• 정보처리학회논문지A
• /
• 제16A권3호
• /
• pp.209-216
• /
• 2009

스마트 홈(smart home)은 인간과 홈의 컨텍스트(context) 정보를 이용하여 인간에게 자동적인 홈 서비스(Home service)를 제공해줄 수 있는 미래의 환경이다. 인간의 위치와 모션은 스마트 홈에서 굉장히 중요한 컨텍스트이다. 본 논문은 스마트 홈에서 인간의 위치와 모션을 예측할 수 있는 실시간 휴먼 트랙커(tracker)를 연구하였다. 실시간 휴먼 트랙커를 위해 4개의 네트워크 카메라를 사용하였다. 본 논문에서는 실시간 휴먼 트랙커의 구조를 설명하고, 인간의 위치와 모션을 자동적으로 예측 및 판단하는 알고리즘을 제안하였다. 인간 위치를 위해서 3개의 배경 이미지를 이용하였다(이미지1: 빈 방 이미지, 이미지2: 거주자가 제외 된 가구 및 가전 이미지, 이미지3: 전체 이미지). 실시간 휴먼 트랙커는 3개의 이미지를 비교하여 각 이미지로부터 추출되는 특징 값을 결정하고, 이들 특징 값을 SVM(Support Vector Machine)을 이용하여 각각의 모션을 예측하였다. 3개의 배경 이미지를 이용한 인간 위치 인식실험은 평균 0.037 초가 소요 되었다. SVM을 이용한 모션 인식 요소에서, 각 동작에 대하여 1000번씩 측정했고, 모든 모션의 정확도 평균은 86.5% 의 정확도를 보였다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2009년도 9th International Meeting on Information Display
• /
• pp.1228-1231
• /
• 2009

This paper presented an automatic system for display quality measurement by image processing. The goal is to replace human eyes for display quality evaluation by computer vision and get the objective quality review for consumer to make purchase of monitor or TV. Color, contrast, brightness, sharpness and motion blur are the main five factors to affect display quality that could be measured by supplying patterns and analyzing the corresponding images captured from webcam. The scores are calculated by image processing techniques. Linear regression model is then adopted to find the relation between human score and the measured display performance.

• Imaging Science in Dentistry
• /
• 제50권3호
• /
• pp.227-236
• /
• 2020

Purpose: Image artifacts caused by patient motion cause problems in cone-beam computed tomography (CBCT) because they lead to distortion of the 3-dimensional reconstruction. This prospective study was performed to quantify patient movement during CBCT acquisition and its influence on image quality. Materials and Methods: In total, 412 patients receiving CBCT imaging were equipped with a wireless head sensor system that detected inertial, gyroscopic, and magnetometric movements with 6 dimensions of freedom. The type and amplitude of movements during CBCT acquisition were evaluated and image quality was rated in 7 different anatomical regions of interest. For continuous variables, significance was calculated using the Student t-test. A linear regression model was applied to identify associations of the type and extent of motion with image quality scores. Kappa statistics were used to assess intra- and inter-rater agreement. Chi-square testing was used to analyze the impact of age and sex on head movement. Results: All CBCT images were acquired in a 10-month period. In 24% of the investigations, movement was recorded (acceleration: >0.10 [m/s²]; angular velocity: >0.018 [°/s]). In all examined regions of interest, head motion during CBCT acquisition resulted in significant impairment of image quality (P<0.001). Movement in the horizontal and vertical axes was most relevant for image quality (R²>0.7). Conclusion: Relevant head motions during CBCT imaging were frequently detected, leading to image quality loss and potentially impairing diagnosis and therapy planning. The presented data illustrate the need for digital correction algorithms and hardware to minimize motion artefacts in CBCT imaging.

• 정보처리학회논문지B
• /
• 제10B권2호
• /
• pp.135-142
• /
• 2003

본 논문은 영상내 객체정보의 정확한 복원을 위하여, 연속된 2차원 영상으로부터 특정 객체의 특징점을 추출하고, 특징점의 위치 데이터들로부터 원형의 3차원 모양 및 모션 정보를 복원하는 알고리즘과 결과를 제시하였다. 2차원 영상의 특징점 검출을 위해서는 물체와 배경이 명확히 구별되는 실험영상 환경에서 색상변환을 통한 자동 추출 방법을 사용하였다. 추출된 2차원 객체의 특징점들로부터 3차원 모앙, 움직임 정보를 복원하기 위하여 스테레오 카메라와 준원근 카메라 모델을 적용하고 SVD(SinEuiar Value Decomposition)에 의한 인수분해연산을 수행하였다. 준원근 카메라 모델의 근본적인 문제인 깊이정보의 복원 에러가, 스테리오 영상 분석에 의해 최소화 되었다. 본 논문에서 제시된 방법들의 성능을 객관적으로 평가하기 위하여 크기와 위치가 알려진 3차원 물체에 대해 실험을 행하였으며, 영상의 21개 특징점 위치와 공간상에서의 3개 방향으로의 움직임 각도를 연산에 의해 복원한 후 원형의 데이터와 비교하여 본 알고리즘의 정확성을 증명하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.63.5-63
• /
• 2001

