Buried object classification using holographic radar
The ability of RASCAN holographic radar to distinguish buried objects through their shape and texture has been investigated. RASCAN produces data that can be processed into a two-dimensional subsurface image suitable for object identification either by eye or by computer, where scanned receptive fields can be used for object location and trained neural networks for object identification. With the eventual objective of distinguishing buried antipersonnel landmines from battlefield clutter, the five objects considered were: a simulated mine, a small unexploded shell, a crushed aluminium can, a short length of barbed wire and a stone. In the first experiments, the objects were buried in fine, dry sand so that the object classification methods could be tested in the absence of the inevitable false alarm features arising from rough and uneven surfaces and soil inhomogeneity. Training data were collected from 11 scans, each containing these five objects at random positions and depths. The simulated mines were identified with 100% success, with zero false alarms in both training and testing. The clutter test objects were identified with around a 75% success rate and about 15% false alarms. An unseen validation image correctly identified the mine and three of the four clutter objects.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: June 1, 2012
More about this publication?
- Official Journal of The British Institute of Non-Destructive Testing - includes original research and devlopment papers, technical and scientific reviews and case studies in the fields of NDT and CM.
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Information for Advertisers
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites