Field line estimatore: Difference between revisions

From Control Systems Technology Group
Jump to navigation Jump to search
No edit summary
No edit summary
Line 1: Line 1:
World map line predictor
World map line predictor
The detection module needs a prediction module to predict the view that the camera on drone would have in each moment.  Because the localization method does not use image processing and there is no need to provide data of camera view other than side lines, the line predictor block just provides data of visible side lines, visible to drone camera.  
The detection module needs a prediction module to predict the view that the camera on drone would have in each moment.  Because the localization method does not use image processing and there is no need to provide data of camera view other than side lines, the line predictor block just provides data of visible side lines, visible to drone camera.
The input of the drone from other modules and predefined parameters are:
Altitude of drone (From drone IMU)
Drone position (From Localization block)
Camera vision angle (Predefined)
Yaw angle of the drone ( Sensor Fusion or IMU block)
 
The angle of vision of the camera is adjustable so that the module can be reused by different kinds of cameras.
The output of the module is a 4 by4 matrix that each row is correspondent to each side line. The side lines are named from 1 to 4 (A_11 , A_12,A_13,A_14) . Second column gives information about visibility of line for drone camera. If 1, visible and if 0 not in camera range.  Two last columns, ρ and theta, are line coordinates in Hough coordinate system.
 
<mathA=[■(1&0&ρ_1&θ_1@2&0&ρ_2&θ_2@3&0&ρ_3&θ_3@4&0&ρ_4&θ_4 )]</math>
 
In this block the output coordinates (Rho and Theta) are same as Matlab Hough transform coordinate system [1].
 
 
 
[1]: http://nl.mathworks.com/help/images/ref/hough.html?refresh=true

Revision as of 15:58, 31 March 2016

World map line predictor The detection module needs a prediction module to predict the view that the camera on drone would have in each moment. Because the localization method does not use image processing and there is no need to provide data of camera view other than side lines, the line predictor block just provides data of visible side lines, visible to drone camera.