• ETRI Journal
• /
• 제37권5호
• /
• pp.1044-1054
• /
• 2015

The smart media (SM) industry has demonstrated that it has the characteristics to increase user innovative activities, enhance open innovativeness, and increase the segmentation of innovation value. This study introduces and evaluates an innovation system that reflects the characteristics of the SM industry. We categorize the SM industry into hardware, network, platform, and content industries and perform an AHP analysis (based on a survey of 96 experts) to evaluate the relative importance of the factors/factor groups affecting the creation of innovation. The results show that 'collaboration activity" is a more important factor than other innovation factor groups (financial support, R&D, policy environment, human resources) in the SM industry. The results also show that the important factors/factor groups differ by industry.

• 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.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• 패션비즈니스
• /
• 제19권2호
• /
• pp.69-84
• /
• 2015

The objective of this study is to investigate the intention to adopt smart wear, based on extended UTAUT model. We examined the effects of performance expectancy (PE), effort expectancy (EE), hedonic motivation (HE), social influence (SI), facilitating conditions (FC), and price value (PV) on the intended adoption of smart watch and smart shoes, respectively. In addition, moderating effects of gender, age, and innovation resistance were examined. An online survey was conducted, comprised of 2030 consumers who were aware of smart watch or smart shoes. In total, 393 responses were analyzed. About 50.4% were male, and 44.8% were in their 20's. An exploratory factor analysis generated five factors - PE & HM, EE, SI, FC, and PV- which were employed as independent variables in the multiple regression models. PE & HM, PV, and SI influenced on the intention to use both smart devices. FC showed the significant effect only on the intention to adopt the smart watch. In terms of gender differences, SI and PV were the important predictors of the intention to adopt the smart watch in the female group only. With respect to age difference, SI was very effective in explaining the intention of individuals in their 30's to adopt smart wear. Among the low innovation resistance group, SI was significant predictor, while PE & HE and PV were significant among the high resistance group. The findings provide useful information about the possibility of the adoption of smart wear, and new insight into market segmentation.

• 한국콘텐츠학회논문지
• /
• 제16권12호
• /
• pp.19-26
• /
• 2016

모바일 뱅킹을 위해 제공되는 다양한 서비스들 중에 은행 보안카드를 이용한 사용자 인증 방식이 여전히 많이 활용되고 있다. 보안카드의 보안코드를 스마트폰에 암호화하여 저장해 두고 모바일 뱅킹을 위해 사용자 인증이 필요할 때 자동 입력되도록 한다면 보안카드를 소지하지 않고서도 모바일뱅킹을 안전하고 편리하게 사용할 수 있다. 본 논문에서는 스마트폰 카메라를 이용하여 보안카드의 보안코드를 자동으로 인식하고 스마트폰에 등록할 수 있는 보안카드 자동 인식 알고리즘을 제안하였다. 다양한 무늬의 배경이 디자인된 보안카드에서 숫자들만 정확하게 추출하기 위해 개선된 적응적 이진화 방법을 사용하였고 훼손되거나 붙은 숫자들까지 분할 인식하기 위해 적응적 2차원 레이아웃 해석 기법도 제안하였다. 제안한 알고리즘을 안드로이드 및 아이폰에 구현하고 실험해본 결과 매우 우수한 인식 결과를 얻을 수 있었다.

• 한국지반공학회논문집
• /
• 제21권9호
• /
• pp.45-52
• /
• 2005

최근 지질학적 증거, 실내 및 현장 실험을 통해 복잡한 형태의 분할된 수압파쇄균열이 암반에서 자주 관찰되고 있다. 이러한 수압파쇄균열의 분할은 균열간의 기계적 상호작용을 유발하며 균열의 폭이나 측정되는 압력에 상당한 영향을 미칠 것으로 예상된다. 따라서 본 연구는 균열간의 상호작용을 정량화하기 위하여 수압파쇄에 의해 다중으로 분할된 총변위를 경계병치법을 사용하여 계산하였다. 또한 기존의 경계병치법을 보정하여 정확한 균열의 상단과 하단 변위를 평가하였으며 유한요소법과의 비교를 통해 제시된 기법의 신뢰성을 확인하였다.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.383-392
• /
• 2023

