Raytheon Company

James Talamonti

Benjamin P Dolgin

Andrew M Kowalevicz

Gary M Graceffo

Philip A Sallee

Stephen J Raif

Franklin R Tanner

Jonathan Goldstein

Steven A Israel

Jeffrey S Klein

Shane A Zabel

Lisa A Mccoy

An optical signal receivers, systems including the optical signal receivers, and methods of operating the same include a multimode fiber circulator including a first port, a second port, and a third port, a first multimode fiber cable coupled to the first port and having an input configured to receive a complex modulated optical signal and provide the complex modulated optical signal to the first port of the multimode fiber circulator, a second multimode fiber cable including a low Q optical resonator coupled to the second port of the multimode fiber circulator that is configured to receive the complex modulated optical signal from the second port of the multimode circulator, and a third multimode fiber cable coupled to the third port of the multimode fiber circulator that is configured to receive a reflected optical signal from the third port of the multimode circulator, the reflected optical signal being reflected from the low Q optical resonator.

Method for an all fiber optic, polarization insensitive, etalon based optical receiver for coherent signals

An optical signal receiver includes a multimode waveguide for receiving a complex modulated optical signal, an optical resonator that receives the complex modulated optical signal from the multimode waveguide and converts the complex modulated optical signal to an intensity modulated signal, and a detector that is configured to convert the intensity modulated signal into an electrical signal, the electrical signal having an amplitude indicative of an intensity of the intensity modulated signal from the optical resonator, and that provides a detected signal.

Receiver and system for transporting and demodulating complex optical signals

A machine receives a large image having large image dimensions that exceed memory threshold dimensions. The large image includes metadata. The machine adjusts an orientation and a scaling of the large image based on the metadata. The machine divides the large image into a plurality of image tiles, each image tile having tile dimensions smaller than or equal to the memory threshold dimensions. The machine provides the plurality of image tiles to an artificial neural network. The machine identifies, using the artificial neural network, at least a portion of the target in at least one image tile. The machine identifies the target in the large image based on at least the portion of the target being identified in at least one image tile.

Target identification in large image data

Subject matter regards improving image segmentation or image annotation. A method can include receiving, through a user interface (UI), for each class label of class labels to be identified by the ML model and for a proper subset of pixels of the image data, data indicating respective pixels associated with the class label, partially training the ML model based on the received data, generating, using the partially trained ML model, pseudo-labels for each pixel of the image data for which a class label has not been received, and receiving, through the UT, a further class label that corrects a pseudo-label of the generated pseudo-labels.

Labeling using interactive assisted segmentation

Growing community of inventors

McLean, VA, United States of America

James Talamonti