US 11,688,037 B2
Systems and methods involving creation and/or utilization of image mosaics in classification of acoustic events
Robert B. Calhoun, Newark, CA (US); Scott Lamkin, Newark, CA (US); and David Rodgers, Newark, CA (US)
Assigned to ShotSpotter, Inc., Newark, CA (US)
Filed by ShotSpotter, Inc., Newark, CA (US)
Filed on Oct. 12, 2021, as Appl. No. 17/499,846.
Application 17/499,846 is a continuation of application No. 17/381,084, filed on Jul. 20, 2021, abandoned.
Application 17/381,084 is a continuation of application No. 17/317,837, filed on May 11, 2021, abandoned.
Application 17/317,837 is a continuation of application No. PCT/US2020/018697, filed on Feb. 18, 2020.
Application 17/317,837 is a continuation of application No. 16/557,865, filed on Aug. 30, 2019, granted, now 11,004,175, issued on May 11, 2021.
Application PCT/US2020/018697 is a continuation of application No. 16/277,993, filed on Feb. 15, 2019, granted, now 10,424,048, issued on Sep. 24, 2019.
Application 16/557,865 is a continuation of application No. 16/277,993, filed on Feb. 15, 2019, granted, now 10,424,048, issued on Sep. 24, 2019.
Prior Publication US 2022/0180474 A1, Jun. 9, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 3/40 (2006.01); G06T 5/00 (2006.01); G06F 17/15 (2006.01); G06N 3/04 (2023.01); G06N 20/00 (2019.01); G06F 18/24 (2023.01); G06V 10/82 (2022.01)
CPC G06T 3/4038 (2013.01) [G06F 17/15 (2013.01); G06F 18/24 (2023.01); G06N 3/04 (2013.01); G06N 20/00 (2019.01); G06T 5/003 (2013.01); G06V 10/82 (2022.01)] 48 Claims
OG exemplary drawing
 
1. 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.