An automatic approach to the detection and extraction of mine features in sidescan sonar

Scott Reed, Yvan Petillot, Judith Bell

Research output: Contribution to journalArticlepeer-review

221 Citations (Scopus)


Mine detection and classification using high-resolution sidescan sonar is a critical technology for mine counter measures (MCM). As opposed to the majority of techniques which require large training data sets, this paper presents unsupervised models for both the detection and the shadow extraction phases of an automated classification system. The detection phase is carried out using an unsupervised Markov random field (MRF) model where the required model parameters are estimated from the original image. Using a priori spatial information on the physical size and geometric signature of mines in sidescan sonar, a detection-orientated MRF model is developed which directly segments the image into regions of shadow, seabottom-reverberation, and object-highlight. After detection, features are extracted so that the object can be classified. A novel co-operating statistical snake (CSS) model is presented which extracts the highlight and shadow of the object. The CSS model again utilizes available a priori information on the spatial relationship between the highlight and shadow, allowing accurate segmentation of the object's shadow to be achieved on a wide range of seabed types. Results are given for both models on real and synthetic images and are shown to compare favorably with other models in this field.

Original languageEnglish
Pages (from-to)90-105
Number of pages16
JournalIEEE Journal of Oceanic Engineering
Issue number1
Publication statusPublished - Jan 2003


  • A priori information
  • Automated mine detection
  • Image analysis
  • Markov random field (MRF) models
  • Shadow extraction
  • Statistical snakes


Dive into the research topics of 'An automatic approach to the detection and extraction of mine features in sidescan sonar'. Together they form a unique fingerprint.

Cite this