• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.5
• /
• pp.960-966
• /
• 2017

In this paper, we proposed an algorithm that can extract lesion by inputting a medical image. Feature points are extracted using SIFT algorithm to extract genetic training of medical image. To increase the intensity of the feature points, the input image and that raining image are matched using vector similarity and the lesion is extracted. The vector similarity match can quickly lead to lesions. Since the direction vector is generated from the local feature point pair, the direction itself only shows the local feature, but it has the advantage of comparing the similarity between the other vectors existing between the two images and expanding to the global feature. The experimental results show that the lesion matching error rate is 1.02% and the processing speed is improved by about 40% compared to the case of not using the feature point intensity information.

• Bulletin of the Korean Chemical Society
• /
• v.31 no.10
• /
• pp.2841-2848
• /
• 2010

Quasiclassical trajectory (QCT) method has been used to investigate stereodynamics information of the reaction $O(^1D)+H_2{\rightarrow}\;OH$+H on the DK (Dobbyn and Knowles) potential energy surface (PES) at a collision energy of 23.06 kcal/mol, with the initial quantum state of reactant $H_2$ being set for v = 0 (vibration quantum number) and j = 0-5 (rotation quantum number). The PDDCSs (polarization dependent differential cross sections) and the distributions of P($\theta_r$), P($\phi_r$), P($\theta_r$, $\phi_r$) have been presented in this work. The results demonstrate that the products are both forward and backward scattered. As j increases, the backward scattering becomes weaker while the forward scattering becomes slightly stronger. The distribution of P($\theta_r$) indicates that the product rotational angular momentum j' tends to align along the direction perpendicular to the reagent relative velocity vector k, but this kind of product alignment is found to be rather insensitive to j. Furthermore, the distribution of P($\phi_r$) indicates that the rotational angular momentum vector of the OH product is preferentially oriented along the positive direction of y-axis, and such product orientation becomes stronger with increasing j.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.10
• /
• pp.911-920
• /
• 2016

For the pitch and yaw axis attitude control of launch vehicle, thrust vector control which changes the direction of thrust during the engine combustion is commonly used. Hydraulic actuation system has been used generally as a drive system for the thrust vector control of launch vehicles with the advantage of power-to-weight ratio. Nowadays, due to the developments of highly efficient electric motor and motor control techniques, it has done a lot of research to adopt electro-mechanical actuator for thrust vector control of small-sized launch vehicles. This paper describes system design and test results of the prototype of direct drive electro-mechanical actuation system which is being developed for the thrust vector control of $3^{rd}$ stage engine of KSVL-II.

• Journal of Environmental Science International
• /
• v.7 no.3
• /
• pp.335-348
• /
• 1998

The intensive meteorological observations including pibal balloon at Ungcheon, airsonde and 10m meteorological tower observations at Gulup-Do, where are located In the western coastal region, are taken to Investigate the characteristics of the upper and lower atmospheric structure and the local circulation pattern during the period of 17 to 22 September 1996. The diurnal variations of weather elements(i.e. air temperature, humidity, pressure, and Und speeds at Gulup-Do are analyzed and discussed with those at four inland meteorological stations. The vertical profiles of wind vector, ortho- gonality(Ω), and shear obtained from the pibal obsenrations are also presented to examine the change of wand structure according to the synoptic-scale pressure system's movement. The diurnal temperature changes at Gulup-Do are more sensitive than that of Inland meteorological stations In case of the mow of southwesterlies but are not dominant due to the ocean effect under the Influence of relatively cold northerlies. A well defined mixed layer Is developed from the 500m to the maximum 1700m with a significant capping Inversion layer on the top of it. It can be found from the vertical profiles of wind vector that the wind become generally strong at the interface heights between cloud lay- ers and non-cloud layers. The maximum Und shear Is appeared at the bel각t where the varlauon of wand direction Induced by the passage of synoptic-scale pressure system Is accompanied with the In- crease of Und speed. Based on the wind orthogonality, the change of wind direction with height is more complicated In cloudy day than In clear day. In case of a fair weather, the change of wand direction is showed to be at around 2km.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.5
• /
• pp.1085-1092
• /
• 2017

In this paper, we propose a wind forecasting method that reflects wind characteristics to improve the accuracy of wind power prediction. The proposed method consists of extracting wind characteristics and predicting power generation. The part that extracts the characteristics of the wind uses correlation analysis of power generation amount, wind direction and wind speed. Based on the correlation between the wind direction and the wind speed, the feature vector is extracted by clustering using the K-means method. In the prediction part, machine learning is performed using the SVR that generalizes the SVM so that an arbitrary real value can be predicted. Machine learning was compared with the proposed method which reflects the characteristics of wind and the conventional method which does not reflect wind characteristics. To verify the accuracy and feasibility of the proposed method, we used the data collected from three different locations of Jeju Island wind farm. Experimental results show that the error of the proposed method is better than that of general wind power generation.

