AU2021203446A1 - Method and system for compliance monitoring - Google Patents

Abstract

Methods for compliance monitoring are provided. In one embodiment, a method includes identifying users from tracking identifiers and determining whether they comply with distancing requirements. In another embodiment, a method includes using two cameras to capture images of users in an environment and correlating predetermined user and environmental data to the images captured from each of these cameras to determine whether the users comply with distancing requirements. rH 2/4 c 0 0 0 u r'4 oo 7a C +1~ E co LUW 4-. bD Co CJC C) 00 0v -Er 0 0 C Ew o 05 oi 0 -c r

Description

rH 2/4 c 0

0 0 u

r'4

oo

7a C

+1~ E co LUW

4-.

bD Co CJC

C) 00

0v

-Er 0 0

C Ew

o 05 oi 0 -c r

Method and System for Compliance Monitoring

Related application

This application is related to Australian Application Number 2020904140 filed on 12 November 2020, the contents of which are incorporated herein by reference in their entirety.

Field

The present disclosure generally relates to the field of compliance monitoring, in particular monitoring compliance with social distancing requirements.

Background

Compliance monitoring of one or more persons in an environment may be performed under direct supervision. A supervisor reviews the actions of one or more persons in the environment, either by being directly located in the environment or via video footage of the environment and determines whether these actions meet compliance requirements. If an action of a person in the environment does not meet compliance requirements, a warning or alert is issued to the person. However, this process of compliance monitoring is often a cumbersome and inefficient process.

Summary of the invention

According to an embodiment of the present disclosure, there is provided a method including:

capturing, from one or more video monitors, one or more images of a plurality of users located in an environment and providing the images to a processor;

processing, via the processor, the captured images to:

identify each user from one or more tracking identifiers associated with each user; and

determine at least one of a location of and a distance between each user identified in the environment; determining, by the processor based on the processed captured images, whether each user identified in the environment complies with one or more distancing requirements; in accordance with a determination of non-compliance with the one or more distancing requirements, causing by the processor generation of a distancing violation for the user.

In some embodiments, the one or more tracking identifiers may be provided on an item of clothing worn by the user and/or on an item of personal protective equipment worn by the user.

The some embodiments, the location of each identified user and/or the distance between each identified user may be determined based on correlating predetermined user data and/or predetermined environmental data with determined user data from the captured one or more images. In one example, the predetermined and determined user data may include any one or more of: a user's shoulder width, hip width or height. The correlating may further include using predetermined environmental data which includes a position and/or dimension of a landmark located in the environment, wherein the landmark includes any one or more of: a table, chair and/or workstation.

According to another embodiment of the present disclosure, there is provided a method including:

capturing, from each of two or more video monitors, one or more images of a plurality of users located in an environment and providing the images to a processor, wherein the two or more video monitors have overlapping fields of view of at least one workstation in the environment and view the workstation from substantially different view-points;

determining by a processor whether each user identified in the environment complies with one or more distancing requirements, wherein the determining is based on a) the processed captured images and b) correlating predetermined user data and/or predetermined environmental data with determined user data from the captured one or more images; and in accordance with a determination of non-compliance with the one or more distancing requirements, causing by the processor generation of a social distancing violation for the user.

In some embodiments, the determining may be based on predetermined user data and wherein the predetermined and determined user data includes any one or more of: a user's shoulder width, hip width or height.

In some embodiments, the determining may be based on predetermined environmental data and wherein the predetermined environmental data includes a position and/or dimension of at least one landmark located in the environment, wherein the at least one landmark includes the workstation.

In some embodiments, the determining may further include triangulation based on the substantially different view-points and wherein the relative contribution of determining based on triangulation is weighted by a fixed amount or a variable amount. The weighting may be determined by machine learning.

Further aspects of the present invention and further embodiments of the aspects described in the preceding paragraphs will become apparent from the following description, given by way of example and with reference to the accompanying drawings.

