RAMAZAN S. AYGUN
build free website

ROBOT NAVIGATION AND TRACKING


We have two projects: Target Tracking and Mirage Pose Estimation.

PROJECT 1. TARGET TRACKING

Majority of tracking algorithms are based on feature extraction and continuous availability of features. If the target is not detectable or leaves the field-of-view, we analyze the strategies that could be taken. 

ROBOT PARTS

Robot Controller: Serializer .NET Robot Controller

Video Sensor: CmuCam2+

DESCRIPTION

In this project, we have built a robot to track color objects. This project is funded by UAH REU and sponsored by Alabama Space Grant Consortium. The goal is to be able to track an object even if the object goes out of the view of the object permanently.

STUDENTS PARTICIPATED

Jacob Hauenstein

Traxter Robot
Traxter Robot
Traxter Robot
Traxter Robot
CMUCam2+ Video Sensor
CMUCam2+ Video Sensor


PROJECT 2. Mirage Pose Estimation and Trajectory Tracking Method

We also developed 'Mirage' pose estimation and trajectory tracking by computing the error between 2D projection of the desired target and actual image of the target.



P U B L I C A T I O N S

  1. Dinc, S., Fahimi, F., Aygun, R. S. Vision-Based Trajectory Tracking for Mobile Robots using Mirage Pose Estimation Method. IET Computer Vision. (accepted)
  2. Jacob Hauenstein, Ramazan Tinaztepe, Ramazan Aygun: 'You Can Run, but You Cannot Hide': Tracking Objects that leave the Field-of-View. International Journal of Information Technology and Decision Making 11(1): 11-31 (2012)
  3. S. Dinc, F. Fahimi, and R. Aygun “Vision-based trajectory tracking approach for mobile platforms in 3D world using 2D image space,” Proceedings of the ASME 2013 International Mechanical Engineering Congress and Exposition, IMECE2013-64969, November 15-21, 2013