Abstract
The video taken from unmanned aerial vehicles are usually not stabilized by dynamic conditions of the camera platform. This paper presents an improved solution for video stabilization of aerial vehicles by combining “scale invariant feature transform (SIFT)” with “log-polar transform”. The input video frame is transformed into log-polar that provides extended scale and rotation invariance. Afterward, key-points are extracted using the SIFT method and tracked in consecutive frames to eliminate the unwanted motion in a video. Hence, the presented technique performs better even if the object’s scale and orientation vary in video frames when unmanned aerial vehicles change its altitude and orientation during the flight. The results of SIFT and log-polar method are compared with the standard SIFT-ME algorithm to analyze the scale and rotation invariance capability for video stabilization. The proposed technique shows the better capacity to stabilize video even when the UAV changes its attitude and orientation (i.e. scale change tolerance: 44.5% and Rotation tolerance: 53%).
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