Brief description of the drawings

Figure 1 illustrates an exemplary diagrammatic representation of an environment;

Figure 2 illustrates an example video processing system for tracking the location of a user in the environment of Figure 1;

Figure 3 illustrates a block diagram of one example of a computer processing system used in the video processing system of Figure 2;

Figure 4A illustrates an exemplary image of an environment; and

Figure 4B illustrates a diagrammatic representation of a table located in the environment shown in Figure 4A.

Detailed description of the embodiments

The inventors have identified a need for effective systems for monitoring the compliance of one or more persons in an environment to what has been widely called social distancing requirements. For example, a social distancing requirement may include a person being physically located at least 1.5 meters (or another specified amount) from another person and/or a requirement of having only one person per four square meters of space in the environment. Alternatively or additionally, there is a need for monitoring the actions of persons for other reasons, for example to obtain a measure of compliance to work practices or policy, or to facilitate evaluation of worker effectiveness, competence, efficiency or similar.

However, in a work environment it is often difficult to identify and monitor the compliance of a worker's actions to social distancing requirements. The difficulty may be increased, for example, if the worker is wearing personal protective equipment (PPE) or if the actions of one worker obscures the actions of another worker in the field of view of the supervisor.

Figure 1 schematically illustrates an example scenario of the present disclosure as may be implemented in an environment 102, such as a processing factory, an office, a venue, a restaurant, a sporting or recreation facility, a transportation service or the like. Each of one or more users 104 is assigned to a location within the environment 102. In one embodiment, the location may be a spatial location within the environment. In another embodiment, the location may be a volumetric location within the environment. In the example shown in Figure 1, the location may be associated with a workstation 106 to which a user 104 is assigned. In other examples, the location may be associated with a chair and/or table located within the environment 102. In the example of an abattoir, the workstation 106 may be a table in a boning room.

Each user 104 located in the environment 102 is associated with data, for example, one or more images of the user and user details including name, dimensions (e.g. height and width of the user), role, workstation number and other information associated with the user. In one embodiment, the user data is obtained prior to the user 104 entering the environment 102.

In some embodiments, each user 104 is allocated a physical tracking identifier 110 that may be read by one or more video monitors 108 located in the environment 102. By reading the tracking identifier 110 from video data generated by the one or more video monitors 108, the tracking identifier 110 in the field of view of the relevant video monitor(s) 108 may be identified and associated with user data. In one example, the tracking identifier 110 is provided on an item of clothing worn by the user 104. In another example, the tracking identifier 110 is provided on an item of PPE, such as a face shield or mask of the user 104. In some embodiments, the tracking identifier 110 is an alphanumeric identifier and the one or more video monitors 108 are capable of performing Optical Character Recognition (OCR). By reading the tracking identifier 110 associated with a user, the position of the user 104 within the environment is determinable. For example, a video monitor 108 may read an alphanumeric identifier associated with a user 104 as they enter the environment 102, following which a computer processing system can determine, based on for example actual or inferred movement of the user 104, when they are located at workstation 106. In another example, the tracking identifier 110 may be a barcode that is scanned by one or more barcode readers located within the environment 102. For example, a barcode reader may be located at an entry point to the environment 102 and at workstation 106, in which case a direct determination of the user's location in the environment is made (based on knowledge of the location of the barcode reader).

The one or more video monitors 108 provided within the environment 102 may track each user's 104 movement through and/or activities within the environment 102. In some embodiments, a video monitor 108 is positioned at, for example above and/or in front of, each workstation 106 to view the movement and/or actions of a user 104. In some embodiments, a single camera is positioned to have a view of two or more workstations 106, with image processing used to identify movement and/or actions at each workstation 106. In some embodiments, the video monitor 108 includes a camera for producing one or more image sequences of the area of the environment 102.

Each video monitor 108 is used to perform at least one of: a) identify one or more users 104 within the field of view of the video monitor; b) detect the location, movement and/or actions of each user 104 in the environment 102; and c) determine the distance between each user 104 located in the environment 102.

