TY - GEN
T1 - Autonomous altitude estimation of a UAV using a single onboard camera
AU - Cherian, Anoop
AU - Andersh, Jon
AU - Morellas, Vassilios
AU - Papanikolopoulos, Nikolaos
AU - Mettler, Bernard
PY - 2009/12/11
Y1 - 2009/12/11
N2 - Autonomous estimation of the altitude of an Unmanned Aerial Vehicle (UAV) is extremely important when dealing with flight maneuvers like landing, steady flight, etc. Vision based techniques for solving this problem have been underutilized. In this paper, we propose a new algorithm to estimate the altitude of a UAV from top-down aerial images taken from a single on-board camera. We use a semi-supervised machine learning approach to solve the problem. The basic idea of our technique is to learn the mapping between the texture information contained in an image to a possible altitude value. We learn an over complete sparse basis set from a corpus of unlabeled images capturing the texture variations. This is followed by regression of this basis set against a training set of altitudes. Finally, a spatio-temporal Markov Random Field is modeled over the altitudes in test images, which is maximized over the posterior distribution using the MAP estimate by solving a quadratic optimization problem with L1 regularity constraints. The method is evaluated in a laboratory setting with a real helicopter and is found to provide promising results with sufficiently fast turnaround time.
AB - Autonomous estimation of the altitude of an Unmanned Aerial Vehicle (UAV) is extremely important when dealing with flight maneuvers like landing, steady flight, etc. Vision based techniques for solving this problem have been underutilized. In this paper, we propose a new algorithm to estimate the altitude of a UAV from top-down aerial images taken from a single on-board camera. We use a semi-supervised machine learning approach to solve the problem. The basic idea of our technique is to learn the mapping between the texture information contained in an image to a possible altitude value. We learn an over complete sparse basis set from a corpus of unlabeled images capturing the texture variations. This is followed by regression of this basis set against a training set of altitudes. Finally, a spatio-temporal Markov Random Field is modeled over the altitudes in test images, which is maximized over the posterior distribution using the MAP estimate by solving a quadratic optimization problem with L1 regularity constraints. The method is evaluated in a laboratory setting with a real helicopter and is found to provide promising results with sufficiently fast turnaround time.
UR - http://www.scopus.com/inward/record.url?scp=76249096679&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=76249096679&partnerID=8YFLogxK
U2 - 10.1109/IROS.2009.5354307
DO - 10.1109/IROS.2009.5354307
M3 - Conference contribution
AN - SCOPUS:76249096679
SN - 9781424438044
T3 - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
SP - 3900
EP - 3905
BT - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
T2 - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
Y2 - 11 October 2009 through 15 October 2009
ER -