DRONE SURVEILLANCE SYSTEM USING RASPBERRY PI WITH HUSKYLENS CAMERA, WEB SERVER LINK, IOT, LIDAR, AND FOLLOW-ME INTEGRATED MODULE

Abstract

This project aims to design and implement an advanced drone surveillance system using the Raspberry Pi as the central processing unit. By integrating the HuskyLens camera, the system achieves real-time object detection and tracking with high accuracy. Remote monitoring and control are facilitated through an embedded web server, allowing seamless access from anywhere. Leveraging Internet of Things (IoT) technology, the system ensures enhanced connectivity and interoperability with other smart devices and networks. Precision environmental mapping and obstacle detection are enabled by LiDAR sensors, improving navigation safety and situational awareness. Furthermore, an autonomous “follow-me” module allows the drone to dynamically track and follow designated subjects without manual input, expanding its utility for various surveillance and security applications. This study will employ the Experimental Prototyping Methodology, which involves the systematic construction, testing, and iterative refinement of a prototype. Through continuous evaluation and modification based on performance results and feedback, the prototype is progressively improved until it meets the predefined criteria for functionality and quality. This iterative approach ensures that the final design is both effective and reliable, providing a robust foundation for the development and production of the complete system or product. The prototype underwent extensive testing to ensure all components operated smoothly within the integrated control system. Careful adjustments to wiring and cable management were implemented to prevent electrical faults, effectively mitigating the risks of short circuits and damage. Throughout both testing and production phases, the prototype consistently delivered reliable performance, establishing a strong foundation for future improvements and scalability. Survey feedback from evaluators in Brgy. Fairview, City of Quezon, showed a consensus rating of "Agree" or higher, demonstrating high acceptability and user satisfaction. These positive results confirm the system’s feasibility and readiness for wider deployment. The development of the drone surveillance system prototype begins with procuring key hardware components, including the Raspberry Pi as the central processor, HuskyLens camera for object detection, LiDAR sensor for precise distance measurement, follow-me modules using GPS and visual tracking, a drone platform, streaming camera, power supply, and mounting hardware. The setup process involves installing the Raspberry Pi OS and configuring essential libraries for seamless integration with peripherals.  Each component is individually validated to ensure optimal performance—HuskyLens for accurate object detection, LiDAR for reliable range measurement, and follow-me modules for precise tracking. The Raspberry Pi communicates with these devices through multiple protocols such as USB, GPIO, I2C, SPI, and UART, facilitating robust data transfer.  Custom Python scripts capture and process sensor data, extracting object details from HuskyLens, distance readings from LiDAR, and positional data from follow-me modules. The system’s core functionalities include advanced object tracking using filtering and prediction algorithms, LiDAR-based obstacle avoidance, autonomous follow-me capabilities combining GPS and visual tracking, and IoT integration via MQTT for real-time cloud logging and remote monitoring.  Hardware components are securely mounted on the drone, with reliable communication established between the Raspberry Pi and flight controller to coordinate flight operations. Performance evaluation focuses on detection accuracy, obstacle avoidance effectiveness, follow-me tracking stability, IoT communication reliability, and overall flight performance.  An iterative development approach enables ongoing refinement based on testing results. The initial phase emphasizes hardware assembly, stable inter-module communication, and implementation of basic autonomous features, providing a solid foundation for future enhancements