• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.14-16
• /
• 2019

스마트관제 시스템은 딥러닝 서버내 학습된 백본 네트워크 모델이 실시간으로 스트리밍 되는 CCTV 영상으로부터 이상행동 패턴을 선별적으로 탐지하고 관제요원에게 전달하여, 사전에 사건사고를 예방하거나 즉시 대응 체계의 유연한 운영을 가능케하는 시스템이다. 최근 지능형 CCTV(Closed Circuit Television) 서비스가 일부 지역에 선별 관제의 형태로 시범적으로 운영되고 있는 상황이다. 지능형 시범서비스는 공공 영역에서 선별 CCTV 관제의 형태로 이상행동 상황을 즉각 인지하여 사건사고를 예방하거나 피해를 최소화하고자 하는 목적으로 주로 사용되고 있다. 그러나, 범죄 등의 특정 시나리오에만 한정해서도 이상 행동 유형이 너무나 다양하기 때문에 이상행동 영상의 사전분류(Annotation)를 통해 딥러닝 모델을 학습시키는 것이 현실적으로 어려운 상황이다. 따라서 본고에서는 최신 이상 행동 탐지(Anomaly detection) 알고리즘과 응용사례를 분석하여 실제 현장에 적용할 수 있는 현장 중심의 기법을 제안하고자 한다.

• Journal of Industrial Convergence
• /
• v.22 no.7
• /
• pp.1-13
• /
• 2024

Among e-government services, the intelligent CCTV control platform is a screening control service that utilizes artificial intelligence to display major objects such as people, cars, etc. to control personnel when they appear on CCTV. The operation of an intelligent CCTV control platform is expected to improve the quality of life of citizens by enabling rapid response in the event of an emergency and increasing the resolution of complaints. In this study, the benefits of the intelligent CCTV control platform, a non-market good, were estimated by applying the contingent valuation method (CVM), a choice experiment technique, to estimate the average willingness to pay per household and calculate the social benefits. As a result of the analysis, the average willingness to pay per household was estimated to be KRW 6,908 per year, and the economic benefits for the country as a whole were estimated to be about KRW 150.4 billion per year. This study is of academic significance as it extends the application of CVM to the field of intelligent e-Government services. The Intelligent CCTV control platforms is being actively discussed, this study has practical implications in that the benefits were estimated in monetary value.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.189-196
• /
• 2024

Frequent false positives alarm from the Intelligent Selective Control System have raised significant concerns. These persistent issues have led to declines in operational efficiency and market credibility among agents. Developing a new model or replacing the existing one to mitigate false positives alarm entails substantial opportunity costs; hence, improving the quality of the training dataset is pragmatic. However, smaller organizations face challenges with inadequate capabilities in dataset collection and refinement. This paper proposes an automatic human pose data collection system centered around a human pose estimation model, utilizing camera-based sensor fusion techniques and edge devices. The system facilitates the direct collection and real-time processing of field data at the network periphery, distributing the computational load that typically centralizes. Additionally, by directly labeling field data, it aids in constructing new training datasets.