• Title/Summary/Keyword: 컴퓨터 시스템

Search Result 15,119, Processing Time 0.037 seconds

Detection of video editing points using facial keypoints (얼굴 특징점을 활용한 영상 편집점 탐지)

  • Joshep Na;Jinho Kim;Jonghyuk Park
    • Journal of Intelligence and Information Systems
    • /
    • v.29 no.4
    • /
    • pp.15-30
    • /
    • 2023
  • Recently, various services using artificial intelligence(AI) are emerging in the media field as well However, most of the video editing, which involves finding an editing point and attaching the video, is carried out in a passive manner, requiring a lot of time and human resources. Therefore, this study proposes a methodology that can detect the edit points of video according to whether person in video are spoken by using Video Swin Transformer. First, facial keypoints are detected through face alignment. To this end, the proposed structure first detects facial keypoints through face alignment. Through this process, the temporal and spatial changes of the face are reflected from the input video data. And, through the Video Swin Transformer-based model proposed in this study, the behavior of the person in the video is classified. Specifically, after combining the feature map generated through Video Swin Transformer from video data and the facial keypoints detected through Face Alignment, utterance is classified through convolution layers. In conclusion, the performance of the image editing point detection model using facial keypoints proposed in this paper improved from 87.46% to 89.17% compared to the model without facial keypoints.

Analysis of Domestic and International Patent Trends in Anti-drone Technology through Patent Application Status Survey (특허 출원 현황조사를 통한 안티드론 기술의 국내외 특허 동향 분석)

  • Jae-Hyo Hwang;Ki-Jung Kim
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.18 no.6
    • /
    • pp.1217-1228
    • /
    • 2023
  • In this paper, technical and patent analysses of anti-drone technology, which aim to neutralize drone attacks are conducted. We conducted research on the technical definition of anti-drone, the technical elements of anti-drone systems, and investigated the patents related to anti-drone and drone filed domestically and internationally over the past 10 years, starting from 2011. For domestic patents, we examined the number of patent applications related to anti-drone and the overall domestic patent applications over the past 10 years. Regarding international filings, we investigated the patent applications related to anti-drone filed in the United States, Europe, Japan, China, and under the PCT system in the past 10 years. We conducted a search for patents related to anti-drone, including neutralization techniques identified under the keyword "anti-drone," patents related to drone detection and identification techniques, and patents related to drone neutralization techniques. Through the conducted research, a total of 91 patents were filed for drone detection techniques. Out of these, 5 patents, accounting for 5.5%, were filed by public institutions. In the case of patents filed for drone identification techniques, there were a total of 174 patents. Among these, 4 patents, which is 2.3%, were filed by public institutions.

Korean Facial Expression Emotion Recognition based on Image Meta Information (이미지 메타 정보 기반 한국인 표정 감정 인식)

  • Hyeong Ju Moon;Myung Jin Lim;Eun Hee Kim;Ju Hyun Shin
    • Smart Media Journal
    • /
    • v.13 no.3
    • /
    • pp.9-17
    • /
    • 2024
  • Due to the recent pandemic and the development of ICT technology, the use of non-face-to-face and unmanned systems is expanding, and it is very important to understand emotions in communication in non-face-to-face situations. As emotion recognition methods for various facial expressions are required to understand emotions, artificial intelligence-based research is being conducted to improve facial expression emotion recognition in image data. However, existing research on facial expression emotion recognition requires high computing power and a lot of learning time because it utilizes a large amount of data to improve accuracy. To improve these limitations, this paper proposes a method of recognizing facial expressions using age and gender, which are image meta information, as a method of recognizing facial expressions with even a small amount of data. For facial expression emotion recognition, a face was detected using the Yolo Face model from the original image data, and age and gender were classified through the VGG model based on image meta information, and then seven emotions were recognized using the EfficientNet model. The accuracy of the proposed data classification learning model was higher as a result of comparing the meta-information-based data classification model with the model trained with all data.

