• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.111-122
• /
• 2021

Building footprint extraction is an active topic in the domain of remote sensing, since buildings are a fundamental unit of urban areas. Deep convolutional neural networks successfully perform footprint extraction from optical satellite images. However, semantic segmentation produces coarse results in the output, such as blurred and rounded boundaries, which are caused by the use of convolutional layers with large receptive fields and pooling layers. The objective of this study is to generate visually enhanced building objects by directly extracting the vertices of individual buildings by combining instance segmentation and keypoint detection. The target keypoints in building extraction are defined as points of interest based on the local image gradient direction, that is, the vertices of a building polygon. The proposed framework follows a two-stage, top-down approach that is divided into object detection and keypoint estimation. Keypoints between instances are distinguished by merging the rough segmentation masks and the local features of regions of interest. A building polygon is created by grouping the predicted keypoints through a simple geometric method. Our model achieved an F1-score of 0.650 with an mIoU of 62.6 for building footprint extraction using the OpenCitesAI dataset. The results demonstrated that the proposed framework using keypoint estimation exhibited better segmentation performance when compared with Mask R-CNN in terms of both qualitative and quantitative results.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.47-54
• /
• 2022

In this paper, MEMS embedded system design implemented the sensor events via analyzing the characteristics that dynamically happened to an abnormal status in power IoT environments in order to guarantee a maintainable operation. We used three kinds of tools in this paper, at first Bluetooth Low Energy (BLE) technology which is a suitable protocol that provides a low data rate, low power consumption, and low-cost sensor applications. Secondly LSM6DSOX, a system-in-module containing a 3-axis digital accelerometer and gyroscope with low-power features for optimal motion. Thirdly BM1422AGMV Digital Magnetometer IC, a 3-axis magnetic sensor with an I2C interface and a magnetic measurable range of ±120 uT, which incorporates magneto-impedance elements to detect the magnetic field when the current flowed in the power devices. The proposed MEMS system was developed based on an nRF5340 System on Chip (SoC), previously compared to the standalone embedded system without bluetooth technology via mobile App. And also, MEMS embedded system with BLE 5.0 technology broadcasted the MEMS system status to Android mobile server. The experiment results enhanced the performance of MEMS system design by combination of sensors, BLE technology and mobile application.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.49-52
• /
• 2022

건물 외벽에 발생하는 균열은 시설물 구조 안전에 영향을 미치며 그 크기에 따라 위험도가 달라진다. 이에 따라 전문검사관의 현장 점검을 통해 발생 균열 두께를 정밀하게 측정할 필요가 있고 최근에는 이러한 현장 안전점검에 인공지능을 도입하려는 추세다. 그러나 기존의 균열 데이터셋은 주로 콘크리트에만 한정되어 다양한 외벽에 강인한 모델을 구축하기 어렵고 균열 두께를 측정하기 위해 정확한 마스크(Mask) 정보가 필요하나 이를 만족하는 데이터셋이 부재하다. 본 논문에서는 다양한 외벽에 강인한 균열 구획화 모델을 목적으로 2,744장의 이미지를 촬영하고 매직 완드 기법으로 라벨링을 진행해 데이터셋을 구축 후, 이를 바탕으로 딥러닝 기반 균열 구획화 모델을 개발했다. UNet-ResNet50을 최종모델로 선정 및 개발 결과, 테스트 데이터셋에 대해 81.22%의 class IoU 성능을 보였다. 본 연구의 기술을 바탕으로 균열 두께를 측정하여 건축물 안전점검에 활용될 수 있기를 기대한다.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.508-518
• /
• 2023

This paper presents a new approach for the automatic mapping of discontinuities in a tunnel face based on its 3D digital model reconstructed by LiDAR scan or photogrammetry techniques. The main idea revolves around the identification of discontinuity areas in the 3D digital model of a tunnel face by segmenting its 2D projected images using a deep-learning semantic segmentation model called U-Net. The proposed deep learning model integrates various features including the projected RGB image, depth map image, and local surface properties-based images i.e., normal vector and curvature images to effectively segment areas of discontinuity in the images. Subsequently, the segmentation results are projected back onto the 3D model using depth maps and projection matrices to obtain an accurate representation of the location and extent of discontinuities within the 3D space. The performance of the segmentation model is evaluated by comparing the segmented results with their corresponding ground truths, which demonstrates the high accuracy of segmentation results with the intersection-over-union metric of approximately 0.8. Despite still being limited in training data, this method exhibits promising potential to address the limitations of conventional approaches, which only rely on normal vectors and unsupervised machine learning algorithms for grouping points in the 3D model into distinct sets of discontinuities.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2018.06a
• /
• pp.122-122
• /
• 2018

