• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.903-904
• /
• 2008

This paper suggests a simple scheme of block motion estimation in which the search pattern selection is based on the classification of motion content available in the spatio temporal neighboring blocks. The search area is divided into eight sectors and the search pattern selection is also based on the direction of predicted motion vector. Experimental results show that the proposed algorithm has achieved good predicted image quality measured in terms of PSNR and has very less computational complexity.

• 한국멀티미디어학회논문지
• /
• 제14권7호
• /
• pp.858-865
• /
• 2011

압축 상태에서 비디오 구조화 및 분류를 하기 위해서는 먼저 압축된 비디오에서 장면전환을 검출해서 비디오를 샷(shot)으로 분리하고 샷내 움직임 정보에 따라 샷을 특징화해야 한다. 장면전환을 검출하는 방법에는 DC 영상의 분산값 이나 복원영상의 에지 픽셀의 분포를 이용한 방법, P-픽쳐의 인트라 블록의 개수를 이용한 방법 등이 있으며 움직임에 따른 샷의 특징 분류는 움직임 벡터의 각 성분들의 평균값을 이용하는 것이 일반적인 방법이다. 그러나 움직임 벡터를 이용한 샷 움직임 분류 방법은 움직임 벡터 자체가 블록의 국부적(local) 움직임을 나타내는 것이므로 글로벌(global)한 카메라 동작을 예측하기 위해서는 많은 제약이 있다. 따라서 본 논문에서는 이러한 것을 보완하기 위해서 MPEG으로 압축된 비디오에서 인트라 프레임을 부분적으로 복호화 하고 빠른 1차원적인 연산을 통해 수평 및 수직 방향으로 평균 밝기 값의 변화 방향을 추정하여 좀더 정확히 샷내 카메라의 움직임을 분류하고자 한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.367-370
• /
• 1996

This study deals with the motion modeling by the unit motion of robots and the work measurement through classification of robot motions and standardization. The proposed approach is to scrutinize the Predetermined Time Standards(PTS) methods for measurement of manual tasks performed by people and the basic motions for accomplishing that tasks. And then, it constructs the unit motion models as subsets composed with the basic motions. It apply together with movements distance as a time variable, too. These results are used for the work measurements of robots by the unit motion models.

• 재활복지공학회논문지
• /
• 제6권1호
• /
• pp.67-73
• /
• 2012

본 논문에서는 표면 근전도 신호를 사용하여 손목 움직임의 동작을 분류하기 위해 인공 신경 회로망(ANN : Artificial Neural Network)기반의 동작 분류 알고리즘을 제안한다. 손목 움직임에 무리가 없는 20~30대 성인 26명을 대상으로 척측 수근 굴근과 척측 수근 신근에 부착한 2채널의 전극으로부터 표면 근전도 신호를 취득하고, 취득한 근전도로부터 손목의 굴곡, 신전, 내전, 외전, 휴식 다섯 동작을 인식한다. 빠른 처리 속도를 위해 획득한 신호로부터 시간 영역에서의 특징점을 추출하고 ANN을 이용한 동작 분류에 사용된다. 특징점으로 DAMV, DASDV, MAV, RMS를 사용하였으며, ANN 기반의 동작 분류의 인식율은 DAMV는 98.03%, DASDV는 97.97%, MAV는 96.95%, 그리고 RMS는 96.82%의 정확도를 나타낸다.

• 대한물리의학회지
• /
• 제12권4호
• /
• pp.19-28
• /
• 2017

PURPOSE: The purpose of this study was to describe the Proprioceptive Neuromuscular Facilitation (PNF) Intervention strategy applied International Classification of Functioning, Disability and Health (ICF) Tool about strength, range of motion, scapular stability, pain and function of shoulder for patients with adhesive capsulitis. METHODS: The data was collected by patient with adhesive capsulitis. The patient was a 50-year-old male diagnosed with right shoulder with adhesive capsulitis. We applied the PNF Intervention strategy applied ICF Tool to patient with adhesive capsulitis. PNF interventions were consisting of such as combination of isotonic and stabilizing reversal technique and various positions. PNF interventions were applied, such as those aiming at decreasing pain and disability and increasing range of motion and function for the four weeks. Parameters of result were collected for strength, range of motion, scapular stability, pain and function of shoulder using the hand held dynamometer, goniometer, lateral scapula slide test, and shoulder pain and disability index, respectively. RESULTS: Clinical benefits were observed the patient with adhesive capsulitis for strength, range of motion, scapular stability, pain, and function of shoulder. The patient with adhesive capsulitis improved strength, range of motion, scapular stability, pain, and function of shoulder. CONCLUSION: Patient reported improved strength, range of motion, scapular stability, pain, and function of shoulder after intervention.

