• 한국융합학회논문지
• /
• 제12권2호
• /
• pp.1-6
• /
• 2021

현대사회에서는 차량을 소유하는 사람들이 증가하면서 교통문제가 발생하고 있다. 특히 고속도로 교통사고 문제는 발생률이 낮지만 치사율은 높다. 따라서 차량의 이상을 탐지하는 기술이 연구되고 있다. 이 중에는 딥러닝을 이용한 차량 이상탐지 기술이 있다. 이는 사고 및 엔진고장으로 인한 정차차량 등의 차량 이상을 탐지한다. 그러나 도로에서 이상이 발생할 경우 운전자의 위치를 파악할 수 있어야 빠른 대처가 가능하다. 따라서 본 연구에서는 도로 CCTV 데이터를 활용한 딥러닝 기반 차량 이상 감지 방법을 제안한다. 제안하는 방법은 먼저 도로 CCTV 데이터를 전처리한다. 전처리는 배경 추출 알고리즘인 MOG2를 이용하여 배경과 전경을 분리한다. 전경은 변위가 존재하는 차량을 의미하며 도로 위에서 이상이 존재하는 차는 변위가 없어 배경으로 판단된다. 배경이 추출된 이미지는 이상을 탐지하기 위해 YOLOv4를 이용하여 객체를 탐지한다. 해당 차량은 이상이 있음으로 판단한다.

• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1244-1248
• /
• 2003

This paper describes visual tracking procedure of the underwater mobile robot for nuclear reactor vessel inspection, which is required to find the foreign objects such as loose parts. The yellowish underwater robot body tends to present a big contrast to boron solute cold water of nuclear reactor vessel, tinged with indigo by Cerenkov effect. In this paper, we have found and tracked the positions of underwater mobile robot using the two color information, yellow and indigo. The center coordinates extraction procedures are as follows. The first step is to segment the underwater robot body to cold water with indigo background. From the RGB color components of the entire monitoring image taken with the color CCD camera, we have selected the red color component. In the selected red image, we extracted the positions of the underwater mobile robot using the following process sequences; binarization, labelling, and centroid extraction techniques. In the experiment carried out at the Youngkwang unit 5 nuclear reactor vessel, we have tracked the center positions of the underwater robot submerged near the cold leg and the hot leg way, which is fathomed to 10m deep in depth.

• 한국정보기술학회 영문논문지
• /
• 제10권1호
• /
• pp.45-56
• /
• 2020

Despite extensive research, performance enhancement of keyphrase (KP) extraction remains a challenging problem in modern informatics. Recently, deep learning-based supervised approaches have exhibited state-of-the-art accuracies with respect to this problem, and several of the previously proposed methods utilize Bidirectional Encoder Representations from Transformers (BERT)-based language models. However, few studies have investigated the effective application of BERT-based fine-tuning techniques to the problem of KP extraction. In this paper, we consider the aforementioned problem in the context of scientific articles by investigating the fine-tuning characteristics of two distinct BERT models - BERT (i.e., base BERT model by Google) and SciBERT (i.e., a BERT model trained on scientific text). Three different datasets (WWW, KDD, and Inspec) comprising data obtained from the computer science domain are used to compare the results obtained by fine-tuning BERT and SciBERT in terms of KP extraction.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.340-342
• /
• 2021

흔히 DeepFake로 불리는 GAN 기술은 소스 영상과 타겟 이미지를 합성하여 타겟 이미지 내의 사람이 소스 영상에서 나타나도록 합성하는 기술이다. 이러한 GAN 기반 영상 합성 기술은 2018년을 기점으로 급격한 성장세를 보이며 다양한 산업에 접목되어지고 있으나 학습 모델을 얻는 데 걸리는 시간이 너무 오래 소요되고, 감정 표현을 인지하는 데 어려움이 있었다. 본 논문에서는 상기 두가지 문제를 해결하기 위해 Facial Action Coding System(FACS) 및 음성 합성 기술[4]을 적용한 가상 아바타 생성 방법에 대해 제안하고자 한다.

