• 디지털콘텐츠학회 논문지
• /
• 제19권9호
• /
• pp.1787-1793
• /
• 2018

그림자는 자연 경관에서 관찰되는 일반적인 현상이지만 물체 인식, 특징 검출 및 장면 분석등과 같은 영상 분석에 부정적인 영향을 미치는 요소이므로 디지털 영상에 포함된 그림자 처리는 디지털 영상 분석 과정에서 필수적으로 고려되어야 한다. 본 논문에서는 단일 자연 영상에 포함된 그림자를 검출하고 제거하기 위한 특징 요소 중의 하나인 1D 불변 영상의 획득을 위한 기존 방법들에 대해 기술하고, 선형 회귀 기반의 1D 불변 영상 획득 방법을 제안하였다. 제안하는 방법은 RGB 칼라 영상의 각 채널 간의 밴드 비의 로그를 계산한 후 선형 회귀를 통해 그레이스케일 영상 라인을 획득하고, 최종 1D 불변 영상은 밴드 비의 로그 영상들을 추정된 그레이스케일 영상 라인으로 투영시켜 획득하였다. 실험 결과, 제안하는 방법이 기존의 엔트로피 최소화 기반의 투영 각도를 계산하는 방법보다 계산 복잡도가 낮았으며, 1D 불변 영상을 이용한 그림자가 검출 및 제거가 효과적으로 수행됨을 보였다.

• Smart Structures and Systems
• /
• 제32권1호
• /
• pp.23-35
• /
• 2023

Steel bolted joint is an important part of steel structure, and its damage directly affects the bearing capacity and durability of steel structure. Currently, the existing research mainly focuses on the identification of corroded bolts and corroded bolts respectively, and there are few studies on multiple states. A detection framework of corroded and loosened bolts is proposed in this study, and the innovations can be summarized as follows: (i) Vision Transformer (ViT) is introduced to replace the third and fourth C3 module of you-only-look-once version 5s (YOLOv5s) algorithm, which increases the attention weights of feature channels and the feature extraction capability. (ii) Three states of the steel bolts are considered, including corroded bolt, bolt missing and clean bolt. (iii) Line segment detector (LSD) is introduced for bolt rotation angle calculation, which realizes bolt looseness detection. The improved YOLOv5s model was validated on the dataset, and the mean average precision (mAP) was increased from 0.902 to 0.952. In terms of a lab-scale joint, the performance of the LSD algorithm and the Hough transform was compared from different perspective angles. The error value of bolt loosening angle of the LSD algorithm is controlled within 1.09%, less than 8.91% of the Hough transform. Furthermore, the proposed framework was applied to fullscale joints of a steel bridge in China. Synthetic images of loosened bolts were successfully identified and the multiple states were well detected. Therefore, the proposed framework can be alternative of monitoring steel bolted joints for management department.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.783-788
• /
• 2003

In this paper, we present a new approach to detect and recognize human face in the image from vision camera equipped on the mobile robot platform. Due to the mobility of camera platform, obtained facial image is small and pose-various. For this condition, new algorithm should cope with these constraints and can detect and recognize face in nearly real time. In detection step, ‘coarse to fine’ detection strategy is used. Firstly, region boundary including face is roughly located by dual ellipse templates of facial color and on this region, the locations of three main facial features- two eyes and mouth-are estimated. For this, simplified facial feature maps using characteristic chrominance are made out and candidate pixels are segmented as eye or mouth pixels group. These candidate facial features are verified whether the length and orientation of feature pairs are suitable for face geometry. In recognition step, pseudo-convex hull area of gray face image is defined which area includes feature triangle connecting two eyes and mouth. And random lattice line set are composed and laid on this convex hull area, and then 2D appearance of this area is represented. From these procedures, facial information of detected face is obtained and face DB images are similarly processed for each person class. Based on facial information of these areas, distance measure of match of lattice lines is calculated and face image is recognized using this measure as a classifier. This proposed detection and recognition algorithms overcome the constraints of previous approach [15], make real-time face detection and recognition possible, and guarantee the correct recognition irregardless of some pose variation of face. The usefulness at mobile robot application is demonstrated.

• ETRI Journal
• /
• 제38권4호
• /
• pp.776-786
• /
• 2016

The fairly recent standard of equipping mobile devices with advanced imaging sensors has opened the possibility of conveniently diagnosing skin conditions, anywhere, anytime. For this application, we attempted to estimate skin conditions from a skin image taken by a mobile handheld camera. To estimate the skin conditions, we specifically identified three skin features (pigmentation, pores, and roughness) that can be measured quantitatively from a skin image. The experimental data indicate that the existing thresholding methods are inappropriate for extracting the pigmentation and pore skin features. Thus, we propose a new line-fitting based thresholding method for skin feature detection. We thoroughly evaluated our proposed skin condition estimation method using our skin image database. The experimental results show that our proposed thresholding method can better determine the threshold leading to the most visually plausible detection, when compared to existing methods. We also confirmed that skin conditions can be feasibly estimated using a common mobile handheld camera (for example, a smartphone).

• 대한기계학회논문집A
• /
• 제21권10호
• /
• pp.1551-1560
• /
• 1997

This study is devoted to the detection of the 3-dimensional point obstacles on the plane by using accumulated scan line images. The proposed accumulating only one scan line allow to process image at real time. And the change of motion of the feature in image is small because of the short time between image frames, so it does not take much time to track features. To obtain recursive optimal obstacles position and robot motion along to the motion of camera, Kalman filter algorithm is used. After using Kalman filter in case of the fixed environment, 3-dimensional obstacles point map is obtained. The position and motion of moving obstacles can also be obtained by pre-segmentation. Finally, to solve the stereo ambiguity problem from multiple matches, the camera motion is actively used to discard mis-matched features. To get relative distance of obstacles from camera, parallel stereo camera setup is used. In order to evaluate the proposed algorithm, experiments are carried out by a small test vehicle.

