# US 2019/0122065 A1 · Method and system for detecting a person in an image based on location in the image

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

- Number: US 2019/0122065 A1
- Document ID: US20190122065A1
- Status: Published application
- Kind: A1
- Application number: 16/168,904
- Filed: 2018-10-24
- Published: 2019-04-25
- Earliest claimed: 2017-10-24
- Assignees: Pointgrab Ltd.
- Applicants: Pointgrab Ltd.
- Inventors: DAVID UNGARISH; MOSHE NAKASH
- Web page: https://patentgrep.com/patent/US20190122065A1

## CPC

- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes}
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method and system for detecting a person in an image of a space include determining a value of a parameter of an object in the image, wherein if the value exceeds a threshold the object is determined to be a person. If the object is located in a predetermined area in the image, then changing the threshold and determining that the object is a person based on the value of the parameter and the changed threshold.

## Claims

### Claim 1

A method for detecting a person in an image, the method comprising:
detecting an object in an image of a space;
determining a value of a parameter of the object from the image, wherein if the value exceeds a threshold the object is determined to be a person;
if the object is located in a predetermined area in the image then changing the threshold;
determining that the object is a person based on the value of the parameter and the changed threshold; and
generating a signal to control a device based on the determination that the object is a person.

### Claim 2 (depends on 1)

The method of claim 1 wherein changing the threshold comprises lowering the threshold.

### Claim 3 (depends on 1)

The method of claim 1 comprising:
detecting a shape of the object in the image of the space, and
determining that the object is a person based on the detected shape and on the value of the parameter and changed threshold.

### Claim 4 (depends on 1)

The method of claim 1 wherein the predetermined area correlates to a predefined location in the space.

### Claim 5 (depends on 4)

The method of claim 4 comprising:
identifying the predefined location from an image of the space; and
determining the predetermined area based on the identification.

### Claim 6 (depends on 4)

The method of claim 4 comprising:
receiving a signal indicating the predefined location; and
determining the predetermined area based on the signal.

### Claim 7 (depends on 4)

The method of claim 4 wherein the predefined location in the space comprises furniture.

### Claim 8 (depends on 7)

The method of claim 7 wherein the furniture comprises one or more of: a chair, a desk and a bed.

### Claim 9 (depends on 1)

The method of claim 1 comprising aggregating data from images of the space to detect the predetermined area in the image.

### Claim 10 (depends on 1)

The method of claim 1 wherein the parameters of the object comprise one or a combination of: motion size and object size.

### Claim 11 (depends on 1)

The method of claim 1 comprising:
if the value is within a predetermined range then assigning a first weight to the value if the object is located in the predetermined area and assigning a second weight to the value if the object is not located in the predetermined area, obtaining a weighted value and wherein the first weight is higher than the second weight; and
determining that the object is a person based on the weighted value.

### Claim 12 (depends on 1)

The method of claim 1 wherein the signal generated based on the determination that the object is a person is to cause a change in displayed content.

### Claim 13 (depends on 1)

The method of claim 1 wherein the signal generated based on the determination that the object is a person is used to assign space related resources.

### Claim 14 (depends on 1)

The method of claim 1 comprising tracking the object in images of the space and, if the object is determined to be a person, continuing to track the object and, if the object is not determined to be a person, discontinuing tracking of the object.

### Claim 15 (depends on 4)

The method of claim 4 comprising:
receiving an indication of type of location in the space; and
changing the threshold based on the type of location.

### Claim 16 (depends on 15)

The method of claim 15 wherein a type of location comprises one or more of a location with a specific purpose, a location with specific content or a location with specific statistics.

### Claim 17 (depends on 15)

The method of claim 15 wherein the indication of type of location comprises a signal generated by a processor after detecting the predefined area from the image.

### Claim 18 (depends on 15)

The method of claim 15 wherein the indication of type of location is based on user input.

### Claim 19 (depends on 1)

The method of claim 1 wherein the device comprises a space related resource management system to assign workstations to occupants in the space.

### Claim 20 (depends on 1)

The method of claim 1 wherein the image of the space is a top view image.
