• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.351-363
• /
• 2023

Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate high-resolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physics-based graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2^nd International Competition for Structural Health Monitoring.

• 한국철도학회논문집
• /
• 제8권4호
• /
• pp.314-320
• /
• 2005

This paper is designed to help train dispatcher resolve railway conflicts in rent-time. We developed a mixed integer programming model to optimize the train schedule that determines the best overtaking or crossing positions, The objective of the model is to minimize the maximum lateness of the trains and reduce the total sum of the lateness, while satisfying the field constraints associated with the difference between passenger trains and freight trains, and the limited number of sidings. We applied the model on a portion of a single line track, Joong-Ang Line to ascertain the efficiency of the model, and showed how the model can be used to resolve the railway conflicts. The results indicates that our model can provide useful results in terms of optimal schedule for the test problem. This type of modeling approach would be useful for a train dispatcher to make a real-time railway conflict resolution.

• 대한기계학회논문집A
• /
• 제27권1호
• /
• pp.183-193
• /
• 2003

Micro-weighing device by using null balance method is being essential part in fields of high-technology industries such as precision semiconductor industry, precision chemistry, biotechnology and genetics etc. Also, requirements for high resolution and for large measurement range increase more and more. The performance of the micro-weighing device can be determined by the mechanism design and analysis. The analytical design method has been proposed for the performance improvement such as resolution, measurement range and fast response. The 2-stage displacement amplification is designed to overcome the limit of conventional force transmitting lever. The parallel spring is designed for the measurement result independent of the input force position variation. Also, the natural frequency of mechanism is analyzed for the fast response. After each analysis, optimal design has been carried out. To verify the analysis and design result, characteristics experiments had been carried out after construction. Finally, the system had been controlled.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.417-420
• /
• 2006

In these days, mobile application dealing with information contents on mobile or handheld devices such as mobile communicator, PDA or WAP device face the most important industrial needs. The motivation of this study is the design and implementation of mobile application using high resolution satellite imagery, large-sized image data set. Although major advantages of mobile devices are portability and mobility to users, limited system resources such as small-sized memory, slow CPU, low power and small screen size are the main obstacles to developers who should handle a large volume of geo-based 3D model. Related to this, the previous works have been concentrated on GIS-based location awareness services on mobile; however, the mobile 3D terrain model, which aims at this study, with the source data of DEM (Digital Elevation Model) and high resolution satellite imagery is not considered yet, in the other mobile systems. The main functions of 3D graphic processing or pixel pipeline in this prototype are implemented with OpenGL|ES (Embedded System) standard API (Application Programming Interface) released by Khronos group. In the developing stage, experiments to investigate optimal operation environment and good performance are carried out: TIN-based vertex generation with regular elevation data, image tiling, and image-vertex texturing, text processing of Unicode type and ASCII type.

• 한국측량학회지
• /
• 제32권3호
• /
• pp.271-279
• /
• 2014

As an alternative way to overcome the weakness of the global navigation satellite system (GNSS) in hostile situation, a gravity gradient referenced navigation (GGRN) has been developed. This paper analyzed the performance of GGRN with respect to the initial errors, DB resolution as well as update rates. On the basis of simulations, it was found that the performance of GGRN is getting worse when initial errors exist but the navigation results are rapidly converged. Also, GGRN generates better results when DB resolution is higher and update rates are shorter than 20 seconds. However, it is difficult to deduce the optimal parameters for the navigation because some trajectories show better performance in case low-resolution DB is applied or long update rate is supposed. Therefore, further analysis to derive specific update conditions to improve the performance has been performed. Those update conditions would not be generalized for all cases although maximum improvement rate is over 200% in certain case. In the future, some more developments and tests on the combination of various geophysical data and/or algorithms are necessary to construct more stable and reliable navigation system.

