SIXray

SIXray数据集由中国科学院大学模式识别与智能系统开发实验室构建。它包含从几个地铁站收集的 1,059,231 张 X 射线图像。常见的违禁物品有六类，分别是枪、刀、扳手、钳子、剪刀和锤子。它具有三个子集，分别称为 SIXray10、SIXray100 和 SIXray1000，人类安全检查员为整个数据集提供了图像级注释。此外，测试集中的图像用每个违禁物品的边界框进行注释，以评估对象定位的性能。

The SIXray dataset was constructed by the Pattern Recognition and Intelligent System Development Laboratory of the University of Chinese Academy of Sciences. It contains 1,059,231 X-ray images collected from several subway stations. There are six categories of common contraband items, namely guns, knives, wrenches, pliers, scissors, and hammers. It includes three subsets named SIXray10, SIXray100, and SIXray1000. Human security inspectors provided image-level annotations for the entire dataset. In addition, the images in the test set are annotated with bounding boxes for each contraband item to evaluate the performance of object localization.

搜集汇总

背景与挑战

背景概述

SIXray是一个大规模安全检测X射线基准数据集，包含超过100万张从地铁站收集的X射线图像，专注于六类违禁物品（枪、刀、扳手、钳子、剪刀和锤子）的检测。数据集提供图像级注释和测试集的边界框注释，支持对象定位评估，并包含三个子集以适配不同数据需求。