AMLID: An Adaptive Multispectral Landmine Identification Dataset for Drone-Based Detection

TL;DR

This paper introduces AMLID, a comprehensive multispectral dataset combining RGB and LWIR imagery for drone-based landmine detection, aiming to improve safety and efficiency in humanitarian demining efforts.

Contribution

The paper presents the first open-source multispectral landmine dataset with extensive environmental variability, facilitating research and benchmarking of adaptive detection algorithms.

Findings

Contains 12,078 labeled images of 21 landmine types

Includes 11 fusion levels, multiple altitudes, seasons, and lighting conditions

Enables development of robust, adaptable detection methods

Abstract

Landmines remain a persistent humanitarian threat, with an estimated 110 million mines deployed across 60 countries, claiming approximately 26,000 casualties annually. Current detection methods are hazardous, inefficient, and prohibitively expensive. We present the Adaptive Multispectral Landmine Identification Dataset (AMLID), the first open-source dataset combining Red-Green-Blue (RGB) and Long-Wave Infrared (LWIR) imagery for Unmanned Aerial Systems (UAS)-based landmine detection. AMLID comprises of 12,078 labeled images featuring 21 globally deployed landmine types across anti-personnel and anti-tank categories in both metal and plastic compositions. The dataset spans 11 RGB-LWIR fusion levels, four sensor altitudes, two seasonal periods, and three daily illumination conditions. By providing comprehensive multispectral coverage across diverse environmental variables, AMLID enables researchers to develop and benchmark adaptive detection algorithms without requiring access to live ordnance or expensive data collection infrastructure, thereby democratizing humanitarian demining research.