# US 2017/0287145 A1 · Running sensing method and system

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

- Number: US 2017/0287145 A1
- Document ID: US20170287145A1
- Status: Published application
- Kind: A1
- Application number: 15/507,760
- Filed: 2014-10-23
- Published: 2017-10-05
- Earliest claimed: 2014-09-04
- Assignees: S-1 Corporation
- Applicants: S-1 Corporation
- Inventors: Minkook CHO; Dong Sung LEE
- Web page: https://patentgrep.com/patent/US20170287145A1

## CPC

- H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06T 7/73: using feature-based methods
- G06T 7/80: Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G08B 13/19613: {Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion}
- G08B 13/19645: {Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over}
- G06T 7/001: {using an image reference approach}
- G06T 2207/10016: Video; Image sequence
- G06T 2207/30196: Human being; Person
- G06T 2207/30244: Camera pose
- H04N 7/183: {for receiving images from a single remote source}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS

## Abstract

Disclosed are a method and a system for detecting running. The system for detecting running detects a moving object in an input image and detects a foreground edge of the object. Further, the system for detecting running uses the foreground edge to extract a foot-print image coordinate and extract a head coordinate of the object and uses the foot-print image coordinate, a titled angle of the camera, and an installation height of the camera to acquire a foot-print real coordinate. Here, the system for detecting running uses the foot-print real coordinate of the object and the height of the object to determine whether the object runs.

## Claims

### Claim 1

A system for detecting running, comprising:
an object detector detecting a moving object in an image photographed by a camera;
a foreground edge detector detecting a foreground edge of the object;
a foot-print and head coordinate extractor using the foreground edge to extract a foot-print image coordinate and extract a head coordinate that is a coordinate for a head part of the object;
a camera installation angle calculator calculating a tilt angle of the installed camera;
a coordinate converter using the foot-print image coordinate, the angle, and an installation height of the camera to acquire a foot-print real coordinate that is a coordinate where the object is spaced apart from the camera;
a height extractor calculating a height of the object; and
a running condition determinator using the foot-print real coordinate and the height of the object to determine whether the object runs.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the installation height of the camera is a value arbitrarily set by a user.

### Claim 3 (depends on 2)

The system of claim 2, wherein:
the height extractor uses the installation height of the camera, the foot-print image coordinate, and the head coordinate to calculate the height of the object.

### Claim 4 (depends on 1)

The system of claim 1, wherein:
the camera installation angle calculator uses a vertical angle of view of the camera, the number of vertical pixels of the image, and the number of Y-axis coordinate pixels spaced apart from a center of the camera to calculate the angle.

### Claim 5 (depends on 1)

The system of claim 1, wherein:
the coordinate converter acquires the foot-print real coordinate based on a back perspective conversion method.

### Claim 6 (depends on 5)

The system of claim 5, wherein:
the coordinate converter calculates a first distance of the foot-print spaced apart from the camera in a vertical direction and uses the first distance to calculate a second distance that is a distance of the foot-print spaced apart from the camera in a horizontal direction, and
the first distance and the second distance are the foot-print real coordinate.

### Claim 7 (depends on 2)

The system of claim 2, wherein:
the foot-print real coordinate and the height of the object are changed depending on the installation height of the camera.

### Claim 8 (depends on 1)

The system of claim 1, wherein:
the running condition determinator uses the foot-print real coordinate to calculate a moving distance of the object and determines that the object runs when the moving distance is larger than the height of the object.

### Claim 9 (depends on 1)

The system of claim 1, wherein:
the object detector detects the object by a background modeling method.

### Claim 10 (depends on 1)

The system of claim 1, wherein:
the foreground edge detector detects an image edge from the entire image of the object, detects a time edge using a current image of the object and an image temporally continued to the current image of the object, and extracts a common component of the image edge and the time edge as the foreground edge.

### Claim 11 (depends on 1)

The system of claim 1, wherein:
the camera is a pinhole camera.

### Claim 12

A method for detecting running of an object using an image photographed by a camera in a system for detecting running, comprising:
detecting a moving object in the image;
detecting a foreground edge of the object;
extracting a foot-print image coordinate using the foreground edge;
extracting a head coordinate that is a coordinate for a head part of the object using the foreground edge;
calculating a tilt angle of the installed camera;
acquiring a foot-print real coordinate that is a coordinate where the object is spaced apart from the camera using the foot-print image coordinate, the angle, and an installation height of the camera;
calculating a height of the object; and
determining whether the object runs using the foot-print real coordinate and the height of the object.

### Claim 13 (depends on 12)

The method of claim 12, wherein:
the installation height of the camera is a value arbitrarily set by a user.

### Claim 14 (depends on 12)

The method of claim 12, wherein:
the calculating of the height of the object includes calculating the height of the object using the installation height of the camera, the foot-print image coordinate, and the head coordinate.

### Claim 15 (depends on 13)

The method of claim 13, wherein:
the foot-print real coordinate and the height of the object rely on the installation height of the camera.

### Claim 16 (depends on 12)

The method of claim 12, wherein:
the calculating of the angle includes calculating the angle using a vertical angle of view of the camera, the number of vertical pixels of the image, and the number of Y-axis coordinate pixels spaced apart from a center of the camera.

### Claim 17 (depends on 12)

The method of claim 12, wherein:
the acquiring of the foot-print real coordinate includes:
calculating a first coordinate that is a coordinate where the foot-print is spaced apart from the camera in a vertical direction; and
calculating a second coordinate that is a coordinate where the foot-print is spaced apart from the camera in a horizontal direction using the first coordinate.

### Claim 18 (depends on 12)

The method of claim 12, wherein:
the determining includes:
calculating a moving distance of the object using the foot-print real coordinates; and
comparing the moving distance with the height of the object.

### Claim 19 (depends on 18)

The method of claim 18, wherein:
the determining further includes determining that the object runs when the moving distance is larger than the height of the object.
