• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.786-799
• /
• 2021

Road damage detection is important for road maintenance. With the development of deep learning, more and more road damage detection methods have been proposed, such as Fast R-CNN, Faster R-CNN, Mask R-CNN and RetinaNet. However, because shallow and deep layers cannot be extracted at the same time, the existing methods do not perform well in detecting objects with fewer samples. In addition, these methods cannot obtain a highly accurate detecting bounding box. This paper presents a Multi-level Feature Pyramids method based on M2det. Because the feature layer has multi-scale and multi-level architecture, the feature layer containing more information and obvious features can be extracted. Moreover, an attention mechanism is used to improve the accuracy of local boundary boxes in the dataset. Experimental results show that the proposed method is better than the current state-of-the-art methods.

• Journal of the Korea Concrete Institute
• /
• v.17 no.1 s.85
• /
• pp.149-155
• /
• 2005

The purpose of this study is to investigate the flexural strengthening effects of CF(Carbon Fiber) sheet for the full-scale RC beams with multi-layer CF sheets. The partial strength reduction factors of CF sheets are suggested from the full-scale RC beams tests strengthened with multi-layer CF sheets up to six layers as well as material tests. From the material tensile tests, it was observed that the average tensile strengths of CF sheets per layer are decreased as the number of CF sheets is increased. Also the steep strength reductions of CF sheets in material test results at rupture are observed compared with the structural tests results for the full-scale RC beams strengthened with multi-layer CF sheets. Finally, the partial strength reduction factors far CF sheets up to six layers are suggested considering the effects of multi-layer and unit weight of CF sheets.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.27 no.12
• /
• pp.767-775
• /
• 2014

New material design has obtained tremendous attention in material science community as the performance of new materials, especially in nano length scale, could be greatly improved to applied in modern industry. In certain conditions limiting experimental synthesis of these new materials, new approach by computer simulation has been proposed to be applied, being able to save time and cost. Recent development of computer systems with high speed, large memory, and parallel algorithms enables to analyze individual atoms using first principle calculation to predict quantum phenomena. Beyond the quantum level calculations, mesoscopic scale and continuum limit can be addressed either individually or together as a multi-scale approach. In this article, we introduced current endeavors on material design using analytical theory and computer simulations in multi-length scales and on multi-physical properties. Some of the physical phenomena was shown to be interconnected via a cross-link rule called 'cross-property relation'. It is suggested that the computer simulation approach by multi-physics analysis can be efficiently applied to design new materials for multi-functional characteristics.

• Journal of the Korean Statistical Society
• /
• v.30 no.2
• /
• pp.327-345
• /
• 2001

New statistical methods are ended to analyzed data in a multi-scale way. Some multi-scale extensions of stand methods, including novel visualization using dynamic graphics are proposed. These tools are used to explore non-standard structure in internet traffic data.

• Smart Structures and Systems
• /
• v.14 no.3
• /
• pp.285-305
• /
• 2014

This study employs a novel beam-type wavelet finite element model (WFEM) to fulfill an adaptive-scale damage detection strategy in which structural modeling scales are not only spatially varying but also dynamically changed according to actual needs. Dynamical equations of beam structures are derived in the context of WFEM by using the second-generation cubic Hermite multiwavelets as interpolation functions. Based on the concept of modal strain energy, damage in beam structures can be detected in a progressive manner: the suspected region is first identified using a low-scale structural model and the more accurate location and severity of the damage can be estimated using a multi-scale model with local refinement in the suspected region. Although this strategy can be implemented using traditional finite element methods, the multi-scale and localization properties of the WFEM considerably facilitate the adaptive change of modeling scales in a multi-stage process. The numerical examples in this study clearly demonstrate that the proposed damage detection strategy can progressively and efficiently locate and quantify damage with minimal computation effort and a limited number of sensors.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.6
• /
• pp.577-585
• /
• 2015

We fabricated multi-scale such as macro-, micro-, and multi-scale wrinkles by using repetitive volume dividing (RVD) method and thermal curing process. Also wrinkle surface was modified with coating of a self-assembled monolayer (SAM). We measured the contact angle of each wrinkled surface, and observed the behavior of droplets on sloping surface. Through experimental study, we found out that the contact angle was much higher in case of multi-scale and SAM coated wrinkles. And micro-scale wrinkle showed a high contact angle comparing with that of macro-scale wrinkle. Dynamic behaviors of a water droplet like sliding velocity on diverse wrinkled surfaces were dependent on their static contact angles. These results showed that hydro-dynamic characteristics were changed depending on the wrinkle structure and the material forming the wrinkle. These dynamic characteristics can be utilized in bio-chip, microfluidics, and many others in order to control easily chemical reactivity.

• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.474-483
• /
• 2018

In this paper, we propose a multi-scale high dynamic range (HDR) tone mapping algorithm using guided image filter (GIF). The GIF is used to divide an image into a base layer and a detail layer, then the range of the detail layer is reduced with a compression function to enhance the detail information of the image. However, in most cases, an image includes the detail and edge information in different scales. That is to say, it is difficult to represent all detail features under a certain scale, and a single-scale image decomposition method is not free from artifacts around edges. To solve the problems, the multi-scale image decomposition method is proposed. It utilizes the detail layers of several scale to determine how much edge is preserved. Experiment results show that the proposed algorithm has better image performance in preserving edge compared to conventional algorithm.

• Carbon letters
• /
• v.12 no.3
• /
• pp.177-179
• /
• 2011

The use of carbon nanotubes (CNTs) as a reinforcing material in a polymer matrix has increased in various industries. In this study, the flexural behavior of CNT-modified epoxy/basalt (CNT/epoxy/basalt) composites is investigated. The effects of CNT modification with silane on the flexural properties of CNT/epoxy/basalt composites were also examined. Flexural tests were performed using epoxy/basalt, oxidized CNT/epoxy/basalt, and silanized CNT/epoxy/basalt multi-scale composites. After the flexural tests, the fracture surfaces of the specimens were examined via scanning electron microscopy (SEM) to investigate the fracture mechanisms of the CNT/epoxy/basalt multi-scale composites with respect to the CNT modification process. The flexural properties of the epoxy/basalt composites were improved by the addition of CNTs. The flexural modulus and strength of the silane-treated CNT/epoxy/basalt multi-scale composites increased by approximately 54% and 34%, respectively, compared to those of epoxy/basalt composites. A SEM examination of the fracture surfaces revealed that the improvement in the flexural properties of the silane-treated CNT/epoxy/basalt multi-scale composites could be attributed to the improved dispersion of the CNTs in the epoxy.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.62 no.2
• /
• pp.90-94
• /
• 2013

In this paper, we propose a new algorithm to improve the contrast ratio, to preserve information of bright regions and to maintain the color of backlight image that appears with a great relative contrast. Backlight images of the natural environment have characteristics for difference of local brightness; the overall image contrast improvement is not easy. To improve the contrast of the backlight images, MSR (Multi-Scale Retinex) algorithm using the existing multi-scale Gaussian filter is applied. However, existing multi-scale Gaussian filter involves color distortion and information loss of bright regions due to excessive contrast enhancement and noise because of the brightness improvement of dark regions. Moreover, it also increases computational complexity due to the use of multi-scale Gaussian filter. In order to solve these problems, a linear MSR is performed that reduces the amount of computation from the HSV color space preventing the color distortion and information loss due to excessive contrast enhancement. It can also remove the noise of the dark regions which is occurred due to the improved contrast through edge preserving filter. Through experimental evaluation of the average color difference comparison of CIELAB color space and the visual assessment, we have confirmed excellent performance of the proposed algorithm compared to conventional MSR algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.4
• /
• pp.1188-1202
• /
• 2012

In this paper, we propose a new multi-scale connected coherence tree algorithm (MCCTA) by improving the connected coherence tree algorithm (CCTA). In contrast to many multi-scale image processing algorithms, MCCTA works on multiple scales space of an image and can adaptively change the parameters to capture the coarse and fine level details. Furthermore, we design a Multi-scale Connected Coherence Tree algorithm plus Spectral graph partitioning (MCCTSGP) by combining MCCTA and Spectral graph partitioning in to a new framework. Specifically, the graph nodes are the regions produced by CCTA and the image pixels, and the weights are the affinities between nodes. Then we run a spectral graph partitioning algorithm to partition on the graph which can consider the information both from pixels and regions to improve the quality of segments for providing image segmentation. The experimental results on Berkeley image database demonstrate the accuracy of our algorithm as compared to existing popular methods.