Abstract
In this work, we propose an infrared visual inertial odometry (VIO) algorithm for unmanned aerial vehicles (UAV) for both daytime and nighttime. It utilizes images from a single downward-looking thermal camera, and uses a laser scanner to measure relative distance to determine the scale factor. The scale recovery process consists of a comprehensive logic flow to try out measurements into a homography decomposition with a multi-plane constraint, obtaining the results with minimum error, making the algorithm more robust. Moreover, other modifications, such as keyframe idea and pruning KLT tracker with sub-regions further improves the performance. Besides, the results are fused with an on-board IMU through an EKF-based sensor fusion framework. This infrared visual inertial odometry algorithm can still navigate UAVs during the missions when GPS is down or not reliable or under poor illumination condition.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.