MuST-C: The Multi-Sensor and Multi-Temporal Dataset of Multiple Crops for In-Field Phenotyping and Monitoring
Simple
- Title
- MuST-C: The Multi-Sensor and Multi-Temporal Dataset of Multiple Crops for In-Field Phenotyping and Monitoring
- Description
- Phenotyping is crucial for understanding crop trait variation and advancing research, but is currently limited by expensive, labor-intensive monitoring. New methods are proposed to automate phenotypic trait monitoring and reduce this so-called phenotyping bottleneck. These methods are often data-driven, requiring a dataset for novel method development. In this paper, we present the MuST-C (Multi-Sensor, multi-Temporal, multiple Crops) data set, which contains field data from various platforms collected over one growing season, covering six different crop species. All data are georeferenced for alignment across sensors and dates. To collect our dataset, we deployed aerial and ground robotic platforms equipped with RGB cameras, LiDARs, and multispectral cameras to achieve not only a high variety of modalities but also varying viewpoints. In addition to sensor data, our data set provides destructively derived reference measurements of leaf area and biomass. Our data set enables the development of autonomous phenotypic trait estimation techniques, including novel multi-sensor approaches. Moreover, it allows method comparisons using different sensors and investigates their generalizability across crop species.
- Creator
- Linn Chong
- Publisher
- University of Bonn
- Publication Year
- 2025
- Resource Type
- Dataset
- Identifier
- fcf47e7a-bfb0-4e4f-9e47-8b25f8db5423