1. 배경 최근 IoT 기술이 발전함에 따라 각종 전자기기에 들어가는 센서들이 점점 늘어나고 있다. 특히 사용자 중심의 기기들은 기술이 발전함에 따라 집적화가 이루어지면서, 하나의 기기에서 온도, 습도, 조도 등의 다양한 정보를 처리하고 있다. 이에 따라 더 많은 기능을 사용하기 위해, 소모 전력 또한 점차 증가하고 있다. 그러나 부피는 한정되어 있어, 기존 배터리만으로는 증가하는 소모 전력을 모두 보완하기 어렵다. 또한 대표적인 사용자 중심 기기인 스마트폰에서는, 가장 많은 전력을 소모하는 부분이 점점 커지고 있다. 이에 대한 대책으로 버려지는 에너지를 수확하여 전기적인 에너지로 바꿔주는 에너지 하베스팅 기술이 각광을 받고 있다. 에너지 하베스팅 기술은 바람, 진동, 인체의 움직임 등의 기계적 에너지, 태양광, 실내등의 빛 에너지를 전기적인 에너지로 바꿔주는 기술을 말한다. 본 연구에서는 강유전체 고분자 내부에 양자점이 임베딩된 박막을 이용하여, 스마트폰에서 발생하는 빛 에너지와 손가락으로 디스플레이를 터치할 때 발생하는 기계적인 에너지를 모두 수확할 수 있는 새로운 소자를 제시하였다. 소자 내부에 있는 양자점은 빛 에너지를 산란 혹은 흡수하여 발광한 후, 고분자 내부의 전반사를 통해 양 옆에 있는 태양전지로 빛을 전달한다. 또한 컴포짓의 매트릭스를 이루고 있는 강유전체 폴리머인 P(VDF-TrFE)는 강유전 특성을 통해 마찰전기 에너지를 효율적으로 전기 에너지로 전환할 수 있다. 강유전체 특성에 의해 P(VDF-TrFE) 내부에 정렬된 Polarization은 퀀텀닷에 양자구속 스타크 효과(Quantum Confined Stark Effect)를 일으켜 더 긴 파장을 방출한다. 이렇게 바뀐 파장은 실리콘 태양전지에서 더 많이 흡수할 수 있는 영역으로 방출되어 태양전지 출력의 증가를 일으킨다. 마지막으로 실리콘 태양전지의 출력 증가를 보여줌으로써 이를 실험적으로 입증했다.

• Journal of Communications and Networks
• /
• v.13 no.6
• /
• pp.602-611
• /
• 2011

The inter-domain routing scalability issue is a major challenge facing the Internet. Recent wide deployments of multihoming and traffic engineering urge for solutions to this issue. So far, tunnel-based proposals and compact routing schemes have been suggested. An implicit assumption in the routing community is that structured address labels are crucial for routing scalability. This paper first systematically examines the properties of identifiers and address labels and their functional differences. It develops a simple Internet routing model and shows that a binary relation T defined on the address label set A determines the cardinality of the compact label set L. Furthermore, it is shown that routing schemes based on flat address labels are not scalable. This implies that routing scalability and routing stability are inherently related and must be considered together when a routing scheme is evaluated. Furthermore, a metric is defined to measure the efficiency of the address label coding. Simulations show that given a 3000-autonomous system (AS) topology, the required length of address labels in compact routing schemes is only 9.12 bits while the required length is 10.64 bits for the Internet protocol (IP) upper bound case. Simulations also show that the ${\alpha}$ values of the compact routing and IP routing schemes are 0.80 and 0.95, respectively, for a 3000-AS topology. This indicates that a compact routing scheme with necessary routing stability is desirable. It is also seen that using provider allocated IP addresses in multihomed stub ASs does not significantly reduce the global routing size of an IP routing system.

• Korean Journal of Optics and Photonics
• /
• v.1 no.2
• /
• pp.210-216
• /
• 1990

This study was performed to obtain fundamental data on temperature increases in the dental tissues irradiated by IO.opm laser radiation. For this purpose a experimental facility was established. which was composed of a CO2 laser. a shutter unit and a temperature sensing device. The temperature changes in the pulp chamber of extracted molars. during and after the laser irradiation. were measured as function of laser power. the time of irradration and the thickness of the sample. An empirical formula for the maximum temperature increases, $\DeltaT_m$ was derived from the measured data as follows; $\DeltaT_m=\alphaP\Delta\tauexp(-\betad)$$ where P. $\Delta\tau$ and d are the laser power(W). irradiation time{sec) and the thickness(mm) between pulp chamber and occlusal surface. respectively. Also a theoretical calculation model based on simplified assumptions were established and the results from the calculation were compared with the measured temperature data. A fairly good agreement was obtained.obtained.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.5
• /
• pp.1001-1010
• /
• 2021

Normal people are not deeply aware of their dependence on sight when eating. However, since the visually impaired do not know what kind of food is on the table, the assistant next to them holds the blind spoon and explains the position of the food in a clockwise direction, front and rear, left and right, etc. In this paper, we describe the development of a meal assistance system that recognizes each food image and announces the name of the food by voice when a visually impaired person looks at their table using a smartphone camera. This system extracts the food on which the spoon is placed through the YOLO model that has learned the image of food and tableware (spoon), recognizes what the food is, and notifies it by voice. Through this system, it is expected that the visually impaired will be able to eat without the help of a meal assistant, thereby increasing their self-reliance and satisfaction.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.5
• /
• pp.303-313
• /
• 2021

Recently, quality control of the Liquefied Natural Gas Carrier (LNGC) cargo hold and block-erection interference areas using 3D scanners have been performed, focusing on large shipyards and the international association of classification societies. In this study, as a part of the research on LNGC cargo hold quality management advancement, a study on deep-learning-based scaffolding system 3D point cloud object detection and post-processing were conducted using a LNGC cargo hold 3D point cloud. The scaffolding system point cloud object detection is based on the PointNet deep learning architecture that detects objects using point clouds, achieving 70% prediction accuracy. In addition, the possibility of improving the accuracy of object detection through parameter adjustment is confirmed, and the standard of Intersection over Union (IoU), an index for determining whether the object is the same, is achieved. To avoid the manual post-processing work, the object detection architecture allows automatic task performance and can achieve stable prediction accuracy through supplementation and improvement of learning data. In the future, an improved study will be conducted on not only the flat surface of the LNGC cargo hold but also complex systems such as curved surfaces, and the results are expected to be applicable in process progress automation rate monitoring and ship quality control.