A Study on Low-Light Image Enhancement Technique for Improvement of Object Detection Accuracy in Construction Site (건설현장 내 객체검출 정확도 향상을 위한 저조도 영상 강화 기법에 관한 연구)

  • Jong-Ho Na;Jun-Ho Gong;Hyu-Soung Shin;Il-Dong Yun
    • Tunnel and Underground Space
    • /
    • v.34 no.3
    • /
    • pp.208-217
    • /
    • 2024
  • There is so much research effort for developing and implementing deep learning-based surveillance systems to manage health and safety issues in construction sites. Especially, the development of deep learning-based object detection in various environmental changes has been progressing because those affect decreasing searching performance of the model. Among the various environmental variables, the accuracy of the object detection model is significantly dropped under low illuminance, and consistent object detection accuracy cannot be secured even the model is trained using low-light images. Accordingly, there is a need of low-light enhancement to keep the performance under low illuminance. Therefore, this paper conducts a comparative study of various deep learning-based low-light image enhancement models (GLADNet, KinD, LLFlow, Zero-DCE) using the acquired construction site image data. The low-light enhanced image was visually verified, and it was quantitatively analyzed by adopting image quality evaluation metrics such as PSNR, SSIM, Delta-E. As a result of the experiment, the low-light image enhancement performance of GLADNet showed excellent results in quantitative and qualitative evaluation, and it was analyzed to be suitable as a low-light image enhancement model. If the low-light image enhancement technique is applied as an image preprocessing to the deep learning-based object detection model in the future, it is expected to secure consistent object detection performance in a low-light environment.

Creating and Utilization of Virtual Human via Facial Capturing based on Photogrammetry (포토그래메트리 기반 페이셜 캡처를 통한 버추얼 휴먼 제작 및 활용)

  • Ji Yun;Haitao Jiang;Zhou Jiani;Sunghoon Cho;Tae Soo Yun
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.25 no.2
    • /
    • pp.113-118
    • /
    • 2024
  • Recently, advancements in artificial intelligence and computer graphics technology have led to the emergence of various virtual humans across multiple media such as movies, advertisements, broadcasts, games, and social networking services (SNS). In particular, in the advertising marketing sector centered around virtual influencers, virtual humans have already proven to be an important promotional tool for businesses in terms of time and cost efficiency. In Korea, the virtual influencer market is in its nascent stage, and both large corporations and startups are preparing to launch new services related to virtual influencers without clear boundaries. However, due to the lack of public disclosure of the development process, they face the situation of having to incur significant expenses. To address these requirements and challenges faced by businesses, this paper implements a photogrammetry-based facial capture system for creating realistic virtual humans and explores the use of these models and their application cases. The paper also examines an optimal workflow in terms of cost and quality through MetaHuman modeling based on Unreal Engine, which simplifies the complex CG work steps from facial capture to the actual animation process. Additionally, the paper introduces cases where virtual humans have been utilized in SNS marketing, such as on Instagram, and demonstrates the performance of the proposed workflow by comparing it with traditional CG work through an Unreal Engine-based workflow.

Development of Database-Based Pedestrian Accident Scenarios and Analysis of Accident Prevention Effects from V2X Application (데이터베이스 기반의 보행자 사고 시나리오 개발 및 V2X 적용에 따른 사고예방 효과 분석)

  • Seryong Baek;Yoowon Kim;Taehyun Yoo;Cheonho Kim
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.23 no.5
    • /
    • pp.274-292
    • /
    • 2024
  • The purpose of this study is to develop test scenarios utilizing V2X (Vehicle-to-Everything) communication technology for the prevention of pedestrian accidents and to validate these scenarios through simulation. To this end, this researcher used existing traffic accident databases to categorize vehicle-to-pedestrian accident data, and drew key accident patterns through the analysis of accident types and the speeds of pedestrians and vehicles. Based on the analyzed data, scenarios were established where V2X technology can be applied under various conditions of pedestrians and vehicles. These scenarios were specifically classified into conditions where physical avoidance of an accident is impossible and conditions where accident avoidance is possible through V2X technology. In the developed test matrix, simulations were conducted in diverse scenarios to evaluate the performance of the V2X-based accident prevention system. The research results confirmed that the application of V2X technology is effective for preventing pedestrian accidents. It is expected that these scenarios can serve as standardized guidelines for future traffic safety improvements. This study provides useful data for policymakers for traffic safety, vehicle manufacturers, and technology developers, and proposes a new approach to enhance pedestrian safety.

