Vision-Based Remote Sensing Imagery Datasets From Benkovac Landmine Test Site Using An Autonomous Drone For Detecting Landmine Locations

Abstract

Mapping millions of buried landmines rapidly and removing them cost-effectively is supremely important to avoid their potential risks and ease this labour-intensive task. Deploying uninhabited vehicles equipped with multiple remote sensing modalities seems to be an ideal option for performing this task in a non-invasive fashion. This report provides researchers with vision-based remote sensing imagery datasets obtained from a real landmine field in Croatia that incorporated an autonomous uninhabited aerial vehicle (UAV), the so-called LMUAV. Additionally, the related knowledge regarding the literature survey is presented to guide the researchers properly. More explicitly, two remote sensing modalities, namely, multispectral and long-wave infrared (LWIR) cameras were mounted on an advanced autonomous UAV and datasets were collected from a well-designed field containing various types of landmines. In this report, multispectral imagery and LWIR imagery datasets are presented for researchers who can fuse these datasets using their bespoke applications to increase the probability of detection, decrease the false alarm rate, and most importantly, improve their techniques based on the features of vision-based imagery datasets.