• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.495-497
• /
• 2022

COVID-19 상황이 지속됨에 따라 플라스틱 쓰레기 배출량은 해마다 기하급수적으로 증가하고 있는 반면 플라스틱 폐기물의 재활용률은 현저히 낮은 편에 속한다. 이러한 문제점들을 해결하기 위해 국가적으로 여러 플라스틱 폐기물 중 순환 가능한 PET를 분리하여 수거하고자 하는 노력을 하고 있다. 하지만, 현재 대량의 플라스틱 폐기물은 수거되는 시점부터 여러 폐기물과 혼합된 형태로 재활용 센터에 수거되어 추가 분류하는 인적자원이 요구되는 문제점이 존재한다. 따라서 본 논문에서는 이러한 한계점들을 해결하기 위해 AI 기술 중 하나인 Multi-Object Detection의 YOLOv7 모델을 적용하여 실시간으로 PET에 부착된 객체들을 탐지함으로써 순환 가능한 PET만을 분류하는 YOLOv7 기반 순환 가능한 PET 분류시스템을 설계 및 구현한다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.1-13
• /
• 2024

This study aims to provide a customized dynamic kiosk screen that considers user characteristics to cope with changes caused by increased use of kiosks. In order to optimize the screen composition according to the characteristics of the digital vulnerable group such as the visually impaired, the elderly, children, and wheelchair users, etc., users are classified into nine categories based on real-time analysis of user characteristics (wheelchair use, visual impairment, age, etc.). The kiosk screen is dynamically adjusted according to the characteristics of the user to provide efficient services. This study shows that the system communication and operation were performed in the embedded environment, and the used object detection, gait recognition, and speech recognition technologies showed accuracy of 74%, 98.9%, and 96%, respectively. The proposed technology was verified for its effectiveness by implementing a prototype, and through this, this study showed the possibility of reducing the digital gap and providing user-friendly "barrier-free kiosk" services.

• Korean Journal of Construction Engineering and Management
• /
• v.18 no.6
• /
• pp.78-88
• /
• 2017

With the growing use of BIM in the AEC industry, various new applications are being developed to meet these specific needs. Such developments have increased the importance of Industry Foundation Classes, which is the international standard for sharing BIM data and thus ensuring interoperability. However, mapping individual BIM objects to IFC entities is still a manual task, and is a main cause for errors or omissions during data transfers. This research focused on addressing this issue by applying novelty detection, which is a technique for detecting anomalies in data. By training the algorithm to learn the geometry of IFC entities, misclassifications (i.e., outliers) can be detected automatically. Two IFC classes (ifcWall, ifcDoor) were trained using objects from three BIM models. The results showed that the algorithm was able to correctly identify 141 of 160 outliers. Novelty detection is thus suggested as a competent solution to resolve the mapping issue, mainly due to its ability to create multiple inlier boundaries and ex ante training of element geometry.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.1
• /
• pp.129-139
• /
• 2019

Mapping urban areas using the earth observation satellites is useful for monitoring urban expansions and measuring urban developments. In this research, the different thresholds for detecting the urban areas separately from the remote-sensing index images (normalized-difference built-up index(NDBI) and urban index(UI) images) generated from the Landsat-8 image acquired in Daegu, South Korea were evaluated through the following steps: (1) the NDBI and UI images were separately generated from the given Landsat-8 image; (2) the different thresholds (-0.4, -0.2, and 0) for detecting the urban areas separately from the NDBI and UI images were evaluated; and (3) the accuracy of each detected urban area was assessed. The experiment results showed that the threshold -0.2 had the best performance for detecting the urban areas from the NDBI image, while the threshold -0.4 had the best performance for detecting the urban areas from the UI image. Some misclassification errors, however, occurred in the areas where the bare soil areas were classified into urban areas or where the high-rise apartments were classified into other areas. In the future research, a robust methodology for detecting urban areas, including the various types of urban features, with less misclassification errors will be proposed using the satellite images. In addition, research on analyzing the pattern of urban expansion will be carried out using the urban areas detected from the multi-temporal satellite images.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.558-559
• /
• 2023

