• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.117-123
• /
• 2023

Recently, as the demand for Generative Artificial Intelligence (AI) and artificial intelligence has increased, the seriousness of misuse and abuse has emerged. However, intelligent CCTV, which maximizes detection of abnormal behavior, is of great help to prevent crime in the military and police. AI performs learning as taught by humans and then proceeds with self-learning. Since AI makes judgments according to the learned results, it is necessary to clearly understand the characteristics of learning. However, it is often difficult to visually judge strange and abnormal behaviors that are ambiguous even for humans to judge. It is very difficult to learn this with the eyes of artificial intelligence, and the result of learning is very many False Positive, False Negative, and True Negative. In response, this paper presented standards and methods for clarifying the learning of AI's strange and abnormal behaviors, and presented learning measures to maximize the judgment ability of intelligent CCTV's False Positive, False Negative, and True Negative. Through this paper, it is expected that the artificial intelligence engine performance of intelligent CCTV currently in use can be maximized, and the ratio of False Positive and False Negative can be minimized..

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.523-525
• /
• 2022

CCTV 시스템은 다양한 목적으로 매우 많은 곳에서 유용하게 활용되고 있으나, 해킹 또는 기타의 이유로 사생활 침해에 대한 우려가 커지고 있다. 본 논문에서는 영상의 입수 시점에서부터 사생활침해가 발생할 수 있는 영상 정보를 제거하고, 대신 인공지능 기술을 활용하여 이를 대체할 수 있는 인물의 스켈레톤 정보를 추가로 제공함으로써 사생활 정보를 침해하지 않으면서도 상황을 충분히 인식할 수 있는 CCTV 용 카메라 시스템을 여러 인공지능 알고리즘을 비교하여 설계하였다. 또한 카메라 및 인공지능 기술을 쉽게 사용할 수 있으면서도 주변에서 쉽게 구할 수 있는 안드로이드 스마트폰을 이용하여 설계를 실제 구현한 후 영상의 각 해상도별 초당 처리 성능 및 스켈레톤 인식률 등의 성능을 평가하여 실제로 제품구현 및 제품화 시 중점을 두어야할 주요 개선점 및 향후 연구과제를 도출하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.498-500
• /
• 2022

CCTV protects people and assets safely by identifying dangerous situations and responding promptly. However, it is difficult to continuously monitor the increasing number of CCTV images. For this reason, there is a need for a device that continuously monitors CCTV images and notifies when abnormal behavior occurs. Recently, many studies using artificial intelligence models for image data analysis have been conducted. This study simultaneously learns spatial and temporal characteristic information between image data to classify various abnormal behaviors that can be observed in CCTV images. As an artificial intelligence model used for learning, we propose a multi-classification deep learning model that combines an end-to-end 3D convolutional neural network(CNN) and ResNet.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1130-1135
• /
• 2022

In Seoul, about 75,000 CCTVs are installed in 25 district offices. Each ward office has built a control center for CCTV control and is performing 24-hour CCTV video control for the safety of citizens. Seoul Metropolitan Government is building a smart city integrated platform that is safe for citizens by providing CCTV images of the ward office to enable rapid response to emergency/emergency situations by signing an MOU with related organizations. In this paper, when an incident occurs at the Seoul Metropolitan Government Office, the escape route is predicted by discriminating people and vehicles using the AI DNN-based Template Matching technology, MLP algorithm and CNN-based YOLO SPP DNN model for CCTV images. In addition, it is designed to automatically disseminate image information and situation information to adjacent ward offices when vehicles and people escape from the competent ward office. The escape route prediction and tracking system using artificial intelligence can expand the smart city integrated platform nationwide.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.317-318
• /
• 2020

본 논문에서는 얼굴검출 후 MobilnetV2의 방법을 이용하여 적은 연산량으로 CCTV가 실시간으로 마스크 착용 유무를 판단할 수 있는 방법을 제시하였다. 이를 통해 현재 이슈가 되고있는 코로나19 등 전염병의 전염 위험이 있는 주요 장소에서 인공지능 CCTV가 마스크 미착용자를 식별해 알려줌으로써 마스크 미착용자를 관리할 수 있는 방법을 제공하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.615-618
• /
• 2023

