contrast, the image edge blur, the image color difference, the image saturation, the image noise, and the integrated imaging effect index. A linear weighted function is employed to carry out the SIEA computation and the Analytic Hierarchy Process (AHP) technique is used to estimate its weights. Second, a SIEA software is developed. It can play images after the settings of assessment index or assessment reaction time, etc. Third, two cases are used to illustrate the application effects of proposed method: the image enhancement system design for surveillance camera and the imaging environment perception system design for intelligent lighting terminal. A Prior Sequential Stimulus (PSS) experiment is proposed to improve the evaluation stability of SIEA method. Many experiment results have shown the proposed method can realize a stable system design or parameters setting for the intelligent imaging terminal in engineering site.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.950-953
• /
• 2007

본 논문에서는 인간과 환경사이의 물리적 또는 심리적 인터액션을 통한 인간중심의 적절한 서비스를 제공하는 공간지능화(iSpace: Intelligent Space) 구현하고자 네트웍 센서 인식공간을 소개하고 있다. 영상 데이터 처리 및 정보 네트웍 기능을 갖는 다수의 컬러 CCD 카메라를 iSpace 공간에 분산 배치하였다. iSpace내의 정보획득을 위한 네트웍 센서를 분산 지능형 네트웍 디바이스(DIND: Distributed Intelligent Network Devices)라고 명명하고 있으며, 각 DIND는 일종의 클라이언트 역할을 수행하도록 하였으며, DIND는 카메라 센서를 이용하는 이른바 카메라 네트워크를 구성한 것으로 이를 통해 실내 환경을 인식하고 모델링 하며 공간 내 거주자의 의도를 인식하기 위한 시스템을 구축하였다.