• 한국지능시스템학회논문지
• /
• 제26권4호
• /
• pp.259-266
• /
• 2016

최근 감시와 보안을 목적으로 활발하게 CCTV가 설치되고 있고, 지능형 감시시스템은 영상에서 객체의 검출 및 감시 등으로 광범위하게 응용되고 있다. 본 연구에서는 지능형 영상 감시 시스템에서 HOG 특징과 FCM 기반의 RBFNN 분류기를 이용한 상반신 검출 방법을 제안한다. HOG는 보행자를 검출하기 위해 기존에 제안되었던 특징으로 본 논문에서는 이를 사용해 상반신의 고유한 기울기를 학습하였다. HOG 특징은 입력 이미지의 크기에 비례하는 고차원의 특징 벡터로 기울기를 표현하기 때문에 RBFNN분류기의 입력데이터로 쓰려면 차원 축소가 필요하다. 이를 위해 PCA 알고리즘을 RBFNN 분류기 앞에 적용하여 HOG 특징의 차원을 저차원으로 축소하였다. 컴퓨터 실험에서는 미리 분류된 상반신 영상과 사람이 아닌 영상을 통해 분류기를 훈련시킨 후 테스트 영상과 동영상을 이용하여 제안된 상반신 검출 방법의 성능을 평가하였다.

• 전자공학회논문지
• /
• 제51권11호
• /
• pp.181-186
• /
• 2014

본 논문에서는 보행자 상반신 검출기의 성능을 향상하기 위한 세그먼테이션에 기반한 특징 추출 방법을 제안한다. 상반신의 부분별 색상 분포를 활용한 멀티 파트 컬러 세그먼테이션을 사용하여 국소 특징이 갖는 한계로 인해 발생하는 오검출의 감소에 효과적인 "전역적" 윤곽 특징을 추출한다. 컬러 공간과 히스토그램 분해도에 따른 성능을 분석하였으며, 자체 구축한 보행자 상반신 영상을 사용한 실험을 통해서 제안한 방법으로 추출한 특징이 국소 특징 기반 검출기의 오검출 감소에 효과적임을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제19권12호
• /
• pp.1927-1935
• /
• 2016

This paper propose a framework for human body parts in RGB-D image. We conduct tasks of obtaining person area, finding candidate areas and local detection in order to detect hand, foot and head which have features of long accumulative geodesic distance. A person area is obtained with background subtraction and noise removal by using depth image which is robust to illumination change. Finding candidate areas performs construction of graph model which allows us to measure accumulative geodesic distance for the candidates. Instead of raw depth map, our approach constructs graph model with segmented regions by quadtree structure to improve searching time for the candidates. Local detection uses HOG based SVM for each parts, and head is detected for the first time. To minimize false detections for hand and foot parts, the candidates are classified with upper or lower body using the head position and properties of geodesic distance. Then, detect hand and foot with the local detectors. We evaluate our algorithm with datasets collected Kinect v2 sensor, and our approach shows good performance for head, hand and foot detection.

• 한국군사과학기술학회지
• /
• 제8권2호
• /
• pp.14-21
• /
• 2005

This paper describes the system for detecting the tank crew's(loader's) hand, arm, head and the upper half of the body in a danger area between the turret ceiling and the upper breech mechanism by computer vision-based method. This system informs danger of pressed to death to gunner and commander for the safety of operating mission. The camera mounted ort the top portion of the turret ceiling. The system sets search moving object from this image and detects by using change of image, laplacian operator and clustering algorithm in this area. It alarms the tank crews when it's judged that dangerous situation for operating mission. The result In this experiment shows that the detection rate maintains in $81{\sim}98$ percents.

• 로봇학회논문지
• /
• 제13권1호
• /
• pp.38-44
• /
• 2018

In this paper, we propose Intelligent Driver Assistance System (I-DAS) for driver safety. The proposed system recognizes safety and danger status by analyzing blind spots that the driver cannot see because of a large angle of head movement from the front. Most studies use image pre-processing such as face detection for collecting information about the driver's head movement. This not only increases the computational complexity of the system, but also decreases the accuracy of the recognition because the image processing system dose not use the entire image of the driver's upper body while seated on the driver's seat and when the head moves at a large angle from the front. The proposed system uses a convolutional neural network to replace the face detection system and uses the entire image of the driver's upper body. Therefore, high accuracy can be maintained even when the driver performs head movement at a large angle from the frontal gaze position without image pre-processing. Experimental result shows that the proposed system can accurately recognize the dangerous conditions in the blind zone during operation and performs with 95% accuracy of recognition for five drivers.

