Identifying anomalous objects in SAS imagery using uncertainty

Calum Blair, John Thompson, Neil M. Robertson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


Object detection in modalities such as synthetic aperture sonar (SAS) is affected by the difficulty of acquiring a large number of training samples. If object classes not present in the training dataset are detected during testing, they can be mis-classified as one of the training classes. This increases overall false alarm rate and affects operator reliability and trust in the detection algorithm. Previous work showed that classification algorithms are often overconfident in their predictions and hence cannot reliably flag image regions about which the algorithm is uncertain or which need further sampling or processing. This paper describes object detectors based on SVMs and Gaussian Processes for SAS imagery, followed by probabilistic calibration of detector confidence scores. The entropy or uncertainty of these scores is then used to identify low-confidence regions and indicate the presence of previously unseen or anomalous objects.

Original languageEnglish
Title of host publication2015 18th International Conference on Information Fusion (Fusion)
Number of pages7
ISBN (Print)9780982443866
Publication statusPublished - 2015
Event18th International Conference on Information Fusion 2015 - Washington, United States
Duration: 6 Jul 20159 Jul 2015


Conference18th International Conference on Information Fusion 2015
Country/TerritoryUnited States

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing
  • Computer Networks and Communications


Dive into the research topics of 'Identifying anomalous objects in SAS imagery using uncertainty'. Together they form a unique fingerprint.

Cite this