Automated Water Operations Using Image-Based Occupancy Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aquatic facilities like swimming pools face challenges in managing freshwater usage efficiently due to the difficulty in tracking the number of swimmers, leading to either under or over-addition of water, resulting in waste and non-compliance with health regulations.
Innovation Solution
An automated system using machine learning models to monitor occupancy, water level, and turbidity through image processing, which controls water flow regulators to add or drain water based on real-time data, ensuring compliance with health codes and minimizing water and energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If manual tracking of swimmer numbers is used, then staffing costs are reduced, but water management precision deteriorates leading to under or over-addition of water
Solution Approach 1:
The patent replaces manual mechanical counting methods with an automated optical detection system using cameras and machine learning algorithms. The system captures images of the pool area, processes them through trained detection models to identify and count swimmers, and automatically controls water flow based on the detected occupancy numbers, eliminating the need for manual tracking while improving water addition accuracy.
Solution Approach 2:
The system enables self-service operation where the automated detection and control system manages water addition without human intervention. The machine learning model independently processes camera feeds, determines swimmer counts, and adjusts water flow regulators accordingly, allowing the facility to operate with reduced staffing while maintaining compliance with health regulations.
2Reliability
If over-addition of water is performed to ensure compliance, then health regulation compliance is maintained, but water and energy waste increases
Solution Approach 1:
The system implements a closed-loop feedback mechanism where the machine learning model continuously monitors swimmer occupancy in real-time and dynamically adjusts water flow regulator commands based on the detected numbers. This precise feedback control ensures that water is added only to the extent required by health regulations, preventing both under-addition and over-addition, thereby maintaining compliance while eliminating unnecessary water and energy waste.
Solution Approach 2:
The system transitions from static, predetermined water addition schedules to dynamic, real-time adjustment based on actual swimmer occupancy. The water flow regulator commands are continuously modified according to the current number of swimmers detected by the machine learning model, allowing the system to adapt to changing conditions and optimize water and energy usage while ensuring ongoing compliance.
3Reliability
If frequent water addition is performed, then water quality is maintained, but energy consumption increases
Solution Approach 1:
The system implements periodic monitoring and control actions based on actual occupancy patterns rather than continuous operation. The machine learning model processes camera feeds at intervals to detect swimmer numbers, and water flow regulators are activated only when and if needed based on these periodic assessments. This periodic action maintains water quality through timely additions while minimizing energy consumption by avoiding continuous or unnecessary pump operation.
Data Source
AI summary
There is provided systems and methods for automated water operations for aquatic facilities using at least one image captured of the aquatic facilities. A method includes: receiving an input signal including a detected number of occupants in the water at the aquatic facilities, the number of occupants determined using a trained detection machine learning model, the detection machine learning model receiving the captured image with an associated feature map as input, and outputting a detection of each occupant in the water, the water level machine learning model trained using training images each including a respective label for each occupant in the training image; determining a volume of water to add by multiplying the number of occupants by a predetermined volume of freshwater to add per occupant; and directing one or more water flow regulators to permit inflow of water approximately equivalent to the volume of water to add.