3 May 2017 Investigation of training sample selection methods for object classification in sonar imagery
Author Affiliations +
For Sonar Automatic Target Recognition problems, the number of mine-like objects is relatively small compared to the number non-mine-like objects available. This creates a heavy bias towards non-mine-like objects and increases the processing resources needed for classifier training. In order to reduce resource needs and the bias towards non-mine-like objects, we investigate selection methods for reducing the non-mine-like target samples while still maintaining as much of the original training information as possible. Specifically, we investigate methods for reducing sample size and bias while maintaining good classifier performance. Several methods are considered during this investigation that cover a wide range of techniques, including clustering and evolutionary algorithms. Each method is evaluated based on the classifier performance when trained on the chosen data samples and the execution time to select the new training set. Results on each method tested are presented using sonar data collected using a sidescan sonar system.
Conference Presentation
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Matthew Cook, Bradley Marchand, "Investigation of training sample selection methods for object classification in sonar imagery", Proc. SPIE 10182, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXII, 101820G (3 May 2017); doi: 10.1117/12.2262201; https://doi.org/10.1117/12.2262201


On the limits of target recognition in the presence of...
Proceedings of SPIE (April 17 2008)
Automated recognition of acoustic-image clutter
Proceedings of SPIE (May 31 1996)
Feature-based RNN target recognition
Proceedings of SPIE (September 15 1998)
ATR Systems: A Northrop Perspective
Proceedings of SPIE (September 20 1987)
Aided target recognition processing of MUDSS sonar data
Proceedings of SPIE (September 04 1998)

Back to Top