The algorithm will provide automatic detection of lithium batteries in all freight and baggage screened for explosives by the HI-SCAN 10080 EDX-2is, reducing the burden on image analysts with very low false alarm rates. Image: Smiths Detection
Consumer demand for lithium batteries is growing exponentially, as these batteries are the primary power source for personal and portable electronic devices. Classified as dangerous goods because of the potential for these batteries to ignite, lithium batteries pose a significant safety threat. Since January 2006, a total of 310 incidents of smoke, heat, fire or explosion involving lithium batteries in air cargo or hold baggage has been recorded.
The lithium battery algorithm is part of Smiths Detection’s family of AI-algorithms, iCMORE, which provides powerful automatic detection of dangerous goods and weapons across its conventional x-ray and EDS technologies using deep learning and classical material discrimination, increasing the safety of passengers, staff, goods and aircrafts in a quick and efficient way. The iCMORE algorithms are complementary solutions to existing screening technology.
“We are continually striving to develop new technologies to ensure the safety of people globally” said Richard Thompson, global director aviation for Smiths Detection. “Harnessing the power of deep learning is crucial in further developing object recognition algorithms. This new technology has been developed by working with our customers to capture thousands of X-ray images to then be analysed by the new algorithm so it can learn to detect lithium batteries based on shape. This algorithm will provide the powerful detection of lithium batteries while increasing efficiency and speed for users.”
Stay up to date
Subscribe to the free Times Aerospace newsletter and receive the latest content every week. We'll never share your email address.