• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.281-282
• /
• 2022

현재 전동 킥보드 헬멧 미착용으로 인한 사고가 끊임없이 야기되고 있다. 개인형 이동장치 이용자 수가 증가함에 따라 법 개정을 통하여 헬멧 착용이 의무 사항이지만 여전히 낮은 착용률을 나타내고 있다. 본 논문에서는 모든 공유 킥보드 회사에서 사용 가능한 딥러닝 기반의 전동킥보드 헬멧 착용 인식시스템을 제시한다. 타 공유 전동킥보드 회사 앱에서 본 논문의 결과물을 사용할 때는 사용자가 타사 앱에서 헬멧 인식 요청 시 자사 앱에서 헬멧 착용 여부를 인식하여 결과를 전송한다. 자사 앱 사용자는 인식 기록을 조회할 수 있고, 타사 관리자는 사용자의 정보를 조회 및 관리할 수 있다. 본 시스템을 통해 전동킥보드 이용 시 헬멧 착용을 장려하여 착용률 증가와 사고 시 인명피해 감소를 기대한다.

• Journal of the Society of Disaster Information
• /
• v.18 no.1
• /
• pp.154-162
• /
• 2022

Purpose: The government intends to come up with measures to revitalize safety management at construction sites to shift safety management at construction sites from human capabilities to system-oriented management systems using advanced technologies AIoT and Mobile technologies. Method: The construction site safety management monitoring system using AIoT and Mobile technology conducted an experiment on the effectiveness of the construction site by applying three algorithms: virtual fence, fire monitoring, and recognition of not wearing a safety helmet. Result: The number of workers in the experiment was 215 and 7.61 virtual fence intrusion was 3.5% compared to the number of subjects and 0.16 fire detection were 0.07% compared to the subjects, and the average monthly rate of not wearing a safety helmet was 8.79, 4.05% compared to the subjects. Conclusion: It was found that the construction site safety management monitoring system using AIoT and Mobile technology has a valid effect on the construction site.

• Journal of the HCI Society of Korea
• /
• v.6 no.1
• /
• pp.1-8
• /
• 2011

As virtual realty has become an issue of providing immersive services, in the area of virtual realty, it has been actively investigated to develop user interfaces for immersive interaction. In this paper, we propose a gesture recognition based immersive user interface by using an IR LED embedded helmet and data gloves in order to reflect the user's movements to the virtual reality environments effectively. The system recognizes the user's head movements by using the IR LED embedded helmet and IR signal transmitter, and the hand gestures with the data gathered from data gloves. In case of hand gestures recognition, it is difficult to recognize accurately with the general recognition model because there are various hand gestures since human hands consist of many articulations and users have different hand sizes and hand movements. In this paper, we applied the Mixture-of-Experts based gesture recognition for various hand gestures of multiple users accurately. The movement of the user's head is used to change the perspection in the virtual environment matching to the movement in the real world, and the gesture of the user's hand can be used as inputs in the virtual environment. A head mounted display (HMD) can be used with the proposed system to make the user absorbed in the virtual environment. In order to evaluate the usefulness of the proposed interface, we developed an interface for the virtual orchestra environment. The experiment verified that the user can use the system easily and intuituvely with being entertained.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.277-278
• /
• 2022

최근 전동킥보드 보급이 이루어지면서 이와 관련된 교통사고가 증가하고 있다. 이에 따라 전동킥보드 주행 시 헬멧 착용을 의무화하는 도로교통법 개정안이 시행되고 있지만, 물리적으로 대부분 현장에서 단속이 어렵다. 본 논문에서는 딥러닝 영상인식 기술을 활용한 객체검출(object detection) 모델인 YOLOv4를 기반으로 전동킥보드 사용자의 헬멧 미착용 검출시스템을 제안하였다. 이를 통해 전동킥보드 주행 시 헬멧 착용 여부를 효율적으로 단속하는데 활용 할 수 있을 것으로 기대한다.