US 12,442,658 B2
Determining motion in indoor space using probabilistic representation of motion transition
Sean Huberman, Guelph (CA); Ahmed Mahmood, Milton (CA); and Vera Miller, Toronto (CA)
Assigned to Mapsted Corp, Oakville (CA)
Filed by Mapsted Corp, Oakville (CA)
Filed on Jul. 19, 2022, as Appl. No. 17/867,923.
Prior Publication US 2024/0027223 A1, Jan. 25, 2024
Int. Cl. G01C 21/00 (2006.01); G01C 21/20 (2006.01); H04W 4/021 (2018.01); H04W 4/33 (2018.01)
CPC G01C 21/3811 (2020.08) [G01C 21/383 (2020.08); H04W 4/021 (2013.01); H04W 4/33 (2018.02)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying a plurality of points-of-interest (POIs) in a pedestrian area of an indoor space, the plurality POIs being identified by filling the indoor space with a predefined number of points at which probabilistic representation of motion transition is determined;
for each POI from amongst the plurality of POIs, associating with each POI a probabilistic representation of motion transition of a device from the POI, wherein the probabilistic representation of motion transition is indicative of a probability distribution of likely directions of motion that the device can exhibit from the POI, and wherein the associating comprises determining the probabilistic representation of motion transition of the device from the POI based on a geometry of a region of the POI in the indoor space, and a position of the POI in the indoor space and neighboring POIs;
generating a map of the indoor space based on the associating; and
ascertaining a probable motion of the device in the indoor space based on the generated map.