10.60507/FK2/NUMVO1
Guclu, Esra
Esra
Guclu
https://orcid.org/0000-0003-1106-5566
University of Bonn
Halstead, Michael
Michael
Halstead
https://orcid.org/0000-0001-7185-9304
University of Bonn
Denman, Simon
Simon
Denman
https://orcid.org/0000-0002-0983-5480
Queensland University of Technology
McCool, Chris
Chris
McCool
https://orcid.org/0000-0002-0577-1299
University of Bonn
BUP-ST20: Weakly Labelled Spatial Temporal Sweet Pepper Data
bonndata
2025
Agricultural Sciences
Güclü, Esra
Esra
Güclü
University of Bonn
Agricultural Robotics Group
Guclu Esra
Halstead Michael
McCool Chris
Denman Simon
2025-09-29
2025-09-29
2025-10-06
2025-10-13
2020-09-24/2020-10-01
Images;Numerical;Spreadsheet;Structured;Qualitative
10.1177/02783649251379093
10.60507/FK2/NUMVO1/KGUKLG
10.60507/FK2/NUMVO1/BMBJV0
10.60507/FK2/NUMVO1/HWHQM8
10.60507/FK2/NUMVO1/PXNNYZ
10.60507/FK2/NUMVO1/QHSXKJ
10.60507/FK2/NUMVO1/QYU9YA
10.60507/FK2/NUMVO1/XQEQX7
10.60507/FK2/NUMVO1/VAGBJV
10.60507/FK2/NUMVO1/6ULDH6
10.60507/FK2/NUMVO1/XOG4SE
10.60507/FK2/NUMVO1/UOJ2DM
10.60507/FK2/NUMVO1/BU9UV2
10.60507/FK2/NUMVO1/W3KD3I
10.60507/FK2/NUMVO1/2XTFIR
10.60507/FK2/NUMVO1/MDSTHT
10.60507/FK2/NUMVO1/FGBDO6
4294967296
4294967296
4294967296
4294967296
4294967296
3779149996
4294967296
910408094
4294967296
252713
201284699
1670
280
5206
3009
5629
5647
application/octet-stream
application/octet-stream
application/octet-stream
application/pkix-attr-cert
audio/x-pn-audibleaudio
image/x-applix-graphics
application/octet-stream
application/octet-stream
audio/x-pn-audibleaudio
application/gzip
application/gzip
application/x-yaml
application/x-yaml
text/markdown
text/markdown
text/plain
text/plain
2.0
Creative Commons Attribution 4.0 International License.
Accurate monitoring of crop phenotypic traits is essential for efficient farm management and automation in agriculture. Multi-object tracking (MOT) and video instance segmentation (VIS) offer promising approaches to enhance agricultural robotic vision systems, yet a major limitation is the scarcity of high-quality spatial-temporal datasets. We introduce BUP-ST20, a novel weakly labelled spatial-temporal dataset for sweet pepper tracking and segmentation captured on a robotic platform. BUP-ST20 contains 16,240 images from 275 sequences, each with bounding boxes, instance segmentation masks, and temporal identities.The dataset has weakly labelled training and validation sets, while the evaluation set includes 3810 frames with hand-labelled ground truth annotations.