A plug and play system for improved threat detection performance at security sensitive infrastructure

这项为期18个月的工业研究项目将开发一种SafetyNet设备，用于使用深度学习技术的自动图像解读，解读来自随身行李、手提行李和包裹安检扫描仪的x射线图像。该系统将自动确定扫描仪下物体所构成的威胁程度，并在操作人员决策时提供安全网。该设备输出将与现有扫描仪集成，用于提醒操作员存在威胁项目。该设备将在实验室和客户现场的双能x射线设备上进行测试。该设备将具有普遍的吸引力，集成到许多扫描仪型号，使其成为改造和新产品线集成的完美选择。底层算法和检测技术将基于自适应自学习神经网络的使用，该神经网络使用深度学习的基本原理。这种系统将从数百万张由人工操作员在线扫描和测试的图像中学习。一旦经过训练，这些将用于威胁检测，以协助人类决策。随着更多的数据被扫描，这些系统将有更大的档案可以学习，并将随着时间的推移继续增长它们的智能。该系统预计将显著提高威胁检测质量，提高筛选吞吐量，减少误报和由此导致的延误。SafetyNet将作为硬件/软件组合产品提供给潜在客户，并提供云后端，设备将与云后端通信系统和操作人员的数据，随后可用于向客户提供数据服务，以报告减少视觉疲劳风险和员工培训不足的情况。这种系统的目标市场将包括体育场、竞技场、边境管制、港口、航空、商业总部、数据中心和国防应用。

This 18 months industrial research project will develop a SafetyNet device for interpretation of x-ray images from security scanners for carry-on, hold luggage and parcels using automated image interpretation with deep learning technology. The system will automatically determine the level of threat posed by the object under the scanner, and provide a safety net around the human operator decision making. The device output will be integrated with existing scanners and used to alert the operator to the presence of threat items. The device will be tested on dual energy x-ray equipment in laboratory and at customer sites. The device will have universal appeal, integrating to a number of scanner models, making it a perfect option for retrofitting and new product line integration. The underlying algorithms and detection technology will be based around the use of adaptive self-learning neural networks which use underlying principles of deep learning. Such systems will learn from millions of images scanned and tested by human operators in an online setting. Once trained these will be applied for threat detection to assist human decision making. As more data is scanned, these systems will have larger archives to learn from, and will continue to grow their intelligence over time. The systems are expected to markedly improve performance in terms of increased quality of threat detection, higher screening throughput and reduced false alarms and resulting delays. SafetyNet will be offered to potential customers as a combined hardware/software offering with a cloud backend to which the device will communicate data on system and operators, which can be used subsequently for delivering data services to customers to report on reducing the risk of visual fatigue and inadequate staff training. The target markets for such system will include stadiums, arenas, border control, ports, aviation, commercial head offices, data centres and defence applications.