TY - GEN
T1 - Feature based recognition of submerged objects in holographic imagery
AU - Ratto, Christopher R.
AU - Beagley, Nathaniel
AU - Baldwin, Kevin C.
AU - Shipley, Kara R.
AU - Sternberger, Wayne I.
PY - 2014
Y1 - 2014
N2 - The ability to autonomously sense and characterize underwater objects in situ is desirable in applications of unmanned underwater vehicles (UUVs). In this work, underwater object recognition was explored using a digital holographic system. Two experiments were performed in which several objects of varying size, shape, and material were submerged in a 43,000 gallon test tank. Holograms were collected from each object at multiple distances and orientations, with the imager located either outside the tank (looking through a porthole) or submerged (looking downward). The resultant imagery from these holograms was preprocessed to improve dynamic range, mitigate speckle, and segment out the image of the object. A collection of feature descriptors were then extracted from the imagery to characterize various object properties (e.g., shape, reflectivity, texture). The features extracted from images of multiple objects, collected at different imaging geometries, were then used to train statistical models for object recognition tasks. The resulting classification models were used to perform object classification as well as estimation of various parameters of the imaging geometry. This information can then be used to inform the design of autonomous sensing algorithms for UUVs employing holographic imagers.
AB - The ability to autonomously sense and characterize underwater objects in situ is desirable in applications of unmanned underwater vehicles (UUVs). In this work, underwater object recognition was explored using a digital holographic system. Two experiments were performed in which several objects of varying size, shape, and material were submerged in a 43,000 gallon test tank. Holograms were collected from each object at multiple distances and orientations, with the imager located either outside the tank (looking through a porthole) or submerged (looking downward). The resultant imagery from these holograms was preprocessed to improve dynamic range, mitigate speckle, and segment out the image of the object. A collection of feature descriptors were then extracted from the imagery to characterize various object properties (e.g., shape, reflectivity, texture). The features extracted from images of multiple objects, collected at different imaging geometries, were then used to train statistical models for object recognition tasks. The resulting classification models were used to perform object classification as well as estimation of various parameters of the imaging geometry. This information can then be used to inform the design of autonomous sensing algorithms for UUVs employing holographic imagers.
KW - Holography
KW - feature extraction
KW - image processing
KW - object recognition
KW - unmanned underwater vehicles
UR - http://www.scopus.com/inward/record.url?scp=84905675072&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84905675072&partnerID=8YFLogxK
U2 - 10.1117/12.2049742
DO - 10.1117/12.2049742
M3 - Conference contribution
AN - SCOPUS:84905675072
SN - 9781628410099
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XIX
PB - SPIE
T2 - Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XIX
Y2 - 5 May 2014 through 7 May 2014
ER -