# US 10,664,986 B2 · Method and system for assigning space related resources

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,664,986 B2
- Document ID: US10664986B2
- Status: Granted
- Kind: B2
- Application number: 15/810,475
- Filed: 2017-11-13
- Published: 2018-05-24
- Granted: 2020-05-26
- Earliest claimed: 2016-11-20
- Assignees: Pointgrab Ltd.
- Applicants: Pointgrab Ltd.
- Inventors: Itamar Roth; Haim Perski; Udi Benbaron
- Web page: https://patentgrep.com/patent/US10664986B2

## CPC

- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 7/62: of area, perimeter, diameter or volume
- G06T 11/26: Drawing of charts or graphs
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Determining occupants' interactions in a space by applying a computer vision algorithm to track an occupant in a set of images of a space to obtain locations in the space of the occupant over time, where a history log of the occupant includes the locations of the occupant in the space over time is created and history logs of a plurality of occupants are compared to extract interaction points between the plurality of occupants.

## Claims

### Claim 1

A method for determining occupants' interactions in a space, the method comprising:
applying a computer vision algorithm to track an occupant in a set of images of a space to obtain locations in the space of the occupant over time;
creating a history log of the occupant, based on non-image-based information related to the occupant, the history log comprising the locations of the occupant in the space over time; and
using a processor
to compare the history logs of a plurality of occupants to extract interaction points between the plurality of occupants, and
create a map of occupant interactions from the interaction points.

### Claim 2 (depends on 1)

The method of claim 1 wherein the computer vision algorithm comprises detecting a shape of the occupant and tracking the shape of the occupant.

### Claim 3 (depends on 1)

The method of claim 1 wherein interaction points comprise locations in the space in which a number of occupants above a specified threshold are located within a defined time period.

### Claim 4 (depends on 1)

The method of claim 1 wherein interaction points comprise locations in the space in which at least two occupants are located for a time period over a specified threshold.

### Claim 5 (depends on 1)

The method of claim 1 wherein interaction points comprise locations in the space in which at least two occupants are located within a defined time period, in a repetitive pattern.

### Claim 6

A system comprising:
a processor configured to
receive images of a space,
create a history log of an occupant based on tracking of the occupant through the images of the space to obtain locations in the space of the occupant over time,
maintain a database of the history logs, and
create a map of occupant interaction in the space based on comparison of history logs, the map comprising locations fulfilling predetermined conditions.

### Claim 7 (depends on 6)

The system of claim 6 comprising an image sensor to obtain the images of the space.

### Claim 8 (depends on 7)

The system of claim 7 wherein the image sensor is configured to obtain top view images of the space.

### Claim 9 (depends on 6)

The system of claim 6 wherein the processor is configured to create a map of occupant interactions comprising locations in the space in which at least two occupants are located for a time period over a specified threshold.

### Claim 10 (depends on 6)

The system of claim 6 wherein the processor is configured to create a map of occupant interactions comprising locations in the space in which at least two occupants are located within a defined time period, in a repetitive pattern.

### Claim 11 (depends on 6)

The system of claim 6 wherein the processor is configured to apply a shape detection algorithm on the images to detect if a body position of the occupant is sitting or standing and creating a map of occupant interactions comprising locations in the space in which a sitting body position of an occupant is detected.

### Claim 12

A method for determining occupants' interactions in a space, the method comprising:
applying a computer vision algorithm to track an occupant in a set of images of a space to obtain locations in the space of the occupant over time;
using a shape detection algorithm to detect if a body position of the occupant is sitting or standing;
creating a history log of the occupant comprising the locations of the occupant in the space over time; and
using a processor
to compare the history logs of a plurality of occupants to extract interaction points between the plurality of occupants, wherein the interaction points comprise locations in the space in which a sitting body position of an occupant is detected, and
create a map of occupant interactions from the interaction points.