• 한국안전학회지
• /
• 제19권4호
• /
• pp.123-128
• /
• 2004

This study investigated effect of arm posture, repetition of wrist motion and external load on perceived discomfort. The arm postures were controlled by shoulder flexion, elbow flexion, and ist motions such as flexion, extension, radial deviation and ulnar deviation. An experiment was conducted to measure discomfort scores for experimental treatments using the magnitude estimation, in which the L16 orthogonal array was adopted for reducing the size of experiment. The results showed that while the effect of the shoulder flexion, repetition of wrist motion and external load was statistically significant at $\alpha=0.05$or 0.10, that of the elbow and wrist motions was not. Discomfor ratings increased linearly as levels of wrist repetition and external load increased. This implies that the existing posture classification schemes such as OWAS, RULA, which do not properly consider effect of motion repetition and external load, may underestimate postural load. Based on the regression equation for wrist repetition and external load, isocomfort region indicating the region within which discomfort scores were expected to be the same was proposed. It is recommended that when assessing risk of postures or developing new posture classification schemes, motion repetition and external load as well as posture itself be fully taken into consideration for precisely evaluating postural stress.

• 로봇학회논문지
• /
• 제15권3호
• /
• pp.240-247
• /
• 2020

This paper presents a novel knitted data glove system for pattern classification of hand posture. Several experiments were conducted to confirm the performance of the knitted data glove. To find better sensor materials, the knitted data glove was fabricated with stainless-steel yarn and silver-plated yarn as representative conductive yarns, respectively. The result showed that the signal of the knitted data glove made of silver-plated yarn was more stable than that of stainless-steel yarn according as the measurement distance becomes longer. Also, the pattern classification was conducted for the performance verification of the data glove knitted using the silver-plated yarn. The average classification reached at 100% except for the pointing finger posture, and the overall classification accuracy of the knitted data glove was 98.3%. With these results, we expect that the knitted data glove is applied to various robot fields including the human-machine interface.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권10호
• /
• pp.5074-5094
• /
• 2016

Screen splitting is one of the fundamental tasks in different methods including video and image compression, screen classification, screen content coding and the like. These methods in turn support various applications in data communications, remote screen sharing, remote desktop delivery to assist teaching-learning, telemedicine, Desktop as a Service etc. In the literature we find systems requiring splitting assumes a fixed size split that do not change dynamically, also there is no analysis why that split is chosen in terms of performance. By doing mathematical analysis this paper first finds the efficient splitting schemes that can be easily automated to make a system adaptive. Thereafter, taking the screen motion detection as a case study, it demonstrates the effects of various splitting methods on motion detection performance. The simulation results clearly shows how classification performances varies with different splitting which will facilitate to choose the best splitting for a specific application scenario as well as making the system adaptive by providing dynamic splitting.

• 천문학회지
• /
• 제55권3호
• /
• pp.67-74
• /
• 2022

In this study, we perform a statistical investigation of the kinematic classification of 4,264 coronal mass ejections (CMEs) from 1996 to 2015 observed by SOHO/LASCO C3. Using the constant acceleration model, we classify these CMEs into three groups: deceleration, constant velocity, and acceleration motion. For this, we devise three different classification methods using fractional speed variation, height contribution, and visual inspection. The main results of this study can be summarized as follows. First, the fractions of three groups depend on the method used. Second, about half of the events belong to the groups of acceleration and deceleration. Third, the fractions of three motion groups as a function of CME speed are consistent with one another. Fourth, the fraction of acceleration motion decreases as CME speed increases, while the fractions of other motions increase with speed. In addition, the acceleration motions are dominant in low speed CMEs whereas the constant velocity motions are dominant in high speed CMEs.

• 정보처리학회논문지B
• /
• 제14B권2호
• /
• pp.89-98
• /
• 2007

비디오와 브라우징, 검색, 조작을 위해서 비디오 내용을 기술하는 색인이 요구된다. 지금까지 색인의 구성은 대부분 비디오 내용에 제한된 키워드를 수작업으로 할당하는 전문가에 의해 수행되었는데 이는 비용과 시간을 소비하는 사업이므로 비디오 내용을 자동으로 분류하는 것이 필요하다. 이 연구는 축구, 골프, 야구, 농구, 배구 등 5종의 스포츠 뉴스 비디오의 분석과 요약을 위해서 자동적이고 효율적인 방법을 제안한다. 우선, 스포츠 뉴스 비디오를 앵커 장면과 스포츠 기사 장면으로 분류한다. 장면 분류는 앵커 장면의 영상 전처리와 색상 특정을 기반으로 한다. 그리고 필드의 우세색상과 모션 방향을 특징으로 이용하여 스포츠 장면을 5개의 장르로 분류한다. 241개의 스포츠 뉴스 장면에 대한 실험에서 75%의 정확도를 얻었다. 따라서 제안된 기법은 향후 개별 스포츠 뉴스와 스포츠 하이라이트를 위한 뉴스 비디오를 검색하는데 이용될 수 있을 것이다.