The distance between each user located in the environment 102 may be used to determine compliance or non-compliance of each user with predetermined social distancing requirements. A user will comply with social distancing requirements when a distance between the user and another user meets or exceeds predetermined social distancing requirements, for example, 1-2 meters and more preferably 1.5 meters. A user will not comply with social distancing requirements when a distance between the user and another user does not meet predetermined social distancing requirements. In one embodiment, if a user does not comply with social distancing requirements, a social distancing violation is associated with the user. In one example, the social distancing violation associated with the user is recorded in database 214. In another example, the social distancing violation associated with the user is a notice or warning issued to the user, for example by a communication to a personal communication device of the user (e.g. a mobile phone) and/or by an announcement over a speaker system of the environment 102.

In some embodiments, the one or more video monitors 108 are used to identify a user by comparing captured images of a user to previously obtained user data, for example, one or more images of the user. In some embodiments, a user 104 may be identified instead or additionally by the one or more video monitors 108 reading the tracking identifier 110 associated with the user 104.

In some embodiments, the one or more video monitors 108 are used to detect the location of each user 104 in the environment 102. In one example, a video monitor 108 may identify a user as the user enters the environment 102, following which the computer processing system can determine from the video data subsequent locations of the user, based on for example tracking the actual or inferred movement of the user 104. The system may also use the position of known landmarks, for example, a table, chair and/or workstation 106, within the field of view of the video monitors 108 to determine location. For example, when a user is detected at a workstation 106 and the workstation 106 is assigned a spatial or volumetric location in the environment 102, the spatial or volumetric location of the user within the environment is determinable.

In some embodiments, the one or more video monitors 108 are used to determine the distance between each user 104 located in the environment 104. In one embodiment, each user 104 located in the environment 102 is associated with a 2D coordinate space. In another embodiment, each user located in the environment is associated with a 3D coordinate space. The distance between each user in the 2D or 3D coordinate space may be determined, for a Cartesian coordinate system, by Equations 1 or 2, respectively: d2 D - - x1 )2 + (Y2- (Equation 1) d 3D -- VX2 - X 1 ) 2 + (Y2 - y1)2 + (z2 - zi) 2 (Equation 2)

Where xi, y1, zi is the coordinates of a first user,X2, y2, Z2 is coordinates of a second user and d is distance between the first user and the second user.

In another embodiment, the location of a user 104 and/or the distance between users 104 in the environment 102 is determined based on predetermined user data (e.g. a user's dimensions, such as shoulder width, hip width or the user's height) and/or based on predetermined environmental data (e.g. the physical dimensions of a table, chair and/or workstation or separation distance between a table, chair and/or workstation). The predetermined user data and/or predetermined environmental data may be predetermined from physical measurements or from experimental determinations. In one example, a user's dimension is correlated, for example by a look up table or formula, with distance from a camera of the video monitor 108. In another example, if a first user is identified at a first location in the environment and a second user is identified at a second location in the environment, each user's dimensions, such as shoulder and/or hip width, may be used to determine the distance between the first and second user in the environment. In another example, if a first user is detected at a first workstation and a second user is detected at a second workstation, the predetermined separation distance between the first and second workstations may be used to determine the distance between the first and second user in the environment. The user's location on the screen can provide the direction from the camera to the user. The combination of distance and direction therefore provides a vector on the location of the user. In another example, orthogonal projection may be applied to the predetermined user data to determine the distance of each user from the camera. The distance from the camera, and the measured horizontal (x-axis) and vertical (y-axis) locations, of each user is applied to Equation 2 to determine the 3D distance between each user.

