• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.35-41
• /
• 2015

When a video surveillance system tracks a specific object, it is very important to get quickly the information of the object through fast image processing. Usually one camera surveillance system for tracking the object made results in various problems such like occlusion, image noise during the tracking process. It makes difficulties on image based moving object tracking. Therefore, to overcome the difficulties the multi video surveillance system which installed several camera within interested area and looking the same object from multi angles of view could be considered as a solution. If multi cameras are used for tracking object, it is capable of making a decision having high accuracy in more wide space. This paper proposes a method of recognizing and tracking a specific object like a car using the homography in which multi cameras are installed at the crossroad.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.35-41
• /
• 2018

The Q-learning algorithm based on reinforcement learning is useful for learning the goal for one behavior at a time, using a combination of discrete states and actions. In order to learn multiple actions, applying a behavior-based architecture and using an appropriate behavior adjustment method can make a robot perform fast and reliable actions. Q-learning is a popular reinforcement learning method, and is used much for robot learning for its characteristics which are simple, convergent and little affected by the training environment (off-policy). In this paper, Q-learning algorithm is applied to a lamp robot to learn multiple behaviors (human recognition, desk object recognition). As the learning rate of Q-learning may affect the performance of the robot at the learning stage of multiple behaviors, we present the optimal multiple behaviors learning model by changing learning rate.

• 한국전산유체공학회:학술대회논문집
• /
• 1996.05a
• /
• pp.105-110
• /
• 1996

In the present paper, flow fields around two dimensional single and two circular cylinders are analysed by a finite difference method. Navier-Stokes and the continuity equations an solved to simulate the flow fields. A overlapped grid system(the composite of a body boundary-fitted grid system near the body and a rectangular grid system for other flow fields) is used for this calculation. In the use of overlapped grid system, it is most significant thing to exchange the physical quantities from one grid system to the other one continuously, In this research, the linear interpolations of physical quantaties are done for this purpose in the overlapped region. The numerical calculations are carried out for the flows around a circular cylinder and two cylinders to verify the accuracy of present method. The flow fields around two cylinders facing the flow with side by side and tandem arrangement are analysed. The results are compared to other experimental and computational ones done in other single grid system.

• Korean Journal of Optics and Photonics
• /
• v.2 no.1
• /
• pp.1-6
• /
• 1991

This paper describes the theoretical analysis of a diffraction pattern analyzer for the characterization of microscale object fields and a method for obtaining size and size distribution from the measured diffraction pattern of the object fields. For the experimental verification, a typical optical Fourier transform system was set up and calibrated with 2 5$\mu \textrm m$ and 50$\mu \textrm m$ pinholes. The system responses to distilled water droplets, alcohol, glycerin and silicon oil were imaged with vidicon, and the image was processed to determine the size distribution of each liquid particle field. The energy distribution function which is defined as the total intensity of a circular ring in the diffraction pattern was used to determine the dominant particle size of each liquid particle field.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2003.11a
• /
• pp.37-42
• /
• 2003

전반사는 물체의 사실적인 모습을 나타내는데 중요한 요소이지만 컴퓨터 비전에서는 처리하기 어려운 장애 요소이다. 본 논문에서는 영상기반 재조명을 위하여 조명 조건이 다른 복수의 영상으로부터 전반사 성분과 난반사 성분을 분리하는 효과적인 알고리즘을 제안한다. 이 알고리즘은 전반사 성분이 존재하는 영상과 난반사 성분만이 존재하는 영상에 대하여 난반사 성분의 RGB 값은 서희 비율을 유지하면서 변한다는 성질을 이용하여 전반사 성분을 분리한다. 그리고 실험을 통하여 이 알고리즘의 유효성을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.630-639
• /
• 2001

This study proposes a new calculation method for generating real nighttime lamp-lit images. In order to improve the color appearance in the prediction of a nighttime lamp-lighted scene, the lamp-lit image is synthesized based on spectral distribution using the estimated local spectral distribution of the headlamps and the surface reflectance of every object. The Principal component analysis method is introduced to estimate the surface color of an object, and the local spectral distribution of the headlamps is calculated based on the illuminance data and spectral distribution of the illuminating headlamps. HID and halogen lamps are utilized to create beam patterns and captured road scenes are used as background images to simulate actual headlamp-lit images on a monitor. As a result, the reproduced images presented a color appearance that was very close to a real nighttime road image illuminated by single and multiple headlamps compared to the conventional graphic-based algorithm.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.19 no.6
• /
• pp.688-697
• /
• 2008

In this paper, an analysis method for indoor optical wireless channel properties based on photon model is presented for characterization of communication environment. In contrast to radio waves, optical waves have very short wave-lengths and very high frequencies, so that material properties become important. Channel models including diffuse reflections and absorption effects due to material surface textures make conventional electromagnetic wave analysis methods based on ray tracing consume enormous time. To overcome these problems, an analysis method using photon model is presented that approximates light intensity by a density of photons. The photon model ensures that simulation time is within a predictable limit.

• Journal of Advanced Navigation Technology
• /
• v.14 no.5
• /
• pp.640-647
• /
• 2010

Many methods have been proposed to detect faults of carrier phase measurements, but there are no distinguished methods for land transportation systems. in this paper, the baseline constraints are used to detect faults in GPS carrier phase measurements with vehicle dynamic information. The faults include the multipath on GPS carrier measurements. Multiple antenna groups are used for this research. In the measurement domain the fault detection has been accomplished so that the implementation is easier than other methods.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.1
• /
• pp.38-48
• /
• 2007

In this paper, we propose an image-based method for modeling 3D objects with curved surfaces based on the NURBS (Non-Uniform Rational B-Splines) representation. Starting from a few calibrated images, the user specifies the corresponding curves by means of an interactive user interface. Then, the 3D curves are reconstructed using stereo reconstruction. In order to fit the curves easily using the interactive user interface, NURBS curves and surfaces are employed. The proposed surface modeling techniques include surface building methods such as bilinear surfaces, ruled surfaces, generalized cylinders, and surfaces of revolution. In addition to these methods, we also propose various advanced surface modeling techniques, including skinned surfaces, swept surfaces, and boundary patches. Based on these surface modeling techniques, it is possible to build various types of 3D shape models with textured curved surfaces without much effort. Also, it is possible to reconstruct more realistic surfaces by using proposed view-dependent texture acquisition algorithm. Constructed 3D shape model with curves and curved surfaces can be exported in VRML format, making it possible to be used in different 3D graphics softwares.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.3
• /
• pp.95-103
• /
• 1998

This paper deals with a problem occuring in recognition of tactile images due to the effects of imposed force at a me urement moment. Tactile image of a contact surface, used for recognition of the surface type, varies depending on the forces imposed so that a false recognition may result in. This paper fuzzifies two parameters of the contour of a tactile image with the membership function formed by considering the imposed force. Two fuzzifed paramenters are fused by the average Minkowski's dist; lnce. The proposed algorithm was implemented on the multisensor system cnmposed of an optical tact le sensor and a 6 axes forceltorque sensor. By the experiments, the proposed algorithm has shown average recognition ratio greater than 869% over all imposed force ranges and object models which is about 14% enhancement comparing to the case where only the contour information is used. The pro- ~oseda lgorithm can be used for end-effectors manipulating a deformable or fragile objects or for recognition of 3D objects by implementing on multi-fingered robot hand.