The Silicon Review
Drowning incidents are increasing and are considered the third leading cause of unintentional injury and death. Several companies have utilized AI technologies, to prevent drowning incidents. Although there have been various regulations put into place to reduce drowning accidents in some countries, communities still experience many drowning incidents. These real-time systems will track swimmers in a pool using machine learning techniques and prevents drowning accidents is proposed. The rapid development in both Internet of Things technologies and artificial intelligence algorithms has attracted the attention of many companies seeking to design and develop intelligent drowning detection systems.
Coral Detection Systems is one such AI-based drowning detection system for residential swimming pools. The company offers a unique video-analytics-based drowning detection system designed for private pools. The system uses an underwater camera and advanced software that alerts users when a potential drowning is detected. Coral's patent-pending system consists of a pool unit, in-home alarm unit, and smartphone app. The pool unit uses an underwater camera and proprietary software to track people and objects in the pool and detect drowning risks. The Coral system constantly looks for drowning events. Only when it detects a child or adult at risk of drowning will it generate alarms, locally, through the in-home alarm unit, and to the user's smartphone.
CORAL MANTA 3000 – The Smartest Drowning Detection System
CORAL MANTA 3000 is the first and only computer vision based drowning detection system for residential swimming pools. This innovative drowning detection system uses Artificial Intelligence technology to track everyone in the pool and detect risk of drowning 24/7. The system is powered by solar energy. Existing pool safety devices such as fences, pool covers or mechanical alarms merely attempt to prevent unauthorized access to the pool. But they become useless when someone is already in the pool (whether authorized or not). In contrast, CORAL MANTA "watches" the pool 24/7 when there are people in the pool and when the pool is not in use. Moreover, while existing alarms require you to deactivate and reactivate when using or exiting the pool, with CORAL MANTA you do not need to worry about forgetting to activate or deactivate, covering or uncovering, locking or unlocking anything.
CORAL MANTA 3000 is on the lookout nonstop, day and night. The system constantly monitors the pool with its built-in underwater video camera, using computer vision and artificial intelligence technology and is programmed to detect people in the pool as well as their position and motion. Using this technology it constantly analyzes the real time video that it captures from the underwater camera and whenever it identifies a near drowning event it generates an alarm. Simultaneously and just in case you are not around, it is sending alerts to all household members via their smart-phones / tablets.
CORAL MANTA is using Artificial Intelligence technology that constantly continues to "learn" and improve, and even to adjust to your own pool and comes out of the box with a lot of "knowledge" that enables it to detect most drowning events, while generating minimum false alarms. But, your pool may have different and unique features that CORAL MANTA never "saw" before. Thus, in the first couple of weeks, it may generate more false alarms than usual. When there is a false alarm, using your App, you can tell CORAL MANTA to ignore it, and this is how it learns and the rate of false alarms will drop dramatically to close to zero.
The Leader Upfront
Tamar (Fortuna) Avraham, co-founder serves as the Chief Technology Officer of Coral Detection Systems. She has over 20 years of experience in developing image processing and computer vision algorithms and software.
Tamar has a B.Sc. (summa-cum-laude) and a Ph.D. from the Technion.