SBIR-STTR Award

Deep learning offers a powerful and extensible toolset to achieve or exceed human-level accuracy for automatic object detection in stream of commerce data. However, in order to train deep machine learning-models for 2D and 3D screening a significant quantity of high-quality ground-truth training data is required.We propose SoCPhysics: A Stream-of-Commerce Physics-Based Data Generation Application, which leverages an implementation stragegy widely used in high performance computing environments for this purpose. We will generate lightweight Python wrappers around existing X-Ray/MMW simulation codes that may be written in C/C++/Fortran, and allow them to be called as Python modules. This allows the codes to retain the performance of native code, while allowing them to interact with other Python libraries and data structures (e.g. MakeHuman, Blender, BulletPhysics, etc.). This also allows us to deliver the code in formats that are useful across the model development cycle, and to different users who may have variable needs we make the code accessible via: 1) integration/extension of Blender's GUI through a custom input panel, 2) via a scriptable command-line interface, and 3) as an importable Python module which can be used to generate training data on-the-fly during model development, training, validation and testing (essential!). Critically, our proposed integration plan allows us to achieve this with no duplication of core code or libraries, meaning the code is easier to develop, test, verify and validate, and will result in fewer bugs and lower maintenance costs for the lifecycle of the SoCPhysics product.

Deep learning offers a powerful and extensible toolset to achieve or perhaps even exceed human-level accuracy for automatic object detection in stream of commerce data, and offers a path toward improving the effectiveness of scanners, reducing wait times, and radically increasing the accuracy of screening, where automatic object detection support is essential. A deep learning-based system for automatic detection is compelling, as it can be trained, never gets fatigued or distracted, and it can improve over time as more examples become available. However, in order to train deep machine learning-models to operate on 2D and 3D screening data, a significant quantity of high-quality ground-truth training examples are required. We propose SoCPhysics: A Stream-of-Commerce Physics-Based Data Generation Application, which combines state of the art physics-based modeling and simulation, extensible and performant 3D modeling and real-time physics libraries, light-weight Python code wrappers, and scalable container-based architectures to produce high-quality, physics-based x-ray and mmw synthetic training data for machine learning model training, verification and validation. The training data and subsequent machine learning models generated and supported via the SoCPhysics application will serve to support Nninvasive screening at speed that will provide comprehensive threat protection while helping to adapt security to the pace of life rather than life to security. Furthermore, this project provides fundamental support toward realizing uNbtrusive screening of people, baggage, and cargo, and will help enable the seamless detection of threats while respecting privacy, with minimal impact to the pace of travel and speed of commerce.