George Mason University

George Mason Intellectual Properties, Inc.

Duminda Wijesekera

Khaled Soliman Alghathbar

Thabet Kacem

Alexandre De Barros Barreto

Eniye Tebekaemi

Paulo Cesar Guerreiro Da Costa

Yongxin Wang

A computer-implemented method of detecting one or more objects in a driving environment located externally to a vehicle, and a vehicle imaging system configured to detect one or more objects. The computer-implemented method includes training a first neural network to detect objects in a color video stream, the first neural network having a plurality of mid-level color features at a plurality of scales, and training a second neural network, operatively coupled to color neural network and an infrared video stream, to match, at the plurality of scales, mid-level infrared features of the second neural network to mid-level color features of the first neural network. A pixel-level invisibility map is then generated from the color video stream and the infrared video stream by determining differences, at each of the plurality of scales, between mid-level color features at the first neural network and mid-level infrared features at the second infrared neural network, and coupling the result to a fusing function.

Detecting objects non-visible in color images

A system for autonomous control in power systems is disclosed. In particular, a secure overlay communication model ('SOCOM') is disclosed, the system including a combination of hardware and software for detecting power grid states, and determining appropriate actions for addressing detected states. The SOCOM is a logic-based system deployed onto computing devices such as field programmable gate arrays installed at bus controllers, Supervisory Control and Data Acquisition Systems ('SCADAs'), Intelligent Electronic Devices (&#x201c;IEDs&#x201d;), or other computing devices in power grid stations and substations. The logic-based nature of the SOCOM allows for seamless integration with preexisting power system equipment. In response to detecting various power grid faults such as line failures and over-current states, the system automatically rearranges power line configurations at the power stations and/or substations. The SOCOM further provides improvements relating to optimal power flow, cost-based power distribution, load management, voltage/volt-amp reactance (&#x201c;VAR&#x201d;) optimization, and self-healing.

Secure overlay communication model for decentralized autonomous power grid

Automatic Dependent Surveillance Broadcast (ADS-B) is one of the most prominent air traffic surveillance technologies. It can be used not only as a complement in existing radar-based technologies to locate aircraft, but also as a replacement in areas without radar coverage. However, a major flaw in the deployment of this technology is it reliance on clear-text, open broadcast of messages, which makes it vulnerable to attackers. A solution to this vulnerability is ADS-Bsec, a holistic framework that solves the root cause of ADS-B problems by enforcing authenticity and integrity in ADS-B messages. This is accomplished without changing the message format and, along with a proper key exchange mechanism. The framework also leverages results from radio-location add risk-adaptive techniques in order to prevent attacks targeting ADS-B. ADS-Bsec is a promising framework for integrating ADS-B to NextGen infrastructure in a secure and affordable fashion.

ADS-Bsec: a holistic framework to secure ADS-B

Disclosed is an access and information flow control framework. The framework includes: creating consistent and conflict-free authorization requirement(s) from the raw authorization requirement(s); creating consistent case authorization(s); creating information flow and propagated information flow requirement(s) that are consistent with an information flow policy; creating operation authorization(s); resolving inconsistencies in operation authorization(s); and ensuring that the operation authorization(s) are conflict-free.

Growing community of inventors

McLean, VA, United States of America

Duminda Wijesekera