Accessible Aerial Autonomy? Lilian de Greef, Brad Jensen, Kim Sheely Nick Berezny, Cal Poly Pomona '12 Malen Sok, Cal Poly Pomona '13 special guest star!

Slides:



Advertisements
Similar presentations
Distinctive Image Features from Scale-Invariant Keypoints
Advertisements

Complex Networks for Representation and Characterization of Images For CS790g Project Bingdong Li 9/23/2009.
Distinctive Image Features from Scale-Invariant Keypoints David Lowe.
Automatic Color Gamut Calibration Cristobal Alvarez-Russell Michael Novitzky Phillip Marks.
Presented by Xinyu Chang
Content-Based Image Retrieval
BRISK (Presented by Josh Gleason)
Human Identity Recognition in Aerial Images Omar Oreifej Ramin Mehran Mubarak Shah CVPR 2010, June Computer Vision Lab of UCF.
An appearance-based visual compass for mobile robots Jürgen Sturm University of Amsterdam Informatics Institute.
Introduction To Tracking
Database-Based Hand Pose Estimation CSE 6367 – Computer Vision Vassilis Athitsos University of Texas at Arlington.
Automatic Feature Extraction for Multi-view 3D Face Recognition
Computer Vision Detecting the existence, pose and position of known objects within an image Michael Horne, Philip Sterne (Supervisor)
Neurocomputing,Neurocomputing, Haojie Li Jinhui Tang Yi Wang Bin Liu School of Software, Dalian University of Technology School of Computer Science,
Nearest Neighbor. Predicting Bankruptcy Nearest Neighbor Remember all your data When someone asks a question –Find the nearest old data point –Return.
CMPT-884 Jan 18, 2010 Video Copy Detection using Hadoop Presented by: Cameron Harvey Naghmeh Khodabakhshi CMPT 820 December 2, 2010.
Patch Descriptors CSE P 576 Larry Zitnick
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
1998/5/21by Chang I-Ning1 ImageRover: A Content-Based Image Browser for the World Wide Web Introduction Approach Image Collection Subsystem Image Query.
Scale Invariant Feature Transform
3D Hand Pose Estimation by Finding Appearance-Based Matches in a Large Database of Training Views
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
FLANN Fast Library for Approximate Nearest Neighbors
Juan Guzman ASU Mentor: Shea Ferring. About Me Name: Juan Guzman Computer Science major ASU Senior (graduating December 2012) Have prior internship with.
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Hubert CARDOTJY- RAMELRashid-Jalal QURESHI Université François Rabelais de Tours, Laboratoire d'Informatique 64, Avenue Jean Portalis, TOURS – France.
Circular Augmented Rotational Trajectory (CART) Shape Recognition & Curvature Estimation Presentation for 3IA 2007 Russel Ahmed Apu & Dr. Marina Gavrilova.
Driver’s View and Vehicle Surround Estimation using Omnidirectional Video Stream Abstract Our research is focused on the development of novel machine vision.
CS 376b Introduction to Computer Vision 04 / 29 / 2008 Instructor: Michael Eckmann.
Knowledge Systems Lab JN 9/10/2002 Computer Vision: Gesture Recognition from Images Joshua R. New Knowledge Systems Laboratory Jacksonville State University.
CS 5 for all! Bridgette Eichelburger ’14, David Lingenbrink ‘14, Yael Mayer ‘11, Obosa Obazuaye ‘14, Becca Thomas ‘14, Maia Valcarce ‘13, Joshua Vasquez.
Tracking with Unreliable Node Sequences Ziguo Zhong, Ting Zhu, Dan Wang and Tian He Computer Science and Engineering, University of Minnesota Infocom 2009.
PR2 Christian Sanchez MIS 304. PR2 Video Willow Garage Research lab in Menlo Park, California Develop hardware and open source software (for personal.
Generalized Hough Transform
Submitted by: Giorgio Tabarani, Christian Galinski Supervised by: Amir Geva CIS and ISL Laboratory, Technion.
NSF Engineering Research Center for Reconfigurable Manufacturing Systems University of Michigan College of Engineering Reconfigurable System for Turbine.
Tool Integration with Data and Computation Grid GWE - “Grid Wizard Enterprise”
A Two-level Pose Estimation Framework Using Majority Voting of Gabor Wavelets and Bunch Graph Analysis J. Wu, J. M. Pedersen, D. Putthividhya, D. Norgaard,
CS332 Visual Processing Department of Computer Science Wellesley College Binocular Stereo Vision Region-based stereo matching algorithms Properties of.
21 June 2009Robust Feature Matching in 2.3μs1 Simon Taylor Edward Rosten Tom Drummond University of Cambridge.
Autonomous Navigation Based on 2-Point Correspondence 2-Point Correspondence using ROS Submitted By: Li-tal Kupperman, Ran Breuer Advisor: Majd Srour,
Object Recognition in ROS Using Feature Extractors and Feature Matchers By Dolev Shapira.
Robotics Club: 5:30 this evening
Graphs David Johnson. Describing the Environment How do you tell a person/robot how to get somewhere? –Tell me how to get to the student services building…
One reason for this is that curricular resources for robot mapping are scarce. This work fills the gap between research code, e.g., at openslam.org, and.
Autonomous Robots Vision © Manfred Huber 2014.
COMP 417 – Jan 12 th, 2006 Guest Lecturer: David Meger Topic: Camera Networks for Robot Localization.
CSE 185 Introduction to Computer Vision Feature Matching.
MIT AI Lab / LIDS Laboatory for Information and Decision Systems & Artificial Intelligence Laboratory Massachusetts Institute of Technology A Unified Multiresolution.
Tool Integration with Data and Computation Grid “Grid Wizard 2”
Optic Flow QuadCopter Control
Frank Bergschneider February 21, 2014 Presented to National Instruments.
Accessible Aerial Autonomy via ROS Nick Berezny ’12, Lilian de Greef ‘12, Brad Jensen ‘13, Kimberly Sheely ‘12, Malen Sok ‘13, and Zachary Dodds Tasks.
Recognizing specific objects Matching with SIFT Original suggestion Lowe, 1999,2004.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
Distinctive Image Features from Scale-Invariant Keypoints Presenter :JIA-HONG,DONG Advisor : Yen- Ting, Chen 1 David G. Lowe International Journal of Computer.
SIFT.
April 21, 2016Introduction to Artificial Intelligence Lecture 22: Computer Vision II 1 Canny Edge Detector The Canny edge detector is a good approximation.
Face Detection and Notification System Conclusion and Reference
VEX IQ Curriculum Smart Machines Lesson 09 Lesson Materials:
SIFT Scale-Invariant Feature Transform David Lowe
Paper – Stephen Se, David Lowe, Jim Little
Lecture 26 Hand Pose Estimation Using a Database of Hand Images
Simultaneous Localization and Mapping
PixelLaser: Range from texture
PixelLaser: Range from texture
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
CAP 5415 Computer Vision Fall 2012 Dr. Mubarak Shah Lecture-5
SIFT.
Presentation transcript:

