Resumen
Unexploded ordnance (UXO) is a worldwide problem and a long-term hazard because of its ability to harm humanity by remaining active and destructive decades after a conflict has concluded. In addition, the current UXO clearance methods mainly involve manual clearance and depend on the deminer?s experience. However, this approach has a high misclassification rate, which increases the likelihood of an explosion ending the deminer?s life. This study proposes a new approach to identifying the UXO based on augmented reality technology. The methodology is presented based on two phases. Firstly, a new dataset of UXO samples is created by printing 3D samples and building a 3D model of the object data file with accurate data for 3D printed samples. Secondly, the development of the UXO-AID mobile application prototype, which is based on augmented reality technology, is provided. The proposed prototype was evaluated and tested with different methods. The prototype?s performance was measured at different light intensities and distances for testing. The testing results revealed that the application could successfully perform in excellent and moderate lighting with a distance of 10 to 30 cm. As for recognition accuracy, the overall recognition success rate of reached 82.5%, as the disparity in the number of features of each object affected the accuracy of object recognition. Additionally, the application?s ability to support deminers was assessed through a usability questionnaire submitted by 20 deminers. The questionnaire was based on three factors: satisfaction, effectiveness, and efficiency. The proposed UXO-AID mobile application prototype supports deminers to classify the UXO accurately and in real time, reducing the cognitive load of complex tasks. UXO-AID is simple to use, requires no prior training, and takes advantage of the wide availability of mobile devices.