• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.5
• /
• pp.449-457
• /
• 2011

As automated image processing techniques have been required in multi-temporal/multi-sensor geospatial image applications, use of automated but highly invariant image matching technique has been a critical ingredient. Note that there is high possibility of geometric and spectral differences between multi-temporal/multi-sensor geospatial images due to differences in sensor, acquisition geometry, season, and weather, etc. Among many image matching techniques, the SIFT (Scale Invariant Feature Transform) is a popular method since it has been recognized to be very robust to diverse imaging conditions. Therefore, the SIFT has high potential for the geospatial image processing. This paper presents a performance test results of the SIFT on geospatial imagery by simulating various image differences such as shear, scale, rotation, intensity, noise, and spectral differences. Since a geospatial image application often requires a number of good matching points over the images, the number of matching points was analyzed with its matching positional accuracy. The test results show that the SIFT is highly invariant but could not overcome significant image differences. In addition, it guarantees no outlier-free matching such that it is highly recommended to use outlier removal techniques such as RANSAC (RANdom SAmple Consensus).

• Journal of the Korean Operations Research and Management Science Society
• /
• v.26 no.4
• /
• pp.55-70
• /
• 2001

Artificial neural network(ANN) models have been widely used for the classification problems in business such as bankruptcy prediction, credit evaluation, etc. Although the application of ANN to classification of consumers＇ choice behavior is a promising research area, there have been only a few researches. In general, most of the researches have reported that the classification performance of the ANN models were better than conventional statistical model Because the survey data on consumer behavior may include much noise and missing data, ANN model will be more robust than conventional statistical models welch need various assumptions. The purpose of this paper is to study the potential of the ANN model for forecasting consumers＇ choice behavior based on survey data. The data was collected by questionnaires to the shoppers of department stores and discount stores. Then the correct classification rates of the ANN models for the training and test sample with that of multiple discriminant analysis(MDA) and logistic regression(Logit) model. The performance of the ANN models were betted than the performance of the MDA and Logit model with respect to correct classification rate. By using input variables identified as significant in the stepwise MDA, the performance of the ANN models were improved.

• Smart Structures and Systems
• /
• v.3 no.2
• /
• pp.201-217
• /
• 2007

An active damage detection technique is introduced to locate damage in an isotropic plate using Lamb waves. This technique uses a time-domain energy model of Lamb waves in plates that the wave amplitude inversely decays with the propagation distance along a ray direction. Accordingly the damage localization is formulated as a least-squares problem to minimize an error function between the model and the measured data. An active sensing system with integrated actuators/sensors is controlled to excite/receive $A_0$ mode of Lamb waves in the plate. Scattered wave signals from the damage can be obtained by subtracting the baseline signal of the undamaged plate from the recorded signal of the damaged plate. In the experimental study, after collecting the scattered wave signals, a discrete wavelet transform (DWT) is employed to extract the first scattered wave pack from the damage, then an iterative method is derived to solve the least-squares problem for locating the damage. Since this method does not rely on time-of-flight but wave energy measurement, it is more robust, reliable, and noise-tolerant. Both numerical and experimental examples are performed to verify the efficiency and accuracy of the method, and the results demonstrate that the estimated damage position stably converges to the targeted damage.

• International Journal of Aeronautical and Space Sciences
• /
• v.18 no.4
• /
• pp.688-696
• /
• 2017

This paper presents an integrated roll-pitch-yaw autopilot using an equivalent based sliding mode control for skid-to-turn nonlinear time-varying missile system with lumped disturbances in its six-equations of motion. The considered missile model are developed to integrate the model uncertainties, external disturbances, and parameters perturbation as lumped disturbances. Moreover, it considers the coupling effect between channels, the variation of missile velocity and parameters, and the aerodynamics nonlinearity. The presented approach is employed to achieve a good tracking performance with robustness in all missile channels simultaneously during the entire flight envelope without demand of accurate modeling or output derivative to avoid the noise existence in the real missile system. The proposed autopilot consisting of a two-loop structure, controls pitch and yaw accelerations, and stabilizes the roll angle simultaneously. The Closed loop stability is studied. Numerical simulation is provided to evaluate performance of the suggested autopilot and to compare it with an existing autopilot in the literature concerning the robustness against the lumped disturbances, and the aforesaid considerations. Finally, the proposed autopilot is integrated in a six degree of freedom flight simulation model to evaluate it with several target scenarios, and the results are shown.