In some embodiments, the distance between each user in the 3D coordinate space may be determined using a Pinhole camera projection model. In one example shown in Figures 4A-4B, each user's predetermined data (for example, shoulder width) is used to assign a spatial or volumetric boundary box to each user identified in a captured image 400 from a camera located in front of a table 402. Each spatial or volumetric boundary box is associated with a centroid. The table 402 is associated with a predetermined width (e.g. 0.9 m) and length (e.g. 5.9 m) and a calculated width (e.g. 0.54 m) and length (e.g. 5.87 m) calculated from the captured image 400. Pinhole camera projections are applied to the ratio of the predetermined and calculated dimensions of the table to determine a horizontal and vertical (e.g. depth) projection. The distance between the centroid of two boundary boxes representing a first user and a second user is calculated from Equation 2 and each horizontal and vertical projection obtained from the pinhole camera projections.

In another embodiment, two or more video monitors 108 located in the environment 102 detect and/or track a user's 104 movement through the environment 102. The position of the user within the environment is determinable from images of the environment captured by the two or more video monitors 108. The use of two cameras with overlapping fields of view from different view-points, provides an ability to use triangulation to determine the location of the user. Triangulation may be used instead of detecting a dimension of the user as described above, or in combination with it. When used in combination, the relative contributions to the determination of locations may be weighted, either by a fixed amount or a variable amount, for example based on machine learning across the fields of view of the cameras of the video monitors. In some embodiments, prior to triangulation being performed, the fields of view of the cameras are used to create a 3D reconstruction of the environment using non-rigid image registration techniques.

In the instance that a position of the user within the environment is not determinable from images captured by a video monitor, the position of the user within the environment may be predicted from the user's last known position. In one embodiment, a Kalman filter and/or Hungarian algorithm is applied to the user's last known positions and captured images of the environment to predict the movement of the user in the environment. In one example, a Hungarian algorithm can determine whether an object (for example, a user or workstation) on a captured image is the same object that was detected on a previously captured image. In another example, a Kalman filter can predict the most probable location of an object on a subsequently captured image, using the location history of the object from previously captured video and/or image/s. Two or more video monitors 108 in the environment may provide a system that continuously monitors and/or predicts a user's position in the environment, for example, in the instance that the field of view of one of the video monitors is obscured or when the position of a second user in the environment obscures the position of a first user in the field of view of one of the video monitors. Further, if an object is not able to be detected on a particular image of a video (for example, due to occlusion of the object), Kalman and Hungarian algorithms may collectively predict the location of the object.

The one or more video monitors 108 may be a video camera or a still camera, configured to take images at predetermined intervals. In some embodiments, the camera operates in the visible light spectrum. The video monitor 108 includes or is in communication with image processing circuitry to perform tracking and/or measurement functions, for example as described herein.

In some embodiments, the one or more video monitors 108 may include bi directional communication to indicate an event, for example, non-compliance with social distancing requirements. In one example, this bi-directional communication is in the form of indicator lights and/or audible tones. The video monitor 108 and/or camera may be controlled remotely through network configurations to allow flexibility of panning, zooming and dynamic changes of the field of view.

Figure 2 illustrates an example video processing system 200 for tracking the location of a user in an environment, for example, an environment as described with reference to Figure 1. In this example, the system 200 includes a tracking system 202 in communication with the one or more video monitors 108 of Figure 1.

In the following description, reference is made to "modules". This is intended to refer generally to a collection of processing functions that perform a function. It is not intended to refer to any particular structure of computer instructions or software or to any particular methodology by which the instructions have been developed.

The video monitor module 204 interacts with the one or more video monitors 108 to identify a user and detect and/or track a user's location in the environment. The video monitor module 204 may be trained to identify a user and detect and/or track a user's location in the environment by the training and/or other data included in video training database 206. In some embodiments, the video monitor module 204 may obtain images of the user 104 before they enter the environment 102. In one embodiment, the one or more video monitors 108 read the tracking identifier 110 associated with a user 104 and the video monitor module 204 compares the tracking identifier 110 to the user's data stored in user database 208 to determine the identity of the user 104. In another embodiment, the video monitor module 204 determines the position of the user 104 in the environment 102 from images captured from the one or more video monitors 108. In another example, the video monitor module 204 determines the location of the user 104 in the environment 102 by determining the workstation (such as workstation 106 described with reference to Figure 1) at which the user 104 is to be located. For example, the video monitor module 204 uses an association of the user 104 to workstation 106 stored in user database 208 to make the determination that the user 104 is located at workstation 106. The video monitor module 204 may determine a spatial or volumetric position of the user 104 in the environment 102.

