MineInsight: A Multi-sensor Dataset for Humanitarian Demining Robotics in Off-Road Environments

2025-06-05

AI Summary

To address the lack of realistic, diverse, multimodal field datasets for humanitarian mine detection—limiting algorithmic reliability validation—this work introduces the first public, multisensor, multispectral field benchmark dataset specifically designed for mine detection. The dataset uniquely integrates dual-perspective cooperative perception from an unmanned ground vehicle (UGV) platform and its manipulator arm, enabling full-day (day/night) operation. It synchronously captures RGB, visible–short-wave infrared (VIS-SWIR), long-wave infrared (LWIR) imagery, and dual LiDAR point clouds, totaling 209,000 frames (38k RGB, 53k VIS-SWIR, 108k LWIR). It provides high-precision 3D pose annotations for 35 object classes, including 15 real landmines. Its key innovation lies in being the only publicly available benchmark supporting occlusion-resilient detection and 3D reconstruction via全天时 multispectral imaging combined with dual LiDAR. The dataset is openly released and has been adopted as a de facto standard for detection evaluation in the international community.

Technology Category

• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

The use of robotics in humanitarian demining increasingly involves computer vision techniques to improve landmine detection capabilities. However, in the absence of diverse and realistic datasets, the reliable validation of algorithms remains a challenge for the research community. In this paper, we introduce MineInsight, a publicly available multi-sensor, multi-spectral dataset designed for off-road landmine detection. The dataset features 35 different targets (15 landmines and 20 commonly found objects) distributed along three distinct tracks, providing a diverse and realistic testing environment. MineInsight is, to the best of our knowledge, the first dataset to integrate dual-view sensor scans from both an Unmanned Ground Vehicle and its robotic arm, offering multiple viewpoints to mitigate occlusions and improve spatial awareness. It features two LiDARs, as well as images captured at diverse spectral ranges, including visible (RGB, monochrome), visible short-wave infrared (VIS-SWIR), and long-wave infrared (LWIR). Additionally, the dataset comes with an estimation of the location of the targets, offering a benchmark for evaluating detection algorithms. We recorded approximately one hour of data in both daylight and nighttime conditions, resulting in around 38,000 RGB frames, 53,000 VIS-SWIR frames, and 108,000 LWIR frames. MineInsight serves as a benchmark for developing and evaluating landmine detection algorithms. Our dataset is available at https://github.com/mariomlz99/MineInsight.

Problem

• Lack of diverse datasets for landmine detection validation
• Need for multi-sensor, multi-spectral off-road mine detection data
• Absence of dual-view robotic scans to reduce occlusions

Innovation

• Multi-sensor dataset for landmine detection
• Dual-view scans from UGV and robotic arm
• Diverse spectral ranges including VIS-SWIR and LWIR