A Study on the Optimization of Fire Awareness Model Based on Convolutional Neural Network: Layer Importance Evaluation-Based Approach (합성곱 신경망 기반 화재 인식 모델 최적화 연구: Layer Importance Evaluation 기반 접근법)

  • Won Jin;Mi-Hwa Song
    • The Transactions of the Korea Information Processing Society
    • /
    • v.13 no.9
    • /
    • pp.444-452
    • /
    • 2024
  • This study proposes a deep learning architecture optimized for fire detection derived through Layer Importance Evaluation. In order to solve the problem of unnecessary complexity and operation of the existing Convolutional Neural Network (CNN)-based fire detection system, the operation of the inner layer of the model based on the weight and activation values was analyzed through the Layer Importance Evaluation technique, the layer with a high contribution to fire detection was identified, and the model was reconstructed only with the identified layer, and the performance indicators were compared and analyzed with the existing model. After learning the fire data using four transfer learning models: Xception, VGG19, ResNet, and EfficientNetB5, the Layer Importance Evaluation technique was applied to analyze the weight and activation value of each layer, and then a new model was constructed by selecting the top rank layers with the highest contribution. As a result of the study, it was confirmed that the implemented architecture maintains the same performance with parameters that are about 80% lighter than the existing model, and can contribute to increasing the efficiency of fire monitoring equipment by outputting the same performance in accuracy, loss, and confusion matrix indicators compared to conventional complex transfer learning models while having a learning speed of about 3 to 5 times faster.

Evaluation of Effective Dose and Image Quality According to Arm height angle(AHA) during Chest Lateral Radiography : Retrospective Research (흉부 측면 방사선 검사 시 팔 높이 각도(AHA)에 따른 유효선량과 화질 평가 : 후향적 연구)

  • Kang-Min Lee
    • Journal of the Korean Society of Radiology
    • /
    • v.18 no.6
    • /
    • pp.663-671
    • /
    • 2024
  • This study aims to evaluate the effects of Arm Height Angle (Arm Heiht Angle : AHA) on patient effective dose and image quality in lateral chest radiography, and to propose the optimal arm positioning for minimizing radiation exposure while ensuring diagnostic efficacy. Using consistent X-ray equipment with Automatic Exposure Control (AEC), examinations were performed on 10 patients at AHA settings of 90°, 120°, and 150°. For each angle, Dose-Area Product (DAP) values were measured, and effective dose was calculated using the Monte Carlo simulation-based software PCXMC 2.0. The findings revealed a 53% increase in effective dose when AHA was adjusted from 150° to 120°, although this difference was not statistically significant (p=0.3). However, setting the AHA to 90° resulted in an approximately 140% increase in effective dose, a statistically significant change (p=0.00). Quantitative assessment showed no statistically significant differences in image quality metrics across the 90°, 120°, and 150° groups, as measured by TT SNR (p=0.1), TT CNR (p=0.6), AA SNR (p=0.2), AA CNR (p=0.8), LA SNR (p=0.2), and LA CNR (p=0.8). Visual assessments indicated that the 150° AHA setting received the highest scores, suggesting that an arm height angle of 150° or greater may optimize image quality while reducing patient radiation exposure. Based on these results, this study recommends an AHA of 150° or higher as the optimal positioning for lateral chest radiography, providing an effective balance between radiation dose minimization and diagnostic image quality.

