• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.476-477
• /
• 2011

본 논문에서는 홈 헬스케어 환경에서 위험 동작이 발생할 경우 이를 검지하는 방법으로, 물체 검출을 위해 입력받은 영상으로 부터 배경모델을 생성하여 이를 이용해 관심 물체를 검출한다. 검출된 물체 영역 내에서 중심점의 주변 탐색을 통해 관심 물체를 추적하며, 관심 물체의 모멘트 분석 정보와 깊이 정보를 활용하여 정상 동작이 아닌 낙상과 같은 비정상적인 위험 동작이 발생되었을 경우 검출할 수 있다. 기존 비전 센서 기반 방법들은 2차원 영상 정보를 이용하기 때문에 다양한 낙상 동작에 대해 낮은 검출율을 보이고 있다. 이에 대한 개선책으로 깊이정보를 활용하여 검출함으로써 신뢰성있는 검출율을 보여주는 실시간 비전 센서 기반을 둔 위험 낙상 검출기를 제안한다.

• Broadcasting and Media Magazine
• /
• v.25 no.2
• /
• pp.52-60
• /
• 2020

최근 생체 정보를 이용한 사용자 인증 기술이 발전하면서 이를 모바일 기기에 적용하는 사례가 크게 증가하고 있다. 특히, 얼굴 기반 인증 방식은 비접촉식이며 사용이 편리하여 적용 범위가 점점 확대되고 있는 추세이다. 그러나, 사용자의 얼굴 사진이나 동영상 등을 이용한 위변조가 용이하기 때문에 모바일 기기 내 보안 유지에 어려움을 야기한다. 본 고에서는 이러한 문제를 해결하기 위해 최근 활발히 연구되고 있는 심층신경망 기반 얼굴 위변조 검출 연구의 최신 동향을 소개하고자 한다. 먼저, 기본 합성곱 신경망 구조부터 생성모델 기반의 위변조 검출 방법까지 다양한 신경망 구조를 이용한 위변조 검출 방법에 대해 설명한다. 또한, 심층신경망 학습을 위해 사용되는 얼굴 위변조 데이터셋에 대해서도 간략히 살펴보고자 한다.

• Proceedings of the IEEK Conference
• /
• 2001.06e
• /
• pp.55-58
• /
• 2001

본 논문에서는 해석적인 모델에 기초한 고장 검출 기법의 하나인 fault detection filter를 적용한 고장 검출 알고리듬을 개발하고 이를 적용하여 고장검출 필터의 유효성을 보이고자 한다. Fault detection filter는 특수한 형태의 observer로써 특정한 고장의 발생시 잔차가 출력 공간에서 일정한 방향을 유지함으로써 고장 개소의 판별이 가능하다. 이에 본 논문에서는 fault detection filter에 기초한 고장 감지 시스템을 적용하기 위한 다이나믹 시스템 모델링과 고장감지 시스템의 설계과정 및 이를 적용 모의시험 결과를 수록하였다. 결과를 통하여 fault detection filter가 갖는 방향성에 대한 sensitivity 효과를 고장 감지 목적에 유효하게 적용할 수 있음을 보였다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.183-190
• /
• 2013

In this paper, we propose an improved anisotropic diffusion model for micro-crack detection in heterogeneously textured surface of polycrystalline solar wafers. Due to the nature of the image sensor, the gray-level of the diagonal micro-crack is non-uniform. Thus, the conventional algorithms can't fully detect diagonal micro-cracks when the number of iteration is not enough. However, the increasing of the iteration number leads to increase computation time and detects micro-crack thicker than the original micro-crack. In order to overcome this drawback, we use the gradient of north, south, east, and west directions as well as extended directions. To calculate the diffusion coefficients, we compare the gradients of conventional directions and extended directions and apply the larger gradient values to the coefficient function. This is because the proposed method reflects the information of diagonal micro-crack. Comparing to Tsai et al.'s and Ko and Rheem's, the proposed algorithm shows superior efficiency in detecting the diagonal micro-cracks with less iterations in the images of polycrystalline solar wafers. In addition, it also shows that the thickness of segmented micro-crack is similar to the orignal micro-crack.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.460-468
• /
• 2023

