Smart Multi Sensor Marine Security & Surveillance System

The proposed Smart Multi Sensor Marine Security & Surveillance System provides an integrated approach to intelligent marine monitoring by combining embedded systems, IoT communication, multi-sensor data acquisition, computer vision, and AI/ML-based object detection. The ESP32-based system collects and processes information from the camera, GPS, IMU, distance, environmental, and water-level sensors, while Wi-Fi and 4G/LTE enable real-time transmission of sensor data, location, video, and alerts to a centralized dashboard. The integration of multiple sensors and AI-based object detection can improve situational awareness and assist in identifying potentially suspicious marine objects. The proposed system also provides simulated response mechanisms using a buzzer, LED indicators, servo motor, and searchlight for demonstration purposes. Overall, the system demonstrates the potential of integrating IoT, sensor fusion, AI/ML, embedded systems, and real-time communication for marine security and surveillance. Future development can focus on extensive real-world testing, improved AI models, reliable communication under marine conditions, optimized power consumption, larger marine datasets, and advanced sensor-fusion techniques.

[1]G. Xu, Y. Shi, X. Sun, and W. Shen, “Internet of Things in Marine Environment Monitoring: A Review,” Sensors, vol. 19, no. 7, p. 1711, 2019. doi: 10.3390/s19071711. MDPI [2]               W. Zhang et al., “Survey on Deep Learning-Based Marine Object Detection,” Journal of Advanced Transportation, vol. 2021, Article ID 5808206, 2021doi: 10.1155/2021/5808206. Wiley Online Library [3]               G. Potamos, E. Stavrou, and S. Stavrou, “Enhancing Maritime Cybersecurity through Operational Technology Sensor Data Fusion: A Comprehensive Survey and Analysis,” Sensors, vol. 24, no. 11, p. 3458, 2024. doi: 10.3390/s24113458. MDPI [4]      “Ship Detection of Unmanned Surface Vehicle Based on YOLOv8,” 2024 IEEE 13th Global Conference on Consumer Electronics  (GCCE),    2024.doi: 10.1109/GCCE62371.2024.10760724. DOI [5]            “YOLOv8 Neural Network Application for Noncollaborative Vessel Detection Using Sentinel-1 SAR Data: A Case Study,” IEEE Geoscience and Remote Sensing Letters, vol. 22, 2024. doi: 10.1109/LGRS.2024.3508462.IEEE Xplore [6]               “Vessel Detection Leveraging Satellite Imagery and YOLO in Maritime Surveillance,” Remote Sensing Applications: Society and Environment, vol. 40, Article 101730, 2025. doi: 10.1016/j.rsase.2025.101730. ScienceDirect [7]               J. Mu et al., “M2S-YOLOv8: Multi-Scale and Asymmetry-Aware Ship Detection for Marine Environments,” Sensors, vol. 26, no. 2, p. 502, 2026. doi: 10.3390/s26020502.