Some public areas like beaches are crowded during the weekends and are tedious to manage with a limited number of authorities. People in these places are prone to danger. Aside from cases of drowning, there have also been reports of suicide on beaches. Other mischievous or dangerous activities (e.g., theft) happen in such places. Most of these incidents happen when the crowd is bigger and those in charge of surveillance will find it challenging to monitor on the ground. The proposed solution is to build a deep learning‐based model for the detection of drowning in the sea or any swimmers taken into sudden high waves. We will be using thermal images from the drone and extracting the features of humans, the model is trained to detect those large sets of images. So, once a person moves away from the safety swimming line on the beach, the system will alert the persons near the shoreline and the coast guards. We will also use the posture estimation model to detect miscellaneous activities and take pictures and alert the officials to take action. This drone will be self‐automated based on its set boundary and it will map with GPS integration. With this, we can avoid untoward activities from happening with smart surveillance using drones.
AI‐Based Smart Surveillance for Drowning and Theft Detection on Beaches Using Drones
Drone Technology ; 243-256
2023-05-22
14 pages
Article/Chapter (Book)
Electronic Resource
English