• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.639-641
• /
• 2012

기울기 값과 방향성의 특징 값을 이용하는 HOG와 선형SVM을 분류기로 사용하는 사람검출 기법은 슬라이딩 윈도우 기반 사람검출에 성공적으로 적용되었다. 또한 텍스처 구별에 강인한 특징을 가지고 있는 LBP를 HOG와 함께 특징 서술자로 적용하는 방법은 서로의 단점을 상호 보안하여 향상된 성능을 보인다. 본 논문에서는 기존 HOG제곱근 Gamma 보정을 다양한 Gamma 보정 값으로 대체하고 성능을 분석한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1464-1467
• /
• 2005

In this research, we developed a system, which can find the location of vehicle when people park their cars in a big parking lot or large area. People can find their cars readily through this simple device and they can save their time and effort. This is the purpose of this research. Performing this, detection of electromagnetic wave's direction is needed and we used shielding effectiveness of electromagnetic waves for the method of it. An absolute coordinate indicates four directions (E, W, S, N) by using an electronic compass module, and it is needed for the localization. The device can check the received count of the electromagnetic waves coming from all other directions through the system, which is installed in the vehicle. The direction recorded the least received count would be the location of the parked vehicles. We can add on the function of this research by using the same frequency of cars alarm goods. Also, it is useful in the huge indoor parking lot.

• Journal of Gastric Cancer
• /
• 제19권3호
• /
• pp.315-328
• /
• 2019

Purpose: To investigate the clinical value of serum miR-221-3p and miR-122-5p expression levels in the diagnosis and prognosis of gastric cancer. Materials and Methods: Serum samples from 141 gastric cancer cases (gastric cancer group), 110 gastric polyps (gastric polyp group), and 75 healthy people (healthy control) were used to detect miR-221-3p and miR-122-5p expression using real-time reverse transcription polymerase chain reaction. Results: Serum miR-221-3p expression was significantly higher in the gastric cancer group than in the gastric polyp group, and it was significantly lower than that before operation. The miR-221-3p expression was significantly higher in the death group than in the survival group. The proliferation and migration ability significantly increased and the apoptosis rate significantly decreased by miR-221-3p transfection in gastric cancer cells. In contrast, the function of miR-122-5p in gastric cancer cells was opposite of miR-221-3p. Serum miR-221-3p expression was negatively correlated with that of miR-122-5p in gastric cancer. Serum miR-221-3p and miR-122-5p expressions were significantly correlated with the degree of differentiation, tumor, node, metastasis stage, lymph node metastasis, and invasion depth. miR-221-3p and miR-122-5p expression levels were independent prognostic factors for postoperative gastric cancer. In the diagnosis and predicting prognosis of gastric cancer, receiver operating characteristic analysis revealed that the area under curve of combined detection of serum miR-221-3p and miR-122-5p expression had a greater diagnostic effect than either single maker. Conclusions: The miR-221-3p and miR-122-5p are involved in the development of gastric cancer, and they have important clinical values in gastric cancer diagnosis and prognosis.

• Journal of Information Processing Systems
• /
• 제13권3호
• /
• pp.590-598
• /
• 2017

Recently, there has been an increase in the number of hazardous events, such as fire accidents. Monitoring systems that rely on human resources depend on people; hence, the performance of the system can be degraded when human operators are fatigued or tensed. It is easy to use fire alarm boxes; however, these are frequently activated by external factors such as temperature and humidity. We propose an approach to fire detection using an image processing technique. In this paper, we propose a fire detection method using multichannel information and gray level co-occurrence matrix (GLCM) image features. Multi-channels consist of RGB, YCbCr, and HSV color spaces. The flame color and smoke texture information are used to detect the flames and smoke, respectively. The experimental results show that the proposed method performs better than the previous method in terms of accuracy of fire detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1796-1816
• /
• 2020

The health and safety of elderly and disabled patients who cannot live alone is an important issue. Timely detection of sudden events is necessary to protect these people, and anomaly detection in smart homes is an efficient approach to extracting such information. In the real world, there is a causal relationship between an occupant's behaviour and the order in which appliances are used in the home. Bayesian networks are appropriate tools for assessing the probability of an effect due to the occurrence of its causes, and vice versa. This paper defines different subsets of random variables on the basis of sensory data from a smart home, and it presents an anomaly detection system based on various models of Bayesian networks and drawing upon these variables. We examine different models to obtain the best network, one that has higher assessment scores and a smaller size. Experimental evaluations of real datasets show the effectiveness of the proposed method.

