• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1401-1403
• /
• 2013

사건 발생 후의 대응이 아닌 영상 분석을 통해 실시간으로 위협 상황에 대응할 수 있는 지능형 영상 보안 기술이 매우 중요한 이슈가 되고 있다. 본 논문에서는 지능형 영상 보안에 사용할 수 있는 실시간 얼굴 인식 및 추적 기법을 제안한다. 사람의 정면 얼굴 영상을 ASM(Active Shape Model) 알고리즘을 이용하여 정규화 시키고 Gabor Wavelet Filter를 이용하여 얼굴 고유 특징 벡터를 추출하여 인식에 사용하였다. 인식이 완료된 얼굴은 Camshift와 Kalman Filter를 이용하여 카메라 감시 영역에서 벗어날 때까지 강건한 추적을 통하여 관리자가 실시간으로 확인 및 대응할 수 있게 하였다.

• Journal of Internet Computing and Services
• /
• v.18 no.4
• /
• pp.61-67
• /
• 2017

Recently, CCTV has been combined with areas such as big data, artificial intelligence, and image analysis to detect various abnormal behaviors and to detect and analyze the overall situation of objects such as people. Image analysis research for this intelligent video surveillance function is progressing actively. However, CCTV images using 2D information generally have limitations such as object misrecognition due to lack of topological information. This problem can be solved by adding the depth information of the object created by using two cameras to the image. In this paper, we perform background modeling using Mixture of Gaussian technique and detect whether there are moving objects by segmenting the foreground from the modeled background. In order to perform the depth information-based segmentation using the RGB information-based segmentation results, stereo-based depth maps are generated using two cameras. Next, the RGB-based segmented region is set as a domain for extracting depth information, and depth-based segmentation is performed within the domain. In order to detect the center point of a robustly segmented object and to track the direction, the movement of the object is tracked by applying the CAMShift technique, which is the most basic object tracking method. From the experiments, we prove the efficiency of the proposed object detection and tracking method using the RGB-D model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.471-479
• /
• 2018

Recently, the spread of smart TV based Android iOS Set Top box has become common. This paper propose a new approach to control the TV using gestures away from the era of controlling the TV using remote control. In this paper, the AdaBoost algorithm is applied to gesture recognition by using a mono camera. First, we use Camshift-based Body tracking and estimation algorithm based on Gaussian background removal for body coordinate extraction. Using global and local feature vectors, we recognized gestures with speed change. By tracking the time interval trajectories of hand and wrist, the AdaBoost algorithm with CART algorithm is used to train and classify gestures. The principal component feature vector with high classification success rate is searched using CART algorithm. As a result, 24 optimal feature vectors were found, which showed lower error rate (3.73%) and higher accuracy rate (95.17%) than the existing algorithm.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.5
• /
• pp.490-498
• /
• 2010

This paper presents an autonomous target tracking approach and technique for transmitting ground control station image periodically for an unmanned aerial vehicle using onboard gimbaled(pan-tilt) camera system. The miniature rotary UAV which was used in this study has a small, high-performance camera, improved target acquisition technique, and autonomous target tracking algorithm. Also in order to stabilize real-time image sequences, image stabilization algorithm was adopted. Finally the target tracking performance was verified through a real flight test.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.209-214
• /
• 2010

In this paper, We analyzes the image along the platform (Open Eye), through prevention of dementia or stroke patients and cognitive rehabilitation for the proposed system. This way through the camera image according to user's movement gained OpenCV image processing library, which is based on motion analysis, a part of this rehabilitation is to apply to cognitive rehabilitation. Therefore, this paper proposes a new image analysis system has been exposed to the elderly or stroke patients with dementia, their hand gestures through which patients can detect the image of the cognitive rehabilitation to help them in the analysis of the image analysis system is proposed.