• Structural Engineering and Mechanics
• /
• v.16 no.1
• /
• pp.17-34
• /
• 2003

This paper presents a damage assessment procedure applied to periodic spring mass systems using an eigenvalue sensitivity-based method. The damage is directly related to the stiffness reduction of the damage element. The natural frequencies of periodic structures with one single disorder are found by adopting the transfer matrix approach, consequently, the first order approximation of the natural frequencies with respect to the disordered stiffness in different elements is used to form the sensitivity matrix. The analysis shows that the sensitivity of natural frequencies to damage in different locations depends only on the mode number and the location of damage. The stiffness changes due to damage can be identified by solving a set of underdetermined equations based on the sensitivity matrix. The issues associated with many possible damage locations in large structural systems are addressed, and a means of improving the computational efficiency of damage detection while maintaining the accuracy for large periodic structures with limited available measured natural frequencies, is also introduced in this paper. The incomplete measurements and the effect of random error in terms of measurement noise in the natural frequencies are considered. Numerical results of a periodic spring-mass system of 20 degrees of freedom illustrate that the proposed method is simple and robust in locating single or multiple damages in a large periodic structure with a high computational efficiency.

• Smart Structures and Systems
• /
• v.6 no.4
• /
• pp.405-421
• /
• 2010

This paper proposes a method for early warning of hazard for pipelines. Many pipelines transport dangerous contents so that any damage incurred might lead to catastrophic consequences. However, most of these damages are usually a result of surrounding third-party activities, mainly the constructions. In order to prevent accidents and disasters, detection of potential hazards from third-party activities is indispensable. This paper focuses on recognizing the running of construction machines because they indicate the activity of the constructions. Acoustic information is applied for the recognition and a novel pipeline monitoring approach is proposed. Principal Component Analysis (PCA) is applied. The obtained Eigenvalues are regarded as the special signature and thus used for building feature vectors. One-class Support Vector Machine (SVM) is used for the classifier. The denoising ability of PCA can make it robust to noise interference, while the powerful classifying ability of SVM can provide good recognition results. Some related issues such as standardization are also studied and discussed. On-site experiments are conducted and results prove the effectiveness of the proposed early warning method. Thus the possible hazards can be prevented and the integrity of pipelines can be ensured.

• Korean Journal of Cognitive Science
• /
• v.21 no.1
• /
• pp.145-156
• /
• 2010

This paper presents a new contents-based digital still image protection method which includes a copyright message. Since the existing method using gradient values used a pixel based $3{\times}3$ Sobel operator, it was sensitive to attacks and could not extract exact copyright message. Therefore, in this paper, we present a algorithm which uses block based OCL(Orientation Certainty Level) instead of pixel. The experimental results show that the proposed scheme not only has good image quality, but also is robust to JPEG lossy compression, filtering, sharpening, blurring and noise. Moreover, the proposed algorithm has good performance more than 10% in rotation attacks than the existing method.

• Proceedings of the KIPE Conference
• /
• 2012.11a
• /
• pp.217-218
• /
• 2012

A load motor used for warship or submarine is with limited volume and weight, also specific environmental tests like impact, vibration, noise, temperature and EMC/EMI have to be satisfied. Induction motors, synchronous motors, BLDC motor and etc, are used depending on the purpose of using military equipment. Induction Motors are used for a number of military equipment more commonly due to the robust structure and simple maintenance. Domestic and foreign warships have a wide range of voltages as the DC voltage sources with battery are mainly used for them. The ${\Delta}-connection$ operation of the induction motor is required to make the maximum power in a low voltage level. But the elements' temperature of the inverter increases due to high input current when it is in the ${\Delta}-connection$ operation. Therefore, the induction motor must be driven with the Y-connection. The lack of voltage needs to be with the field weakening control. This paper suggests the optimum field weakening control algorithm to drive the induction motor with maximum power in a limited thermal and DC voltage condition.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.1
• /
• pp.79-87
• /
• 2005

This paper presents an active contour model for extracting accurate facial regions in complex environments. In the model, a contour is represented by a zero level set of level function φ, and evolved via level set partial differential equations. Then, unlike general active contours, skin color information that is represented by 2D Gaussian model is used for evolving and slopping a curve, which allows the proposed method to be robust to noise and varying pose. To assess the effectiveness of the proposed method it was tested with several natural scenes, and the results were compared with those of geodesic active contours. Experimental results demonstrate the superior performance of the proposed method.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.14 no.2
• /
• pp.212-226
• /
• 2014

This paper presents the design and implementation of a pipelined architecture and a method for real-time human detection using depth image from a Time-of-Flight (ToF) camera. In the proposed method, we use Euclidean Distance Transform (EDT) in order to extract human body location, and we then use the 1D, 2D scanning window in order to extract human joint location. The EDT-based human extraction method is robust against noise. In addition, the 1D, 2D scanning window helps extracting human joint locations easily from a distance image. The proposed method is designed using Verilog HDL (Hardware Description Language) as the dedicated hardware architecture based on pipeline architecture. We implement the dedicated hardware architecture on a Xilinx Virtex6 LX750 Field Programmable Gate Arrays (FPGA). The FPGA implementation can run 80 MHz of maximum operating frequency and show over 60fps of processing performance in the QVGA ($320{\times}240$) resolution depth image.