首页> 外文会议>International Conference on Safety and Security Engineering >Using threat image projection data for assessing individual screener performance
【24h】

Using threat image projection data for assessing individual screener performance

机译:使用威胁图像投影数据来评估单个筛选器性能

获取原文

摘要

Threat image projection (TIP) is a technology of current x-ray machines that allows exposing screeners to artificial but realistic x-ray images during the routine baggage x-ray screening operation. If a screener does not detect a TIP within a specified amount of time, a feedback message appears indicating that a projected image was missed. Feedback messages are also shown when a TIP image is detected or in the case of a non-TEP alarm, i.e. when the screener indicated that there was a threat but in fact no TIP was shown. TIP data is an interesting source for quality control, risk analysis and the assessment of individual screener performance. In two studies we examined the conditions for using TIP data for the latter purpose. Our results strongly suggest using aggregated data in order to have a large enough data sample as the basis for statistical analysis. Second, an appropriate TIP library containing a large number of threat items, which are representative for the prohibited items to be detected, is recommended. Furthermore, consideration should be given to image-based factors such as general threat item difficulty, viewpoint difficulty, superposition and bag complexity. Different methods to cope with these issues are discussed in order to achieve reliable, valid and standardized measurements of individual screener performance using TIP.
机译:威胁图像投影(尖端)是当前X射线机的技术,允许在日常行李X射线筛选操作期间将筛选器暴露于人工而是现实的X射线图像。如果筛选器在指定的时间内未检测到尖端,则会出现反馈消息,指示未丢失投影图像。当检测到尖端图像或在非TEP警报的情况下,也可以示出反馈消息,即筛选器指示存在威胁但实际上没有显示尖端。提示数据是质量控制,风险分析和个人筛选器性能评估的有趣来源。在两项研究中,我们检查了用于后者目的的提示数据的条件。我们的结果强烈建议使用聚合数据,以便具有足够大的数据样本作为统计分析的基础。其次,建议推荐一个适当的提示库,其中包含大量威胁项目,这些威胁项目是要检测的禁止物品的代表。此外,应考虑到基于图像的因素,例如一般威胁物品难度,观点难度,叠加和袋子复杂性。讨论了应对这些问题的不同方法,以便使用Tip实现各个筛选器性能的可靠,有效和标准化的测量。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号