2023_programme: Terrain characterisation for online ATR adaptability: Results and lessons learnt from multiple deployments

Back


  • Session: 15. Towards Automatic Target Recognition. Detection, Classification and Modelling
    Organiser(s): Johannes Groen, Yan Pailhas, Roy Edgar Hansen, Jessica Topple and Narada Warakagoda
  • Lecture: Terrain characterisation for online ATR adaptability: Results and lessons learnt from multiple deployments [invited]
    Paper ID: 1909
    Author(s): Guerneve Thomas, Loizou Stephanos, Munafo Andrea, Mignotte Pierre-Yves
    Presenter: Guerneve Thomas
    Abstract: The performance of Automated Recognition (ATR) algorithms on sidescan sonar imagery has shown to degrade rapidly when deployed on non benign environments. Complex seafloors and acoustic artefacts constitute distractors in the form of strong textural patterns, creating false detections or preventing detections of true objects. This paper presents two online seafloor characterisation techniques to improve explainability during Autonomous Underwater Vehicles (AUVs) missions. Importantly and as opposed to previous work in the domain, these techniques are not based on a model and require limited input from human operators, making it suitable for realtime onboard processing. Both techniques rely on an unsupervised machine learning approach to extract terrain features which relate to the human understanding of terrain complexity. The first technnique provides a quantitative, applicationdriven\nterrain characterisation metric based on the performance of an ATR algorithm. The second method provides a\nway to incorporate subject matter expertise and enables contextualisation and explainability in support for scenariodependent subjective terrain characterisation. The terrain complexity matches the expectation of seasoned users making this tool desirable and trustworthy in\ncomparison to traditional unsupervised approaches. We finally detail an application of these techniques to repair a Mine Countermeasures (MCM) mission carried with SeeByte autonomy framework Neptune.
      Download the full paper
  • Corresponding author: Dr Andrea Munafo
    Affiliation: SeeByte and University of Pisa
    Country: United Kingdom
    e-mail:

Back