# US 2023/0410519 A1 · Suspicious person alarm notification system and suspicious person alarm notification method

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

- Number: US 2023/0410519 A1
- Document ID: US20230410519A1
- Status: Published application
- Kind: A1
- Application number: 18/242,908
- Filed: 2023-09-06
- Published: 2023-12-21
- Earliest claimed: 2021-03-08
- Assignees: I-Pro Co., Ltd.
- Applicants: i-PRO Co., Ltd.
- Inventors: Masashi KOGA
- Web page: https://patentgrep.com/patent/US20230410519A1

## CPC

- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G01S 7/003: {Transmission of data between radar, sonar or lidar systems and remote stations}
- G01S 7/415: {Identification of targets based on measurements of movement associated with the target}
- G01S 7/417: {involving the use of neural networks}
- G01S 13/867: {Combination of radar systems with cameras}
- G01S 13/886: {for alarm systems (alarms with electrical actuation G08B13/22)}
- 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 10/82: using neural networks
- G06V 20/44: {Event detection}
- G06V 40/15: {Biometric patterns based on physiological signals, e.g. heartbeat, blood flow}
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- G08B 13/19602: {Image analysis to detect motion of the intruder, e.g. by frame subtraction}
- G08B 13/19613: {Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion}
- G08B 29/186: {Fuzzy logic; neural networks}
- H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N 7/183: {for receiving images from a single remote source}
- H04N 23/60: Control of cameras or camera modules
- G06T 2207/30196: Human being; Person
- G06T 2207/30232: Surveillance
- G08B 25/00: Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A suspicious person alarm notification system includes one camera including artificial intelligence and a radar and capturing an image of a person, and a server communicating with the camera. The camera receives a signal presenting in an emission direction of the radar, acquires vital information on the person from the signal, acquires, by using the artificial intelligence, motion information on the person from a captured image, calculate an index indicating suspicious person likelihood of the person based on the vital information and the motion information on the person, and transmit, to the server, person information related to the person in response to determining that the index is equal to or greater than a threshold value. The server outputs an alarm indicating that a suspicious person is detected.

## Claims

### Claim 1

A suspicious person alarm notification system comprising:
at least one camera including artificial intelligence and a radar and being configured to capture an image of a person; and
a server configured to communicate with the camera, wherein
the camera is configured to
receive a signal emitted by the radar and reflected by an object present in an emission direction of the radar,
acquire vital information on the person from the signal,
acquire, by using the artificial intelligence, motion information on the person from a captured image obtained by capturing an image of the person,
calculate an index indicating suspicious person likelihood of the person based on the vital information and the motion information on the person, and
transmit, to the server, person information related to the person in which the vital information and the motion information on the person are associated with each other in response to determining that the index is equal to or greater than a threshold value, and
the server is configured to
output, based on the person information transmitted from the camera, an alarm indicating that a suspicious person is detected.

### Claim 2 (depends on 1)

The suspicious person alarm notification system according to claim 1, wherein
the camera is configured to
calculate, by using the artificial intelligence, an emotion index of the person based on the vital information,
acquire behavior analysis information by executing behavior analysis processing on the person based on the motion information, and
calculate the index based on the emotion index and the behavior analysis information.

### Claim 3 (depends on 2)

The suspicious person alarm notification system according to claim 2, wherein
the camera is configured to
acquire first position information on the person based on the signal,
generate, based on the first position information, first time series data in which the vital information on the person is arranged in time series,
acquire second position information on the person based on a position of the person appearing in the captured image,
generate, based on the second position information, second time series data in which the motion information on the person is arranged in time series,
calculate the emotion index based on the first time series data, and
acquire the behavior analysis information by executing the behavior analysis processing based on the second time series data.

### Claim 4 (depends on 3)

The suspicious person alarm notification system according to claim 3, wherein
the camera is configured to
calculate the emotion index of the person in response to determining that the first time series data is present for a first predetermined time or more.

### Claim 5 (depends on 3)

The suspicious person alarm notification system according to claim 3, wherein
the camera is configured to
acquire the behavior analysis information on the person in response to determining that the second time series data is present for a second predetermined time or more.

### Claim 6 (depends on 1)

The suspicious person alarm notification system according to claim 1, wherein
the camera is configured to
acquire first position information on the person based on the signal,
acquire second position information on the person based on a position of the person appearing in the captured image, and
collating the first position information with the second position information to assign the same identification information to the vital information and the motion information corresponding to the person.

### Claim 7 (depends on 6)

The suspicious person alarm notification system according to claim 6, wherein
the camera is configured to
transmit, to the server, the person information further including the second position information on the person and the captured image in which the person is imaged, and
the server is configured to
superimpose a frame line on the person appearing in the captured image based on the second position information, and
generate and output an alarm screen including a captured image on which the frame line is superimposed.

### Claim 8 (depends on 6)

The suspicious person alarm notification system according to claim 6, wherein
the camera is configured to
transmit, to the server, the person information further including position information on another person of which the index is not equal to or greater than the threshold value, the second position information on the person of which the index is equal to or greater than the threshold value, and the captured image in which the another person and the person are imaged, and
the server is configured to
superimpose a first frame line on the person appearing in the captured image based on the second position information,
superimpose a second frame line on the another person appearing in the captured image based on the position information on the another person, and
generate and output an alarm screen including a captured image on which the first frame line and the second frame line are superimposed.

### Claim 9 (depends on 1)

The suspicious person alarm notification system according to claim 1, wherein
the server is configured to
generate and output, based on the person information, an alarm screen further including a report button for reporting to a preset report destination.

### Claim 10 (depends on 9)

The suspicious person alarm notification system according to claim 9, wherein
the server is configured to
transmit the captured image and the person information to the report destination when the report button is selected by a user operation.

### Claim 11

A suspicious person alarm notification method that is executed by a computer communicably connected to a server configured to output an alarm indicating that a suspicious person is detected, the suspicious person alarm notification method comprising:
receiving a signal emitted by a radar and reflected by an object present in an emission direction of the radar;
acquiring vital information on a person from the signal;
acquiring, by using artificial intelligence, motion information on the person from a captured image obtained by capturing an image of the person;
calculating an index indicating suspicious person likelihood of the person based on the vital information and the motion information on the person; and
outputting, based on person information related to the person in which the vital information and the motion information on the person are associated with each other, an alarm indicating that a suspicious person is detected in response to determining that the index is equal to or greater than a threshold value.

### Claim 12 (depends on 11)

A computer readable storage medium storing a computer program that causes a computer to execute the suspicious person alarm notification method according to claim 11.
