Authors
ABDELAZIZ MOHAMED, AHMED MOHAMED, KHALED LOAY, ESLAM MAGDY, DR. MUSTAFA ABDULSALAM, ENG. MENNA GAMIL
Publishing Date
28-OCT-2020
Abstract
Nowadays swimming pools is considered one of the main luxuries in the world right now and can be found in clubs, residents, hotels, and schools. Most of these places have a lifeguard to keep an eye on swimmers and rescue them if an accident happens but lifeguards always face difficulties like swimmers who drown in blind spots, So we propose a system based on IOT technology that classifies swimmers behavior underwater and switches on alerts if the system detects a drowning behavior. The system consists of main 3 nodes. The camera captures videos underwater with microcontroller “nividea jetson”. As a result,Drowning is detected using machine learning, image processing techniques and CNN . Finally, a mobile message notification will be sent to the medical support account on the mobile application and additionally, a light alarm will alert the pool.
1.1 Purpose of this document
THE PURPOSE OF THIS SOFTWARE OF THIS SOFTWARE SPECIFICATION DOCUMENT IS TO ILLUSTRATE DROWNING DETECTION SYSTEM. THE DROWNING DETECTION SYSTEM
WILL DETECT POSSIBLE DROWNING IN THE EARLY OR LATE STAGE OF DROWNING BY USING UNDERWATER CAMERA TO CAPTURE THE VIDEO WITH THE SWIMMERS AND PASS
EACH FRAME TO THE CNN~CITE{LI2016SURVEY} ALGORITHM TO CLASSIFY EACH OF THEM. OUR AIM HERE TO HELP LIFEGUARDS AND MEDIC TEAMS IN CLUBS, HOTELS
OR ANY PLACE WITH SWIMMING POOLS TO GET ATTENTION FOR ANY POSSIBLE DROWNING. THIS DOCUMENT WILL REPRESENT A FULLY AND DETAILED DESCRIPTION
ABOUT EACH STAGE OF INPUT AND OUTPUT AND ALGORITHMS THAT USED IN EACH STAGE WITH ILLUSTRATION OF THE HARDWARE, AND SOFTWARE REQUIREMENTS.
1.2 Scope of this document
THE PROJECT AIMS TO HELP IN DECREASING DROWNING VICTIMS BY DETECTING THE DROWNING IN AN EARLY STAGE AND THE SYSTEM IS BASED ON REAL-TIME SO
WHEN THE DROWNING HAPPENS IMMEDIATELY THE LIFEGUARD WILL RECEIVE AN ALERT AND WILL BE ABLE TO SEND A REPORT TO THE MEDIC TEAM FOR ANY FURTHER
ACTIONS.
1.3 System Overview
THE SYSTEM CONSISTS OF 5 DIFFERENT CONNECTED NODES :
A CAMERA TO CAPTURE THE VIDEOS UNDERWATER AND LINKED TO A NVIDIA JETSON NANO.
A NVIDIA JETSON NANO TO SEND DATA TO THE CLOUD SERVER AND IT WILL BE LINKED WITH CAMERA, CLOUD SERVER AND LIGHT ALARM.
A CLOUD SERVER TO STORE USERS DATA AND RECEIVE RESULTS FROM THE NVIDIA JETSON NANO.
A LIGHT ALARM TO OPERATE WHENEVER IT GET SIGNALS FROM THE LINKED NVIDIA JETSON NANO.
A MOBILE APPLICATION TO RECEIVE NOTIFICATION MESSAGE SENT BY THE LINKED CLOUD SERVER.
THE CAMERA IS USED TO CAPTURE A VIDEO UNDERWATER AND IT WILL BE CONNECTED TO A NVIDIA JETSON NANO. IN THE PROCESSING,
THE VIDEO WILL BE ANALYZED TO DETECT ANY POSSIBLE DROWNING BEHAVIOR AND CLASSIFY IT’S TYPE USING CLASSIFICATION ALGORITHMS
LIKE CNN, WHENEVER IT DETECTS POSSIBLE DROWNING THE JETSON WILL SEND THE RESULT TO CLOUD SERVER THAT WILL SEND A NOTIFICATION
TO THE LIFE GUARD MOBILE APPLICATION AND THE NVIDIA JETSON NANO WILL OPERATE A LIGHT ALARM.
1.4 System Scope
THE SYSTEM SHALL DETECT AND TRACK SWIMMERS USING A CAMERA PLACED UNDERWATER.
THE SYSTEM SHALL DETECT THE DROWNING BEHAVIOR OF THE SWIMMER.
THE SYSTEM WILL HAVE MEDICAL SUPPORT USERS.
THE SYSTEM WILL ALERT THE LIFEGUARDS WHENEVER THE PROBABILITY OF SOMEONE DROWNING IS HIGH.