• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.36 no.5
• /
• pp.93-103
• /
• 2020

The purpose of this study is to suggest a supervisory way to improve the efficiency of Building Supervision using Deep Learning, especially object detecting technology. Since the establishment of the Building Supervision system in Korea, it has been changed and improved many times systematically, but it is hard to find any improvement in terms of implementing methods. Therefore, the Supervision is until now the area where a lot of money, time and manpower are needed. This might give a room for superficial, formal and documentary supervision that could lead to faulty construction. This study suggests a way of Building Supervision which is more automatic and effective so that it can lead to save the time, effort and money. And the way is to detect the hoop-bars of a column and count the number of it automatically. For this study, we made a hoop-bar detecting network by transfor learnning of YOLOv2 network through MATLAB. Among many training experiments, relatively most accurate network was selected, and this network was able to detect rebar placement in building site pictures with the accuracy of 92.85% for similar images to those used in trainings, and 90% or more for new images at specific distance. It was also able to count the number of hoop-bars. The result showed the possibility of automatic Building Supervision and its efficiency improvement.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.611-622
• /
• 2020

As the advancement of technologies on indoor positioning systems and measuring devices such as LiDAR (Light Detection And Ranging) and cameras, the demands on analyzing and searching indoor spaces and visualization services via virtual and augmented reality have rapidly increasing. To this end, it is necessary to model 3D objects from measured data from real-world structures. In addition, it is important to store these structured data in standardized formats to improve the applicability and interoperability. In this paper, we propose a method to construct IndoorGML data, which is an international standard for indoor modeling, from point cloud data acquired from LiDAR sensors. After examining considerations that should be addressed in IndoorGML data, we present a construction method, which consists of free space extraction and connectivity detection processes. With experimental results, we demonstrate that the proposed method can effectively reconstruct the 3D model from point cloud.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.93-101
• /
• 2021

In this paper, a vehicle license plate detection scheme is proposed that uses the spatial attention areas to detect accurately the license plates in various real-road situations. First, the previous WPOD-NET was analyzed, and its detection accuracy is evaluated as lower due to the unnecessary noises in the wide detection candidate areas. To resolve this problem, a vehicle license plate detection model is proposed that uses the candidate area of the license plate as a spatial attention areas. And we compared its performance to that of the WPOD-NET, together with the case of using the optimal spatial attention areas using the ground truth data. The experimental results show that the proposed model has about 20% higher detection accuracy than the original WPOD-NET since the proposed scheme uses tight detection candidate areas.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.17-22
• /
• 2022

In this paper, we design a lightweight embedded device that can support intelligent edge computing, and show that the device quickly detects an object in an image input from a camera device in real time. The proposed system can be applied to environments without pre-installed infrastructure, such as an intelligent video control system for industrial sites or military areas, or video security systems mounted on autonomous vehicles such as drones. The On-Device AI(Artificial intelligence) technology is increasingly required for the widespread application of intelligent vision recognition systems. Computing offloading from an image data acquisition device to a nearby edge device enables fast service with less network and system resources than AI services performed in the cloud. In addition, it is expected to be safely applied to various industries as it can reduce the attack surface vulnerable to various hacking attacks and minimize the disclosure of sensitive data.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.1-9
• /
• 2022

In this paper, we propose the Deep Learning-Based Companion Animal Abnormal Behavior Detection Service, which using video and sensor data. Due to the recent increase in households with companion animals, the pet tech industry with artificial intelligence is growing in the existing food and medical-oriented companion animal market. In this study, companion animal behavior was classified and abnormal behavior was detected based on a deep learning model using various data for health management of companion animals through artificial intelligence. Video data and sensor data of companion animals are collected using CCTV and the manufactured pet wearable device, and used as input data for the model. Image data was processed by combining the YOLO(You Only Look Once) model and DeepLabCut for extracting joint coordinates to detect companion animal objects for behavior classification. Also, in order to process sensor data, GAT(Graph Attention Network), which can identify the correlation and characteristics of each sensor, was used.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.369-376
• /
• 2021