• 대한방사선기술학회지:방사선기술과학
• /
• 제22권2호
• /
• pp.9-15
• /
• 1999

The aim of this study is to measure the application of prone compression study using compression paddle for obese patients in upper gastrointestinal series. Prone compression study using compression paddle was performed in fifty patients, who were not examined completely erect compression study for obesity. The radiographs of stomach were classified into the lower, middle, and high body and then we gave five points included 'very poor', 'poor', 'suspicious', 'good', and 'complete' according to level of detection for area gastrica and mucosal fold. Statistic analysis was performed using T-test and ANOVA, and confidence rate was fixed in 95%(P<0.05) for the significance. The results were as follows : 1. The compression marks on high body was 'poor' grades in erect and prone compression study. The points were 1.64 and 1.86, respectively. 2. The compression marks on middle body was 1.68 in erect compression study, and 'suspicious' in prone compression study. 3. The compression marks on lower body was 'poor' in erect compression study, and 'good' in prone compression study. 4. There was a high statistic signification between the two study on middle and lower body except for high body(P<0.01). 5. The average abdominal thickness of subjects was 23.98 centimeter. There was no statistic signification between the difference of average marks by the abdominal thickness(P>0.05). As these results, the prone compression study in upper gastrointestinal serie seem to be an useful study for obese patients, because it decreases pain and the feeling of uneasiness, and improve compression efficiency remarkably.

• 대한의용생체공학회:의공학회지
• /
• 제25권1호
• /
• pp.5-10
• /
• 2004

체동은 수면 분석에 있어서 중요한 변수중의 하나이다. 본 연구에서는 수면 중에 발생하는 체동을 비접촉 방식으로 검출하기 위하여 4채널의 써모파일 검출기를 구현하였으며, 써모파일 센서를 이용한 방식의 체통 검출 가능성을 확인하기 위해 열적외선 카메라를 통해 획득한 영상을 써모파일의 수학적 모델에 적용하였다 합성된 체동 신호는 Haar 웨이브렛을 이용하여 변환함으로써 체통이 발생한 시점과 움직임의 크기를 상체 및 하체로 나누어 순간 체동을 검출하였다. 또한 뉴로-퍼지 알고리즘인 ANFIS를 이용하여 발생한 체동이 상체만 움직인 것인지 또는 하체만 움직인 것인지 또는 몸 전체가 움직인 것인지에 대한 부위별 체동을 검출하였고, 총 3명의 피험자에 대해 60분간의 데이터를 획득하여 실험한 결과 순간 체동과 부위별 체통에 대해 각각 평균 96.3％와 39.2％ 의 검출률을 나타냈다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1249-1253
• /
• 2003

License plate recognition is very important in an automobile society. This is because, since plate detection accuracy has large influence on subsequent number recognition, it is very important. However, it is very difficult to do it, because a background and a body color of cars are similar to that of the license plate. In this paper, we propose a new thresholds determination method in the various background by using the real-coded genetic algorithm (RGA). By using RGA, the most likely plate colors are decided under various lighting conditions. First, the average brightness Y values of images are calculated. Next, relationship between the Y value and the most likely plate color thresholds (upper and lower bounds)are obtained by RGA. The relationship between thresholds decided from RGA and brightness average is aproximate by using the recursive least squares (RLS) algorithm. In the case of plate detection, thresholds are decided from these functions.

• 대한의용생체공학회:의공학회지
• /
• 제38권5호
• /
• pp.264-270
• /
• 2017

A Doppler radar sensor was applied to detect respirations and heartbeats of persons who were lying on a bed. This study is preliminary study aiming at non-contact and non-intrusive respiration and heart rate monitoring during sleep in daily life. For the experiments, 10GHz Doppler radar with patch-type antenna was used and installed on the upper right and the distance between the body and the antenna was 1 m. The results show that each signal of respiration and heartbeat is observed in each frequency band however the frequency band and the waveform vary according to the subjects and the posture. The results show that the heartbeats can be detected with the peak detection in some frequency band. This study shows the feasibility of applying the Doppler radar to detection of heartbeat and respiration during sleep and further studies about heartbeat detection algorithm are required.

• 한국멀티미디어학회논문지
• /
• 제19권1호
• /
• pp.68-79
• /
• 2016

Electromyographic (EMG) signals have been widely used as motion commands of prosthetic arms. Although EMG signals contain meaningful information including the movement intentions of human body, it is difficult to predict the subject's motion by analyzing EMG signals in real-time due to the difficulties in extracting motion information from the signals including a lot of noises inherently. In this paper, four Ag/AgCl electrodes are placed on the surface of the subject's major muscles which are in charge of four upper arm movements (wrist flexion, wrist extension, ulnar deviation, finger flexion) to measure EMG signals corresponding to the movements. The measured signals are sampled using DAQ module and clustered sequentially. The Fuzzy C-Means (FCMs) method calculates the center values of the clustered data group. The fuzzy system designed to detect the upper arm movement intention utilizing the center values as input signals shows about 90% success in classifying the movement intentions.