FieldSAFE: Dataset for Obstacle Detection in Agriculture

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.

arXiv commentSubmitted to special issue of MDPI Sensors: Sensors in Agriculture

References in corpus (3)

• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Virtual Worlds as Proxy for Multi-Object Tracking Analysis
• Ambient awareness for agricultural robotic vehicles

Cited by in corpus (5)

• Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behavior
• ROVER: A Multi-Season Dataset for Visual SLAM
• DAC-SDC Low Power Object Detection Challenge for UAV Applications
• The Rosario Dataset v2: Multimodal Dataset for Agricultural Robotics
• Addressing the challenges of loop detection in agricultural environments