TY - GEN
T1 - Feature-based covariance matching for a moving target in multi-robot following
AU - Min, Hyeun Jeong
AU - Papanikolopoulos, Nikolaos
AU - Smith, Christopher E.
AU - Morellas, Vassilios
PY - 2011/9/8
Y1 - 2011/9/8
N2 - In this work we present a moving target segmentation technique and apply it to a vision-based robot-following problem. The capability to do autonomous multi-robot following is useful for many robot-team applications; however, the problem becomes very challenging when the robots can carry only a small camera or when they exhibit unpredictable motion. The ability to segment a moving target while the camera is also in motion is critical to the solution of this problem and is the focus of our work. Our contributions include: (i) Matching targets using feature-based covariance matrices; (ii) Enhancing matching performance by using features based upon the Fourier transform; and (iii) Initializing a target model for cases without a known target model. We compare the proposed method with the scale-invariant feature transform and existing covariance matching methods. We then validate our proposed segmentation method through real-robot experiments.
AB - In this work we present a moving target segmentation technique and apply it to a vision-based robot-following problem. The capability to do autonomous multi-robot following is useful for many robot-team applications; however, the problem becomes very challenging when the robots can carry only a small camera or when they exhibit unpredictable motion. The ability to segment a moving target while the camera is also in motion is critical to the solution of this problem and is the focus of our work. Our contributions include: (i) Matching targets using feature-based covariance matrices; (ii) Enhancing matching performance by using features based upon the Fourier transform; and (iii) Initializing a target model for cases without a known target model. We compare the proposed method with the scale-invariant feature transform and existing covariance matching methods. We then validate our proposed segmentation method through real-robot experiments.
UR - http://www.scopus.com/inward/record.url?scp=80052384533&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052384533&partnerID=8YFLogxK
U2 - 10.1109/MED.2011.5983102
DO - 10.1109/MED.2011.5983102
M3 - Conference contribution
AN - SCOPUS:80052384533
SN - 9781457701252
T3 - 2011 19th Mediterranean Conference on Control and Automation, MED 2011
SP - 163
EP - 168
BT - 2011 19th Mediterranean Conference on Control and Automation, MED 2011
T2 - 2011 19th Mediterranean Conference on Control and Automation, MED 2011
Y2 - 20 June 2011 through 23 June 2011
ER -