玉米幼苗与杂草数据集

该数据集是在新疆昌吉华兴农场玉米试验田采集，共有4130张图片、10521个边界框，用于玉米田真实场景杂草检测算法研究。反枝苋1304个实例、灰黎717个实例、龙葵290个实例、骆驼刺328个实例、马齿苋1390个实例、田旋花1227个实例、狗尾草891个实例、合被苋859个实例和玉米幼苗3515个实例。yolo类别标签如下：Amaranthus': 0, 'Chenopodium': 1, 'Solanum nigrum': 2, 'Alhagi sparsifolia': 3, 'Purslane': 4, 'Convolvulus': 5, 'Setaria': 6, 'Amaranthus polygonoides': 7, 'Corn': 8。现有的数据集多为单目标的图片，本次的数据集以多目标为主，弥补了杂草检测领域的数据集短缺的不足。This dataset was collected from a corn experimental field at Huaxing Farm, Changji, Xinjiang Uygur Autonomous Region. It contains a total of 4130 images and 10521 bounding boxes, and is intended for research on weed detection algorithms in real-world cornfield scenarios. The dataset has the following instance counts: 1304 instances of Amaranthus retroflexus, 717 instances of Chenopodium album, 290 instances of Solanum nigrum, 328 instances of Alhagi sparsifolia, 1390 instances of Portulaca oleracea, 1227 instances of Convolvulus arvensis, 891 instances of Setaria viridis, 859 instances of Amaranthus polygonoides, and 3515 instances of corn seedlings. The corresponding YOLO category labels are listed below: "Amaranthus": 0, "Chenopodium": 1, "Solanum nigrum": 2, "Alhagi sparsifolia": 3, "Purslane": 4, "Convolvulus": 5, "Setaria": 6, "Amaranthus polygonoides": 7, "Corn": 8. Most existing datasets in this field mostly contain images with single target objects, whereas this dataset focuses on multi-target scenarios, which addresses the shortage of available datasets in the weed detection research area.

搜集汇总

背景与挑战

背景概述

该数据集包含4130张玉米田图片和10521个边界框，涵盖8种杂草和玉米幼苗共9个类别，用于真实场景杂草检测研究。数据集以多目标图片为主，弥补了现有杂草检测数据集的不足。