{"success":true,"data":{"author":"Jordi Gené Mola, Mar Ferrer Ferrer, Eduard Gregorio López, Joan Ramon Rosell Polo, Verónica Vilaplana and Javier Ruiz Hidalgo (Universitat de Lleida and Universitat Politècnica de Catalunya); Hugging Face mirror by Project-AgML","bucketAccessType":"public","bucketName":"Project-AgML/papple_rgbd_amodal_segmentation","bucketPrefix":"","category":"Agriculture & Environment","cloudProvider":"huggingface","createdAt":"2026-11-22T01:09:13.000Z","description":"PApple_RGB-D-Size holds 3,925 RGB-D images (1300 x 1300) of Fuji apple trees at growth stages BBCH77 and BBCH85, built to estimate the size of on-tree apples that are partly hidden by leaves and other fruit. Each apple has a modal (visible) and an amodal (complete) segmentation outline, matching boxes, an apple ID and fruit diameter ground truth. Depth maps from photogrammetry are kept as the original float64 arrays, with a focal length of 5805.34 pixels for every image, and the source train, validation and test split is preserved; 15,335 apple boxes in all. The data trained the Amodal_Fruit_Sizing network from the GRAP group. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset(\"Project-AgML/papple_rgbd_amodal_segmentation\") or through the AgML Python library (Project-AgML, UC Davis), which reformatted the original release. License: CC BY 4.0, as stated by the original publisher; cite Jordi Gené Mola, Mar Ferrer Ferrer, Eduard Gregorio López, Joan Ramon Rosell Polo, Verónica Vilaplana and Javier Ruiz Hidalgo et al. and the DOI 10.5281/zenodo.7260694.","displayTitle":"PApple_RGB-D-Size: Fuji Apple Tree RGB-D Images with Modal and Amodal Fruit Masks and Diameter Ground Truth, 3,925 Images (Universitat de Lleida, AgML Mirror)","doi":"10.5281/zenodo.7260694","huggingFaceUrl":"https://huggingface.co/datasets/Project-AgML/papple_rgbd_amodal_segmentation","id":"876f2cb5-6491-5aa3-bec3-ad4fdcdf74df","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/7260694","objectCountEstimate":121,"probeStatus":"ok","referenceUrl":"https://huggingface.co/datasets/Project-AgML/papple_rgbd_amodal_segmentation","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Project-AgML/papple_rgbd_amodal_segmentation\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Project-AgML/papple_rgbd_amodal_segmentation\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Project-AgML, license:cc-by-4.0, size_categories:1K<n<10K, format:parquet, downloads=402"],"format":"mixed","generatedAt":"2026-11-22T01:10:04.411Z","layout":{"example":"data/train-00000-of-00119.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"50415231150015f0bcad0115f0bcad012c150215001506150600000200000002022eaf150089504e470d0a1a0a0000000d4948445200000514000005140802000000218409bf0000000774494d4507e6021612192655d452e70000200049444154789cecdd598f24c9952ff6b398b97b2cb9d4d64d36b72609ceccbd33b81abd08102041c0d51710f4c5f4a86f22400f7a1704612eaeeecc7019924df65a5d5bae111eee66e71c3d984764563547afd302febf876655323233c2dddcccceb1635644000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000","encoding":"hex","key":"data/train-00000-of-00119.parquet","truncatedAt":512}],"sampleObjects":["data/train-00000-of-00119.parquet","data/train-00001-of-00119.parquet","data/train-00002-of-00119.parquet","data/train-00003-of-00119.parquet","data/train-00004-of-00119.parquet"],"sidecars":[{"bytes":"---\nconfigs:\n- config_name: default\n  data_files:\n  - split: train\n    path: data/train-*\ndataset_info:\n  features:\n  - name: image\n    dtype: image\n  - name: depth\n    dtype: binary\n  - name: mask\n    dtype: image\n  - name: objects\n    struct:\n    - name: bbox\n      list:\n        list: float64\n    - name: categories\n      list:\n        class_label:\n          names:\n            '0': apple\n    - name: apple_id\n      list: int32\n    - name: polygon\n      list:\n        list: float64\n    - name: amodal_polygon\n      list:\n        list: float64\n    - name: amodal_bbox\n      list:\n        list: float64\n  - name: split\n    dtype: string\n  splits:\n  - name: train\n    num_bytes: 59462813532\n    num_examples: 3925\n  download_size: 19133406734\n  dataset_size: 59462813532\nlicense: cc-by-4.0\ntask_categories:\n- object-detection\nsize_categories:\n- 1K<n<10K\n---\n# Papple Rgbd Amodal Segmentation\n\nPApple_RGB-D-Size: 3,925 RGB-D images (1300x1300) of Fuji apple trees at growth stages BBCH77 and BBCH85, released with a study on estimating the size of on-tree fruit hidden behind occlusions. Each apple carries a modal (visible) outline and an amodal (complete) outline, with matching boxes and its apple ID. The mask column marks the visible apple pixels. Depth maps produced by photogrammetry are kept in their own column as the original float64 .npy arrays, with the source's train/val/test split; the record gives a focal length of 5805.34 px for every image. The dataset contains 3,925 images with 15,335 bounding box annotations across 1 category.\n\nThis dataset is indexed on https://project-agml.github.io/ as part of the AgML python library.\n\nThe original train/test/val split has been preserved in the `split` column.\n\n## Citation\n\n```bibtex\n@article{genmola2023looking,\n  title={Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation},\n  author={Gené-Mola, Jordi and Ferrer-Ferrer, Mar and Gregorio, Eduard and Blok, Pieter M. and Hemming, Jochen and Morros, Josep-Ramon and Rosell-Polo, Joan R. and Vilaplana, Verónica and Ruiz-Hidalgo, Javier},\n  journal={Computers and Electronics in Agriculture},\n  volume={209},\n  pages={107854},\n  year={2023},\n  publisher={Elsevier}\n}\n```\n\n\nThe dataset itself can be cited as:\n\nMola, J. G., Ferrer, M. F., López, E. G., Polo, J. R. R., Vilaplana, V., Hidalgo, J. R., &amp; Morros, J. R. (2022). *PApple_RGB-D-Size dataset* [Dataset]. Zenodo. https://doi.org/10.5281/ZENODO.7260694\n\n\n*This dataset was reformatted from its original format to match HuggingFace standards.*\n","encoding":"utf8","key":"README.md","name":"README.md","size":2569,"truncated":false}],"sourceObjectKey":"data/train-00000-of-00119.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"Project-AgML/papple_rgbd_amodal_segmentation\")\nprint(ds)","starterSamplePath":"data/train-00000-of-00119.parquet","totalObjects":121},"summary":"PApple_RGB-D-Size holds 3,925 RGB-D images (1300 x 1300) of Fuji apple trees at growth stages BBCH77 and BBCH85, built to estimate the size of on-tree apples that are partly…","title":"PApple_RGB-D-Size: Fuji Apple Tree RGB-D Images with Modal and Amodal Fruit Masks and Diameter Ground Truth, 3,925 Images (Universitat de Lleida, AgML Mirror)","updatedAt":"2026-11-22T04:03:01.695Z","visibility":"public","websiteUrl":"https://project-agml.github.io/"}}