Water Motion Safety Recognition and Monitoring System Based on the Wireless Signal Transmission

Abstract

Motion process monitoring is the core component of motion state analysis system and motion safety assurance system. For the water sport, implementation of monitoring is directly related to the safety and security of sportsmen, which is more significant. This paper presents a kind of underwater sports safety monitoring system based on radar idea. The system consists of four parts: video acquisition, image processing, data sample comparison and signal transmission. Reasonable cameras are used to capture the whole swimming pool, and then the motion information parameters of the swimmers are obtained by image segmentation and tracking, and compared with the standard drowning behavior parameters, so as to determine whether the swimmers are drowning or not. If it is judged that a person may be drowning, the system will send out a corresponding rescue signal, which will quickly alert and notify rescuers through the wireless signal transmission system, so as to rescue those who may be drowning, so as to enhance the safety of people’s movement in the water. The drowning behavior is identified by the established drowning feature data sample set, which avoids the occurrence of invisible drowning events that are difficult to detect. By using the high-speed DSP, the data processing and alarm system’s timely response can be realized, which greatly shortens the rescue time, directly improves the survival probability of drowning and reduces the physiological damage. The design of the monitoring system will eventually help the lifeguards to complete the task of underwater movement safety.

Exercise fatigue diagnosis method based on short-time Fourier transform and convolutional neural network

“…Exercise duration on the other hand only applies to sustained aerobic activities like track and field or cycling. For discontinuous and fixed-position training like weight-lifting, indicators such as respiratory rate, heart rate and exercise duration are not applicable, and it is difficult to obtain an accurate result only with them ( Gatti et al, 2014 ; Yang et al, 2019 ; Huang et al, 2020 ; Gundogdu et al, 2021 ).…”

“…In recent years, researchers have turned their attention to other more informative physical indicators for detecting fatigue during exercise ( Garcia-Garcia et al, 2016 ; Chai et al, 2019 ; Yang et al, 2019 ). Padhmashree and Bhattacharyya, (2022) used multi-channel EEG signals and extract features for emotion recognition.…”