RestoreAI -- Pattern-based Risk Estimation Of Remaining Explosives

TL;DR

RestoreAI introduces a novel AI system that leverages landmine spatial patterns for risk prediction, significantly improving landmine clearance efficiency by reducing time and increasing detection accuracy.

Contribution

This work is the first to utilize landmine pattern information for AI-based risk estimation, incorporating linear, curved, and Bayesian models to enhance detection accuracy.

Findings

Achieved a 14.37 percentage point increase in cleared landmines per timestep.

Reduced clearance time by 24.45% compared to baseline methods.

Linear and curved pattern deminers performed similarly, indicating linear patterns are effective.

Abstract

Landmine removal is a slow, resource-intensive process affecting over 60 countries. While AI has been proposed to enhance explosive ordnance (EO) detection, existing methods primarily focus on object recognition, with limited attention to prediction of landmine risk based on spatial pattern information. This work aims to answer the following research question: How can AI be used to predict landmine risk from landmine patterns to improve clearance time efficiency? To that effect, we introduce RestoreAI, an AI system for pattern-based risk estimation of remaining explosives. RestoreAI is the first AI system that leverages landmine patterns for risk prediction, improving the accuracy of estimating the residual risk of missing EO prior to land release. We particularly focus on the implementation of three instances of RestoreAI, respectively, linear, curved and Bayesian pattern deminers. First, the linear pattern deminer uses linear landmine patterns from a principal component analysis (PCA) for the landmine risk prediction. Second, the curved pattern deminer uses curved landmine patterns from principal curves. Finally, the Bayesian pattern deminer incorporates prior expert knowledge by using a Bayesian pattern risk prediction. Evaluated on real-world landmine data, RestoreAI significantly boosts clearance efficiency. The top-performing pattern-based deminers achieved a 14.37 percentage point increase in the average share of cleared landmines per timestep and required 24.45% less time than the best baseline deminer to locate all landmines. Interestingly, linear and curved pattern deminers showed no significant performance difference, suggesting that more efficient linear patterns are a viable option for risk prediction.