Design of Real-time Safety Accident Prevention Solution for Socially Vulnerable using Object Recognition and Tracking Technology

All countries around the world want to create a safe society and a safe nation. However, crime targeting the socially vulnerable groups continues to increase. This is because the vulnerable groups have physical and physical weaknesses. Therefore, in order to pursue a safe society, it is necessary to protect the socially vulnerable. In this paper, we utilize the latest trend, drones, to protect against vulnerable groups. That is, we designed a real-time accident prevention solution for the elderly, the disabled, children and women using the drones. Drones' autonomous flight technology, obstacle detection technology, collision avoidance technology, wireless communication linkage technology, and real time image transmission technology. Through this, we have studied to enable safe activities in the blind spot of CCTV. In this paper, we have identified the problem of crime prevention system using existing CCTV system. To solve this problem, we have developed a safety accident prevention solution using drones. To this end, we designed the drones to enable real-time tracking by applying autonomous flight technology, obstacle avoidance technique, and object tracking technology. In addition, wireless communication between the object and the drone was applied to prevent flight deviation. And, it is designed to link emergency notification service through real-time video transmission during flight.

Download Full-text

The Effect of Sports Instructor's Safety Awareness and Safety Accident Prevention Activities on Sports Safety Culture

Korean Journal of Sports Science ◽

10.35159/kjss.2019.06.28.3.49 ◽

2019 ◽

Vol 28 (3) ◽

pp. 49-59

Author(s):

Kyung-Eun Lee ◽

Young-Shin Won ◽

Soo-Yeon Kim

Keyword(s):

Safety Culture ◽

Accident Prevention ◽

Safety Awareness ◽

Prevention Activities ◽

Safety Accident

Download Full-text

Real-time Track Obstacle Detection from 3D LIDAR Point Cloud

Journal of Physics Conference Series ◽

10.1088/1742-6596/1910/1/012002 ◽

2021 ◽

Vol 1910 (1) ◽

pp. 012002

Author(s):

Chao He ◽

Jiayuan Gong ◽

Yahui Yang ◽

Dong Bi ◽

Jianpin Lan ◽

...

Keyword(s):

Real Time ◽

Point Cloud ◽

Obstacle Detection ◽

3D Lidar

Download Full-text

Real-Time Monocular Obstacle Detection Based on Horizon Line and Saliency Estimation for Unmanned Surface Vehicles

Mobile Networks and Applications ◽

10.1007/s11036-021-01752-2 ◽

2021 ◽

Author(s):

Jingyi Liu ◽

Hengyu Li ◽

Jun Liu ◽

Shaorong Xie ◽

Jun Luo

Keyword(s):

Real Time ◽

Obstacle Detection ◽

Unmanned Surface Vehicles ◽

Horizon Line

Download Full-text

RSNet: Rail semantic segmentation network for extracting aerial railroad images

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-210349 ◽

2021 ◽

pp. 1-18

Author(s):

R.S. Rampriya ◽

Sabarinathan ◽

R. Suganya

Keyword(s):

Real Time ◽

Visual Processing ◽

Feature Fusion ◽

Semantic Segmentation ◽

Vital Role ◽

Obstacle Detection ◽

Aerial Images ◽

Computationally Efficient ◽

Fusion Algorithm ◽

Uav Images

In the near future, combo of UAV (Unmanned Aerial Vehicle) and computer vision will play a vital role in monitoring the condition of the railroad periodically to ensure passenger safety. The most significant module involved in railroad visual processing is obstacle detection, in which caution is obstacle fallen near track gage inside or outside. This leads to the importance of detecting and segment the railroad as three key regions, such as gage inside, rails, and background. Traditional railroad segmentation methods depend on either manual feature selection or expensive dedicated devices such as Lidar, which is typically less reliable in railroad semantic segmentation. Also, cameras mounted on moving vehicles like a drone can produce high-resolution images, so segmenting precise pixel information from those aerial images has been challenging due to the railroad surroundings chaos. RSNet is a multi-level feature fusion algorithm for segmenting railroad aerial images captured by UAV and proposes an attention-based efficient convolutional encoder for feature extraction, which is robust and computationally efficient and modified residual decoder for segmentation which considers only essential features and produces less overhead with higher performance even in real-time railroad drone imagery. The network is trained and tested on a railroad scenic view segmentation dataset (RSSD), which we have built from real-time UAV images and achieves 0.973 dice coefficient and 0.94 jaccard on test data that exhibits better results compared to the existing approaches like a residual unit and residual squeeze net.

Download Full-text

The Study and Application of the Nitrile Gloves’ Production Line’s Online Measurement

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.727-728.804 ◽

2015 ◽

Vol 727-728 ◽

pp. 804-808

Author(s):

Jian Jun Cai ◽

Jian Bing Han ◽

Su Qin Qu

Keyword(s):

Temperature Measurement ◽

Real Time ◽

Temperature Sensor ◽

Production Line ◽

Moving Objects ◽

Mold Temperature ◽

Configuration Software ◽

Online Measurement ◽

Line Process ◽

Tracking Technology

In order to solve the problem of the hand module’s online temperature measurement in Nitrile glove production line process, we have developed a set of moving objects or device used for online temperature measurement. The device is mounted infrared temperature sensor, by using PLC-controlled synchronous tracking technology it can track the hand module in the production line, so it can ensure the infrared temperature sensor and hand module synchronously measure its temperature correctly. By using configuration software kingview, we have developed mold temperature monitoring online measurement interface, real-time monitoring of the mold temperature opponents. After analysis of experimental results we concluded that the device work stable, acquisition of temperature reliably, so it has a promotional value.

Download Full-text

Transfusion Monitoring and Controlling System Based on Wireless Communication

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.214.579 ◽

2012 ◽

Vol 214 ◽

pp. 579-583

Author(s):

Jiang Ma ◽

Yu Qiao Wen ◽

Ling Yan Du ◽

Xiao Xiao Liang ◽

Chong Gang Wei

Keyword(s):

Communication Network ◽

Wireless Communication ◽

Real Time ◽

Wireless Transmission ◽

The Core ◽

Wireless Transceiver ◽

Controlling System ◽

Transceiver Module ◽

Medical Accident

Transfusion monitoring and controlling system of wireless communication is designed for avoidance of medical accident due to inconsiderate care. This system is based on RS-485 bus protocol to build the communication network, consisting of master computer and slave computer. STM32F103R8T6 MCU is the core of the master computer, and MSP430F2132 MCU for slave computer. The wireless transmission of data between master computer and slave computer can be done by nRF905 wireless transceiver module. One new calculation of drop speed is used for better real-time displaying thereof. Provided that abnormal occurrence is during the transfusion, the transfusion tube will be closed by controlling order from system, in order to protect the patient.

Download Full-text