• 인터넷정보학회논문지
• /
• 제15권4호
• /
• pp.33-42
• /
• 2014

수신호는 음성을 사용할 수 없는 상황, 특히 군인들에게 있어 효과적인 통신 수단이다. 기존의 수신호 인식 방법으로 카메라를 입력 장치로 하는 비젼 인식 방식들이 많이 활용되었다. 그러나 시야가 보이지 않는 군인들의 의사소통에는 적합하지 않다. 또 수신호 전달을 위한 장갑을 제작하는 기존의 방식들은 단지 손가락 움직임 정보만을 활용하고 있기 때문에 손가락뿐만 아니라 손의 회전 등의 추가적인 정보를 필요로 하는 군대 수신호 인식에는 부족하다. 본 논문에서는 수신호 장갑과 3축 모션 센서를 기반으로 군에서 널리 활용되는 6 가지 동작, 즉, 준비, 이동, 빨리 이동, 낮은 보폭, 정지, 그리고 엎드려 동작을 인식할 수 있는 시스템을 설계하고 제안하였다. 이를 위하여 손 모양을 인식하는 방법과 손의 모션을 인식하는 방법을 제안하였다. 손 모양 인식은 각 손가락을 굽힌 정도에 따라 완전히 펴진 상태, 조금 펴진 상태, 조금 굽힌 상태, 완전히 굽힌 상태로 구분한 것을 기반으로 하였다. 손의 모션 인식은 3축을 기준으로 각 동작의 특성을 분석하여 이를 알고리즘화 하였다. 반복 실험을 통한 시험 결과 평균 91.2%의 인식 성공률을 보였다.

• 디지털산업정보학회논문지
• /
• 제11권2호
• /
• pp.121-129
• /
• 2015

Interactive media is a method of communication in which the output from the media comes from the input of the users. The interactive media lets the user go back with the media. Interactive media works with the user's participation. The media still has the same purpose but the user's input adds the interaction and brings interesting features to the system for a better enjoyment. We need a digital content using a dynamic motion and gesture of the mobile device. We made an authoring tool for content producers to easily create interactive content. We have tried to take advantage of the interaction by using a touch screen and a gravity sensor of the mobile device. This interaction may lead to allow the user to participate in the content, it can be used as a key device to assist in engagement. Furthermore, our authoring tool can be applied to various fields of publishing content.

• 제어로봇시스템학회논문지
• /
• 제19권7호
• /
• pp.626-632
• /
• 2013

When a conductive rod is put within rotating axial magnet wheels arranged parallel, three-axial magnetic forces generate on the rod. In some region, the forces has a property of negative stiffness, thus they can be applied to noncontact conveyance of the rod without a control load. Apart from the passive driving, the magnet wheel should be controlled for the rod to be stayed at the still state or be moved in a specified velocity. But, because a control input is just the rotating speed of the magnet wheel, the number of input is less than that of variables to be controlled. It means that levitation force and thrust force increase at the same time for increasing wheel speed, resulting from a strong couple between two forces. Thus, in this paper, a novel method, in which the longitudinal motion of the rod is controlled indirectly by the normal motion of the rod with respect to the wheel center, is introduced to manipulate the rod without mechanical contact on space.

• Clinics in Shoulder and Elbow
• /
• 제8권2호
• /
• pp.181-186
• /
• 2005

An anterior dislocation of the elbow without a fracture of the olecranon is an extremely rare injury. This paper reports a 36-year-old male who stumbled and fell on his outstretched hand during a soccer game. The anteroposterior and lateral radiographs indicated a simple anterior dislocation of the elbow, which was reduced using a closed method. The elbow joint was stable in the range of motion, but the sensation of the two ulnar digits was still reduced. MRI was useful for the identification of the pathoanatomy. At the follow-up examination three months after the initial trauma, the hypesthesia has fully recovered and the patient regained the full range of the elbow and forearm motion without pain and instability. After 18 months, the patient had a normal elbow function, and could play various sports. If an anterior elbow dislocation is detected early, a closed reduction with careful pathoanatomical considerations would be successful.

• 제어로봇시스템학회논문지
• /
• 제21권8호
• /
• pp.729-734
• /
• 2015

Improvement in the control strategy for continuous casting is a crucial requirement to enhance the slab's quality and to increase productivity. The mold oscillator adopts the dual cylinders due to its heavy weight, so the synchronized motion of two cylinders is an important aspect when precise control is needed. The conventional method uses the master-slave control applied to the valve input reference, but the synchronization performance should still be improved. This paper proposes a novel synchronization algorithm for dual cylinders used in a mold oscillator. The master-slave concept is applied to the target reference position, that is, the slave target reference position is controlled to match the slave cylinder's position with the master cylinder's position. In the simulation based on a Simulink model, the proposed algorithm shows a better synchronization performance in aspect of the mean of the absolute error and the peak synchronization error.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.

