Raytheon Company

The Penn State Research Foundation

Robert J Cole

Geoffrey Guisewite

Thomas P Deardorff

Mac Allen Cody

Gabriel D Comi

Megan J Roberts

Michael R Gabrovsek

Brian J Simpson

Bryan D Glick

Stephen Schadler

Chen Liang

Heidi Jean Kruesi

Richard Matthew Wright

Brady R Bickel

Zhaohui Wu

Jason A Staph

Clyde Lee Giles

David C James

Generally discussed herein are systems and apparatuses that are configured to and techniques for associating a SIGnal INTelligence (SIGINT) signal with an object or tracklet. According to an example a technique can include estimating Times of Arrival (ToAs) at each of a plurality of collectors of a first signal from each of a plurality of moving transmitters, each first signal transmitted from a transmitter on a tracklet extracted from video data and received at the plurality of collectors, wherein a location of each of the plurality of collectors is known, comparing each estimated ToA to a respective actual ToA of a SIGINT signal received at each of the collectors, or determining a likelihood that the signal corresponds to the SIGINT signal to determine whether the SIGINT signal was transmitted from a transmitter on the corresponding tracklet.

Associating signal intelligence to objects via residual reduction

Generally discussed herein are systems and apparatuses that are configured to and techniques for matching track fragments. According to an example, a technique can include receiving data indicating a first and second actual ToA of first and second SIGINT signals at a collector, estimating first and second sets of estimated ToAs of the first and second SIGINT signals at a collector, respectively, each of the first and second sets of estimated ToAs based on a different track fragment of a first plurality of track fragments active at the first time and a different track fragment of a second plurality of track fragments active at the second time, respectively, or matching a track fragment of the first plurality of track fragments with a track fragment of the second plurality of track fragments based on the first and second sets of estimated ToAs and the first and second actual ToAs.

Track fusion using SIGINT or estimated speed

Generally discussed herein are systems, apparatuses, and methods for organizing and/or searching news events. In one or more embodiments, a method can include encoding a news event based on named entities, actors, and actions mentioned in the news event, calculating a locality sensitive hash (LSH) key on the news event encoding, comparing the calculated LSH key to a plurality of LSH keys of respective stories, wherein each story of the respective stories comprises one or more associated news events that include LSH keys that are within a specified distance from each other, and associating the news event with a story of the respective stories that includes an LSH key that has a smallest distance from the LSH key of the received news event and is less than the specified distance.

Systems and methods for news event organization

Generally discussed herein are systems and apparatuses that are configured to and techniques for associating a SIGINT signal with an object or tracklet. According to an example, a technique can include (1) estimating a first set of times, each time of the first set of times can indicate how much time it would take for a respective SIGINT signal of a set of SIGINT signals to travel from a point on a tracklet extracted from video data to a respective collector, (2) estimating a second set of times corresponding to times at which the video data corresponding to the point on the tracklet was gathered, or (3) associating the set of SIGINT signals with a tracklet of the plurality of tracklets based on the first set of times, the second set of times, and a set of ToAs of SIGINT signals at the plurality of collectors.

A method for estimating a boundary for a future location of a moving object includes: receiving location information about two previous locations of the moving object represented by a first and a second elliptical error probabilities (EEPs); representing each of the EEPs as a conic section via an implicit quadratic equation; defining four tangent lines from the implicit quadratic equation, each tangent line being tangent to both of the EEPs; determining two transverse tangent lines from the four tangent lines; forming a cone in a direction from the first EEP to the second EEP from the two transverse tangent lines; and estimating the boundary of the future location of the moving object as a first side of the cone formed by a first transverse tangent line and a second side of the cone formed by a second transverse tangent line, of the two transverse tangent lines.

Method for determining future position boundary for a moving object from location estimates

Methods and apparatus to identify a type of acoustic event Mel Frequency Cepstral Coefficients (MFCCs). In one embodiment, received sound is processed using the MFCCs to locate a peak for comparison with a stored event to determine if the peak corresponds to the acoustic event.

Methods and apparatus for acoustic event detection

When using intrusion detection systems, security specialists are concerned with false positive rates and true positive rates. False positives are when an alert is raised, but no actual intrusion occurs. True positives are when an alert is raised for an actual intrusion. Ideally, true positive rate is 1 and false positive rate is zero, but such a situation is impossible in the real world. So one must balance a true positive rate and a false positive rate to produce the best result at the best price. One can simplify the choice of detection sets by, instead of determining each possible operating point of the information detection system, by only choosing operating points that are not dominated by other operating points.

Growing community of inventors

PA Furnace, PA, United States of America

Robert J Cole