Digital Surgery Limited

Ford Global Technolgoies, LLC

Evangello Flouty

Danail Stoyanov

Andre Chow

Petros Giataganas

Imanol Luengo Muntion

Jean Nehme

Odysseas Zisimopoulos

Mark Stacey

Sam Muscroft

Tarik Safir

Endre Hanak

Benjamin George Brown

Examples provide systems and methods for detecting vehicle tamper events without relying on a clear line-of-sight. Namely, examples leverage an intelligent insight that many types of vehicle tamper events have unique audio signatures. Accordingly, examples detect/classify vehicle tamper events based on these unique audio signatures. Moreover, examples can verify these audio-based classifications by analyzing acceleration-related data (e.g., relative acceleration data for a body of a vehicle, relative jerk data for a body of a vehicle, etc.) to determine suspicious movement of a body of a vehicle during a potential/suspected vehicle tamper event. This acceleration-related verification step can reduce occurrence of false positive audio-based classifications caused by other noise events proximate to the vehicle that have similar audio signatures to vehicle tamper events (e.g., drilling or other noise from a construction site, rain, etc.).

Systems and methods of using a machine learning model to classify catalytic converter theft tamper events based on audio data

A set of virtual images can be generated based on one or more real images and target rendering specifications, such that the set of virtual images correspond to (for example) different rendering specifications (or combinations thereof) than do the real images. An image style can be transferred to the at least some of the virtual images of the set of virtual images to generate a stylized virtual image. A machine-learning model can be trained using a plurality of stylized virtual images. Another real image can then be processed using the trained machine-learning model. The processing can include segmenting the other real image to detect whether and/or which objects are represented (and/or a state of the object). The object data can then be used to identify (for example) a state of a procedure.

State detection using machine-learning model trained on simulated image data

A set of virtual images can be generated based on one or more real images and target rendering specifications, such that the set of virtual images correspond to (for example) different rendering specifications (or combinations thereof) than do the real images. A machine-learning model can be trained using the set of virtual images. Another real image can then be processed using the trained machine-learning model. The processing can include segmenting the other real image to detect whether and/or which objects are represented (and/or a state of the object). The object data can then be used to identify (for example) a state of a procedure.

Surgical simulation for training detection and classification neural networks

Growing community of inventors

London, United Kingdom

Evangello Flouty