• Journal of the Korea Convergence Society
• /
• v.12 no.2
• /
• pp.1-6
• /
• 2021

In the modern society, traffic problems are occurring as vehicle ownership increases. In particular, the incidence of highway traffic accidents is low, but the fatality rate is high. Therefore, a technology for detecting an abnormality in a vehicle is being studied. Among them, there is a vehicle anomaly detection technology using deep learning. This detects vehicle abnormalities such as a stopped vehicle due to an accident or engine failure. However, if an abnormality occurs on the road, it is possible to quickly respond to the driver's location. In this study, we propose a deep learning-based vehicle anomaly detection using road CCTV data. The proposed method preprocesses the road CCTV data. The pre-processing uses the background extraction algorithm MOG2 to separate the background and the foreground. The foreground refers to a vehicle with displacement, and a vehicle with an abnormality on the road is judged as a background because there is no displacement. The image that the background is extracted detects an object using YOLOv4. It is determined that the vehicle is abnormal.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• 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
• /
• 2003.10a
• /
• 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.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.1
• /
• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.5
• /
• pp.2425-2433
• /
• 2011

DSM (Deep Soil Mixing) is to establish soil-cement column by injecting of cement slurry and blending it in soft ground and have been introduced to Singapore in 1980s and now a days quite popular and considered as alternative method to the jet grouting for temporary earth retaining works and foundations. Herein this paper, the results of lab mixing test based on comparison of characteristics between OPC (Original Portland Cement) and PBFC (Portland Blast Furnace Slag Cement), DSM field trial test and main installation results including monitoring, was presented and it would be referred to similar site later.

• Proceedings of the Korean Geotechical Society Conference
• /
• 1990.10a
• /
• 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
• /
• v.32 no.6
• /
• 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.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.1
• /
• pp.17-27
• /
• 2023

Weeds are one of the factors that reduce crop yield through nutrient and photosynthetic competition. Quantification of weed density are an important part of making accurate decisions for precision weeding. In this study, we tried to quantify the density of weeds in images of maize fields taken by unmanned aerial vehicle (UAV). UAV image data collection took place in maize fields from May 17 to June 4, 2021, when maize was in its early growth stage. UAV images were labeled with pixels from maize and those without and the cropped to be used as the input data of the semantic segmentation network for the maize detection model. We trained a model to separate maize from background using the deep learning segmentation networks DeepLabV3+, U-Net, Linknet, and FPN. All four models showed pixel accuracy of 0.97, and the mIOU score was 0.76 and 0.74 in DeepLabV3+ and U-Net, higher than 0.69 for Linknet and FPN. Weed density was calculated as the difference between the green area classified as ExGR (Excess green-Excess red) and the maize area predicted by the model. Each image evaluated for weed density was recombined to quantify and visualize the distribution and density of weeds in a wide range of maize fields. We propose a method to quantify weed density for accurate weeding by effectively separating weeds, maize, and background from UAV images of maize fields.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• 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.