In this paper, moving objects tracking and dynamic characteristic analysis are studied. Kohonen´s self-organizing neural network models are used for moving objects tracking and time delay neural networks are used for dynamic characteristic analysis. Instead of objects brightness, neuron projections by Kohonen Networks are used. The motion of target objects can be analyzed by using the differential neuron image between the two projections. The differential neuron image which is made by two consecutive neuron projections is used for center detection and moving objects tracking. The two differential neuron images which are made by three consecutive neuron projections are used for the moving trajectory estimation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권6호
• /
• pp.1194-1208
• /
• 2010

As visual surveillance systems gain wider usage in a variety of fields, it is important that they are capable of interpreting scenes automatically, also known as "human motion analysis" (HMA). However, existing HMA methods are too domain specific and computationally expensive. This paper proposes a general purpose HMA method that is based on the idea that human beings tend to exhibit erratic motion patterns during abnormal situations. Limb movements are characterized using the statistics of angular and linear displacements. In addition, the method is enhanced via the use of the entropy of the Fourier spectrum to measure the randomness of subject's motions. Various experiments have been conducted and the results indicate that the proposed method has very high classification accuracy in identifying anomalous behavior.

• 제어로봇시스템학회논문지
• /
• 제13권6호
• /
• pp.537-641
• /
• 2007

In this paper, motion analysis algorithm is presented for home surveillance of the aged who lives alone. For the first step, we acquire images from a camera. To enhance the image, we use median filtering and binarize it to reduce processing time. And then morphological operations are performed to remove small blobs and small holes. At the forth step, blobs are analysed to extracts tor foreground region. Then, motions are predicted from these images by using optical tlow technique, and the predicted motion data are refined by comparing our cardboard models so as to judge behavior pattern.

• Journal of Astronomy and Space Sciences
• /
• 제24권3호
• /
• pp.235-248
• /
• 2007

이 연구는 통신해양기상위성의 영상위치유지 (Image Navigation and Registration, INR) 시스템의 시뮬레이션을 위한 프로그램을 개발하고, 영상오차보상(Image Motion Compensation, IMC) 알고리즘의 성능을 비교분석 하였다. 통신해양기상위성 궤도와 자세 요소를 모델링 하고 궤도오차와 자세오차를 계산하여 이러한 궤도 및 자세오차가 영상왜곡에 미치는 영향을 분석하였다. 또한 영상오차보상을 하지 않았을 경우와 GOES 위성의 영상오차보상 알고리즘을 적용하였을 경우, 그리고 선행 연구를 통해 개발되었던 개량된 영상오차보상 알고리즘을 적용하였을 경우의 영상들을 비교하여 각 알고리즘의 성능을 확인하였다. 개량된 영상오차보상 알고리즘은 GOES위성의 알고리즘보다 효율적으로 영상왜곡을 보상하였다. 이러한 연구는 통신해양기상위성의 INR시스템을 효과적으로 운용하고 그 성능을 향상시킬 수 있는 기술적 토대를 마련하는데 기여할 것이다.

• 전자공학회논문지B
• /
• 제30B권2호
• /
• pp.59-68
• /
• 1993

The motion vector estimation and motion boundary detection have been briskly studied since they are an important clue for analysis of object structure and 3-d motion. The purpose of this researches is more exact estimation, but there are two main causes to make inaccurate. The one is the erroneous measurement of gradients in brightness values and the other is the blurring of motion boundries which is caused by the smoothness constraint. In this paper, we analyze the gradient measurement error of conventional methods and propose new technique based on it. When the proposed method is applied to the motion boundary detection in Schunck and motion vector estimation in Horn & Schunck, it is shown to have much better performance than conventional method is some artificial and real image sequences.

• 대한인간공학회지
• /
• 제17권2호
• /
• pp.11-23
• /
• 1998

Dynamic motion difference between normal subjects and low-back pain (LBP) patients has been investigated in terms of kinematic variables such as range of motion, velocity and acceleration of the back and hip. Ten healthy subjects and ten LBP patients were recruited in this study. Electro-goniometer such as Lumbar Motion Monitor and Hip Monitor have been used for quantitative measurement of the trunk motion during repetitive flexion and extension for ten seconds. Results indicated that the velocity and acceleration of the back and hip were important parameters to quantitatively identify LBP patients. The consistency of cyclic trunk motion and the relationship between the back and hip were measured in terms of Variance Ratio and Phase Angle in order to accurately assess the motion characteristics of LBP patients. In particular, the hip motion has been proven to be a very important factor in describing the kinematics of damaged lower back. The functional evaluation technique suggested in this study will be a tool to assist physicians for an accurate diagnosis and timely rehabilitation along with current image diagnosis techniques.