• Investigative Magnetic Resonance Imaging
• /
• 제22권1호
• /
• pp.71-77
• /
• 2018

Purpose: To develop a two-dimensional (2D) image-based respiratory motion correction technique for free-breathing coronary magnetic resonance angiography (MRA). Materials and Methods: The proposed respiratory navigator obtained aliased a 2D sagittal image from under-sampled k-space data and utilized motion correlation between the aliased images. The proposed navigator was incorporated into the conventional coronary MRA sequence including the diaphragm navigator and tested in three healthy subjects. Results: The delineation of major coronary arteries was significantly improved using the proposed 2D motion correction (S/I and A/P) compared to one-dimensional (S/I) correction using the conventional diaphragm navigator. Conclusion: The 2D image-based respiratory navigator was proposed for free-breathing coronary angiography and showed the potential for improving respiratory motion correction compared to the conventional 1D correction.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.605-608
• /
• 1999

In this paper, we proposed several scene analysis algorithms. These algorithms using image difference and histogram operate on the sequence of DC coefficient which is extracted from Motion JPEG or MPEG without full-frame decompression. Since DC sequence has the most information of full frame while it has reduced data. Experimental results show less than 1/64 of full frame analysing complexity and exactly analyze scene changes and extract key frames.

• 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%.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 학술대회
• /
• pp.109-114
• /
• 1999

Due to the temporal correlation of the image sequence, the motion vector of a block is highly related to the motion vector of the same coordinate block in the previous image frame. If we can obtain useful and enough information from the motion vector of the same coordinate block of the previous image frames, the total number of search points used to find the motion vector of the current block may be reduced significantly. Using that idea, an efficient new predicted direction search algorithm (PDSA) for block matching motion estimation is proposed in this paper.

• 전자공학회논문지S
• /
• 제36S권11호
• /
• pp.79-88
• /
• 1999

본 논문은 움직이는 물체가 존재하는 영상열에서 특정 물체만을 계속 추적하고자 하는 방법을 제안하였다. 밝기값과 동작(motion)경계점에 기반을 둔 윤곽선(contour) 추적 알고리즘을 이용하였다. 영상에서 움직이는 물체의 윤곽선의 동작은 이동, 회전, 크기변화를 나타내는 아핀 동작 모델에 의해 잘 묘사되어짐을 가정한다. 움직이는 물체의 윤곽선은 영상열을 따라 추정되는 B-스플라인에 의해 위치와 동작이 표현된다. 패턴인식을 이용하여 추적하고자하는 물체인지를 판별한다. 선형 칼만 필터를 사용하기 위해 아핀 동작 매개변수와 움직이는 물체의 윤곽선 모양(shape)의 두 필터로 추정과정을 나누었다. 차량계기판을 대상으로 한 실험영상에서 이 방법을 이용하여 방해물체가 존재하는 경우에도 안정된 동작의 추정과 추적된 궤적의 획득이 가능함을 보였다.

• 방송공학회논문지
• /
• 제2권2호
• /
• pp.125-135
• /
• 1997

This paper is concerned with realistic mainpulation of content in video sequences. Manipulation of content in video sequences is one of the content-based functionalities for MPEG-4 Visual standard. We present an approach to synthesizing video sequences by using the intermediate outputs of three-dimensional (3D) motion and depth analysis. For concreteness, we focus on video showing 3D motion of an observer relative to a scene containing planar runways (or roads). We first present a simple runway (or road) model. Then, we describe a method of identifying the runway (or road) boundary in the image using the Point of Heading Direction (PHD) which is defined as the image of, the ray along which a camera moves. The 3D motion of the camera is obtained from one of the existing 3D analysis methods. Then, a video sequence containing a runway is manipulated by (i) coloring the scene part above a vanishing line, say blue, to show sky, (ii) filling in the occluded scene parts, and (iii) overlaying the identified runway edges and placing yellow disks in them, simulating lights. Experimental results for a real video sequence are presented.

• 한국산업정보학회논문지
• /
• 제19권5호
• /
• pp.9-14
• /
• 2014

최근 컴퓨터 비젼이나 게임과 같은 분야에서 사람의 모션을 이용한 다양한 콘텐츠들이 개발되고 있다. 모션을 이용하여 콘텐츠를 제작하거나 응용프로그램을 개발하게 되면, 사용자는 게임이나 콘텐츠에 더욱 몰입감을 느낄 수 있고, 그에 따른 콘텐츠 사용의 만족도가 향상된다. 본 논문에서는 웹 카메라를 이용해서 캡처한 영상으로부터 모션을 인식하고, 이를 별도의 장비 없이 게임의 인터페이스로 활용할 수 있는 방법을 개발한다. 제안된 방법은 MHI(Motion History Image)와 피부색 검출 결과를 결합하여 입력영상으로부터 사람의 머리 부분을 분할하고, MHI 시퀀스(Sequence)를 이용하여 방향과 이동거리를 계산한다. 실험결과에서 제안된 사람의 머리 모션 인식 결과를 실제 게임에 적용하여 게임 캐릭터를 제어하기 위해 사용하였다. 제안된 방법은 사용자의 몰입감 정도를 향상시킬 수 있음을 증명하였고, 그로인해 기능성 게임의 사용자 인터페이스로의 가능성을 확인하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 G
• /
• pp.2237-2239
• /
• 1998

A limitation is assumed that In this paper, a generalized method is proposed to extract a period of a motion of on object. To detect a periodic motion, we put restrictions on a stationary camera and on a motion of an object. We ca derive the necessary and sufficient condition that an image sequence consists of the projection of the periodic motion by the affine transformation that is a reasonally good approach to the perspective projection. The difficulty of detecting its periodic motion is to select its have period in sequence and to define its width.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.365-368
• /
• 2001

This work describes a real-time method, based on motion energy detection, for detecting and tracking moving object in the consecutive image sequences. The motion of moving objects is detected by taking the difference of the two consecutive image frames. In addition an edge information of the current image is utilized in order to further increase the accuracy of detection. We can track the moving objects continuously by detecting the motion of objects from the sequence of image frames. A prototype system has been implemented using a TI TMS320C6201 EVM fixed-point DSP board, which can successfully track a moving human in real-time.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.327-328
• /
• 2006

This paper proposes a method for rejecting false matches in automobile rear view camera image sequences. Our method consists of two submethods which utilize the motion characteristics of an automobile. One is for a straight motion and the other is for a curve motion. First, we classify an image sequence into a straight motion or a curve motion and then apply an appropriate submethod. Our method works in cases where the percentage of true matches is as low as 30%.