Animal Infectious Diseases Prevention through Big Data and Deep Learning (빅데이터와 딥러닝을 활용한 동물 감염병 확산 차단)

  • Kim, Sung Hyun;Choi, Joon Ki;Kim, Jae Seok;Jang, Ah Reum;Lee, Jae Ho;Cha, Kyung Jin;Lee, Sang Won
    • Journal of Intelligence and Information Systems
    • /
    • v.24 no.4
    • /
    • pp.137-154
    • /
    • 2018
  • Animal infectious diseases, such as avian influenza and foot and mouth disease, occur almost every year and cause huge economic and social damage to the country. In order to prevent this, the anti-quarantine authorities have tried various human and material endeavors, but the infectious diseases have continued to occur. Avian influenza is known to be developed in 1878 and it rose as a national issue due to its high lethality. Food and mouth disease is considered as most critical animal infectious disease internationally. In a nation where this disease has not been spread, food and mouth disease is recognized as economic disease or political disease because it restricts international trade by making it complex to import processed and non-processed live stock, and also quarantine is costly. In a society where whole nation is connected by zone of life, there is no way to prevent the spread of infectious disease fully. Hence, there is a need to be aware of occurrence of the disease and to take action before it is distributed. Epidemiological investigation on definite diagnosis target is implemented and measures are taken to prevent the spread of disease according to the investigation results, simultaneously with the confirmation of both human infectious disease and animal infectious disease. The foundation of epidemiological investigation is figuring out to where one has been, and whom he or she has met. In a data perspective, this can be defined as an action taken to predict the cause of disease outbreak, outbreak location, and future infection, by collecting and analyzing geographic data and relation data. Recently, an attempt has been made to develop a prediction model of infectious disease by using Big Data and deep learning technology, but there is no active research on model building studies and case reports. KT and the Ministry of Science and ICT have been carrying out big data projects since 2014 as part of national R &D projects to analyze and predict the route of livestock related vehicles. To prevent animal infectious diseases, the researchers first developed a prediction model based on a regression analysis using vehicle movement data. After that, more accurate prediction model was constructed using machine learning algorithms such as Logistic Regression, Lasso, Support Vector Machine and Random Forest. In particular, the prediction model for 2017 added the risk of diffusion to the facilities, and the performance of the model was improved by considering the hyper-parameters of the modeling in various ways. Confusion Matrix and ROC Curve show that the model constructed in 2017 is superior to the machine learning model. The difference between the2016 model and the 2017 model is that visiting information on facilities such as feed factory and slaughter house, and information on bird livestock, which was limited to chicken and duck but now expanded to goose and quail, has been used for analysis in the later model. In addition, an explanation of the results was added to help the authorities in making decisions and to establish a basis for persuading stakeholders in 2017. This study reports an animal infectious disease prevention system which is constructed on the basis of hazardous vehicle movement, farm and environment Big Data. The significance of this study is that it describes the evolution process of the prediction model using Big Data which is used in the field and the model is expected to be more complete if the form of viruses is put into consideration. This will contribute to data utilization and analysis model development in related field. In addition, we expect that the system constructed in this study will provide more preventive and effective prevention.

The Design of Mobile Medical Image Communication System based on CDMA 1X-EVDO for Emergency Care (CDMA2000 1X-EVDO망을 이용한 이동형 응급 의료영상 전송시스템의 설계)

  • Kang, Won-Suk;Yong, Kun-Ho;Jang, Bong-Mun;Namkoong, Wook;Jung, Hai-Jo;Yoo, Sun-Kook;Kim, Hee-Joung
    • Proceedings of the Korean Society of Medical Physics Conference
    • /
    • 2004.11a
    • /
    • pp.53-55
    • /
    • 2004
  • In emergency cases, such as the severe trauma involving the fracture of skull, spine, or cervical bone, from auto accident or a fall, and/or pneumothorax which can not be diagnosed exactly by the eye examination, it is necessary the radiological examination during transferring to the hospital for emergency care. The aim of this study was to design and evaluate the prototype of mobile medical image communication system based on CDMA 1X EVDO. The system consists of a laptop computer used as a transmit DICOM client, linked with cellular phone which support to the CDMA 1X EVDO communication service, and a receiving DICOM server installed in the hospital. The DR images were stored with DICOM format in the storage of transmit client. Those images were compressed into JPEG2000 format and transmitted from transmit client to the receiving server. All of those images were progressively transmitted to the receiving server and displayed on the server monitor. To evaluate the image quality, PSNR of compressed image was measured. Also, several field tests had been performed using commercial CDMA2000 1X-EVDO reverse link with the TCP/IP data segments. The test had been taken under several velocity of vehicle in seoul areas.

  • PDF