Loading...

Design of a Module for Cross Checking Images from Quadrotor within a Refrence Image

Farahani, Ali | 2015

1010 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 47688 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Bagheri Shouraki, Saeed
  7. Abstract:
  8. Quadrotors are vertical take-off and landing (VTOL) aircrafts with high maneuver capabilities thanks to their four blades. They are widely used for various applications more than any other unmanned aircraft. Taking photos in military zones and industrial complexes is one such application. Due to the highly noisy radio and GPS (Global Positioning System) signals that are a characteristic of these environments, the task of controlling the quadrotors using them is impossible. An alternative approach that is employed in our research is the use of the aerial images from the on-board camera for autonomous navigation. To this end, we first obtain a reference image for the operation area. These images are freely available through services such as Google Earth. Then, our system performs localization of the images received from the on-board camera within the larger reference image if they are compatible (also known as image cross checking or image registration). There are various challenges posed by the image registration task such as differences in scales and orientations of the two images, non-identical cameras, images that are from different time snaps causing subtle variations such as changes to the roads and colors of leaves, and the time consuming searching and handling of the large reference image. All of these challenges amount to a complex image processing and machine vision problem which has remained largely unsettled. In this thesis, we have developed a novel method for this problem by combining fuzzy logic with current practices for image registration that can effectively address many of the aforementioned difficulties. Furthermore, we compare our method to the state of the art in image registration. In our comparison, we consider various performance metrics such as precision and computational complexity
  9. Keywords:
  10. Fuzzy Logic ; Quadrotor Helicopter ; Image Registration ; Aerial Image Cross Checking

 Digital Object List

 Bookmark

...see more