# US 2023/0410512 A1 · Autonomous safety violation detection system through virtual fencing

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

- Number: US 2023/0410512 A1
- Document ID: US20230410512A1
- Status: Published application
- Kind: A1
- Application number: 18/035,272
- Filed: 2021-11-04
- Published: 2023-12-21
- Earliest claimed: 2020-11-04
- Assignees: Astoria Solutions Pte Ltd.
- Applicants: Astoria Solutions Pte Ltd.
- Inventors: Dominic Loke; Kamatchi Kannan Ramkumar; Chun Ee Kho
- Web page: https://patentgrep.com/patent/US20230410512A1

## CPC

- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06T 7/74: {involving reference images or patches}
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G08B 13/19652: {Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm}
- G08B 13/1968: {Interfaces for setting up or customising the system}
- H04N 5/91: Television signal processing therefor
- H04N 7/183: {for receiving images from a single remote source}
- G06T 2207/10016: Video; Image sequence
- G06T 2207/30196: Human being; Person
- G06T 2207/30232: Surveillance
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A virtual fencing system. The system includes one or more virtual fencing devices that include image sensors, capturing images of a region in the vicinity of boundary of a hazard area. The device may operate autonomously to detect one or more humans represented in captured images. The device may process images to determine position parameters of the human and compare those position parameters to the boundary to detect a safety event. Based on the severity of the event, the device may generate one or more outputs, which may be a local audible or visible alert or an electronic message sent to a remote user. The system may also archive or provide to a remote user addition information on the event, such as a snapshot of the human involved in the event, a video clip of the event or a video stream of the event.

## Claims

### Claim 1

A method for configuring a virtual fencing system comprising an image sensor, the method comprising:
presenting an image on a user interface of a computing device, the image having been captured using the image sensor;
receiving through the user interface a boundary; and
storing, in connection with the image sensor, a plurality of boundaries, including the boundary, wherein each of at least some of the plurality of boundaries corresponds to a respective level of a plurality of levels of an alert system.

### Claim 2 (depends on 1)

The method of claim 1,
wherein the virtual fencing system comprises a device, the device comprising:
the image sensor;
non-volatile memory; and
a processor, coupled to the image sensor and the non-volatile memory, the processor configured to detect a human in an image captured using the image sensor, and wherein the method further comprises storing the boundary in the non-volatile memory.

### Claim 3

(canceled)

### Claim 4 (depends on 1)

The method of claim 1, wherein:
a first level of the alert system comprises an alert indicating a presence of a human in proximity of the boundary; and
a second level of the alert system comprises an alert indicating a breach of the boundary.

### Claim 5 (depends on 2)

The method of claim 2, wherein:
the device comprises a network interface; and
the method further comprising configuring the device to communicate through the network interface to a server.

### Claim 6

A method of operating a device comprising a sensor to implement a virtual fence, wherein the sensor is configured to output a stream of image frames, the method comprising:
processing output of the sensor to:
identify a human in the region; and
compute at least one position parameter of the human in the region;
selectively, based on identifying the human in the region, storing sensor output at least in part by storing a portion of the stream of image frames following at least one image frame of the stream of image frames in which the human is represented; and
selectively, based on a comparison of the at least one position parameter to a boundary within the region, outputting an indication of an event.

### Claim 7

(canceled)

### Claim 8 (depends on 6)

The method of claim 6, wherein:
storing the portion of the stream of image frames comprises recording the portion of the stream of image frames as a video, and
selectively storing the sensor output further comprises:
repetitively processing image frames of the stream of image frames to determine whether the human is represented in the image frames; and
based on determining that the human is no longer represented in the image frames, ending recording of the stream of image frames.

### Claim 9 (depends on 6)

The method of claim 6, wherein computing the at least one position parameter of the human comprises detecting a direction of motion of the human.

### Claim 10 (depends on 6)

The method of claim 6, wherein the comparison of the at least one position parameter to the boundary comprises determining whether the human breached the boundary.

### Claim 11 (depends on 6)

The method of claim 6, wherein outputting the indication of the event comprises transmitting an indication of a safety violation in conjunction with at least a portion of the stored sensor output.

### Claim 12 (depends on 11)

The method of claim 11, wherein the portion of the stored sensor output comprises a snapshot representing the human.

### Claim 13 (depends on 6)

The method of claim 6, wherein the comparison of the at least one position parameter to the boundary comprises determining whether the human is in proximity to the boundary.

### Claim 14

The method of clam 6, wherein outputting the indication of the event comprises activating an audible output device and/or a visible output device.

### Claim 15 (depends on 6)

The method of claim 6, wherein outputting the indication of the event comprises electronically transmitting a message comprising a warning of a safety violation.

### Claim 16 (depends on 6)

The method of claim 6, wherein:
the region comprises a facility entrance comprising a pedestrian lane and a vehicle lane;
the boundary is positioned between the pedestrian lane and the vehicle lane; and
outputting the indication of the event comprises outputting an indication that the human has breached the boundary and/or entered the vehicle lane.

### Claim at position 17

17-20. (canceled)

### Claim 21

A device configured for implementing a virtual fence, the device comprising:
one or more image sensors configured to output image frames;
at least one processor coupled to the one or more image sensors; and
a non-transitory computer-readable storage medium storing:
a boundary;
processor executable instructions that, when executed by the at least one processor, cause the at least one processor to perform:
identifying a human in an image frame output by the one or more image sensors;
computing at least one position parameter of the human based on a result of the identifying; and
selectively transmitting a message based on a comparison of the at least one position parameter to the boundary; and
selectively storing a plurality of image frames output by at least one image sensor of the one or more image sensors based at least in part on the at least one position parameter.

### Claim 22 (depends on 21)

The device of claim 21, wherein:
the at least one processor comprises a single-board processor; and
the non-transitory computer-readable storage medium comprises non-volatile memory on the single-board processor.

### Claim 23 (depends on 21)

The device of claim 21, wherein the one or more image sensors comprise at least one of a visible light sensor, an infrared radiation sensor, an ultrasonic sensor, a LIDAR sensor, a RADAR sensor, and a laser sensor.

### Claim 24 (depends on 21)

The device of claim 21, wherein:
the device further comprises a physical output device; and
the processor-executable instructions further cause the at least one processor to perform:
selectively activating the physical output device based at least in part on the at least one position parameter.

### Claim 25 (depends on 21)

The device of claim 21, wherein the processor-executable instructions further cause the at least one processor to perform:
selectively transmitting the stored plurality of image frames based on the comparison of the at least one position parameter to the boundary.

### Claim 26 (depends on 21)

The device of claim 21, wherein the processor-executable instructions further cause the at least one processor to perform:
selectively transmitting a plurality of image frames output by at least one image sensor of the one or more image sensors as a video stream based on the comparison of the at least one position parameter to the boundary.
