【目标检测】小轿车车身缺陷检测数据集6957张YOLO+VOC(已增强)

作品简介

数据集格式:VOC格式+YOLO格式

压缩包内含:3个文件夹,分别存储图片、xml、txt文件

JPEGImages文件夹中jpg图片总计:6957

Annotations文件夹中xml文件总计:6957

labels文件夹中txt文件总计:6957

标签种类数:14

标签名称:["Front-windscreen-damage","Headlight-damage","Rear-windscreen-Damage","Runningboard-Damage","Sidemirror-Damage","Taillight-Damage","bonnet-dent","boot-dent","doorouter-dent","fender-dent","front-bumper-dent","quaterpanel-dent","rear-bumper-dent","roof-dent"]

每个标签的框数(注意yolo格式类别顺序不和这个对应,而以labels文件夹classes.txt为准):

Front-windscreen-damage 框数 = 293(前挡风玻璃损坏)

Headlight-damage 框数 = 664(前照灯损坏)

Rear-windscreen-Damage 框数 = 458(后挡风玻璃损坏)

Runningboard-Damage 框数 = 347(踏板损坏)

Sidemirror-Damage 框数 = 283(后视镜损坏)

Taillight-Damage 框数 = 449(尾灯损坏)

bonnet-dent 框数 = 1256(发动机罩凹痕)

boot-dent 框数 = 167(行李箱凹痕)

doorouter-dent 框数 = 1599(车门外部凹痕)

fender-dent 框数 = 1041(挡泥板凹痕)

front-bumper-dent 框数 = 1913(前保险杠凹痕)

quaterpanel-dent 框数 = 841(后翼子板凹陷)

rear-bumper-dent 框数 = 1060(后保险杠凹痕)

roof-dent 框数 = 398(车顶凹痕)

总框数:10769

图片清晰度(分辨率:像素):清晰

图片是否增强:是

标签形状:矩形框,用于目标检测识别

重要说明:暂无

特别声明:本数据集不对训练的模型或者权重文件精度作任何保证,数据集只提供准确且合理标注

图片概况




创作时间: