Amodal_Fruit_Sizing

We provide a deep-learning method to better estimate the size of partially occluded apples. The method is based on ORCNN (https://github.com/waiyulam/ORCNN) and sizecnn (https://git.wur.nl/blok012/sizecnn), which extended Mask R-CNN network to simultaneously perform modal and amodal instance segment...

Descripción completa

Detalles Bibliográficos
Autores: Gené Mola, Jordi, Ferrer Ferrer, Mar, Blok, Pieter, Hemming, Jochen, Rosell Polo, Joan Ramon, Morros Rubió, Josep Ramon, Vilaplana Besler, Verónica, Ruiz Hidalgo, Javier, Gregorio López, Eduard
Tipo de recurso: conjunto de datos
Fecha de publicación:2025
País:España
Institución:Consorci de Serveis Universitaris de Catalunya (CSUC)
Repositorio:CORA.Repositori de Dades de Recerca
OAI Identifier:oai:dnet:cora.rdr____::47f4d07a87e5b0f33aeb421d778cc955
Acceso en línea:https://doi.org/10.34810/DATA2315
Access Level:acceso abierto
Palabra clave:Agricultural Sciences
Engineering
Precision agriculture
Fruit size
Horticulture
Remote sensing
Descripción
Sumario:We provide a deep-learning method to better estimate the size of partially occluded apples. The method is based on ORCNN (https://github.com/waiyulam/ORCNN) and sizecnn (https://git.wur.nl/blok012/sizecnn), which extended Mask R-CNN network to simultaneously perform modal and amodal instance segmentation. The amodal mask is used to estimate the fruit diameter in pixels, while the modal mask is used to measure in the depth map the distance between the detected fruit and the camera and calculate the fruit diameter in mm by applying the pinhole camera model.