Flying Vehicle Attitude Determination through Optical Flow Interpretation by Neural Network

Please enable javascript in your browser.

Tasouji Zadeh Aghdam, Ramin | 2014

427 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 46478 (45)
University: Sharif University of Technology
Department: Aerospace Engineering
Advisor(s): Saghafi, Fariborz
Abstract:
Attitude estimation means calculating the state variables during the flight, especially in landing and takeoff phases. If we can extract the optical flow using the sensors mounted on the flying object, due to the fact that the optical flow is created by linear and rotational speed of the object relative to the surrounding, we are able to calculate the relative attitude by analyzing the optical flow. Indeed the purpose is developing this idea by using artificial neural networks.
First, we find the optical flow patterns for every attitude condition near the ground, using geometrical calculations. Then we produce an optimal neural network by these patterns. This network has the ability to estimate the attitude of flying object by recognizing the pattern created by the camera. In this thesis we use constant brightness, flat ground, and ideal camera assumptions for simplification.
In fact, in this project we are seeking a solution for navigation of flying vehicle near the ground that with reasonable accuracy can calculate the attitudes and velocities of the vehicle besides the existing navigation equipments
Keywords:
Neural Network ; Geometric Modeling ; Navigation ; Machine Vision ; Optical Flow

No TOC