A new occupancy index model based on artificial vision for enhancing beach management

Area of Science:

• Environmental Management
• Computer Vision
• Public Health

Background:

• Effective beach management requires monitoring user density and social distancing.
• Traditional methods for monitoring beach occupancy are often manual and labor-intensive.
• The need for real-time data on beach usage and crowd distribution is critical for public safety and resource allocation.

Purpose of the Study:

• To develop and validate a novel system for real-time beach occupancy monitoring.
• To introduce the Overcrowding Index (Iocr) and Distancing Index (Idis), combined into an Occupancy Index (Iocu).
• To assess the system's effectiveness in managing beach capacity and ensuring adequate social distancing.

Main Methods:

• Utilized cameras and computer vision algorithms (YOLOX, ByteTrack) for automated people counting and distance measurement.
• Developed and integrated the Overcrowding Index (Iocr) and Distancing Index (Idis) into a unified Occupancy Index (Iocu).
• Implemented a functional prototype for real-time calculation and display of beach occupancy indices.

Main Results:

• The Overcrowding Index (Iocr) demonstrated an inverse relationship with density, approaching zero at maximum capacity.
• The Distancing Index (Idis) was found to be low (0.18) even at medium densities near the shoreline, indicating failure to meet the 2m distance.
• The integrated Occupancy Index (Iocu) achieved a value of 0.31, validating the combined index approach.

Conclusions:

• The proposed artificial vision system accurately monitors beach user numbers and distribution.
• The developed indices provide a valuable tool for efficient beach management based on real-time occupancy.
• This technology enables proactive and data-driven decision-making for optimizing beach utilization and public safety.