• Journal of Communications and Networks
• /
• 제17권3호
• /
• pp.275-285
• /
• 2015

To improve the efficiency of carrier sense multiple access (CSMA)-based medium access control (MAC) protocols, CSMA with collision resolution (CSMA/CR) has been proposed. In the CSMA/CR, a transmitting station can detect a collision by employing additional sensing after the start of a data transmission and then resolve the next collision that might occur by broadcasting a jam signal during a collision detection (CD) period. In this paper, we analyze the delay of a CSMA/CR based on a generic p- persistent CSMA model and obtain the minimum achievable delay of the CSMA/CR by finding the optimal length of the CD period according to the number of contending stations. Through this delay analysis, we also investigate the throughput-delay characteristics of the CSMA/CR protocol according to various parameters. Analysis and simulation results show that the CSMA/CR has a considerably lower delay and its throughput-delay characteristic is significantly improved than the conventional CSMA/CA and wireless CSMA/CD protocols.

• 제어로봇시스템학회논문지
• /
• 제20권10호
• /
• pp.1030-1035
• /
• 2014

Machine vision inspection systems have replaced human inspectors in defect inspection fields for several decades. However, the inspection results of machine vision are often affected by small changes of illumination. When small changes of illumination appear in image histograms, the influence of illumination can be decreased by transformation of the histogram. In this paper, we propose an enhanced histogram matching algorithm which corrects distorted histograms by variations of illumination. We use the resolution resizing method for an optimal matching of input and reference histograms and reduction of quantization errors from the digitizing process. The proposed algorithm aims not only for improvement of the accuracy of defect detection, but also robustness against variations of illumination in machine vision inspection. The experimental results show that the proposed method maintains uniform inspection error rates under dramatic illumination changes whereas the conventional inspection method reveals inconsistent inspection results in the same illumination conditions.

• 전력전자학회논문지
• /
• 제10권6호
• /
• pp.618-625
• /
• 2005

본 논문은 CRT 표시장치에서 고전류밀도를 구현하기 위한 전자총의 히터와 캐소드의 최적의 저전력설계와 실험을 수행하였다. CRT 표시장치에서 밝기, 고휘도, 고해상도와 대화면화를 위해서는 전자총 캐소드(cathode)의 고전류밀도가 필수적이다. 이를 위해서는 함침형 캐소드가 사용되며, 고전류밀도를 얻기 위해 히터의 동작온도를 높여야하는데 이에 비례하여 소비전력도 증가한다. 본 논문에서는 고전류밀도 캐소드 히터의 저전력 설계를 위하여 히터의 리드형태(Lead Type), 코팅(Coating)법, 발열부의 1차 및 2차 코일링의 피치와 권선수를 달리한 샘플을 제작, 시험하였다.

• 대한원격탐사학회지
• /
• 제24권1호
• /
• pp.57-64
• /
• 2008

In the previous study, the Haar wavelet was used as the sole basis function for the 3D discrete wavelet transform because the number of bands is too small to decompose a remotely sensed image in band direction with other basis functions. However, it is possible to use other basis functions for wavelet decomposition in horizontal and vertical directions because wavelet decomposition is independently performed in each direction. This study aims to classify a high spatial resolution image with the six types of basis function including the Haar function and to compare those results. The other wavelets are more helpful to classify high resolution imagery than the Haar wavelet. In overall accuracy, the Coif4 wavelet has the best result. The improvement of classification accuracy is different depending on the type of class and the type of wavelet. Using the basis functions with long length could be effective for improving accuracy in classification, especially for the classes of small area. This study is expected to be used as fundamental information for selecting optimal basis function according to the data properties in the 3D DWT based image classification.

• Journal of Mechanical Science and Technology
• /
• 제17권3호
• /
• pp.409-421
• /
• 2003

The hierarchical recursive local-correlation PIV algorithm with CBC (correlation based correction) method was employed to increase the spatial resolution of PIV results and to reduce error vectors. The performance of this new PIV algorithm was tested using synthetic images, PIV standard images of Visualization Society of Japan, real flows including ventilation flow inside a vehicle passenger compartment and wake behind a circular cylinder with riblet surface. As a result, most spurious vectors were suppressed by employing the CBC method, the hierarchical recursive correlation algorithm improved the sub-pixel accuracy of PIV results by decreasing the interrogation window size and Increased spatial resolution significantly. However, with recursively decreasing of interrogation window size, the SNR (signal-to-noise ratio) in the correlation plane was decreased and number of spurious vectors was increased. Therefore, compromised determination of optimal interrogation window size is required for given flow images, the performance of recursive algorithm is also discussed from a viewpoint of recovery ratio and error ratio in the paper.