FieldSAFE: Dataset for Obstacle Detection in Agriculture

TL;DR

FieldSAFE introduces a comprehensive multi-modal dataset for obstacle detection in agricultural settings, combining various sensors and precise localization to aid development of autonomous farming systems.

Contribution

The paper provides a novel, multi-modal dataset with synchronized sensor data, ground truth labels, and geographic coordinates for obstacle detection in agriculture.

Findings

Dataset includes diverse obstacle types and sensor modalities.

Provides ground truth labels and geographic coordinates.

Facilitates development of autonomous agricultural systems.

Abstract

In this paper, we present a novel multi-modal dataset for obstacle detection in agriculture. The dataset comprises approximately 2 hours of raw sensor data from a tractor-mounted sensor system in a grass mowing scenario in Denmark, October 2016. Sensing modalities include stereo camera, thermal camera, web camera, 360-degree camera, lidar, and radar, while precise localization is available from fused IMU and GNSS. Both static and moving obstacles are present including humans, mannequin dolls, rocks, barrels, buildings, vehicles, and vegetation. All obstacles have ground truth object labels and geographic coordinates.