• 한국정보기술응용학회:학술대회논문집
• /
• 한국정보기술응용학회 2005년도 6th 2005 International Conference on Computers, Communications and System
• /
• pp.153-156
• /
• 2005

Skin region detection in images is an important process in many computer vision applications targeting humans such as hand gesture recognition and face identification. It usually starts at a pixel-level, and involves a pre-process of color spae transformation followed by a classification process. A color space transformation is assumed to increase separability between skin classes and other classes, to increase similarity among different skin tones, and to bring a robust performance under varying imaging conditions, without any complicated analysis. In this paper, we examine if the color space transformation actually brings those benefits to the problem of skin region detection on a set of human hand images with different postures, backgrounds, people, and illuminations. Our experimental results indicate that color space transfomation affects the skin detection performance. Although the performance depends on camera and surround conditions, normalized [R, G, B] color space may be a good choice in general.

• 한국멀티미디어학회논문지
• /
• 제25권10호
• /
• pp.1433-1447
• /
• 2022

Recently, as the demand for physical security technology to prevent leakage of technical and business information of companies and public institutions increases, the high tech companies are operating X-ray security checkpoints at building entrances to protect their intellectual property and technology. X-ray security checkpoints are operated to detect cameras and storage media that may store or leak important technologies in the bags of people entering and leaving the building. In this study, we propose an X-ray security checkpoint system that automatically detects a storage medium in an X-ray image using a deep learning based object detection method. The proposed system consists of an edge computing unit and a cloud-computing unit. We employ the RetinaNet for automatic storage media detection in the X-ray security checkpoint images. The proposed approach achieved mAP of 95.92% on private dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.631-653
• /
• 2020

Sign language is a natural, visually oriented and non-verbal communication channel between people that facilitates communication through facial/bodily expressions, postures and a set of gestures. It is basically used for communication with people who are deaf or hard of hearing. In order to understand such communication quickly and accurately, the design of a successful sign language translation system is considered in this paper. The proposed system includes object detection and classification stages. Firstly, Single Shot Multi Box Detection (SSD) architecture is utilized for hand detection, then a deep learning structure based on the Inception v3 plus Support Vector Machine (SVM) that combines feature extraction and classification stages is proposed to constructively translate the detected hand gestures. A sign language fingerspelling dataset is used for the design of the proposed model. The obtained results and comparative analysis demonstrate the efficiency of using the proposed hybrid structure in sign language translation.

• 한국산업정보학회논문지
• /
• 제18권4호
• /
• pp.19-24
• /
• 2013

고령화 사회에서는 노인의 신체적 취약성으로 인한 안전문제가 사회문제로 대두되고 있다. 판단, 상황대처 능력이 떨어진 노인은 체력과 균형감각 저하로 인하여 잦은 낙상을 경험한다. 낙상은 자칫 인명피해 및 골절, 유조직 손상 등을 유발 할 수 있으므로 빠른 응급대처가 필요하다. 따라서 본 논문에서는 사용자의 허리에 부착하여 일상적인 움직임에 대한 가속도의 변화 및 낙상이 발생하였을 때의 가속도의 변화를 측정하였다. 측정한 값을 이용하여 낙상 감지 시스템을 구현하였으며, 여러 가지 낙상 상황을 가정하여 낙상 검출 여부를 판별 하였다.

• 한국항해항만학회지
• /
• 제36권3호
• /
• pp.163-168
• /
• 2012

최근 물 가까이에서 생활하고 여가를 보낼 수 있는 친수공간에 대한 욕구가 증가하면서 플로팅 구조물에 대한 관심이 커져가고 있다. 이에 본 연구에서는 정적 변형률을 이용한 플로팅 구조물의 손상탐지기법을 제안하였다. 손상을 탐지하기 위한 손상지수는 기존의 모달 변형에너지를 이용한 손상지수 법을 변형률을 적용할 수 있도록 확장하여 손상 전과 손상 후의 변형률로 나타내었으며, 손상지수 계산 후 손상부위를 결정하는 손상탐지는 패턴인식을 이용하였다. 제안된 이론의 정확성과 타당성은 플로팅 구조물의 축소모형을 제작하고 계측된 변형률 데이터에 적용하여 검증하였다.