Beetle Indicator Dataset

The Beetle Detection Dataset consists of 2,400 samples, equally divided into 1,200 beetlewood and 1,200 no-beetlewood samples, totaling 4,800 images (one trunk and one cross-sectional image per sample). The no-beetlewood category includes 50% class B and 50% class C samples. Class D is excluded, as infested wood may also be classified as D. The dataset is split using stratified sampling, with 1,920 samples (80%) for training and 480 samples (20%) for testing. Each sample is saved along with its corresponding cross-sectional image and a log file. The log file follows this structure: log; protocol number; stem length [cm]; diameter D1 base [mm]; diameter D2 middle [mm]; diameter D3 top [mm]; taper [mm/m]; species; quality.甲虫检测数据集（Beetle Detection Dataset）包含2400个样本，均匀划分为1200个虫蛀木材样本与1200个无虫蛀木材样本，总计包含4800张图像——每个样本对应一张原木图像与一张横截面图像。无虫蛀木材类别包含占比各50%的B类与C类样本。D类样本被排除在外，因为受虫害侵染的木材也可能被归类为D类。本数据集采用分层抽样法进行划分，其中1920个样本（占比80%）用于训练集，剩余480个样本（占比20%）用于测试集。每个样本均附带其对应的横截面图像与一份日志文件，日志文件的格式如下：日志; 协议编号; 原木长度[厘米]; 基部直径D1[毫米]; 中部直径D2[毫米]; 顶部直径D3[毫米]; 锥度[毫米/米]; 树种; 品质等级