Analysis module 208 analyses the one or more images captured by the one or more video monitors 108 to determine the distance between each user 104 located in the environment 102. In one embodiment, the analysis module 208 calculates the distance between each user 104 in the environment 102 using the determined spatial or volumetric location of each user and Equations 1 or 2. In another embodiment, the distance between each user 104 in the environment 102 is determined from predetermined user data and/or predetermined environmental data.

Compliance module 210 determines whether each user 104 located in the environment 102 complies or does not comply with predetermined social distancing requirements. In one example, the compliance module 210 compares the calculated distance measurements between each user 104 in the environment 102 to one or more social distancing requirements stored in database 212. A user will comply with a social distancing requirement when a distance between the user and another user meets or exceeds a predetermined social distancing requirement. A user will not comply with social distancing requirement when a distance between the user and another user does not meet a predetermined social distancing requirement. In one embodiment, if a user does not comply with a social distancing requirement, a social distancing violation may be recorded in database 214 for the user.

Video monitor

The video monitor module 204 may be trained to identify and track a user 104 as they move through the environment 102. The video monitor module 204 can be trained using machine learning techniques to identify and track a user by, for example identifying visual features of the user and/or identifying a tracking identifier associated with a user.

The process of training the video monitor 204 to identify and track a user as they move through the environment includes determining a training set, which can be stored on the video training database 206. Typically, a video training database 206 would involve a training set including images of all the users of an environment which can be input into a machine learning algorithm. In one embodiment, the process involves the video monitor 204 identifying a user 104 and/or their tracking identifier 110 based on an image or video and then the video monitor is provided with feedback from a person or algorithm as to whether the identification of the user was correct or not. This may enable the machine learning to apply incremental learning techniques that improve the trained machine learning efficiently and effectively during the training process. Hence, as each identification of a user in the environment is factored in, the video monitor 204 improves any following identifications. When a new image or video of a user is acquired by the video monitor 204, the video monitor can attempt to identify the user. Typically, the video monitor 204 would be able to be trained to identify a match over a certain threshold value. In practice, the threshold value may be 90-95%, such that the video monitor module 204 is able to identify the correct user 90-95% of the time or identify the user within a percentage of accuracy that provides a useful measure for the specific application.

In some embodiments, a deep learning convolutional neural network (CNN) can be used to identify objects of interest in the environment (such as a user 104, workstation 106, and/or a tracking identifier 110) and thereby determine a user's location in the environment. The trained CNN can be then utilised in a tracking system 201 to efficiently track the position of the user in a series of images, in close to or in real time.

Each image whether part of the initial training set or not can be stored in the video training database 206. This means that any determined identification of a user by the video monitor 204 can be used to improve any subsequent identification.

Video training

Video as used in this disclosure comprises individual images so training can be done on images or of sequences of images (compiled as videos).

The training of a machine learning algorithm typically requires a large dataset of training images for it to accurately learn the required features. A separate validation dataset can be used after training to assess the performance (e.g. the accuracy and/or speed) of the trained algorithm on new unseen images or, in combination with or alternatively, feedback can be provided by an appropriate trained person as to whether the identification was correct.

Video can be pre-processed to improve results. For example, a temporal filter may be used to reduce the level of noise. The temporal filter can be performed by, for example, averaging three consecutive frames.