Developmental Dysplasia of the Hip (DDH) is a pathological condition commonly occurring during the growth phase of infants. It acts as one of the factors that can disrupt an infant's growth and trigger potential complications. Therefore, it is critically important to detect and treat this condition early. The traditional diagnostic methods for DDH involve palpation techniques and diagnosis methods based on the detection of keypoints in the hip joint using X-ray or ultrasound imaging. However, there exist limitations in objectivity and productivity during keypoint detection in the hip joint. This study proposes a deep learning model-based keypoint detection method using X-ray and ultrasound imaging and analyzes the performance of keypoint detection using various deep learning models. Additionally, the study introduces and evaluates various data augmentation techniques to compensate the lack of medical data. This research demonstrated the highest keypoint detection performance when applying the residual network 152 (ResNet152) model with simple & complex augmentation techniques, with average Object Keypoint Similarity (OKS) of approximately 95.33 % and 81.21 % in X-ray and ultrasound images, respectively. These results demonstrate that the application of deep learning models to ultrasound and X-ray images to detect the keypoints in the hip joint could enhance the objectivity and productivity in DDH diagnosis.

• Annual Conference of KIPS
• /
• 2017.04a
• /
• pp.865-867
• /
• 2017

본 논문에서는 데이터스트림 환경에서 개념 변화를 탐지하기 위해 합성곱 신경망(CNN)을 사용하는 방법을 제시한다. 데이터스트림 환경에서 입력될 수 있는 데이터를 패턴화하여 신경망 모델에 학습시키고, 패턴화한 데이터를 학습시킨 신경망 모델을 이용하여 스트림 환경에서 개념 변화를 검출 가능함을 보인다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.10C
• /
• pp.958-966
• /
• 2003

Change detection algorithms based on frame difference are frequently used for finding moving objects in image sequences. These algorithms detect the change of frames using estimated statistical background model. But, if this estimated background model is different from the actual statistical distribution, false detections are generated. In this paper, we propose an improved change detection algorithm using euler number and structure tensor. The proposed mapping method which is based on the euler number can be used for reducing the false detections that generated by nonparametric change detection algorithm. In this paper, the change in the region of moving object also can be detected by the proposed method using structure tensor. Experimental result shows that the proposed method reduces the false detections effectively by 90% on "Weather", by 34% on "Mother & daughter" and by 43% on "Aisle" than an existing method does.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.3
• /
• pp.97-102
• /
• 2008

In this paper we propose an object-based image retrieval method using spatial color model and feature points registration method for an effective color query detection. The proposed method in other to overcome disadvantages of existing color histogram methods and then this method is use the HMMD model and rough set in order to segment and detect the wanted image parts as a real time without the user's manufacturing in the database image and query image. Here, we select candidate regions in the similarity between the query image and database image. And we use SIFT registration methods in the selected region for object retrieving. The experimental results show that the proposed method is more satisfactory detection radio than conventional method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.9
• /
• pp.977-982
• /
• 2014

In this paper, we propose a system which can detect the flame in real time from the high-quality IP camera. First, open directly the RTSP streams transmitted from the IP camera using the library FFmpeg as opening a video file. The second thing is to extract the background images from video signal using Gaussian mixture model. Then the foreground images are obtained through subtracting operation between the input image and the background image. Separated foreground image through a mathematical morphology operation are considered as candidate area. By analysing colour information and dynamic characteristics of the candidate area, flame is determined finally. Through the experiments with input videos from IP camera, the proposed algorithms were useful to detect flames.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.3
• /
• pp.130-135
• /
• 2012

In this paper, we propose a technique to detect the size and location of the small target in images by using Gaussian kernel repeatedly. In order to detect the size and location of the small target, we find the local maximum value by applying the facet model and then use the $3{\times}3$ Gaussian kernel repeatedly. we determine the size of small target by comparing the local maximum value $D_2$ according to the number of iteration. To reduce the computational complexity, we use the Gaussian pyramid when using the kernel repeatedly. Through the experiment, we verified that the size and location of the small target is detected by the number of iterations and results show improvements from conventional methods.