Research Fellow
CurrentAs part of my work on an AI-based drone system, I was responsible for developing an object detection algorithm that could accurately identify and track objects in real-time. This was a critical component of the system, as it allowed the drone to navigate its environment safely and avoid collisions.To accomplish this, I used a deep learning approach, leveraging convolutional neural networks (CNNs) to train a model on a large dataset of images. The dataset consisted of various objects and backgrounds, including buildings, trees, people, and vehicles.After training the model, I tested it on a set of validation images to evaluate its performance. The results were promising, with the model achieving high accuracy in detecting and localizing objects in various environments and lighting conditions.I then integrated the object detection algorithm into the drone system, enabling it to detect and track objects in real-time during flight. This allowed the drone to adjust its flight path and avoid obstacles in its path, making it safer and more efficient.Overall, my work on the AI-based drone system object detection was a critical step in developing a more capable and intelligent drone system. It demonstrated the power of deep learning and its potential to revolutionize the way we approach aerial robotics.