• 대한의용생체공학회:의공학회지
• /
• 제17권1호
• /
• pp.109-120
• /
• 1996

Cardiac function is evaluated quantitatively using angiographic images via the analysis of the shape change or the heart wall boundaries. To kin with, boundary defection or ESLV(End Systolic Lert Ventricular) and EDLV(End Diastolic Left Ventricular) is essential for the quantitative analysis of cardiac function. The boundary detection methods proposed in the past were almost semi-automatic. Intervention by a knowledgeable human operator was still required Of con, manual tracing of the boundaries is currently used for subsequent analysis and diagnosis. This method would not cut excessive time, labor, and subjectivity associated with manual intervention by a human operator. EDLV images have noncontiguous and ambiguous edge signal on some boundary regions. In this paper, we propose a new method for automated detection of boundaries in noncontiguous and ambiguous EDLV images. The boundary detection scheme which based on a priori knowledge information is divided into two steps. The first step is to detect the candidate edge points of EDLV using ESLV boundaries. The second step is to correct detected boundaries of EDLV using the LV shape. We developed the algorithm of modifying EDLV boundaries defined adaptive modifier. We experimented the method proposed in this paper and compared our proposed method with the manual method in detecting boundaries of EDLV. In the areas within estimated boundaries of EDLV, the percentage of error was about 1.4%. We verified the useflilness and obtained the satisfying results througll the experiments of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.1981-1995
• /
• 2021

When a person tries to conceal emotions, real emotions will manifest themselves in the form of micro-expressions. Research on facial micro-expression recognition is still extremely challenging in the field of pattern recognition. This is because it is difficult to implement the best feature extraction method to cope with micro-expressions with small changes and short duration. Most methods are based on hand-crafted features to extract subtle facial movements. In this study, we introduce a method that incorporates optical flow and deep learning. First, we take out the onset frame and the apex frame from each video sequence. Then, the motion features between these two frames are extracted using the optical flow method. Finally, the features are inputted into an improved MobileNetV2 model, where SVM is applied to classify expressions. In order to evaluate the effectiveness of the method, we conduct experiments on the public spontaneous micro-expression database CASME II. Under the condition of applying the leave-one-subject-out cross-validation method, the recognition accuracy rate reaches 53.01%, and the F-score reaches 0.5231. The results show that the proposed method can significantly improve the micro-expression recognition performance.

• 대한토목학회논문집
• /
• 제32권1A호
• /
• pp.19-30
• /
• 2012

최근 캠코더와 같은 영상 장비의 고성능화 및 대중화, 그리고 화상 처리(image procession) 기술의 발달 등으로 인하여 영상 기반의 구조물 동적변위 계측에 관한 연구가 활발하며, 이러한 연구개발의 결과로 관련 시스템의 사용성 및 정확도가 많이 개선되고 있다. 그러나 이러한 영상 기반 시스템의 경우 장비 측면에서 볼 때 영상 장비 자체의 진동에 의한 오차, 화상 처리 과정에서의 오차 등을 개선할 필요가 있으며, 또한 적용 측면에서 볼 때 교량의 수직 처짐이나 건축구조물의 수평변위 계측에 제한되어 있어 부유체의 파랑응답과 같은 3차원 운동을 하는 구조물에 대한 확장이 필요한 시점이다. 이 연구에서는 이러한 영상 기반 동적변위 계측방법을 3차원 문제에 적용하기 위하여 다중 표적(multiple target)을 사용한 방법을 제시하고, 또한 화상 처리 과정에서의 정량적 판단 기준을 제시함으로써 간접적으로 영상 기반 시스템의 계측 정확도를 평가하여, 영상 기반 방법에 의하여 계측된 동적변위 계측결과의 유효성을 판단할 수 있도록 하였다. 제안된 방법을 $50m{\times}30m{\times}5m$ 규모의 대형 부유체에 대한 실해역 파랑 응답 실험에 적용하여, 부유체의 동적변위를 계측하였으며, 그 결과를 기존의 RTK-GPS(Real Time Kinematics-Global Positioning System), MRU(Motion Reference Unit) 등의 장비를 이용한 계측결과와 비교함으로써 그 성능을 검증하였다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집B
• /
• pp.523-528
• /
• 2001

There are many difficult problems in analyzing the flow characteristics in a high voltage circuit breaker such as shock wave and complex geometries, which may be either static or in relative motion. Although a variety of mesh generation techniques are now available, the generation of meshes around complicated, multicomponent geometries like a gas circuit breaker is still a tedious and difficult task for the computational fluid dynamics. This paper presents the computational method for analyzing the compressible flow fields in a high voltage gas circuit breaker using the Cartesian cut-cell method based on the CFD-CAD integration, which can achieve the accurate representation of the geometry designed by a CAD tools. The technique is frequently satisfied, and it will be almost universally so in the future, as the CFD-CAD traffic increases.