US 12,073,610 B1
Universally trained model for detecting objects using common class sensor devices
Eric Allen Duff, San Diego, CA (US); and Amit Verma, San Diego, CA (US)
Assigned to CAPTURE LLC, San Diego, CA (US)
Filed by CAPTURE LLC, San Diego, CA (US)
Filed on Jan. 11, 2024, as Appl. No. 18/410,603.
Claims priority of provisional application 63/510,134, filed on Jun. 25, 2023.
Claims priority of provisional application 63/484,454, filed on Feb. 10, 2023.
Int. Cl. G06V 10/80 (2022.01); G06V 10/764 (2022.01)
CPC G06V 10/803 (2022.01) [G06V 10/764 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for performing target detection using a trained universal sensor model, the computer-implemented method comprising:
producing, by at least one computer processor, the trained universal sensor model using a training dataset by:
receiving, from a plurality of sensor devices, a first dataset and a second dataset, wherein the first dataset is provided by a first sensor device of the plurality of sensor devices, the second dataset is provided by a second sensor device of the plurality of sensor devices, wherein the plurality of sensor devices comprises a device class, and the first sensor device is a different sensor type than the second sensor device;
determining, based on one or more suitability criteria, whether to combine the first dataset and the second dataset;
generating, based on the determining, the training dataset by combining the first dataset and the second dataset; and
training the trained universal sensor model to identify one or more targets in the training dataset;
receiving, from a sensor device of the device class, a new dataset;
performing, by the trained universal sensor model, the target detection on the new dataset in response to receiving the new dataset, wherein the target detection comprises determining whether the one or more targets are in the new dataset;
generating an output indicating a result of the target detection on the new dataset; and
transmitting the output to a decision node.