Accessible Aerial Autonomy? Lilian de Greef, Brad Jensen, Kim Sheely Nick Berezny, Cal Poly Pomona '12 Malen Sok, Cal Poly Pomona '13 special guest star! Steve Matsumoto, HMC '12

Motivation Key lesson: Neither all drones – nor all programmers – are created equal

Question Does the ARDrone make an effective robot?

Question Does the ARDrone make an effective robot? Raw material: Goal: accomplish tasks with the drone, the create, and computer vision closed hardware but an open, ASCII API two cameras internal sensing (gyro/accel.)

blind-enord.py OpenCV FLANN for nearest neighbors pydrone libardrone ARDrone msg srv arnetwork generic API/ framework too low level for our needs Other ROS facilities ROS ~ Robot Operating System

i Several tasks tried... (0) Room/hallway flying (1) Cooperating with the Create (2) Navigating among landmarks (3) Localization without landmarks (4) Room/hallway flying

Task 1: Follow that ! We put a ! on the Create to help discern location help discern orientation Image processing approach: (1) threshold image to find dark regions and contours (2) circle? compare region with min. enclosing circle (3) rectangle? compare region with min. enclosing rect. (4) filter noise, find centers, and construct heading line

! finding

GCER!

GCER cooperation demo

Lessons learned The ! was far from a perfect landmark We wanted to use something more robust that could give us more accurate pose estimation We decided to explore April Tags...

APRIL tags Autonomy, Perception, Robotics, Interfaces, and Learning Java-based landmark library from U. Michigan We integrated it into ROS using Python's os.system call... an example tag in the center...provides full 6 DOF pose and scale

APRIL tags' scale range an example tag in the center...provides full 6 DOF pose and scale

Task 2: The Hula-hoop hop Getting from A to B A B

getting from point A to point B Task 2: The Hula-hoop hop

Hula-hop's state machine all transitions can also be made by the keyboard

Hula-hop demo sliding-scale autonomy is crucial

Hula-hop challenges Drone challenges: drift ~ not easily positionable connection ~ video freezes artifacts ~ image stream noise APRIL tag challenges: too narrow a field of view: height/scale tradeoffs call to APRIL library is slow (.5 second/image) unmodifiable environments? Could we do without tags? example encoding (?) artifact

Localization without tags? SURF features locally unique image patches fast libraries for extraction each SURF feature is described by a 64- or 128-dimensional vector that encodes size and local edge orientations in general, similar descriptor vectors are likely to be similar (or identical) image features SURF features are great for place-recognition training!

Localization plan? Mapping (by hand) collect images and positions extract & store SURF features Localization take a new image extract SURF features match them against the map estimate a pose distribution new image map images + matches

Image-based map... Locations with stored images == nodes in a graph four locations in the NW corner of Sprague

Image-based map... beside the kitchen, facing roughly W

Image-based map... beside the boardgames, facing roughly N

Live localization top three matches and their likelihood distribution plotted on the map

Demo...

Results Simply counting the # of matches did not yield good localization results: < 25% of correct locations < 10% of correct orientations matches m  simple image-match score 1

Other scoring systems... matches m  distance-scaled score 1  + dist(m)... and filters bidirectional matches only strong ratio-matches only weights features inversely proportional to their SURF distance omits features whose nearest neighbor is about as good a match as its 2 nd nearest neighbor omits features whose best match is not unique in both directions

Without bidirectional filtering many different features can have the same best match

With bidirectional filtering only mutually unique best matches are considered

Comparative results

The AR Drone is a capable platform -- as long as precise positioning is not required Options include o research to improve localization o tasks that do not require precision The ROS software scaffolding is excellent -- (though not always thoroughly documented) The project's AR Drone drivers and supporting software generated interest at AAAI and will be released into the community's (Willow Garage's) repository. Comparative results

Thoughts or comments? i

AR Drone Mechanics Drone itself has only 4 degrees of freedom. (roll, pitch, yaw, thrust) Commands give us control of 4 different degrees of freedom. (x, y, z and yaw) Roll Yaw Key lesson learned: The drone is NOT precisely positionable.