• 한국산학기술학회논문지
• /
• 제12권5호
• /
• pp.2425-2433
• /
• 2011

1980년대에 싱가포르에 도입된 심층혼합공법 DSM (Deep Soil Mixing )은 시멘트 슬러리를 지중에 주입시킨 후 이를 원지반 연약토와 교반시킴으로써 견고한 흙-시멘트 기둥을 형성시켜 지반을 보강하는 지반개량공법으로 최근 깊은 굴착을 위한 가설 흙막이 공사에 제트그라우팅의 대안으로 많이 사용되고 있다. 본 논문에서는 OPC (Original Portland Cement)와 PBFC (Portland Blast Furnace Slag Cement)를 이용한 실내배합시험 결과, DSM 시험시공, 그리고 계측을 포함한 본 시공 결과를 분석하였으며, 이 결과는 향후 비슷한 지반에서의 DSM적용 시 참고자료로 사용될 수 있을 것으로 판단된다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 1990년도 PROCEEDINGS OF THE FIRST KOREA-JAPAN JOINT GEOTECHNICAL SEMINAR ON EXCAVATION and TUNNELING IN URBAN AREAS
• /
• pp.97-110
• /
• 1990

This paper presents a case history of a deep open cut excavation of Nakagawa section for Futuoka Subway construction which adopted observational mettled against boiling failure and completed with success by modifying construction based upon field monitoring. One of the difficult conditions for the excavation was sandy layer with high water pressure which was anticipated boiling failure. The boiling was generally considered as one of the difficult phenomena to work with the observational method because of its unpredictable catastrophic nature. Laboratory experiments showed the existence of the prefailure movements of the ground and the possibility of the application of the observational method against the boiling failure. Construction step was planned to be modified, if necessary, based upon field monitoring and was completed with success.

• Computers and Concrete
• /
• 제32권6호
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• 한국농림기상학회지
• /
• 제25권1호
• /
• pp.17-27
• /
• 2023

포장에서 잡초의 발생은 농작물의 생산량을 크게 떨어트리는 원인 중 하나이고 SSWM을 기반으로 잡초를 변량 방제하기 위해서 잡초의 발생 위치, 밀도 그리고 이를 정량화하는 것은 필수적이다. 본 연구에서는 2020년의 국립식량과학원에서 잡초 피해를 입은 옥수수 포장의 영상데이터를 무인항공기를 활용해서 수집하였고 이를 배경과 옥수수로 분리하여 딥러닝 기반 영상 분할 모델 제작을 위한 학습데이터를 획득하였다. DeepLabV3+, U-Net, Linknet, FPN의 4가지의 영상 분할 네트워크들의 옥수수의 검출 정확도를 평가하기 위해 픽셀정확도, mIOU, 정밀도, 재현성의 지표를 활용해서 정확도를 검증하였다. 검증 결과 DeepLabV3+ 모델이 0.76으로 가장 높은 mIOU를 나타냈고, 해당 모델과 식물체의 녹색 영역과 배경을 분리하는 지수인 ExGR을 활용해서 잡초의 면적을 정량화, 시각화하였다. 이러한 연구의 결과는 무인항공기로 촬영된 영상을 활용해서 넓은 면적의 옥수수 포장에서 빠르게 잡초의 위치와 밀도를 특정하고 정량화하는 것으로 잡초의 밀도에 따른 제초제의 변량 방제를 위한 의사결정에 도움이 될 것으로 기대한다.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.791-802
• /
• 2023

The manual inspection of photovoltaic (PV) panels to meet the requirements of inspection work for large-scale PV power plants is challenging. We present a hot spot detection and positioning method to detect hot spots in batches and locate their latitudes and longitudes. First, a network based on the YOLOv3 architecture was utilized to identify hot spots. The innovation is to modify the RU_1 unit in the YOLOv3 model for hot spot detection in the far field of view and add a neural network residual unit for fusion. In addition, because of the misidentification problem in the infrared images of the solar PV panels, the DeepLab v3+ model was adopted to segment the PV panels to filter out the misidentification caused by bright spots on the ground. Finally, the latitude and longitude of the hot spot are calculated according to the geometric positioning method utilizing known information such as the drone's yaw angle, shooting height, and lens field-of-view. The experimental results indicate that the hot spot recognition rate accuracy is above 98%. When keeping the drone 25 m off the ground, the hot spot positioning error is at the decimeter level.