Dragon Fruit Image Dataset

We created a 2563-image custom dragon fruit image dataset, with 1248 images of raw dragon fruits and 1315 photographs of ripe dragon fruits. The images were taken with the Nikon D5200 DSLR and OnePlus 6's Sony IMX 519 16 megapixel camera. The photographs taken with the DSLR camera had a resolution of 4000 by 6000 pixels, while those taken with the OnePlus6 had a resolution of 3456 by 4608 pixels. They were photographed in natural sunlight. The average temperature during that time was 28°C (84.2°F), with partly sunny skies, 65 percent humidity, and 17 km/h wind speeds. The images were captured between the end of June and the middle of July 2021 at a dragon fruit farm in Baramati, Maharashtra, India. We collected data at both ends of the dragon fruit growth cycle, which lasts about a month from flowering to harvest.

本研究构建了一套包含2563张图像的定制化火龙果图像数据集，其中未成熟火龙果图像1248张，成熟火龙果图像1315张。图像采集设备包括尼康D5200数码单反相机（Nikon D5200 DSLR），以及一加6（OnePlus 6）搭载的索尼IMX 519 1600万像素摄像头（Sony IMX 519 16 megapixel camera）。使用数码单反相机拍摄的图像分辨率为4000×6000像素，而使用一加6拍摄的图像分辨率为3456×4608像素。所有图像均采用自然光拍摄，拍摄期间平均气温为28℃（84.2℉），天气为晴间多云，相对湿度65%，风速17 km/h。图像采集工作于2021年6月底至7月中旬，在印度马哈拉施特拉邦巴拉马蒂（Baramati）的一处火龙果种植园开展。本次数据采集覆盖了火龙果生长周期的两个关键阶段——从开花到收获的生长周期约为1个月。

搜集汇总

背景与挑战

背景概述

该数据集是一个专门用于农业计算机视觉研究的火龙果图像集合，包含2563张高分辨率图像，按成熟度分为未成熟和成熟两类。所有图像在自然农田环境下拍摄，适用于果实成熟度分析、自动收获和产量估算等农业AI应用场景。