Image Processing on Drone
Lorant Andras Szolga · IntechOpen eBooks · 2025
A new drone-based image processing technique for item and human detection is presented in this work. Unlike previous methods that relied on a steady network connection for optimal results, a Raspberry Pi 4 module was installed on the drone for local processing and detection. In the first investigation, a lightweight drone was constructed using some of the most advanced racing components, specifically chosen to meet particular needs. Convolutional neural networks and TensorFlow Lite were used in the second stage to develop a computationally efficient detection method on the Raspberry Pi. Multiple objects in a single image might be detected in a single algorithm iteration thanks to the chosen algorithm, Single Shot Detection (SSD). To securely mount the drone’s battery, Raspberry Pi module, and additional battery, a container was created and 3D printed.