• Journal of Korea Multimedia Society
• /
• v.16 no.2
• /
• pp.213-225
• /
• 2013

This paper proposes a design method of ball-plate robot controller using single camera and two motors to balance the ball on plate and reduce steady state control error. To design the ball-plate system, it is necessary to observe state of the ball and maintain balance of the plate. The state of the ball is tracked by using the CAMShift algorithm and position error of the ball is compensated by the Kalman filter. Balance of the plate is controlled by driving two motors and we used DC motors which has smaller measurement error. Due to surface condition of the plate or tracking error of ball's position, there are small errors remained. These errors are accumulated and disturb maintaining balance of the ball. To handle the problem, we propose a controller supplemented with an integrator.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.2
• /
• pp.710-726
• /
• 2018

This paper presents an extended particle filter to increase the accuracy and decrease the computation load of vehicle tracking. Particle filter has been the subject of extensive interest in video-based tracking which is capable of solving nonlinear and non-Gaussian problems. However, there still exist problems such as preventing unnecessary particle consumption, reducing the computational burden, and increasing the accuracy. We aim to increase the accuracy without an increase in computation load. In proposed method, we calculate the direction angle of the target vehicle. The angular difference between the direction of the target vehicle and each particle of the particle filter is observed. Particles are filtered and weighted, based on their angular difference. Particles with angular difference greater than a threshold is eliminated and the remaining are stored with greater weights in order to increase their probability for state estimation. Threshold value is very critical for performance. Thus, instead of having a constant threshold value, proposed algorithm updates it online. The first advantage of our algorithm is that it prevents the system from failures caused by insufficient amount of particles. Second advantage is to reduce the risk of using unnecessary number of particles in tracking which causes computation load. Proposed algorithm is compared against camshift, direction-based particle filter and condensation algorithms. Results show that the proposed algorithm outperforms the other methods in terms of accuracy, tracking duration and particle consumption.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.2
• /
• pp.95-100
• /
• 2013

Smart surveillance, is the use of automatic video analysis technologies in video surveillance applications. We present a robust object tracking method using pan-tilt-zoom camera for intelligent surveillance System, As the result of the experiment using 78 vehicle, the success rate of the tracking for moving object & non-moving object werw 97.4% and 91%. and 84.6%. the success rate o PTZ control for license plate image.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.899-902
• /
• 2005

언제, 어디서, 누구나 대용량 네트워크를 사용할 수 있는 유비쿼터스(ubiquitous) 시대가 다가오면서, 카메라가 장착되어 있고 무선 통신이 가능한 PDA, 웨어러블(wearable) 컴퓨터와 같은 휴대용장치가 가까운 미래에는 일상의 한 부분이 될 것이다. 이런 상황을 반영하듯, 휴대용 장치를 이용하여 실감형 게임(augmented game)을 수행하는 다양한 연구가 진행되어 왔다. 기존의 실감형 게임들은 전통적인 ‘backpack’ 시스템을 이용하거나 패턴마커(pattern marker)를 이용하였다. ‘backpack’ 시스템은 비싸고, 거추장스러우며, 사용하기 불편한 단점을 가지고 있으며, 패턴마커를 이용하면 미리 정한 장소에서만 게임을 즐길 수 있는 단점을 가지고 있다. 본 논문에서는 Flying Cake이라는 실감형 게임을 소개하며, 거추장스러운 장비 대신, 가볍고 휴대 가능한 PDA를 이용하여 게임을 수행하며, 실제 세계에서 가상의 물체를 접목할 위치를 지정하기 위해, 미리 정해져 있는 패턴마커 대신 얼굴 영역을 이용한다. Flying Cake은 연산자원이 부족한 PDA에서 실시간으로 얼굴 영역을 찾기 위해 스킨칼라(skin-color) 모델과 CAMShift 알고리즘을 이용하며, PDA상에서 카메라를 이용하여 실제 세계와 가상의 물체 사이의 상호작용을 제공하는 새로운 게임 패러다임(paradigm)을 통해 사용자에게 새로운 즐거움을 제공한다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.1 no.2
• /
• pp.65-70
• /
• 2008

Smart surveillance, is the use of automatic video analysis technologies in video surveillance applications. We present a robust object tracking method using pan-tilt-zoom camera for intelligent surveillance System, As the result of the experiment using 78 vehicle, the success rate of the tracking for moving object & non-moving object werw 97.4% and 91%. and 84.6%. the success rate o PTZ control for license plate image.