US 11,688,037 B2 · Systems and methods involving creation and/or utilization of image mosaics in classification of acoustic events

Abstract

Systems and methods that yield highly-accurate classification of acoustic and other non-image events, involving pre-processing data from one or more transducers and generating a visual representation of the source as well as associated features and processing, are disclosed. According to certain exemplary implementations herein, such pre-processing steps may be utilized in situations where 1) all impulsive acoustic events have many features in common due to their point source origin and impulsive nature, and/or 2) the error rates that are considered acceptable in general purpose image classification are much higher than the acceptable levels in automatic impulsive incident classification. Further, according to some aspects, the data may be pre-processed in various ways, such as to remove extraneous or irrelevant details and/or perform any required rotation, alignment, scaling, etc. tasks, such that these tasks do not need to be “learned” in a less direct and more expensive manner in the neural network.

Claims48

Dependent claims

A method for processing image mosaics suitable for machine classification of non-image data the method comprising:

generating the image mosaics for use in the machine classification, the image mosaics comprised of image data and graphical indicia derived based on the non-image data, the image mosaics comprised of two or more different image subcomponents that are created based on information associated with an incident or event characterized by the non-image data;
assembling and/or arranging the two or more different image subcomponents in a spatial orientation within a single image mosaic as a function of correlating factors associated with the non-image data underlying the image mosaics, the correlating factors including data that enables a test incident or event to be correlated with known incidents or events;
and
analyzing an image mosaic of the test incident or event against the image mosaics of the known incidents or events, wherein recognition of the test incident or event is improved by comparison of image mosaics of the test incident or event against image mosaics of the known incidents or events, the image mosaics being derived via machine learning.

1 more element

A system configured to process image mosaics suitable for machine classification of non-image data, the system comprising:

one or more servers and/or computer processors comprising computer readable media containing computer program instructions that, when executed by at least one processor, cause the at least one processor to perform operations including:
generating the image mosaics for use in the machine classification, the image mosaics comprised of image data and other graphical indicia derived based on the non-image data, the image mosaics comprised of two or more different image subcomponents that are created based on information associated with an incident or event characterized by the non-image data;
assembling and arranging the two or more different image subcomponents in a spatial orientation within a single image mosaic as a function of correlating factors associated with the non-image data underlying the image mosaics, the correlating factors including data that enables a test incident or event to be correlated with known incidents or events;
and
analyzing an image mosaic of the test incident or event against the image mosaics of the known incidents or events, wherein recognition of the test incident or event is improved by comparison of image mosaics of the test incident or event against image mosaics of the known incidents or events, the image mosaics being derived via machine learning.

2 more elements

One or more computer-readable media storing a sequence of instructions that, when executed by at least one processor, cause the at least one processor to perform operations including:

generating the image mosaics for use in the machine classification, the image mosaics comprised of image data and other graphical indicia derived based on the non-image data, the image mosaics comprised of two or more different image subcomponents that are created based on information associated with an incident or event characterized by the non-image data;
assembling and arranging the two or more different image subcomponents in a spatial orientation within a single image mosaic as a function of correlating factors associated with the non-image data underlying the image mosaics, the correlating factors including data that enables a test incident or event to be correlated with known incidents or events;
and
analyzing an image mosaic of the test incident or event against the image mosaics of the known incidents or events, wherein recognition of the test incident or event is improved by comparison of image mosaics of the test incident or event against image mosaics of the known incidents or events, the image mosaics being derived via machine learning.

1 more element

Dependencies are inferred from the claim text.

Systems and methods involving creation and/or utilization of image mosaics in classification of acoustic events

Life of this patent

Systems and methods involving creation and/or utilization of image mosaics in classification of acoustic events

Life of this patent

Abstract

Claims48