logo
Social Media
twitter
youtube

  • Home
  • Team
  • Vehicles
    • SubjuGator 9
    • SubjuGator 8
    • SubjuGator 7
    • SubjuGator 6
    • SubjuGator 5
    • SubjuGator 4
    • SubjuGator 3
    • SubjuGator 2 (Coming Soon)
    • SubjuGator 1 (Coming Soon)
  • Press
  • Sponsors
    • Sponsors 2022
    • Sponsors 2021
    • Sponsors 2020
    • Sponsors 2019
    • Sponsors 2018
    • Sponsors 2017
    • Sponsors 2016
    • Sponsors 2015
    • Sponsors 2014
    • Sponsors 2013
    • Sponsors 2012
  • Blog
  • Outreach
  • Media
  • Contact Information



Begining Stages of Machine Learning

Mar 23, 2016
by SubjuGator
Comments are off

This Week We

  • Made a tool for segmenting training data
  • Experimented with using an SVM for segmentation
  • Worked on stuff for easily segmenting/labelling planes in PCL
    • + distinguishing things “on top” of the plane from the plane itself
The training tool: The plot on the right is HSV->XYZ. You draw a box around the desired color groups, and use the resulting segmentation.

This is less annoying than manually drawing on images.

easy_labeller

A SVM was trained on the segmentation data and it ran in ~near~ real-time on a super downsampled input image.
This is one frame of the SVM running on the video. It was just a 2-second demo, the threshold segmentation looks a lot better.
Sci-kit learn’s svm implementation struggles to fit at more than 10k samples, which is another problem.
svm_trainer
About the Author
Social Share

Categories

  • Competition News (10)
  • Sponsorship News (3)
  • Team News (61)

Tag Cloud

anodized assembly auvsi battery pods buoy calibration cnc competition computer controller dvl ethernet fischer grabber gumstix hydrophone imu JDSquared kona kai manufacturing merge board motor drivers navigation navigation computer new paper pcb pipe pool power rain robosub shipping shooter testing thruster thrusters trajectory generator travel trays tuning Twitter videoray website wiring

About Us

The Machine Intelligence Laboratory (MIL) provides a synergistic environment dedicated to the study and development of intelligent, autonomous robots. The faculty and students associated with the laboratory conduct research in the theory and realization of machine intelligence covering topics such as machine learning, real-time computer vision, statistical modeling, robot kinematics, autonomous vehicles, teleoperation and human interfaces, robot and nonlinear control, computational intelligence, neural networks, and general robotics. Applications of MIL research include autonomous underwater vehicles (AUVs), autonomous water surface vehicles (ASVs), autonomous land vehicles, autonomous air vehicles (AAVs including quadcopters and micro air vehicles, MAVs) , swarm robots, humanoid robots, and autonomous household robots.

MIL’s SubjuGator is the three time champion autonomous submarine of the RoboSub AUVSI/ONR underwater competition (2005-2007), and placed in the top 3 in eleven of the 21 years of the competition (including second place in 2012, 2013 and 2014). MIL’s NaviGator AMS, is the defending champion in the Maritime RobotX Challenge (from our victory in our only entry in this biennial competition in 2016). In 2013, MIL participated for the first time in the RoboBoat AUVSI/ONR water surface vechicle competition with our PropaGator robot boat; we won! In 2014, we earned second place in the RoboBoat competition. We also won the static division of the 2011 ION Robot Lawnmower competition with MIL’s InstiGator robot lawnmower.

Calendar

January 2023
S M T W T F S
1234567
891011121314
15161718192021
22232425262728
293031  
« Nov    




RoboSub 2022 begins in:

216
Days
19
Hours
2
Mins
46
Secs

Machine Intelligence Laboratory | University of Florida
Login