Post-earthquake building condition assessment is crucial for subsequent rescue and remediation and can be automated by emerging computer vision and deep learning technologies. This study is based on an endeavour for the 2nd International Competition of Structural Health Monitoring (IC-SHM 2021). The task package includes five image segmentation objectives - defects (crack/spall/rebar exposure), structural component, and damage state. The structural component and damage state tasks are identified as the priority that can form actionable decisions. A multi-task Convolutional Neural Network (CNN) is proposed to conduct the two major tasks simultaneously. The rest 3 sub-tasks (spall/crack/rebar exposure) were incorporated as auxiliary tasks. By synchronously learning defect information (spall/crack/rebar exposure), the multi-task CNN model outperforms the counterpart single-task models in recognizing structural components and estimating damage states. Particularly, the pixel-level damage state estimation witnesses a mIoU (mean intersection over union) improvement from 0.5855 to 0.6374. For the defect detection tasks, rebar exposure is omitted due to the extremely biased sample distribution. The segmentations of crack and spall are automated by single-task U-Net but with extra efforts to resample the provided data. The segmentation of small objects (spall and crack) benefits from the resampling method, with a substantial IoU increment of nearly 10%.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.434-436
• /
• 2022

4차 산업혁명과 각종 통신매체의 발전에 힘입어 다양한 분야에서 무인화와 자동화가 급속도로 진행되고 있다. 특히 스마트팩토리와 자율주행기술 및 지능형 CCTV와 같은 분야에서는 높은 수준의 영상처리 기술이 요구되고 있다. 이에 따라 영상을 기반으로 동작하는 시스템에서 전처리 과정에 대한 중요성이 높아지고 있으며, 영상의 잡음을 효과적으로 제거하기 위한 알고리즘이 주목받고 있다. 본 논문에서는 복합잡음 환경에서 잡음판단과 분할마스크를 사용한 필터링 알고리즘을 제안한다. 제안한 알고리즘은 입력 영상의 화소값을 대상으로 잡음판단을 진행하여 필터링에 적합한 분할마스크를 스위칭하여 최종출력을 계산한다. 제안한 알고리즘의 성능을 검증하기 위해 시뮬레이션을 진행하였으며, 기존 필터 알고리즘과 결과영상을 비교하여 평가하였다.

• Smart Structures and Systems
• /
• 제30권5호
• /
• pp.501-511
• /
• 2022

Three-dimensional (3D) models have become crucial for improving civil infrastructure analysis, and they can be used for various purposes such as damage detection, risk estimation, resolving potential safety issues, alarm detection, and structural health monitoring. 3D point cloud data is used not only to make visual models but also to analyze the states of structures and to monitor them using semantic data. This study proposes automating the generation of high-quality 3D point cloud data and removing noise using deep learning algorithms. In this study, large-format aerial images of civilian infrastructure, such as cut slopes and dams, which were captured by drones, were used to develop a workflow for automatically generating a 3D point cloud model. Through image cropping, downscaling/upscaling, semantic segmentation, generation of segmentation masks, and implementation of region extraction algorithms, the generation of the point cloud was automated. Compared with the method wherein the point cloud model is generated from raw images, our method could effectively improve the quality of the model, remove noise, and reduce the processing time. The results showed that the size of the 3D point cloud model created using the proposed method was significantly reduced; the number of points was reduced by 20-50%, and distant points were recognized as noise. This method can be applied to the automatic generation of high-quality 3D point cloud models of civil infrastructures using aerial imagery.

• IEIE Transactions on Smart Processing and Computing
• /
• 제3권4호
• /
• pp.191-194
• /
• 2014

This paper proposes a fast and efficient method to extract the skin and bone automatically in CT images. First, the images were smoothed by applying an anisotropic diffusion filter to remove noise. The whole body was then detected by thresholding, which was set automatically. In addition, the contour of the skin was segmented using morphological operators and connected component labeling (CCL). Finally, the bone was extracted by iterative thresholding.