지구온난화와 기후변화로 인해 전세계적으로 기업, 정부는 ESG(Environmental, Social and Corporate Governance)에 관심을 가지고 있다. 이에 따라 폐기물 분류 및 재활용에도 관심을 가지고 있지만 국내 외 폐기물 분류는 정확하게 이루어 지지 않고 있다. 이에 본 논문에서는 객체 인식의 대표 모델인 YOLOv5 를 이용해 폐기물 중 대표인 페트병 탐지 시스템을 제안한다. 제안하는 시스템은 페트병 사이 다른 폐기물을 감지해 내고 페트병 중 유색과 투명 페트병을 분류를 한다. 향후, 제안하는 시스템의 성능 평가가 필요하고 다른 폐기물로 확장이 필요하다.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.31-41
• /
• 2024

Deep learning models show excellent performance in tasks such as image classification and object detection in the field of computer vision, and are used in various ways in actual industrial sites. Recently, research on improving robustness has been actively conducted, along with pointing out that this deep learning model is vulnerable to hostile examples. A hostile example is an image in which small noise is added to induce misclassification, and can pose a significant threat when applying a deep learning model to a real environment. In this paper, we tried to confirm the robustness of the edge-learning classification model and the performance of the adversarial example detection model using it for adversarial examples of various algorithms. As a result of robustness experiments, the basic classification model showed about 17% accuracy for the FGSM algorithm, while the edge-learning models maintained accuracy in the 60-70% range, and the basic classification model showed accuracy in the 0-1% range for the PGD/DeepFool/CW algorithm, while the edge-learning models maintained accuracy in 80-90%. As a result of the adversarial example detection experiment, a high detection rate of 91-95% was confirmed for all algorithms of FGSM/PGD/DeepFool/CW. By presenting the possibility of defending against various hostile algorithms through this study, it is expected to improve the safety and reliability of deep learning models in various industries using computer vision.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.1-8
• /
• 2008

Generally, moving objects in surveillance video are extracted by background subtraction or frame difference method. However, moving cast shadows on object distort extracted figures which cause serious detection problems. Especially, analyzing vehicle information in video frames from a fixed surveillance camera on road, we obtain inaccurate results by shadow which vehicle causes. So, Shadow Elimination is essential to extract right objects from frames in surveillance video. And we use shadow removal algorithm for vehicle classification. In our paper, as we suppress moving cast shadow in object, we efficiently discriminate vehicle types. After we fit new object of shadow-removed object as three dimension object, we use extracted attributes for supervised learning to classify vehicle types. In experiment, we use 3 learning methods {IBL, C4.5, NN(Neural Network)} so that we evaluate the result of vehicle classification by shadow elimination.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.265-278
• /
• 2019

Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) data help to enable rapid emergency responses through detection of the artificial and natural disasters occurring at night. The DNB data without correction of lunar irradiance effect distributed by Korea Ocean Science Center (KOSC) has advantage for rapid change detection because of direct receiving. In this study, radiance differences according to the phase of the moon was analyzed for urban and mountain areas in Korean Peninsula using the DNB data directly receiving to KOSC. Lunar irradiance correction algorithm was proposed for the change detection. Relative correction was performed by regression analysis between the selected pixels considering the land cover classification in the reference DNB image during the new moon and the input DNB image. As a result of daily difference image analysis, the brightness value change in urban area and mountain area was ${\pm}30$ radiance and below ${\pm}1$ radiance respectively. The object based change detection was performed after the extraction of the main object of interest based on the average image of time series data in order to reduce the matching and geometric error between DNB images. The changes in brightness occurring in mountainous areas were effectively detected after the calibration of lunar irradiance effect, and it showed that the developed technology could be used for real time change detection.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.353-361
• /
• 2020

Due to the rapid urbanization, various traffic problems such as traffic jams during commute and regular traffic jams are occurring. In order to solve these traffic problems, it is necessary to quickly and accurately estimate and analyze traffic volume. ITS (Intelligent Transportation System) is a system that performs optimal traffic management by utilizing the latest ICT (Information and Communications Technology) technologies, and research has been conducted to analyze fast and accurate traffic volume through various techniques. In this study, we proposed a deep learning-based vehicle detection method using UAV (Unmanned Aerial Vehicle) video for real-time traffic analysis with high accuracy. The UAV was used to photograph orthogonal videos necessary for training and verification at intersections where various vehicles pass and trained vehicles by classifying them into sedan, truck, and bus. The experiment on UAV dataset was carried out using YOLOv3 (You Only Look Once V3), a deep learning-based object detection technique, and the experiments achieved the overall object detection rate of 90.21%, precision of 95.10% and the recall of 85.79%.