PFuji-Size dataset: photogrammetry-derived 3D point clouds of Fuji apples trees with annotations to evaluate fruit detection and size estimation methodologies

The PFuji-Size dataset [2] includes the 3D point clouds of 6 Fuji apple trees containing a total of 615 apples and an additional 25 apples scanned in laboratory conditions. Structure-from-motion and multi-view stereo techniques were used to generate the 3D point clouds of the captured scene. Apple locations and ground truth diameter annotations are provided for assessing fruit detection and size estimation algorithms.PFuji-Size 数据集[2]包含6棵富士苹果树的三维点云，共计涵盖615个苹果，另有25个苹果在实验室环境下完成扫描采集。本数据集通过运动恢复结构（Structure-from-Motion）与多视图立体（multi-view stereo）技术生成采集场景的三维点云。数据集提供了苹果的位置标注与真值直径标注，可用于评估果实检测与尺寸估计算法的性能。

搜集汇总

背景与挑战

背景概述

PFuji-Size数据集是一个用于评估水果检测和尺寸估计算法的三维点云数据集，包含6棵富士苹果树的615个苹果点云及25个实验室扫描苹果，通过运动结构和多视图立体技术生成，并提供了苹果位置和真实直径的标注信息。