MetalScrap: Enabling AI for Automated and Accurate Metallic Scrap Inspection Using Multimodal Digital Images
The United States (U.S.) Army Material Command (AMC) and other DoD agencies define demilitarization (DEMIL) as the destruction of the functional capabilities and inherent military features from DoD materials to prevent further usage of the equipment and materials from the originally intended military design or capabilities. During the DEMIL process, all obsolete munitions are dismantled and incinerated together to form metal scraps. Incineration destroys the energetics in the metal scraps. It is not unusual for some metal scraps to contain energetics even after incineration due to their hollowness and venting cavities. It is therefore important to identify and destroy this energetics before handling the metal scraps to commercial dealers for recycling. The common practice employed by the U.S. Army to ascertain the destruction of energetics in metal scraps is to inspect each metal scrap using two independent trained and certified inspectors. The inspectors classify the metal scraps as Material Documented as Safe (MDAS) or Material Potentially Possessing Explosive Hazard (MPPEH). Due to poor and limited vision of inspectors and human judgment bias, a human-based inspection approach achieves a low MDAS/MPPEH inspection accuracy.
Awarded by U.S Army, InfoBeyond is developing a new technology namely, MetalScrap, to automate metal scrap inspection accurately and effectively. MetalScrap develops an AI (e.g., Swin Transformer)-based architecture to provide metal scrap inspection, classification, energetic residue identification, and flexible GUI (graphic user interfaces)-based human control. It uses multiview-multimodal images (e.g., Transmission and/or Backscatter X-ray) as a training dataset to precisely identify explosives in images of metal scraps, and accurately classify such metal scraps as MPPEH quickly. This removes the limitations of poor accuracy, human judgment bias, and safety risks present with a human inspection. A leading AI algorithm is developed for MetalScrap to analyze the energetic types, location, and quantity to form a severity report for decision-making. Specifically, it consists of multiple functions that provide segmentation and severity analysis based on adaptable material handling, safety and inspection standards. As a software platform, MetalScrap UI (User Interface) allows inspectors to review, control, and manage the entire metallic scrap inspection process.
The accuracy of inspection classification in current practice is limited to human vision. Moreover, human-based inspection of the metal scraps is time-consuming and lack of automation. Aside from these, human inspectors are prone to safety risks from an accidental explosion. Differently, MetalScrap takes advantage of X-ray technology, digital imaging, and advanced deep learning algorithms to provide an alternative metal scrap inspection method that is accurate, safe, and time-effective. Importantly, advanced deep learning algorithms are employed to automatically interpret metal scrap inspection images effectively to achieve high precision to meet Department of Defense Explosive Safety Board (DDESB) requirements in a reliable fashion. For example, it can classify metal scraps as MPPEH in a matter of seconds to facilitate AMC & JMC metal inspection automatically without the need to label dataset which reduces AMC & JMC metal scrap inspection labor cost. It also has a number of applications with DoD-like requirements, e.g., metal scrap inspection for metal recycling.