Image Generation for Efficient Neural Network Training in Autonomous Drone Racing

    Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review


    Drone racing is a recreational sport in which the goal is to pass through a sequence of gates in a minimum amount of time, while avoiding collisions. In autonomous drone racing, one must accomplish this task by flying fully autonomously in an unknown environment by relying only on computer vision methods for detecting the target gates. Due to the challenges such as background objects and varying lighting conditions, traditional object detection algorithms based on colour or geometry tend to fail. Convolutional neural networks offer impressive advances in computer vision, but require an immense amount of data to learn. Collecting this data is a tedious process because the drone has to be flown manually, and the data collected can suffer from sensor failures. In this work, a semi-synthetic dataset generation method is proposed, using a combination of real background images and randomised 3D renders of the gates, to provide a limitless amount of training samples that do not suffer from those drawbacks. Using the detection results, a line-of-sight guidance algorithm is used to cross the gates. In several experimental real-time tests, the proposed framework successfully demonstrates fast and reliable detection and navigation.

    Original languageEnglish
    Title of host publication2020 International Joint Conference on Neural Networks (IJCNN)
    Number of pages8
    Publication dateJul 2020
    Article number9206943
    ISBN (Electronic)9781728169262
    Publication statusPublished - Jul 2020
    Event2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom
    Duration: 19 Jul 202024 Jul 2020


    Conference2020 International Joint Conference on Neural Networks, IJCNN 2020
    Country/TerritoryUnited Kingdom
    CityVirtual, Glasgow


    • convolutional neural networks
    • deep learning
    • drone racing
    • semi-synthetic images generation
    • unmanned aerial vehicles


    Dive into the research topics of 'Image Generation for Efficient Neural Network Training in Autonomous Drone Racing'. Together they form a unique fingerprint.

    Cite this