Data

MMCBE dataset: drone imagery, 3D point clouds, and biomass ground truth of cotton (2022-2023 season)

Commonwealth Scientific and Industrial Research Organisation
Li, Xuesong ; Cassidy, Connor ; Liu, Shiming ; Stiller, Warwick ; Conaty, Warren ; Rolland, Vivien
Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]
ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.25919/a02z-vb88&rft.title=MMCBE dataset: drone imagery, 3D point clouds, and biomass ground truth of cotton (2022-2023 season)&rft.identifier=https://doi.org/10.25919/a02z-vb88&rft.publisher=Commonwealth Scientific and Industrial Research Organisation&rft.description=Crop biomass, a critical indicator of plant growth, health, and productivity, is invaluable for crop breeding programs and agronomic research. However, the accurate and scalable quantification of crop biomass remains inaccessible due to limitations in existing measurement methods. One of the obstacles impeding the advancement of current crop biomass prediction methodologies is the scarcity of publicly available datasets. Addressing this gap, we introduce a new dataset in this domain, i.e. multi-modality dataset for crop biomass estimation (MMCBE). Comprising 216 sets of multi-view drone images, coupled with LiDAR point clouds, and hand-labelled ground truth, MMCBE represents the first multi-modality one in the field. This dataset aims to establish benchmark methods for crop biomass quantification and foster the development of vision-based approaches. We have rigorously evaluated state-of-the-art crop biomass estimation methods using MMCBE and ventured into additional potential applications, such as 3D crop reconstruction from drone imagery and novel-view rendering. With this publication, we are making our comprehensive dataset available to the broader community.Lineage: The experimental area (0.216 ha) was scanned weekly by a P1 camera with the DJI M300 flying 12 m above ground at a speed of 1.5 m/s. The drone captured a new image for every 4 m travelled. Biomass ground truth was collected on the day a flight was performed. We chose 9-time points, targeting key phenological plant stages during periods of high growth rate. The 9 time points are 25-Jan, 03-Feb, 08-Feb, 16-Feb, 23-Feb, 08-Mar, 15-Mar, 22-Mar, and 03-Apr. One meters of above ground plant material was cut at ground level from the 'destructive' data collection section of each plot. Plants were sampled from alternate rows up each plot to avoid any edge effects associated with reduced plant competition associated with previous biomass harvests. The number of plants and fresh weight were recorded. All sampled plants were then cut into ~50mm pieces and dried at 60 °C until no change in sample weight was observed (around 48 h). Over the crop life cycle (6 months), we collected 216 (9 x 24) multi-view image sets with manually-measured biomass ground truth.&rft.creator=Li, Xuesong &rft.creator=Cassidy, Connor &rft.creator=Liu, Shiming &rft.creator=Stiller, Warwick &rft.creator=Conaty, Warren &rft.creator=Rolland, Vivien &rft.date=2025&rft.edition=v1&rft.relation=https://ieeexplore.ieee.org/abstract/document/10869541&rft.coverage=westlimit=149.5735; southlimit=-30.2185; eastlimit=149.6627; northlimit=-30.159899999999997; projection=WGS84&rft_rights=Creative Commons Attribution-Noncommercial 4.0 Licence https://creativecommons.org/licenses/by-nc/4.0/&rft_rights=Data is accessible online and may be reused in accordance with licence conditions&rft_rights=All Rights (including copyright) CSIRO 2024.&rft_subject=cotton&rft_subject=imagery&rft_subject=biomass&rft_subject=point cloud&rft_subject=drone&rft_subject=Gossypium&rft_subject=Crop and pasture production not elsewhere classified&rft_subject=Crop and pasture production&rft_subject=AGRICULTURAL, VETERINARY AND FOOD SCIENCES&rft_subject=Computer vision&rft_subject=Computer vision and multimedia computation&rft_subject=INFORMATION AND COMPUTING SCIENCES&rft.type=dataset&rft.language=English Access the data

Licence & Rights:

Non-Commercial Licence view details
CC-BY-NC

Creative Commons Attribution-Noncommercial 4.0 Licence
https://creativecommons.org/licenses/by-nc/4.0/

Data is accessible online and may be reused in accordance with licence conditions

All Rights (including copyright) CSIRO 2024.

Access:

Open view details

Accessible for free

Contact Information



Full description

Crop biomass, a critical indicator of plant growth, health, and productivity, is invaluable for crop breeding programs and agronomic research. However, the accurate and scalable quantification of crop biomass remains inaccessible due to limitations in existing measurement methods. One of the obstacles impeding the advancement of current crop biomass prediction methodologies is the scarcity of publicly available datasets. Addressing this gap, we introduce a new dataset in this domain, i.e. multi-modality dataset for crop biomass estimation (MMCBE). Comprising 216 sets of multi-view drone images, coupled with LiDAR point clouds, and hand-labelled ground truth, MMCBE represents the first multi-modality one in the field. This dataset aims to establish benchmark methods for crop biomass quantification and foster the development of vision-based approaches. We have rigorously evaluated state-of-the-art crop biomass estimation methods using MMCBE and ventured into additional potential applications, such as 3D crop reconstruction from drone imagery and novel-view rendering. With this publication, we are making our comprehensive dataset available to the broader community.
Lineage: The experimental area (0.216 ha) was scanned weekly by a P1 camera with the DJI M300 flying 12 m above ground at a speed of 1.5 m/s. The drone captured a new image for every 4 m travelled. Biomass ground truth was collected on the day a flight was performed. We chose 9-time points, targeting key phenological plant stages during periods of high growth rate. The 9 time points are "25-Jan", "03-Feb", "08-Feb", "16-Feb", "23-Feb", "08-Mar", "15-Mar", "22-Mar", and "03-Apr". One meters of above ground plant material was cut at ground level from the 'destructive' data collection section of each plot. Plants were sampled from alternate rows up each plot to avoid any edge effects associated with reduced plant competition associated with previous biomass harvests. The number of plants and fresh weight were recorded. All sampled plants were then cut into ~50mm pieces and dried at 60 °C until no change in sample weight was observed (around 48 h). Over the crop life cycle (6 months), we collected 216 (9 x 24) multi-view image sets with manually-measured biomass ground truth.

Available: 2025-02-25

Data time period: 2022-11-10 to 2023-03-10

This dataset is part of a larger collection

Click to explore relationships graph

149.6627,-30.1599 149.6627,-30.2185 149.5735,-30.2185 149.5735,-30.1599 149.6627,-30.1599

149.6181,-30.1892

ACN 633 798 857