In spite of excellent performance of deep learning-based computer vision algorithms, they are not suitable for real-time surveillance to detect abnormal behavior because of very high computational complexity. In this paper, we propose a real-time surveillance system for abnormal behavior analysis in a closed-circuit television (CCTV) environment by constructing an algorithm and system optimized for a CCTV environment. The proposed method combines pedestrian detection and tracking to extract pedestrian information in real-time, and detects abnormal behaviors such as intrusion, loitering, fall-down, and violence. To analyze an abnormal behavior, it first determines intrusion/loitering through the coordinates of an object and then determines fall-down/violence based on the behavior pattern of the object. The performance of the proposed method is evaluated using an intelligent CCTV data set distributed by Korea Internet and Security Agency (KISA).

Abandoned object detection has recently been studied to detect dangerous situations such as illegally dumping explosives. Existing abandoned object detection used background subtraction, which is sensitive to noise and clutters of a similar size in outdoor environments. Unlike existing approaches, this article presents a deep learning-based detection method that is suitable for use in outdoor environments because it is robust to ghost effects and illumination changes. The proposed method consists of three parts: 1) pedestrian detection and tracking; 2) hand luggage detection (HLD); and 3) abandoned object decision. Since the proposed method detects the abandoned object through HLD instead of directly detecting the abandoned object itself, we could successfully improve the detection accuracy and robustness. The proposed method can also detect dangerous weapons or restricted hand luggage through HLD. This article presents an intelligent abandoned object detection system that can be applied for consumer applications.

With the advancement of autonomous driving technology, a driving status monitoring system gains increasing attraction in the mobility field. In this paper, we present a drowsy driving detection system using intelligent recognition of driving status. The proposed method first detects the driver's face, and then extracts face landmarks for face analysis. Drowsiness driving detection is performed by analyzing the following two characteristics based on the extracted landmarks: i) eye condition analysis based on pupil recognition and ii) head movement analysis based on the head pose. The proposed method used an efficient algorithm for real-time analysis, and the performance of the proposed method was evaluated using in-house datasets.

Urban mobility systems increasingly depend on remote sensing and artificial intelligence to enhance traffic monitoring and safety management. This study presents a LiDAR-based framework for urban road condition analysis and risk evaluation using vehicle-mounted sensors as dynamic remote sensing platforms. The framework integrates deep learning based object detection with mathematically defined surrogate safety indicators to quantify collision risk and evaluate evasive maneuverability in real traffic environments. Two indicators, Hazardous Modified Time to Collision (HMTTC) and Searching for Safety Space (SSS), are introduced to assess lane-level safety and spatial availability of avoidance zones. LiDAR point cloud data are processed using a Voxel RCNN architecture and converted into parameters such as density, speed, and spacing. Field experiments conducted on highways and urban corridors in South Korea reveal strong correlations between HMTTC occurrences, congestion, and geometric road features. The results demonstrate that AI-driven analysis of LiDAR data enables continuous, infrastructure-independent urban traffic safety monitoring, thereby supporting data-driven, resilient transportation systems.

This paper presents an efficient schedule method for maintenance, repair, and overhaul (MRO) tasks for aircraft engines using a constraint programming algorithm. Using data obtained from Korean Air’s MRO maintenance logs, we analyze and predict the optimal scheduling of regular inspections and fault repairs for various engine types. By proposing a proper modeling of the problem and preparing data for the constraint programming algorithm, we demonstrate superior performance in scheduling efficiency and resource utilization. The experimental results show an average utilization of 99.35%, and the method can even achieve 100% utilization in some cases.

The field of digital healthcare is rapidly evolving due to advancements in artificial intelligence technologies, particularly deep learning. This study aims to explore new possibilities in telemedicine by applying mixed reality (MR) technology to emergency medical situations. The primary goal of this research is to develop an MR device-based remote medical support system that utilizes MR devices and high-speed wireless communication to transmit onsite conditions to medical control rooms, enabling emergency responders to provide treatment under remote guidance. The system leverages Microsoft's HoloLens 2 to capture and transmit patient biometric information and surrounding environments, utilizing deep learning algorithms for human skeleton recognition and object alignment. The generated 3D avatars and content are then used in remote medical consultations. This article highlights the potential medical applications of HoloLens 2, a cutting-edge consumer electronics device, demonstrating how this system can provide innovative medical solutions through consumer technology and open up new possibilities in the healthcare field.