• Dr. Timothy Smith

The Lifeguard that Never Takes Its Eyes Off the Water

Kid Jumping in the Pool

Photo Source: Max Pixel

Summertime promises hot days and warm evenings that we often spend enjoying the pool or beach. For all the joy and pleasure pools and beaches bring, danger comes along as well. The rate of accidental death due to drowning in the United States averaged over 3,900 per year between 2007 to 2017, according to Centers for Disease Control and Prevention’s WISQARS data. (cdc.gov) Moreover, the most chilling number indicates that children under the age of four are twice as likely than other age groups to drown. Most drownings among children up to four years of age occur in home swimming pools. Such statistics drive the need for improved water safety applications, and new technologies that benefit from artificial intelligence offer new types of protection for home and public pools.

A number of commercially available alarms alert users when a person or an animal has fallen into the pool by measuring disturbances or waves on the surface of the pool. For example, the Pool Patrol PA-30 Pool Alarm floats in a pool and will sound an alarm when it detects the waves made when someone falls into the pool. Pool Patrol retails for around $180. When it does detect a person or an animal entered the pool, it also sends an alarm to a wearable receiver. Another wave detection system made by SmartPool called the PoolEye PE23 ($150) detects objects weighing 15 lbs or more entering the pool using surface and subsurface wave detection.

The wave detection pool safety alarms work on the simple principle that objects, animal or not, will make waves when entering a pool, but they do not differentiate between the ripples caused by someone safely enjoying the water from a person or animal struggling not to drown in the water. More advanced monitoring systems use artificial intelligence to detect the signs of drowning and send an alert to a remote receiver. The Coral Manta 3000, which sells for $2000, uses artificial intelligence and an underwater camera that watches for the signs of drowning such as a person sinking to the bottom of the pool. The system also continues to learn. The user can tell the system when it has sounded a false alarm, and the machine learns to ignore what triggered it.

A more advanced artificial intelligence-based system that uses machine vision, sound, and movement detection to monitor for the signs of struggling in water costs significantly more. Selling for around $100,000, the AI based system manufactured by Maytronics LTD called Poseidon, uses cameras both above and inside the pool. (poseidonsaveslives.com) According to the company, Poseidon, designed to work with lifeguards, continuously monitors all swimmers individually and simultaneously in a pool and will sound an alarm and show a lifeguard where in the pool a person may be drowning. Lifeguards face the challenges of a monitoring a busy pool full of people. They must differentiate between the splashing, yelling, and diving to the bottom of the pool that swimmers usually do. Poseidon distinguishes between such activities and dangerous but similar ones. For example, Poseidon will wait 10 seconds before sounding an alarm if a swimmer stays at the bottom of the pool. Additionally, with the underwater cameras Poseidon does not have the problem of glare that lifeguards sitting above the water do.

Summer fun in the sun often involves being around water either at a pool or the beach, but the increased exposure to water increases the chance of drowning especially for young children. Vigilant lifeguards and parents remain the front line of defense against drowning. In spite of the best intentions, thousands of drownings happen every year in the US alone. New technologies such as surface and subsurface wave detection can send an alert when something enters a pool. Such products add a layer of safety for home pool owners to signal if a person or animal accidentally falls into the pool. More sophisticated systems use artificial intelligence to monitor disturbances in the pool. Such systems use computer vision and analysis to determine if the actions of swimmers look like drowning as opposed to the normal activities of people in the pool. The advanced Poseidon system works to enhance the capabilities of lifeguards by giving them eyes both above and below the water. Have fun with the summer and remember that an alarm marks only the first step in water safety, and we will always need lifeguards and vigilant people to save lives.

Dr. Timothy Smith

Dr. Smith’s career in scientific and information research spans the areas of bioinformatics, artificial intelligence, toxicology, and chemistry. He has published a number of peer-reviewed scientific papers. He has worked over the past seventeen years developing advanced analytics, machine learning, and knowledge management tools to enable research and support high level decision making. Tim completed his Ph.D. in Toxicology at Cornell University and a Bachelor of Science in chemistry from the University of Washington.

You can buy his book on Amazon in paperback and in kindle format here.

How to Profit and Protect Yourself from Artificial Intelligence