US 12,442,889 B2
Multi-channel spatial positioning system
James Francis Hallett, Palo Alto, CA (US); and Kirk Arnold Moir, Palo Alto, CA (US)
Assigned to INPIXON, Palo Alto, CA (US)
Filed by INPIXON, Palo Alto, CA (US)
Filed on Oct. 4, 2021, as Appl. No. 17/493,450.
Application 17/493,450 is a continuation of application No. 16/668,180, filed on Oct. 30, 2019, granted, now 11,164,329.
Claims priority of provisional application 62/754,446, filed on Nov. 1, 2018.
Prior Publication US 2022/0148217 A1, May 12, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 18/214 (2023.01); G01S 5/02 (2010.01); G01S 5/16 (2006.01); G06F 18/22 (2023.01); G06F 18/2431 (2023.01); G06T 7/11 (2017.01); G06T 7/13 (2017.01); G06T 7/277 (2017.01); G06T 7/292 (2017.01); G06T 7/73 (2017.01); G06V 10/764 (2022.01); G06V 20/52 (2022.01); G06V 40/20 (2022.01); G08B 5/22 (2006.01); G08B 13/196 (2006.01); H04N 23/90 (2023.01); G01J 5/10 (2006.01); G01N 33/00 (2006.01); G01S 5/18 (2006.01)
CPC G01S 5/16 (2013.01) [G01S 5/02585 (2020.05); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06F 18/2431 (2023.01); G06T 7/11 (2017.01); G06T 7/13 (2017.01); G06T 7/277 (2017.01); G06T 7/292 (2017.01); G06T 7/73 (2017.01); G06V 10/764 (2022.01); G06V 20/52 (2022.01); G06V 40/25 (2022.01); G08B 5/22 (2013.01); G08B 13/196 (2013.01); H04N 23/90 (2023.01); G01J 5/10 (2013.01); G01N 33/0047 (2013.01); G01S 5/18 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30232 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A non-transitory, machine-readable medium storing instructions that, when executed by one or more processors, effectuate operations comprising:
acquiring, using a computer system, a set of entities, a set of entity attributes associated with each entity of the set of entities, and a dataset associated with each entity of the set of entities, wherein acquiring at least a portion of the set of entities and at least a portion of the set of entity attributes includes:
acquiring, using the computer system, a set of images from a plurality of cameras that each have a different respective field of view and at least part of the fields of view are of a monitored environment, wherein a first subset of the set of images is acquired by a first camera and a second subset of the set of images is acquired by a second camera,
detecting, using the computer system, a first entity based on the first subset of the set of images using a convolutional neural network that includes a convolution layer or a set of convolutional operations that provide translation invariance to detect and localize the first entity that is moving in the first subset of the set of images,
determining, using the computer system, a first set of entity attributes associated with the first entity based on the first subset of the set of images,
detecting, using the computer system, a second entity based on the second subset of the set of images using the convolutional neural network that includes the convolution layer or the set of convolutional operations that provide the translation invariance to detect and localize the second entity that is moving in the second subset of the set of images, and
determining, using the computer system, a second set of entity attributes associated with the second entity based on the second subset of the set of images,
determining, using the computer system, that the first entity of the set of entities and the second entity of the set of entities should be associated based on a set of matching entity confidence factors indicating a likelihood that the first entity and the second entity are based on a same physical entity, wherein entity confidence factors for the first entity and the second entity are based on the first set of entity attributes of the set of entity attributes associated with the first entity and the second set of entity attributes of the set of entity attributes associated with the second entity;
associating the first entity and the second entity as the same physical entity;
calculating, using the computer system, a sequence of locations based on a first set of locations included in a first dataset associated with the first entity and based on a second set of locations included in a second dataset associated with the second entity,
wherein at least a portion of the locations in the sequence of locations are different than the locations included in the first set of locations and the second set of locations, and
wherein at least one of a first portion of the first set of locations or a first portion of the second set of locations are determined from a set of images obtained by at least one of the first camera or the second camera, and at least one of a second portion of the first set of locations or a second portion of the second set of locations is determined from a set of sensor measurements obtained by at least one other sensor that is different than the at least one of the first camera or the second camera;
storing, using the computer system, the sequence of locations in a computer-readable media in communication with the computer system, and
displaying, using the computer system, a graphical representation of the first entity in a graphical representation of the monitored environment on a graphical display device, wherein the graphical representation of the monitored environment dynamically updates based on the sequence of locations.