• 대한전자공학회논문지SP
• /
• 제39권2호
• /
• pp.87-95
• /
• 2002

반화소 단위 움직임 추정(half pixel accuracy motion estimation, HPAME)과 블록 분류(block classification)를 이용한 계층적 고속 움직임 추정 알고리듬을 제안하였다 제안한 알고리듬은 기존의 MRME(multi-resolution motion estimation)알고리듬보다 우수한 화질을 유지하면서 계산량 및 비트량을 크게 줄일 수 있는 장점을 갖는다. 제안한 알고리듬에서는 다해상도 영상에 대한 움직임 추정 시 고주파 부대역의 움직임 추정에 기준 움직임으로 사용되는 기저대역의 움직임 벡터를 정확하게 추정하기 위하여 HPAME을 행한다. 그리고 고주파 부대역에서는 기저대역에서의 HPAME로 인한 계산량 및 비트량의 증가를 보상하기 위하여 움직임 추정이 필요한 블록들에 대하여서만 선별적으로 미소 움직임을 추정한다. 이때 고주파 부대역에서의 미소 움직임 추정의 수행 여부는 대응되는 기저대역 블록의 움직임 벡터 특성과 블록 분류에 따른 클래스 정보를 이용하여 결정한다 제안한 알고리듬의 성능은 컴퓨터 모의 실험 결과로부터 확인하였다.

• 한국정보통신학회논문지
• /
• 제12권3호
• /
• pp.527-533
• /
• 2008

움직임 보상은 고화질의 실시간 비디오 응용에 있어서 언제나 주된 병목을 초래한다. 따라서 실시간 비디오 응용에서는 움직임 보상을 수행하는 고속의 전용 하드웨어를 필요로 한다. 여러 동영상 부호화 방식에서 영상프레임은 픽셀의 블록으로 분할된다. 일반적으로 움직임 보상은 이전 프레임으로부터 움직임을 추정하여 현재의 블록을 예측하게 된다. 움직임 보상에 사용되는 화소 정밀도가 높을수록 보다. 좋은 성능을 갖지만 연산량은 증가하게 된다. 본 논문에서는 1/4 화소 정밀도를 지원하는 H.264/AVC 부호화기에 적합한 움직임 보상기의 아키텍처를 연구하였다. 설계된 움직임 보상기는 전치 배열과 휘도 6-tap 필터 3개를 사용하여 높은 하드웨어 이용률을 갖게 하였으며 내부 메모리의 크기를 감소시켰다. VHDL을 사용하여 기술하였으며, Xilinx ISE툴을 사용하여 합성하고, Modelsim_6.1i를 사용하여 검증하였다. 설계된 움직임 보상기는 단지 3개의 6-tap 필터만을 사용하면서 매크로블록 당 640 클럭 사이클에 수행하였다. 본 논문에서 제안하는 움직임 보상기는 실시간 비디오 처리를 요구하는 분야에 응용 가능할 것으로 사료된다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2011년도 춘계학술대회 논문집
• /
• pp.541-542
• /
• 2011

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 추계학술대회 논문집
• /
• pp.1073-1077
• /
• 1996

This paper presents a recoil and counter recoil(R&CR) motion measurement method using linear variable differential transformers(LVDT). The output of a LVDT is obtained from the differential voltage of the 2nd transformers. As a sensor core is attached at the motion body, the output is directly proportional to the core motion. Displacement, velocity and acceleration are measure from the core length. With a comparison between the measurement result and the known value which is obtained by the precision steel tape, the accuracy and the usefulness of the proposed scheme is validated.

• 제어로봇시스템학회논문지
• /
• 제21권9호
• /
• pp.818-826
• /
• 2015

This paper presents a novel methodology for estimating vehicle ego-motion, i.e. tri-axis linear velocities and angular velocities by using stereo vision sensor and 2G1Y sensor (longitudinal acceleration, lateral acceleration, and yaw rate). The estimated ego-motion information can be utilized to predict future ego-path and improve the accuracy of 3D coordinate of obstacle by compensating for disturbance from vehicle movement representatively for collision avoidance system. For the purpose of incorporating vehicle dynamic characteristics into ego-motion estimation, the state evolution model of Kalman filter has been augmented with lateral vehicle dynamics and the vanishing point estimation has been also taken into account because the optical flow radiates from a vanishing point which might be varied due to vehicle pitch motion. Experimental results based on real-world data have shown the effectiveness of the proposed methodology in view of accuracy.

• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.67-73
• /
• 2020

In this paper, we present a CNN-based gesture recognition approach which reduces the memory burden of input data. Most of the neural network-based gesture recognition methods have used a sequence of frame images as input data, which cause a memory burden problem. We use a motion history image in order to define a meaningful gesture. The motion history image is a grayscale image into which the temporal motion information is collapsed by synthesizing silhouette images of a user during the period of one meaningful gesture. In this paper, we first summarize the previous traditional approaches and neural network-based approaches for gesture recognition. Then we explain the data preprocessing procedure for making the motion history image and the neural network architecture with three convolution layers for recognizing the meaningful gestures. In the experiments, we trained five types of gestures, namely those for charging power, shooting left, shooting right, kicking left, and kicking right. The accuracy of gesture recognition was measured by adjusting the number of filters in each layer in the proposed network. We use a grayscale image with 240 × 320 resolution which defines one meaningful gesture and achieved a gesture recognition accuracy of 98.24%.

• 한국생산제조학회지
• /
• 제7권1호
• /
• pp.82-88
• /
• 1998

It is very important to test linear cycle positioning accuracy of NC lathes as it affect all other machines machined by them in industries. For example, if the linear positioning accuracy of x or z-axis directions is bad, the size of works will be wrong and the change-ability will be bad in the assembly of machine parts. In this paper , measuring systems are organized to measure linear displacement of ATC(Automatic tool changer) of NC lathe using laser interferometer, magnescale and tick pulses coming out from computer in order to get data at constant time intervals from the sensors, And each set of data gotten from test is expressed to a plots by computer treatment and the results of linear positioning error motion is estimated to numerics by statistical treatments.

• 한국생산제조학회지
• /
• 제7권3호
• /
• pp.51-51
• /
• 1998

It is very important to test linear cycle positioning accuracy of Machining centers as it affect all other machines machined by them in industries. For example, if the linear positioning accuracy of each axes directions is bad, the size of works will be wrong and the change-ability will be bad in the assembly of machine parts. In this paper, measuring systems are organized to measure linear displacements of table or spindle of machine center using laser interferometer, magnescale and tick pulses comming out from computer in order to get data at constant time intervals from the sensors. And each set of data gotten from test is expressed to a plots by computer treatment and the results of linear positioning error motion is estimated to numerics by statistical treatments.

• PNF and Movement
• /
• 제9권1호
• /
• pp.55-63
• /
• 2011

Purpose : This study was to investigate the application of Rhythmic Initiation(RI) in the respect of information processing in motor learning. Methods : A computer-aided literature search was performed in PubMed and adapted to the other databases and the others were in published books. The following keywords were used: Rhythmic Initiation, attention, memory, motor accuracy, feedback, motor learning, motor control, PNF, cognition. Results : The characterization of RI is rhythmic motion of limb or body through the desired range, starting with passive motion and progressing to active resisted movement. This study suggested that the relationship between of RI and motor learning through the respect of information processing, memory, attention and motor accuracy. Conclusion : Only Rhythmic Initiation, specifically focused on the effects of information processing approach, suggesting that RI can be positively influeced on sensory-perception, attention, memory, motor accuracy. however, it is unclear whether positive effects in the laboratory and field can be generalized to improve. In addition, sustainability of motor learning with RI remains uncertain.

• 한국멀티미디어학회논문지
• /
• 제21권9호
• /
• pp.1052-1061
• /
• 2018

In this paper, we propose a new algorithm that is robust against the effects of objects that are relatively unaffected by camera motion and can accurately detect camera motion even in high resolution images. First, for more accurate camera motion detection, a global motion filter based on entropy of a motion vector is used to distinguish the background and the object. A block matching algorithm is used to find exact motion vectors. In addition, a matched filter with the angle of the ideal motion vector of each block is used. Motion vectors including 4 kinds of diagonal direction, zoom in, and zoom out are added additionally. The experiment shows that the precision, recall, and accuracy of camera motion detection compared to the recent results is improved by 12.5%, 8.6% and 9.5%, respectively.