• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.143-144
• /
• 2020

4차 산업 시대가 도래하여 빅데이터와 딥러닝 기술은 다양한 분야에서 아주 중요한 기술로 자리 잡고 있으며, 현재 세계 여러 분야에서 이 기술들을 이용하여 일상, 산업 분야에 적용을 시키고자 한다. 국내에서는 스마트 팩토리, 스마트 시티와 같은 분야에 적용하고 있다. 본 논문에서는 스마트 시티에 적용할 수 있는 횡단보도 상황을 인지하여 교통제어에 활용할 수 있는 빅데이터를 생산하거나 효율적인 교통제어에 활용할 수 있도록 Nvidia Jetson TX2와 실시간 객체 감지 기술인 YOLO v3를 이용하여 횡단보도용 상황 인식을 위한 영상인식 장치를 개발하였다. 제안하는 기술들을 이용하여 스마트시티 구축에 활용할 수 있고, 실시간으로 추가적으로 필요한 객체를 감지하여 확장이 용이한 장점이 있다. 또한 구현에서 효율성을 높이기 위하여 에지 컴퓨팅, 스페이스 디텍션과 같은 기술들을 활용하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1266-1271
• /
• 2022

Cats have strong wildness so they have a characteristic of hiding diseases well. The disease may have already worsened when the guardian finds out that the cat has a disease. It will be of great help in treating the cat's disease if the owner can recognize the cat's polydipsia, polyuria, and frequent urination more quickly. In this paper, 1) Efficient version of DeepLabCut for pose estimation, 2) YOLO v4 for object detection, 3) LSTM is used for behavior prediction, and 4) BoT-SORT is used for object tracking running on an artificial intelligence device. Using artificial intelligence technology, it predicts the cat's next, polyuria and frequency of urination through the analysis of the cat's behavior pattern from the home CCTV video and the weight sensor of the water bowl. And, through analysis of cat behavior patterns, we propose an application that reports disease prediction and abnormal behavior to the guardian and delivers it to the guardian's mobile and the server system.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.189-198
• /
• 2023

As crimes frequently occur on the street, the spread of CCTV is increasing. However, due to the shortcomings of passively operated CCTV, the need for intelligent CCTV is attracting attention. Due to the heavy system of such intelligent CCTV, high-performance devices are required, which has a problem in that it is expensive to replace the general CCTV. To solve this problem, an intelligent CCTV system that recognizes low-quality images and operates even on devices with low performance is required. Therefore, this paper proposes a Saying CCTV system that can detect threats in real time by using the AWS cloud platform to lighten the system and convert images into text. Based on the data extracted using YOLO v4 and OpenPose, it is implemented to determine the risk object, threat behavior, and threat situation, and calculate the risk using machine learning. Through this, the system can be operated anytime and anywhere as long as the network is connected, and the system can be used even with devices with minimal performance for video shooting and image upload. Furthermore, it is possible to quickly prevent crime by automating meaningful statistics on crime by analyzing the video and using the data stored as text.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.650-651
• /
• 2020

본 논문은 YOLO v4 알고리즘을 이용하여 산업 현장에서 근로자의 개인 보호장비를 검출하는 방법을 제시한다. 학습데이터 주석은 사람 영역, 안전모, 안전 조끼 혹은 벨트 영역을 검출하도록 처리하였으며, 학습데이터 2,198개, 검증데이터 275개를 학습하는 데 이용하였다. 실험 결과 학습 반복 수 10,000번을 기준으로 81.81%의 mAP가 나옴을 확인하였다. 추후 정확도 개선을 위해 학습데이터 구축 및 전·후처리 알고리즘 관련 연구를 수행할 예정이다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.287-288
• /
• 2020

우리나라의 무단 투기된 쓰레기양은 2019년 2월 기준 33만 톤이며 이를 단속하기 위해 상용화된 쓰레기 무단투기 단속 시스템은 센서를 이용하여 시스템 주변에 사람이 지나가면 영상을 촬영하기 때문에 쓰레기 무단투기자 뿐 아니라 해당 시스템 주변을 지나는 모든 사람을 촬영하기 때문에 불법 쓰레기를 배출하는지 해당 영상을 사람이 일일이 다시 분석해야한다. 본 논문에서는 쓰레기 투기 행위 이미지를 바탕으로 학습시킨 딥러닝 실시간 객체인식 알고리즘인 YOLO-v4를 활용하여 실시간으로 쓰레기 무단투기를 단속하는 시스템을 제시한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.145-146
• /
• 2020

