# US 11,256,910 B2 · Method and system for locating an occupant

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

- Number: US 11,256,910 B2
- Document ID: US11256910B2
- Status: Granted
- Kind: B2
- Application number: 16/926,885
- Filed: 2020-07-13
- Published: 2020-12-31
- Granted: 2022-02-22
- Earliest claimed: 2017-03-19
- Assignees: Pointgrab Ltd.
- Applicants: Pointgrab Ltd.
- Inventors: Itamar Roth; Yonatan Hyatt; David Ungarish
- Web page: https://patentgrep.com/patent/US11256910B2

## CPC

- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 40/23: {Recognition of whole body movements, e.g. for sport training}
- G06V 40/172: {Classification, e.g. identification}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An object is tracked in images of the space. A unique identification is assigned to the object and the uniquely identified object may then be located within the space based on the tracking of the object, without having to again uniquely identify the object.

## Claims

### Claim 1

A method for locating a person in a space, the method comprising
obtaining a first image of a person and a second image of a person;
comparing a descriptor of the person in the first image to a descriptor of the person in the second image;
using a dynamic metric that changes based on a prevailing situation, to determine that the person in the second image is a same person in the first image, based on the comparison.

### Claim 2 (depends on 1)

The method of claim 1 wherein the descriptor comprises one or a combination of components selected from: location of the person, size of the person and shape of the person.

### Claim 3 (depends on 1)

The method of claim 1 wherein the descriptor comprises more than one component.

### Claim 4 (depends on 1)

The method of claim 1 wherein the dynamic metric assigns a weight to a component of the descriptor based on a factor that is unrelated to the descriptor.

### Claim 5 (depends on 4)

The method of claim 4 wherein the factor comprises a time difference between capturing of the first image and capturing of the second image.

### Claim 6 (depends on 5)

The method of claim 5 wherein the component of the descriptor comprises a location of the person and wherein the dynamic metric assigns a weight to the location of the person in inverse proportion to the time difference between capturing the first image and capturing the second image.

### Claim 7 (depends on 1)

The method of claim 1 wherein the dynamic metric assigns a weight to a component of the descriptor based on a variability of appearance of the person in the first image, over time.

### Claim 8 (depends on 7)

The method of claim 7 wherein the component of the descriptor comprises an appearance of the person and wherein the dynamic metric assigns a weight to the appearance of the person in inverse proportion to the variability of appearance of the person in the first image, over time.

### Claim 9 (depends on 1)

The method of claim 1 comprising assigning a unique identity to the person in the first image and assigning the unique identity retroactively to a person in previously stored images, determined to be the same as the person in the first image.

### Claim 10 (depends on 1)

The method of claim 1 wherein the first image is captured by a first camera and the second image is captured by a second camera.

### Claim 11 (depends on 10)

The method of claim 10 wherein each of the first and second cameras are configured to obtain image data from a different portion of the space.

### Claim 12 (depends on 10)

The method of claim 10 comprising
detecting a direction of motion of the person in images obtained from the first camera; and
tracking the person in images obtained by the second camera based on the detected direction.

### Claim 13 (depends on 10)

The method of claim 10 comprising tracking the person in images obtained by the second camera using the descriptor associated with the person and based on shape features of the person detected in the images obtained by the first camera.

### Claim 14 (depends on 1)

The method of claim 1 comprising providing a trajectory in the space of the person from the first image.

### Claim 15 (depends on 1)

The method of claim 1 comprising providing a location of the person from the first image, upon demand.
