English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Buried landmines and unexploded remnants of war are a constant threat for thepopulation of many countries that have been hit by wars in the past years. Thehuge amount of human lives lost due to this phenomenon has been a strongmotivation for the research community toward the development of safe and robusttechniques designed for landmine clearance. Nonetheless, being able to detectand localize buried landmines with high precision in an automatic fashion isstill considered a challenging task due to the many different boundaryconditions that characterize this problem (e.g., several kinds of objects todetect, different soils and meteorological conditions, etc.). In this paper, wepropose a novel technique for buried object detection tailored to unexplodedlandmine discovery. The proposed solution exploits a specific kind ofconvolutional neural network (CNN) known as autoencoder to analyze volumetricdata acquired with ground penetrating radar (GPR) using differentpolarizations. This method works in an anomaly detection framework, indeed weonly train the autoencoder on GPR data acquired on landmine-free areas. Thesystem then recognizes landmines as objects that are dissimilar to the soilused during the training step. Experiments conducted on real data show that theproposed technique requires little training and no ad-hoc data pre-processingto achieve accuracy higher than 93% on challenging datasets.

Landmine Detection Using Autoencoders on Multi-polarization GPR Volumetric Data