현재 4차 산업 혁명 시대에서 가장 중요한 화두는 빅데이터(Big Data), 인공지능이며, 이를 이용한 분야로 생산, 제조 분야에서도 인공지능 영상 인식 기술을 활용한 생산품을 자동으로 분류하고 나아가 품질검사도 할 수 있도록 개발하고 있다. 또한, 로봇을 공장의 생산라인에 운영하여 노동력 감소에 따른 보완이 되고, 제조과정의 효율성 증가와 생산시간 감소로 생산성을 높일 수 있다. 이를 위해 본 논문에서는 실시간 객체감지 기술인 YOLO-v3 알고리즘을 이용해서 PCB보드 인식, 분류할 수 있는 시스템을 개발하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.239-240
• /
• 2023

교통사고는 차량 운전자의 부주의 및 보행자의 안전 불감증 등 여러 가지 이유로 다양한 형태의 교차로에서 사고가 발생한다. 이것을 개선하고자 본 논문에서는 보행자 위험 알림 시스템을 구현하였다. 이 시스템은 YOLO v4 tiny 알고리즘 사용해 약 8,000장의 보행자와 차량의 사진을 학습시켜 객체 인식의 정확도를 높이고 웹캠과 스피커를 사용하여 보행자에게 위험을 알릴 뿐만 아니라, 사고 발생 등의 경우에 대해서 블랙박스 역할을 할 수 있도록 구현하였다.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.883-890
• /
• 2022

Purpose: Currently, in the case of domestic fire fighting facility design, it is difficult to secure highquality manpower due to low design costs and overheated competition between companies, so there is a limit to improving the fire safety performance of buildings. Accordingly, AI-based firefighting design solutions were studied to solve these problems and secure leading fire engineering technologies. Method: Through AutoCAD, which is widely used in existing fire fighting design, the procedures required for basic design and implementation design were processed, and AI technology was utilized through the YOLO v4 object recognition deep learning model. Result: Through the design process for fire fighting facilities, the facility was determined and the drawing design automation was carried out. In addition, by learning images of doors and pillars, artificial intelligence recognized the part and implemented the function of selecting boundary areas and installing piping and fire fighting facilities. Conclusion: Based on artificial intelligence technology, it was confirmed that human and material resources could be reduced when creating basic and implementation design drawings for building fire protection facilities, and technology was secured in artificial intelligence-based fire fighting design through prior technology development.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.211-220
• /
• 2022

Recently, research on smart factories triggered by the 4th industrial revolution is being actively conducted. Accordingly, the manufacturing industry is conducting various studies to improve productivity and quality based on deep learning technology with robust performance. This paper is a study on the method of detecting tire surface defects in the visual inspection stage of the tire manufacturing process, and introduces a tire surface defect detection method using a depth image acquired through a 3D camera. The tire surface depth image dealt with in this study has the problem of low contrast caused by the shallow depth of the tire surface and the difference in the reference depth value due to the data acquisition environment. And due to the nature of the manufacturing industry, algorithms with performance that can be processed in real time along with detection performance is required. Therefore, in this paper, we studied a method to normalize the depth image through relatively simple methods so that the tire surface defect detection algorithm does not consist of a complex algorithm pipeline. and conducted a comparative experiment between the general normalization method and the normalization method suggested in this paper using YOLO V3, which could satisfy both detection performance and speed. As a result of the experiment, it is confirmed that the normalization method proposed in this paper improved performance by about 7% based on mAP 0.5, and the method proposed in this paper is effective.

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.171-184
• /
• 2023

Machine learning (ML)-based cavity detection using a large amount of survey data obtained from vehicle-mounted ground penetrating radar (GPR) has been actively studied to identify underground cavities. However, only simple image processing techniques have been used for preprocessing the ML input, and many conventional seismic and GPR data processing techniques, which have been used for decades, have not been fully exploited. In this study, based on the idea that a cavity can be identified using diffraction, we applied ML-based diffraction separation to GPR data to increase the accuracy of cavity detection using the YOLO v5 model. The original ML-based seismic diffraction separation technique was modified, and the separated diffraction image was used as the input to train the cavity detection model. The performance of the proposed method was verified using public GPR data released by the Seoul Metropolitan Government. Underground cavities and objects were more accurately detected using separated diffraction images. In the future, the proposed method can be useful in various fields in which GPR surveys are used.