최근 computer vision 기술 발달이 가속화되고 있으나, 특정 산업의 경우 산업 적용의 어려움과 데이터적 특성으로 인하여 기술 발전의 속도를 따라가지 못하고 있다. 특히, CCTV 는 대부분 실외 환경에 운영되어 다양한 환경의 변화 및 데이터 고유 특성상 노이즈가 많기 때문에 데이터 산포가 커서 기술의 현장 적용에 어려움이 있다. 본 논문에서는 CCTV 데이터의 특성을 고려하여 CCTV 운용 환경에 강건한 객체탐지(object detector) 학습을 위한 데이터 설계 방안을 제안한다. 제안 기법은 대용량의 CCTV 영상에서 객체탐지에 효과적인 샘플링을 유도하는 방안과 소수의 CCTV 레이블 데이터 외 MS COCO 등 다수 오픈 레이블 데이터를 혼합학습 하여 일반화 성능을 높이는 방안을 제안한다. 다수의 실험을 통해 제안 기법의 우수성을 입증하였으며, 특히 mAP 기준 13.39%의 성능 향상을 꾀할 수 있음을 선보였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.376-378
• /
• 2022

Artificial intelligence technology is widely used in various fields such as artificial intelligence speakers, artificial intelligence chatbots, and autonomous vehicles. Among these AI application fields, the image processing field shows various uses such as detecting objects or recognizing objects using artificial intelligence. In this paper, data synthesized by a virtual human is used as a method to analyze images taken in a specific space.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.691-694
• /
• 2023

본 논문은 CCTV 화면에서의 다양한 이상상황 중 교량 데이터에 특화된 자세 추정 기반 이상탐지 알고리즘을 소개한다. 교량은 크게 도로, 인도 이렇게 두 구역으로 나눠지며, 사람들의 이동방향이 한정적이라는 특징을 가지는 장소 중 하나이다. 이러한 장소적 특징을 이용하고자 사람 자세 추정을 통해 이상의 기준을 잡고 교량 데이터에 특화된 이상탐지 알고리즘을 제안한다. CCTV 영상은 이상을 정하기 어렵고 이상에 대한 레이블이 없는 데이터가 대부분이며 이상에 대한 레이블 생성시 많은 비용 발생이 필수적이다. 본 연구에서는 이러한 한계점을 극복하고자 영상 데이터를 이미지 단위가 아닌 영상 단위로 레이블이 담긴 weakly label 을 가지는 데이터를 활용한 이상탐지 모델을 이용하였다. 특히, 교량에서의 이상상황의 특징인 사람 자세 추정으로 추출한 특질을 추가하여 기존 알고리즘의 이상탐지 예측 성능을 개선하였다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.203-204
• /
• 2023

The construction industry is a hazardous environment in which many field workers work. Therefore, there is a limit to the safety manager's grasp of all situations. In order to solve these problems, the application of automatic control technology in connection with AI and CCTV is being introduced, and the development of intelligent CCTV to reduce the safety accident rate is actively progressing. This study seeks to present future directions by identifying the current status of intelligent CCTV developed to reduce the safety accident rate at construction sites and analyzing its limitations. Through this, the range of accident prevention types of the safety control system at the construction site will be confirmed and the need for future intelligent CCTV function development will be suggested.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.225-227
• /
• 2022

Now In Seoul, about 75,000 CCTVs are installed in 25 district offices. Each ward office in Seoul has built a control center for CCTV control and is building information such as people, vehicle types, license plate recognition and color classification into big data through 24-hour artificial intelligence intelligent image analysis. Seoul Metropolitan Government has signed MOUs with the Ministry of Land, Infrastructure and Transport, the National Police Agency, the Fire Service, the Ministry of Justice, and the military base to enable rapid response to emergency/emergency situations. In other words, we are building a smart city that is safe and can prevent disasters by providing CCTV images of each ward office. In this paper, the CCTV image is designed to extract the characteristics of the vehicle and personnel when an incident occurs through artificial intelligence, and based on this, predict the escape route and enable continuous tracking. It is designed so that the AI automatically selects and displays the CCTV image of the route. It is designed to expand the smart city integration platform by providing image information and extracted information to the adjacent ward office when the escape route of a person or vehicle related to an incident is expected to an area other than the relevant jurisdiction. This paper will contribute as basic data to the development of smart city integrated platform research.