Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
98 views

Vision Based Autonomous Landing of UAV

The document discusses developing vision-based algorithms for autonomous landing of an unmanned aerial vehicle (UAV). It aims to detect a helipad using image processing techniques like thresholding, filtering and segmentation to identify the target landing area. A control architecture is proposed to enable autonomous motion based on visual tracking and state estimation, moving beyond current systems that require manual control. The goal is to enable autonomous landing and reduce crashes due to human error in UAV control.

Uploaded by

Anurag Pandey
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
98 views

Vision Based Autonomous Landing of UAV

The document discusses developing vision-based algorithms for autonomous landing of an unmanned aerial vehicle (UAV). It aims to detect a helipad using image processing techniques like thresholding, filtering and segmentation to identify the target landing area. A control architecture is proposed to enable autonomous motion based on visual tracking and state estimation, moving beyond current systems that require manual control. The goal is to enable autonomous landing and reduce crashes due to human error in UAV control.

Uploaded by

Anurag Pandey
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

Mentor Prof.

Amitabha Mukerjee

Anurag Pandey

Nitish Sharma

UAV
Unmanned Aerial Vehicle
AR DRONE

Vision Based Helipad Detection Autonomous Landing

Previous Work
Unmanned
Vision based target tracking Manually controlled landing

Motivation
Crashes due to human error

Task

Vision Based Tracking

Control Architecture

Vision Algorithm
Thresholding and Filtering
Y = 0.299 * R + 0.596 * G + 0.211 * B

Segmentation and Connected Component Labelling Object Recognition and State Estimation

Vision Algorithm
Optical Character Recognition
Detecting the character H First, second and third moments are sufficient

Control architecture
AR.FreeFlight 2.0 Android App Controls Motion with Human Instructions Our Aim: Make it Autonomous

References
Vision-based Autonomous Landing of an Unmanned Aerial Vehicle by Srikanth

Saripalli', James E Montgomery and Gaurav S. Sukhatme in Proceedings of the 2002 IEEE International Conference on Robotics & Automation Washington, DC May 2002 landing an unmanned aerial vehicle, in In Proceedings of IEEE International Conference on Robotics and Automation, 2001, pp. 1720-1728.

Courtney S. Sharp, Omid Shakemia, and S.Shankar Sastry,A vision system for

R.Gonzalez and R.Woods, Digital Image Processing, Addison-Wesley, 1992. http://www.24-

7pressrelease.com/attachments/016/press_release_distribution_0169459_30112.jp g

http://willyloman.files.wordpress.com/2009/09/cid_post-impact_2.jpg Ryan Miller, Bemard Mettler, and Omead Amidi, camegie mellon universitys

1997 international aerial robotics competition entry, in International Aerial Robotics Competition, 1997.

QUESTIONS??

Thresholding
Threshold - 80% of between the minimum and

maximum gray scale values. Normalized value of 1 to pixel above threshold and 0 to one below threshold.

Filtering
7x7 Median filter for noise rejection Replaces each pixel value by the median of its

neighboring pixel values

Invariant Moments
The (p+q)th moment of an object f(x,y) is : The center of gravity of the object is specified by:

Central Moments about the centre of gravity is:

Object orientation is:

You might also like