# US 2020/0074166 A1 · Method and system for determining occupancy from images

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

- Number: US 2020/0074166 A1
- Document ID: US20200074166A1
- Status: Published application
- Kind: A1
- Application number: 16/609,516
- Filed: 2018-04-26
- Published: 2020-03-05
- Earliest claimed: 2017-04-30
- Assignees: Pointgrab Ltd.
- Applicants: Pointgrab Ltd.
- Inventors: RAM NATHANIEL; MOSHE NAKASH; URI ZACKHEM
- Web page: https://patentgrep.com/patent/US20200074166A1

## CPC

- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06T 2207/30196: Human being; Person
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Embodiments of the invention relate to a method for determining that an object in a sequence of images is a human. The method may include the steps of detecting an object in a first image from the sequence of images and assigning a first score to the object. The object is tracked to a second image from the sequence of images and a second score is assigned to the object in the second image. The second score is compared to a threshold that is inversely realted to the first score and a determination that the object in the second image is a human is made based on the comparison.

## Claims

### Claim at position 1

1-26. (canceled)

### Claim 27

A method for determining that an object in a sequence of images is a human, the method comprising
detecting an object in a first image from the sequence of images;
assigning a first score to the object;
tracking the object to a second image from the sequence of images;
assigning a second score to the object in the second image;
comparing the second score to a threshold that is inversely related to the first score;
determining that the object in the second image is a human based on the comparison; and
controlling a device based on the determination that the object in the second image is a human.

### Claim 28 (depends on 27)

The method of claim 27 comprising assigning the first score to the object based on a shape of the object in the first image.

### Claim 29 (depends on 27)

The method of claim 27 comprising assigning the first score to the object based on motion of the object.

### Claim 30 (depends on 27)

The method of claim 27 comprising assigning the first score to the object based on location of the object in the first image.

### Claim 31 (depends on 27)

The method of claim 27 comprising assigning the first score to the object based on a size of the object in the first image.

### Claim 32 (depends on 27)

The method of claim 27 comprising determining that the object in the second image is a human based on a shape of the object in the second image and based on the comparison to the threshold.

### Claim 33 (depends on 27)

The method of claim 27 comprising determining that the object in the second image is a human based on motion of the object in the sequence of images and based on the comparison to the threshold.

### Claim 34 (depends on 27)

The method of claim 27 comprising determining that the object in the second image is a human based on a location of the object in the second image and based on the comparison to the threshold.

### Claim 35 (depends on 27)

The method of claim 27 comprising determining the second score based on a shape of the object in the second image.

### Claim 36 (depends on 27)

The method of claim 27 wherein the sequence of images comprises top view images of the space.

### Claim 37

A method for determining occupancy in a space, the method comprising
assigning a first score to an object in an image from a sequence of images of the space;
assigning a second score to the object in a later image from the sequence of images, the second score dependent on the first score and on a location of the object in the later image;
outputting a signal indicating occupancy based on the second score.

### Claim 38 (depends on 37)

The method of claim 37 comprising assigning the first score based on a shape of the object in the image.

### Claim 39 (depends on 37)

The method of claim 37 comprising assigning the first score based on motion of the object.

### Claim 40 (depends on 39)

The method of claim 39 wherein the motion comprises typical human movements.

### Claim 41 (depends on 37)

The method of claim 37 comprising assigning the first score based on a location of the object in the image.

### Claim 42 (depends on 41)

The method of claim 41 wherein the location of the object in the image comprises a location within a predetermined area.

### Claim 43 (depends on 41)

The method of claim 41 comprising assigning the first score based on a size of the object in the image.

### Claim 44 (depends on 37)

The method of claim 37 wherein the location of the object in the later image comprises a location within a predetermined area.

### Claim 45 (depends on 37)

The method of claim 37 comprising changing a threshold for the second score based on a value of the first score.

### Claim 46 (depends on 37)

The method of claim 37 comprising determining a weight of the second score based on a value of the first score.