The automated tracking according to the disclosure requires a fast and accurate machine learning algorithm to identify a user in real time or close to real-time. One such architecture that is suitable for practising the present disclosure may be a convolutional neural network (CNN). Various CNN models and training protocols can be used to determine the best performing model in terms of accuracy and speed of user identification. Typically, CNNs are binary classifiers that classify expected objects (e.g. a user 104) on images or videos against irrelevant objects (e.g. object that are otherwise irrelevant for tracking purposes, such as workstation 106).

One example CNN model that can be used consists of three convolutional layers, two pooling layers and one fully connected layer.

Example tracking system

The tracking system 202 is implemented using an electronic device. The electronic device is, or will include, a computer processing system. Figure 3 provides a block diagram of one example of a computer processing system 300. System 300 as illustrated in Figure 3 is a general-purpose computer processing system. It will be appreciated that Figure 3 does not illustrate all functional or physical components of a computer processing system. For example, no power supply or power supply interface has been depicted, however system 300 will either carry a power supply or be configured for connection to a power supply (or both). It will also be appreciated that the particular type of computer processing system will determine the appropriate hardware and architecture, and alternative computer processing systems suitable for implementing aspects of the invention may have additional, alternative, or fewer components than those depicted, combine two or more components, and/or have a different configuration or arrangement of components.

The computer processing system 300 includes at least one processor 302. The processor 302 may be a single computer-processing device (e.g. a central processing unit, graphics processing unit, or other computational device), or may include a plurality of computer processing devices. In some instances all processing will be performed by a processor 302 with co-located (i.e. local) processing devices, however in other instances processing may also, or alternatively, be performed by remote processing devices accessible and useable (either in a shared or dedicated manner) by the system 300.

Through a communications bus 304 the processor 302 is in data communication with a one or more machine-readable storage (memory) devices that store instructions and/or data for controlling operation of the processing system 300. In this instance system 300 includes a system memory 306 (e.g. a BIOS), volatile memory 308 (e.g. random-access memory such as one or more DRAM modules), and non-volatile memory 310 (e.g. one or more hard disk or solid state drives).

System 300 also includes one or more interfaces, indicated generally by 312 via which system 300 interfaces with various devices and/or networks. Generally speaking, other devices may be physically integrated with system 300, or may be physically separate. Where a device is physically separate from system 300, connection between the device and system 300 may be via wired or wireless hardware and communication protocols and may be a direct or an indirect (e.g. networked) connection.

Wired connection with other devices/networks may be by any appropriate standard or proprietary hardware and connectivity protocols. For example, system 102 may be configured for wired connection with other devices/communications networks by one or more of: USB; FireWire; eSATA; Thunderbolt; Ethernet; OS/2; Parallel; Serial; HDMI; DVI; VGA; SCSI; AudioPort. Other wired connections are, of course, possible.

Wireless connection with other devices/networks may similarly be by any appropriate standard or proprietary hardware and communications protocols. For example, system 300 may be configured for wireless connection with other devices/communications networks using one or more of: infrared; Bluetooth; Wi-Fi; near field communications (NFC); Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), long term evolution (LTE), wideband code division multiple access (W-CDMA), code division multiple access (CDMA). Other wireless connections are, of course, possible.

Generally speaking, the devices to which system 300 connects - whether by wired or wireless means - allow data to be input into/received by system 300 for processing by the processor 302, and data to be output by system 300. Example devices are described below, however, it will be appreciated that not all computer processing systems will include all mentioned devices, and that additional and alternative devices to those mentioned may well be used.

For example, system 300 may include or connect to one or more input devices by which information/data is input into (received by) system 300. Such input devices may include physical buttons, alphanumeric input devices (e.g. keyboards), pointing devices (e.g. mice, track pads and the like), touchscreens, touchscreen displays, microphones, accelerometers, proximity sensors, GPS devices and the like. System 300 may also include or connect to one or more output devices controlled by system 300 to output information. Such output devices may include devices such as indicators (e.g. LED, LCD or other lights), displays (e.g. CRT displays, LCD displays, LED displays, plasma displays, touch screen displays), audio output devices such as speakers, vibration modules, and other output devices. System 300 may also include or connect to devices which may act as both input and output devices, for example memory devices (hard drives, solid state drives, disk drives, compact flash cards, SD cards and the like) which system 300 can read data from and/or write data to, and touch-screen displays which can both display (output) data and receive touch signals (input).

