• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.4
• /
• pp.1-9
• /
• 2023

In this paper, we propose a method to recognize the braille blocks for embedded devices in real time through deep learning. First, a deep learning model for braille block recognition is trained on a high-performance computer, and the learning model is applied to a lightweight tool to apply to an embedded device. To recognize the walking information of the braille block, an algorithm is used to determine the path using the distance from the braille block in the image. After detecting braille blocks, bollards, and crosswalks through the YOLOv8 model in the video captured by the embedded device, the walking information is recognized through the braille block path discrimination algorithm. We apply the model lightweight tool to YOLOv8 to detect braille blocks in real time. The precision of YOLOv8 model weights is lowered from the existing 32 bits to 8 bits, and the model is optimized by applying the TensorRT optimization engine. As the result of comparing the lightweight model through the proposed method with the existing model, the path recognition accuracy is 99.05%, which is almost the same as the existing model, but the recognition speed is reduced by 59% compared to the existing model, processing about 15 frames per second.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.291-299
• /
• 2010

As recent advances in science, technology and performance requirements of the weapons system are getting highly diversified and complex, the performance requirements also get stringent and strict. Moreover, the weapons system should be intimately connected with other systems such as watchdog system, command and control system, C4I system, etc. However, a tremendous amount of time, cost and risk being spent to acquire new weapons system, and not being diminished compared to the rapid pace of its development speed. Defense Modeling and Simulation(M&S) comes into the spotlight as an alternative to overcoming these difficulties as well as constraints. In this paper, we propose the development process of virtual test framework based on the synthetic environment as a tool to analyze the effectiveness of the weapons system of underwater engagement model. To prove the proposed concept, we develop the test-bed of virtual test using Delta3D simulation engine, which is open source S/W. We also design the High Level Architecture and Real-time Infrastructure(HLA/RTI) based Federation for the interoperation with heterogeneous simulators. The significance of the study entails (1)the rapid and easy development of simulation tools that are customized for the Korean Theater of War; (2)the federation of environmental entities and the moving equations of the combat entities to manifest a realistic simulation.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.23 no.1
• /
• pp.26-32
• /
• 2017

Enlargement and speed-up of a ship and diversification of ship's type have served to greatly increase the importance of marine transport means. It's reported that accident occurrence frequency of collision is high next to engine damage among the ship accident types, and that the accident ratio according to human factors is also high. In addition, ship accidents come to occur caused by complex cause factors rather than a sole cause factor, it is necessary to investigate the cause factors through the written verdict. This study proposed the cause factors of collision ship accident on the basis of human factors in collision ship accident among the written verdicts provided by the Korean Maritime Safety Tribunal, and inquired into the cause factor and effect through the correlation analysis of accident occurrence factors. Also, this study predicted the collision accident through analyzed the major cause factor of the occurrence at the zero minute when collision on the basis of the time taken from the time point of detecting collision of ships to the time point of collision occurrence. This study used commercial software-Statistical Package for Social Sciences (SPSS Ver21.0) to do correlation analysis. For time analysis, this study analyzed the cause factor and time by analyzing the time taken from the time point of detected ships to the time point of collision occurrence on the basis of the written verdicts. The study analysis showed that there were many cases of collision ship accidents occurrence caused by more than two sorts of cause factors, and that the case (zero minute) where there is no time to spare for collision avoidance accounted for 36.1 %, and negligence in guard or surveillance of the other ship, and sailing while drowsy, or drinking was a contributor to an accident. Poor watch keeping is very strong relationship with pool ready for sail.