BUTom21: Still image tomato dataset for detection and segmentationhttps://doi.org/10.60507/FK2/DHTEH1Halstead, MichaelGuclu, EsraFarag, MohamedPallotta, EnricoHund, ChristianRoscher, RibanaBennewitz, MarenGall, JuergenMcCool, Chrisbonndata2026-07-172026-07-17T11:55:25ZBUTom21 dataset is a fully hand-annotated still image dataset of tomatoes. It contains 123, 72, 98 images respectively in the training, validation, and evaluation subsets. The dataset contains RGB and noisy depth images captured across 2 capture days and two different RealSense D435i cameras. This creates a fully pixel-wise annotated dataset for tomato detection and segmentation in a real-world robotics scenario.Agricultural SciencesHalstead, Michael; Guclu, Esra; Farag, Mohamed; Pallotta, Enrico; Hund, Christian; Roscher, Ribana; Bennewitz, Maren; Gall Juergen; Stachniss, Cyrill; McCool, Chris,"Still image and spatial-temporal tomato data enabling detection, segmentation, tracking, and video-instance segmentation using strong and weak labels", https://arxiv.org/abs/2607.14934, arXiv, doi, 10.48550/arXiv.2607.14934, https://doi.org/10.48550/arXiv.2607.149342026-07-17Güclü, Esra2026-07-142021-08-182021-09-10Halstead, Michael; Guclu, Esra; Farag, Mohamed; Pallotta, Enrico; Hund, Christian; Roscher, Ribana; Bennewitz, Maren; Gall, Juergen; McCool, Chris, 2026, "BUTom-ST21: Spatial-temporal tomato data enabling detection, segmentation, tracking, and video-instance segmentation using strong and weak labels", https://doi.org/10.60507/FK2/TTPCNV, bonndataImages; Numerical; Spreadsheet; Structured; QualitativeCC BY 4.0