With the development of artificial intelligence (AI) technology, discussions on the use of artificial intelligence are actively taking place in many fields, and various policies for nurturing artificial intelligence talents are being promoted in the field of education. In this study, we propose a robot programming framework using artificial intelligence technology, and based on this, we use Python, which is used frequently in the machine learning field, and an educational robot that is highly utilized in the field of education to provide artificial intelligence. (AI) education program was proposed. The level of autonomous driving (levels 0-5) suggested by the International Society of Automotive Engineers (SAE) is simplified to four levels, and based on this, the camera attached to the robot recognizes and detects lines (objects). The goal was to make a line detector that can move by itself. The developed program is not a standardized form of solving a given problem by simply using a specific programming language, but has the experience of defining complex and unstructured problems in life autonomously and solving them based on artificial intelligence (AI) technology. It is meaningful.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.4
• /
• pp.511-523
• /
• 2023

Research on the integration of unmanned aerial vehicles and deep learning for reinforced concrete damage detection is actively underway. Convolutional neural networks have a high impact on the performance of image classification, detection, and segmentation as backbones. The MobileNet, a pre-trained convolutional neural network, is efficient as a backbone for an unmanned aerial vehicle-based damage detection model because it can achieve sufficient accuracy with low computational complexity. Analyzing vanilla convolutional neural networks and MobileNet under various conditions, MobileNet was evaluated to have a verification accuracy 6.0~9.0% higher than vanilla convolutional neural networks with 15.9~22.9% lower computational complexity. MobileNetV2, MobileNetV3Large and MobileNetV3Small showed almost identical maximum verification accuracy, and the optimal conditions for MobileNet's reinforced concrete damage image feature extraction were analyzed to be the optimizer RMSprop, no dropout, and average pooling. The maximum validation accuracy of 75.49% for 7 types of damage detection based on MobilenetV2 derived in this study can be improved by image accumulation and continuous learning.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.118-118
• /
• 2021

최근 지구 온난화 현상으로 인한 기후변화로 이상기후 현상이 발생하고 있으며 이로 인해 장기적으로 폭염의 빈도 및 강도 상승에 따른 가뭄 피해 우려가 증가하고 있다. 농업 가뭄은 강수량 부족, 토양 수분 부족, 저수량 부족 등 농업분야에 영향을 주는 인자들과 관련되어 있어 농작물 생육 및 수확량 감소를 야기한다. 우리나라는 논농사가 주를 이루고 있어 국내 농업 가뭄은 주수원공인 농업용 저수지의 가용저수용량으로 판단 가능하다. 따라서 안정적인 농업용수 공급을 위해 수리시설물의 모니터링, 공급량 등의 분석이 이루어져야 하며, 농업 가뭄에 대비하기 위해 농업용 저수지의 가용저수용량 파악이 필요하다. 수자원 분야에서 지점자료의 시·공간적 한계점을 보완하기 위해 인공위성 자료를 활용한 연구가 활발히 이루어지고 있으며, 본 연구에서는 위성영상 자료 및 딥러닝 기반 알고리즘을 적용하여 농업용 저수지 수표면 탐지 및 시계열 분석을 목적으로 한다. 위성영상 자료는 5일 주기 및 10 m 공간해상도를 가진 Sentinel-2 위성영상 자료를 활용하고자 하였으며, 딥러닝에 적용하기 위하여 100장 이상의 영상 이미지를 구축하였다. 딥러닝 기반 알고리즘으로는 Convolutional Neural Network (CNN)을 활용하였으며, CNN은 주로 이미지 분류나 객체 검출 문제를 해결하기 위해 제안된 모델로 최근 픽셀 단위로 분류가 가능한 알고리즘이 개발되어 높은 정확도의 수표면 탐지가 가능할 것으로 판단된다. 따라서 본 연구에서는 CNN 기반 수표면 탐지 알고리즘을 개발하여 Sentinel-2 영상 기준 경기도 안성시를 대상으로 소규모 농업용 저수지의 수표면적에 대한 시계열 데이터를 분석하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.213-215
• /
• 2022

Recently, deep learning technology that processes images has been widely used in fire detection, autonomous driving, and defective product detection. In particular, in order to determine whether a product is contaminated or not, it can be identified through the contaminants passed from the existing sensor data, but technologies for recognizing cracks in products or contaminants themselves as images are being actively studied in various fields. In this paper, a system for classifying uncontaminated normal cups and contaminated cups through images was designed and implemented. The image was analyzed using an open image and a photographed image, and the image was analyzed by extracting the upper part of the cup image using Google Objectron for 3D object recognition. Through this study, it is thought that it will be used in various ways for research that can extract the contamination level of products required in the hygiene field based on images.