• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.272-275
• /
• 2016

This paper presents a method of single image dehazing and surface-based feature detection for remote sensing images. In the conventional dark channel prior (DCP) algorithm, the resulting transmission map invariably includes some block artifacts because of patch-based processing. This also causes image blur. Therefore, a refined transmission map based on a hidden Markov random field and expectation-maximization algorithm can reduce the block artifacts and also increase the image clarity. Also, the proposed algorithm enhances the accuracy of image matching surface-based features in an remote sensing image. Experimental results confirm that the proposed algorithm is superior to conventional algorithms in image haze removal. Moreover, the proposed algorithm is suitable for the problem of image matching based on feature extraction.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.247-252
• /
• 2004

This paper proposes a matching algorithm using Voronoi diagram for rotation and translation invariant fingerprint identification. The proposed algorithm extracts geometrical structures that are derived from Voronoi diagram of a fingerprint image. Then two features, distances and angles are extracted from the geometrical structures and saved as indexing form for fingerprint matching. This matching algerian has a lower error rate than indexing based methods of old times.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.11
• /
• pp.137-146
• /
• 2015

In this paper, we propose a pothole detection method using various features of intensity and motion. Segmentation, decision steps of pothole detection are processed according to the values which are derived from feature characteristics. For segmentation using intensity, we use a binarization method using histogram to separate pothole region from background. For segmentation using motion, we filter using high pass filter and get standard deviation value. This value is divided by regression value according to camera environment such as photographing angle, height, velocity, etc. We get binary image by histogram based binarization. For decision, candidate regions are decided whether pothole or not using comparison of candidate and background's features. Experimental results show that our proposed pothole detection method has better results than existing methods and good performance in discrimination between pothole and similar patterns.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.750-753
• /
• 2012

A method detecting the position of eyes and tracking a gaze point of eyes in realtime using POSIT is suggested in this paper. This algorithm find out a candidate area of eyes using topological characteristics of eyes and then decides the center of eyes using physical characteristics of eyes. To find the eyes, a nose and a mouth are used for POSIT. The experimental results show that proposed method effectively performed detection of eyes in facial image in FERET databases and gave high performance when used for tracking a gaze point of eyes.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1718-1720
• /
• 2013

본 논문에서는 다중 손 끝점 검출을 위해 특징 추출 기법 및 이를 기반으로 한 손 끝점 검출 알고리즘을 제안한다. 특징 추출을 위해 Local Binary Feature(LBP)을 사용하였고 특징의 차원을 축소하기 위해 Principal Component Analysis(PCA) 기법을 이용하였다. 손 끝점 판별을 위해 Reduced multivariate polynomial Model(RM) Classifier를 사용하여 실험 결과 제안된 손 끝점 검출 기법이 다양한 환경에서 동작 하는 것을 확인 하였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.381-384
• /
• 2002

본 논문에서는 실험 영상으로부터 학습된 피부색상 정보를 이용하여 컬러 공간테이블을 생성한 후. 입력된 영상의 컬러와 공간정보를 학습된 피부색상 공간테이블로부터 비교, 분석하여 얼굴후보영역을 찾고자 하였다. 또한 추출된 후보영역의 레이블된 특징정보를 이용하여 지역적 특징을 찾아낸 후 얼굴 특징점의 위치에 따른 형태정보를 이용하여 신뢰할 수 있는 얼굴 영역을 검출하고자 하였다. 제안된 피부색상(Skin-tone)공간테이블은 변환하기 쉽고 계산이 빠른 RGB컬러 공간에서 실험, 평가되었으며, 실시간으로 입력된 영상의 정규화된 책상 값을 유사성 정도에 따라 레이블링하여 보다 빠른 얼굴 후보 영역의 검출과 검증을 할 수 있도록 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.108-111
• /
• 2008

본 논문에서는 KLT(Kanade-Lucas-Tomasi) 추적기에서 특징점의 개수를 일정하게 유지시키기 위해 존재하는 특징점의 관리 부분을 FPGA(Field Programmable Gate Array)에 구현하기 위한 구조를 제안한다. FPGA 에 구현하기 위해 한정된 자원을 효과적으로 사용하도록 하는 것을 목표로 연산량이 많은 부분을 적은 연산량으로 구현 가능한 것으로 대체하고, 메모리의 크기와 접근 회수를 줄이기 위한 방법을 고려했다. 구현이 간단한 Harris 코너 검출기를 이용하여 특징점을 선택하고, 나눗셈 연산이 필요 없는 히스토그램을 이용하여 임계값을 설정해 특징점을 관리했다. C 언어로 시뮬레이션을 수행하여 제안한 방법을 확인했고, 기존의 특징점 관리 방법과의 비교를 통해 검증했다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.15-18
• /
• 2011

본 논문에서는 이동형 패럴랙스 배리어 방식의 모바일 3D 디스플레이에 응용하기 위해 개발된 시역계측알고리즘[1]을 실제시스템에 구현한 후 문제점을 분석하고, 그 문제점을 해결할 수 있는 새로운 방법을 제안한다. 본 연구팀에서 이동형 패럴랙스 배리어 방식의 모바일 3D 디스플레이에 응용하기 위해 개발한 이전의 시역계측기술[1]은 기존의 비올라-존스 얼굴 검출기[2]에 의한 얼굴검출 결과와 비올라-존스 얼굴 검출기의 단점을 보완하기 위해 새롭게 추가된 옵티컬-플로우 특징점 추적 알고리즘[3]에 의한 얼굴검출의 두 결과를 선형적으로 결합하여 시청자의 시역위치를 예측하였다. 하지만, 모바일 3D 디스플레이의 특성한 급격한 조명의 변화에서 옵티컬-플로우에 의한 특징점 추적알고리즘에 심각한 오류가 발생하는 문제점이 있다. 이러한 급격한 조명의 변화에 대한 문제점을 해결하기 위해 본 논문에서는 매 프레임마다 정확하게 옵티컬-플로우 얼굴 검출기의 정확도를 판단할 수 있는 방법을 제안하고, 다양한 실험을 통해 그 효과를 검증한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.8
• /
• pp.1129-1135
• /
• 2013

A new vehicle detection algorithm based on the multiple optimal Adaboost classifiers with optimal feature selection is proposed. It consists of two major modules: 1) Theoretical DDISF(Distance Dependent Image Scaling Factor) based image scaling by site modeling of the installed cameras. and 2) optimal features selection by Haar-like feature analysis depending on the distance of the vehicles. The experimental results of the proposed algorithm shows improved recognition rate compare to the previous methods for vehicles and non-vehicles. The proposed algorithm shows about 96.43% detection rate and about 3.77% false alarm rate. These are 3.69% and 1.28% improvement compared to the standard Adaboost algorithmt.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.15-30
• /
• 2023

Recently, various services using artificial intelligence(AI) are emerging in the media field as well However, most of the video editing, which involves finding an editing point and attaching the video, is carried out in a passive manner, requiring a lot of time and human resources. Therefore, this study proposes a methodology that can detect the edit points of video according to whether person in video are spoken by using Video Swin Transformer. First, facial keypoints are detected through face alignment. To this end, the proposed structure first detects facial keypoints through face alignment. Through this process, the temporal and spatial changes of the face are reflected from the input video data. And, through the Video Swin Transformer-based model proposed in this study, the behavior of the person in the video is classified. Specifically, after combining the feature map generated through Video Swin Transformer from video data and the facial keypoints detected through Face Alignment, utterance is classified through convolution layers. In conclusion, the performance of the image editing point detection model using facial keypoints proposed in this paper improved from 87.46% to 89.17% compared to the model without facial keypoints.