# US 2023/0410327 A1 · Method for detecting the motion of at least one object, and corresponding electronic device, system, computer program product and medium.

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

- Number: US 2023/0410327 A1
- Document ID: US20230410327A1
- Status: Published application
- Kind: A1
- Application number: 18/068,792
- Filed: 2022-12-20
- Published: 2023-12-21
- Earliest claimed: 2021-12-21
- Assignees: Orange
- Applicants: Orange
- Inventors: David Excoffier; Franck Roudet; Olivier Hotel
- Web page: https://patentgrep.com/patent/US20230410327A1

## CPC

- G06T 7/215: Motion-based segmentation
- G06T 7/248: {involving reference images or patches}
- G06T 7/254: involving subtraction of images
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10024: Color image
- G06T 2207/20072: Graph-based image processing
- G06T 2207/30232: Surveillance
- G06T 2207/30236: Traffic on road, railway or crossing
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method implemented in an electronic device. The method includes: obtaining two temporally spaced apart images capturing the same scene of a video stream; obtaining a motion map representing differences between the components of the images in at least one video channel; and obtaining at least one geometric shape encompassing a set of moving portions of the motion map. Also provided are the corresponding electronic device, the computer program product and the medium.

## Claims

### Claim 1

A motion detection method, implemented in an electronic device, said method comprising:
obtaining at least two temporally spaced apart images capturing a same scene of a video stream;
obtaining at least a first motion map divided into portions representing differences between values of at least two video channels for a zone of at least two of said images; and
obtaining at least one geometric shape encompassing a set of moving portions of said first motion map.

### Claim 2 (depends on 1)

The motion detection method according to claim 1, wherein a value of a portion of said first motion map is a binary value taking into account differences between the values of each video channel for said zone of said images.

### Claim 3 (depends on 2)

The motion detection method according to claim 2, wherein said value of a portion of said first motion map takes into account the most differences of each video channel for said zone of said images.

### Claim 4 (depends on 1)

The motion detection method according to claim 1, wherein:
the method comprises obtaining a motion map for each video channel of said images, with the motion map of a video channel of said images being divided into portions representing differences for a zone of at least two of said images, for the video channel associated with said motion map;
said first motion map is the motion map, from among the motion maps associated with each of the video channels of said images, that comprises the most portions for which the binary value represents a difference for a zone of said images, for the associated video channel.

### Claim 5 (depends on 1)

The motion detection method according to claim 1, wherein said geometric shape is a rectangular shape.

### Claim 6 (depends on 1)

The motion detection method according to claim 1, wherein said method is iteratively implemented on successive images of the video stream and comprises:
obtaining the first motion map and a second motion map temporally preceding said first motion map,
conditionally associating a first encompassing geometric shape obtained for the first motion map with at least one second encompassing geometric shape obtained for at least said second motion map, said associating taking into account relative positions of said first and second encompassing shapes on said first and second motion maps.

### Claim 7 (depends on 6)

The motion detection method according to claim 6, comprising assigning a same object identifier to said first and second associated geometric shapes.

### Claim 8 (depends on 1)

The motion detection method according to claim 1, comprising assigning a type of object to at least one geometric shape, with said assigning taking into account a size, a width and/or a length of said geometric shape.

### Claim 9 (depends on 1)

The motion detection method according to claim 1, wherein obtaining at least one encompassing geometric shape of a motion map comprises:
obtaining a first histogram relating to portions resulting from a division of said motion map into rows and columns along two different division axes, with the first histogram counting a number of moving portions per column in said motion map;
obtaining a second histogram relating to said portions, with said second histogram counting a number of moving portions per row in said motion map; and
obtaining at least one encompassing geometric shape corresponding to an intersection in the motion map of the columns comprising at least one non-zero element of the first histogram and of the rows comprising at least one non-zero element of the second histogram.

### Claim 10 (depends on 9)

The motion detection method according to claim 9, comprising:
obtaining a third histogram counting the number of moving portions per column in at least one third shape of said obtained encompassing shapes;
obtaining a fourth histogram counting the number of moving portions per row in said third obtained encompassing shape;
obtaining at least a fourth encompassing geometric shape corresponding to an intersection in the motion map of the columns comprising at least one non-zero element of the third histogram and of the rows comprising at least one non-zero element of the fourth histogram.

### Claim 11 (depends on 10)

The motion detection method according to claim 10, wherein said obtaining said third and fourth histograms are implemented successively on at least one previously obtained encompassing geometric shape of the motion map.

### Claim 12 (depends on 11)

The motion detection method according to claim 11, wherein the method comprises rotating said first motion map prior to dividing said first motion map.

### Claim 13

An electronic device comprising:
at least one processor, said at least one processor being configured to:
obtain at least two temporally spaced apart images capturing a same scene of a video stream;
obtaining at least a first motion map divided into portions representing differences between values of at least two video channels, for a zone of at least two of said images; and
obtaining at least one geometric shape encompassing a set of moving portions of said first motion map.

### Claim 14 (depends on 13)

An electronic device according to claim 13, wherein a value of a portion of said first motion map is a binary value taking into account differences between the values of each video channel for said zone of said images.

### Claim 15 (depends on 14)

An electronic device according to claim 14, wherein said value of a portion of said first motion map takes into account the most differences of each video channel for said zone of said images.

### Claim 16 (depends on 13)

An electronic device according to claim 13, wherein said at least one processor is configured to obtain a motion map for each video channel of said images, with the motion map of a video channel of said images being divided into portions representing differences for a zone of at least two of said images, for the video channel associated with said motion map, and wherein said first motion map is the motion map, from among the motion maps associated with each of the video channels of said images, that comprises the most portions for which the binary value represents a difference for a zone of said images, for the associated video channel.

### Claim 17 (depends on 13)

An electronic device according to claim 13, wherein said geometric shape is a rectangular shape.

### Claim 18 (depends on 13)

An electronic device according to claim 13, wherein obtaining at least one encompassing geometric shape of a motion map comprises:
obtaining a first histogram relating to portions resulting from a division of said motion map into rows and columns along two different division axes, with the first histogram counting a number of moving portions per column in said motion map;
obtaining a second histogram relating to said portions, with said second histogram counting a number of moving portions per row in said motion map; and
obtaining at least one encompassing geometric shape corresponding to an intersection in the motion map of the columns comprising at least one non-zero element of the first histogram and of the rows comprising at least one non-zero element of the second histogram.

### Claim 19 (depends on 13)

The electronic device according to claim 13, wherein obtaining at least one encompassing geometric shape of a motion map comprises:
obtaining a first histogram relating to portions resulting from a division of said motion map into rows and columns along two different division axes, with the first histogram counting a number of moving portions per column in said motion map;
obtaining a second histogram relating to said portions, with said second histogram counting a number of moving portions per row in said motion map; and
obtaining at least one encompassing geometric shape corresponding to an intersection in the motion map of the columns comprising at least one non-zero element of the first histogram and of the rows comprising at least one non-zero element of the second histogram.

### Claim 20

A non-transitory computer readable medium comprising a computer program recorded therein comprising instructions for implementing, when the program is executed by a processor of an electronic device, a motion detection method implemented in the electronic device, said method comprising:
obtaining at least two temporally spaced apart images capturing a same scene of a video stream;
obtaining at least one first motion map divided into portions representing differences between values of at least two video channels for a zone of at least two of said images; and
obtaining at least one geometric shape encompassing a set of moving portions of said first motion map.
