大豆作物杂草检测,将植物图像分为4类

From the set of images captured by the UAV, all those with occurrence of weeds were selected resulting a total of 400 images. Through the Pynovisão software, using the SLIC algorithm, these images were segmented and the segments annotated manually with their respective class. These segments were used in the construction of the image dataset. This image dataset has 15336 segments, being 3249 of soil, 7376 of soybean, 3520 grass and 1191 of broadleaf weeds.

从无人机（Unmanned Aerial Vehicle，UAV）拍摄的图像集合中，筛选出存在杂草的图像，最终得到共计400张图像。借助Pynovisão软件，采用SLIC（Simple Linear Iterative Clustering）算法对上述图像进行分割，并对分割得到的图像块手动标注其所属类别。上述图像块被用于构建本图像数据集。该数据集共包含15336个图像块，其中土壤类3249个、大豆类7376个、禾本科杂草类3520个、阔叶杂草类1191个。

搜集汇总

背景与挑战

背景概述

该数据集是一个用于大豆作物杂草检测的图像数据集，包含15336个图像片段，分为土壤、大豆、草和阔叶杂草四类。数据通过无人机拍摄，并利用SLIC算法进行分割和手动标注，适用于农业视觉识别任务。