• The Journal of the Korea Contents Association
• /
• v.12 no.6
• /
• pp.9-20
• /
• 2012

In computer vision, it is very important to obtain reliable corresponding feature points. However, we know it is not easy to find the corresponding feature points exactly considering by scaling, lighting, viewpoints, etc. Lots of SIFT methods applies the invariant to image scale and rotation and change in illumination, which is due to the feature vector extracted from corners or edges of object. However, SIFT could not find feature points, if edges do not exist in the area when we extract feature points along edges. In this paper, we present a new placement method of marker to improve the performance of SIFT feature detection and matching between different view of an object or scene. The shape of the markers used in the proposed method is formed in a semicircle to detect dominant direction vector by SIFT algorithm depending on direction placement of marker. We applied De Bruijn sequence for the markers direction placement to improve the matching performance. The experimental results show that the proposed method is more accurate and effective comparing to the current method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.2
• /
• pp.51-58
• /
• 2018

Recently, various satellite sensors have been developed and it is becoming more convenient to acquire multitemporal satellite images. Therefore, various researches are being actively carried out in the field of utilizing change detection techniques such as disaster and land monitoring using multitemporal satellite images. In particular, researches related to the development of unsupervised change detection techniques capable of extracting rapidly change regions have been conducted. However, there is a disadvantage that false detection occurs due to a spectral difference such as a seasonal change. In order to overcome the disadvantages, this study aimed to reduce the false alarm detection due to seasonal effects using the direction vector generated by applying the $S^2CVA$ (Sequential Spectral Change Vector Analysis) technique, which is one of the unsupervised change detection methods. $S^2CVA$ technique was applied to RapidEye images of the same and different seasons. We analyzed whether the change direction vector of $S^2CVA$ can remove false positives due to seasonal effects. For the quantitative evaluation, the ROC (Receiver Operating Characteristic) curve and the AUC (Area Under Curve) value were calculated for the change detection results and it was confirmed that the change detection performance was improved compared with the change detection method using only the change magnitude vector.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.1-8
• /
• 2010

The researches about gaze recognition which current user gazes and finds the location have increasingly developed to have many application. The gaze recognition of existence all about researches have got problems because of using equipment that Infrared(IR) LED, IR camera and head-mounted of high price. This study propose and implement the gaze recognition system based on SVM using a single PC Web camera. The proposed system that divide the gaze location of 36 per 9 and 4 to recognize gaze location of 4 direction and 9 direction recognize user's gaze. Also, the proposed system had apply on image filtering method using difference image entropy to improve performance of gaze recognition. The propose system was implements experiments on the comparison of proposed difference image entropy gaze recognition system, gaze recognition system using eye corner and eye's center and gaze recognition system based on PCA to evaluate performance of proposed system. The experimental results, recognition rate of 4 direction was 94.42% and 9 direction was 81.33% for the gaze recognition system based on proposed SVM. 4 direction was 95.37% and 9 direction was 82.25%, when image filtering method using difference image entropy implemented. The experimental results proved the high performance better than existed gaze recognition system.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.626-629
• /
• 2004

Texture imaging, which means texture image creation by co-occurrence relation, has been known as one of useful image analysis methodologies. For this purpose, most commercial remote sensing software provides texture analysis function named GLCM (Grey Level Co-occurrence Matrix). In this study, texture-imaging program for GLCM algorithm is newly implemented in the MS Visual IDE environment. While, additional texture imaging modules based on GLDV (Grey Level Difference Vector) are contained in this program. As for GLCM/GLDV texture variables, it composed of six types of second order texture function in the several quantization levels of 2(binary image), 8, and 16: Homogeneity, Dissimilarity, Energy, Entropy, Angular Second Moment, and Contrast. As for co-occurrence directionality, four directions are provided as $E-W(0^{\circ}),\;N-E(45^{\circ}),\;S-W(135^{\circ}),\;and\;N-S(90^{\circ}),$ and W-E direction is also considered in the negative direction of E- W direction. While, two direction modes are provided in this program: Omni-mode and Circular mode. Omni-mode is to compute all direction to avoid directionality problem, and circular direction is to compute texture variables by circular direction surrounding target pixel. At the second phase of this study, some examples with artificial image and actual satellite imagery are carried out to demonstrate effectiveness of texture imaging or to help texture image interpretation. As the reference, most previous studies related to texture image analysis have been used for the classification purpose, but this study aims at the creation and general uses of texture image for urban remote sensing.

• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1229-1235
• /
• 2020

A line parallel to the ground is frequently shown in our daily life, which enables us to guess its direction. Especially, such a guess tends to become clear when a vanishing line of the ground is shown together. In this paper, a vision based pallet measurement method is suggested, which uses a technique for estimating three-dimensional direction of a line parallel to the ground. The technique computes actually a vector heading to intersection of a given imaged line parallel to the ground and the ground vanishing line determined previously on calibrating a measurement camera. Through an experiment of measuring a real commercial pallet with various orientation and distance, we found that the technique could measure the orientation of the pallet correctly and accurately. The technique worked well even though an edge line available on the front plane of a pallet was almost parallel to the ground vanishing line.