• 정보처리학회논문지B
• /
• 제9B권3호
• /
• pp.359-368
• /
• 2002

본 논문에서는 매칭 에러 영상과 이동벡터를 이용한 효율적인 이동물체 외곽선 검출 알고리즘과 부분외곽선 정보를 이용한 이동물체 고속 추적 알고리즘을 제안하였다. 이동물체의 외곽선 검출은 watershed 알고리즘을 기반으로 확률분포함수를 적용하여 seed 영역을 생성하고 seed 영역을 확장하여 이동물체의 윤곽선을 검출한 다음 이동벡터를 이용하여 최종 외곽선을 추출한다. 외곽선 중 일부를 특징으로 하여 이동물체를 추적하는 알고리즘을 사용하였다. 이동물체 초기 특징 벡터는 이동물체의 외곽선 영역 중 상하좌우의 외곽선 일부분을 특징벡터로 정한다. 다음은 추적단계로 이전 프레임에서 얻은 특징벡터를 이용하여 현재 프레임에서 이동물체의 추적을 수행하였다. 실제영상에 대하여 제안된 알고리즘으로 이동물체추적 모의 실험을 수행한 결과 기존 능동 윤곽선 추적알고리즘은 물체 외곽선 전체를 추적하기 때문에 물체의 외곽선 길이에 따라 처리시간이 변화하지만 제안된 알고리즘은 이동물체의 외곽선 영역을 특징정보로 하여 추적하기 때문에 추적 연산이 간단하였다. 고속이동벡터를 추출 BMA 연산은 기존 알고리즘 보다 연산량이 약 39% 감소였고, 이동 물체 외곽선 검출 알고리즘은 과분할 문제점이 발생하지 않았으며, 상하 좌우 외곽선 정보를 이용하여 이동물체를 추적한 결과 추적오차는 특징벡터의 크기가 $(15\times{5)}$일 때 검색오차가 4 화소 이하로 양호하게 나타났다.

• 한국지능시스템학회논문지
• /
• 제19권6호
• /
• pp.852-859
• /
• 2009

TFT-LCD 자동 검사 시스템에서 결함 검출을 위한 영상은 라인 스캔 카메라(line scan camera)나 에어리어 스캔 카메라 (area scan camera)에 의해서 획득하게 된다. 그러나 임펄스 잡음과 가우시안 잡음, CCD 혹은 CMOS 센서의 한계, 조명등의 영향으로 열화된 영상이 획득되며, 한도성 결함 영역을 인간의 육안으로 구분하기 어렵게 된다. 본 논문에서는 효율적인 결함 검출을 위해 특징 추출 방법과 결함 검출 방법을 제안한다. 특징 벡터로 웨버의 법칙을 이용한 결함 영역과 주변 배경 영역의 평균 밝기 차와 주변 배경 영역의 밝기 변화를 이용한 표준편차를 이용하며, 결함 영역 검출를 위해 추출된 특징 벡터를 이용하여 비선형 SVM을 적용한다. 실험 결과는 제안한 방법이 다른 방법들 보다 성능이 우수함을 보여준다.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2007년도 춘계학술대회 논문집
• /
• pp.274-279
• /
• 2007

The fault identification of electrical rotating machinery have been special interests due to one of important elements in the industrial production line. It is directly related with products quality and production costs. The sudden breakdown of a motor will affect to the shut down of the whole processes. Therefore, rotating machines are required to a periodic diagnosis and maintenance for improving its reliability and increasing their lifetime. The objective of this work is to develop the diagnosis system with current signals for the effective identification of healthy and faulty motors using the developed diagnosis algorithm, which consists of the feature calculation, feature extraction, and feature classification procedures.

• 한국ITS학회 논문지
• /
• 제8권1호
• /
• pp.127-135
• /
• 2009

This paper presents a new technique for corner shape based object retrieval from a database. The proposed feature matrix consists of values obtained through a neighborhood operation of detected corners. This results in a significant small size feature matrix compared to the algorithms using color features and thus is computationally very efficient. The corners have been extracted by finding the intersections of the detected lines found using Hough transform. As the affine transformations preserve the co-linearity of points on a line and their intersection properties, the resulting corner features for image retrieval are robust to affine transformations. Furthermore, the corner features are invariant to noise. It is considered that the proposed algorithm will produce good results in combination with other algorithms in a way of incremental verification for similarity.

• International Journal of Contents
• /
• 제9권4호
• /
• pp.16-21
• /
• 2013

Vision system is an indispensable part of constructing the chess-playing robot. Chessboard detection and pieces localization in the captured image of robot's camera are important steps for processes followed such as pieces recognition, move calculation, and robot controlling. We present a method for detecting the Janggi chessboard and pieces based on the edge and color feature. Hough transform combined with line extraction is used for segmenting the chessboard and warping it to form the rectangle shape in order to detect and interpolate the lines of chessboard. Then we detect the existence of pieces and their side by applying the saliency map and checking the color distribution at piece locations. While other methods either work only with the empty chessboard or do not care about the piece existence, our method could detect sufficiently side and position of pieces as well as lines of the chessboard even if the occlusion happens.