System 300 may also connect to communications networks (e.g. the Internet, a local area network, a wide area network, a personal hotspot etc.) to communicate data to and receive data from networked devices, which may themselves be other computer processing systems.

It will be appreciated that system 300 may be any suitable computer processing system such as, by way of non-limiting example, a desktop computer, a laptop computer, a netbook computer, tablet computer, a smart phone, a Personal Digital Assistant (PDA), a cellular telephone, a web appliance. Although the system 300 may act as a server in a client/server type architecture, the system 300 may also include user input/output directly via the user input/output interface 314 or alternatively receiving equivalent input/output of a user via a communications interface 316 for communication with a network 318.

The number and specific types of devices which system 300 includes or connects to will depend on the particular type of system 300. For example, if system 300 is a desktop computer it will typically connect to physically separate devices such as (at least) a keyboard, a pointing device (e.g. mouse), a display device (e.g. a LCD display). Alternatively, if system 300 is a laptop computer it will typically include (in a physically integrated manner) a keyboard, pointing device, a display device, and an audio output device. Further alternatively, if system 300 is a tablet device or smartphone, it will typically include (in a physically integrated manner) a touchscreen display (providing both input means and display output means), an audio output device, and one or more physical buttons. To the extent that system 300 is an example of a user device, then the user input devices as described above will typically be the means by which a user will interact with a system. A person skilled in the art would understand there may be other types of input devices which would operate similarly for the purposes of the present disclosure, such as a microphone for voice activated user commands or other devices not described here.

System 300 stores or has access to instructions and data which, when processed by the processor 302, configure system 300 to receive, process, and output data. Such instructions and data will typically include an operating system such as Microsoft Windows@, Apple OSX, Apple IOS, Android, Unix, or Linux.

System 300 also stores or has access to instructions and data (i.e. software) which, when processed by the processor 302, configure system 300 to perform various computer-implemented processes/methods in accordance with embodiments of the invention (as described below). It will be appreciated that in some cases part or all of a given computer-implemented method will be performed by system 300 itself, while in other cases processing may be performed by other devices in data communication with system 300.

Instructions and data are stored on a non-transient machine-readable medium accessible to system 300. For example, instructions and data may be stored on non transient memory 310. Instructions may be transmitted to/received by system 300 via a data signal in a transmission channel enabled (for example) by a wired or wireless network connection.

It will be understood that the invention disclosed and defined in this specification extends to all alternative combinations of two or more of the individual features mentioned or evident from the text or drawings. All of these different combinations constitute various alternative aspects of the invention.

Claims (10)

1. A method including:

capturing, from one or more video monitors, one or more images of a plurality of users located in an environment and providing the images to a processor;

processing, via the processor, the captured images to:

identify each user from one or more tracking identifiers associated with each user; and

determine at least one of a location of and a distance between each user identified in the environment;

determining, by the processor based on the processed captured images, whether each user identified in the environment complies with one or more distancing requirements;

in accordance with a determination of non-compliance with the one or more distancing requirements, causing by the processor generation of a distancing violation for the user.

2. The method of claim 1, wherein the one or more tracking identifiers are provided on an item of clothing worn by the user and/or on an item of personal protective equipment worn by the user.

3. The method of any one of claims 1-2, wherein a location of each identified user and/or the distance between each identified user is determined based on correlating predetermined user data and/or predetermined environmental data with determined user data from the captured one or more images.

4. The method of claim 3, wherein the predetermined and determined user data includes any one or more of: a user's shoulder width, hip width or height.

5. The method of claim 3, wherein the correlating includes using predetermined environmental data which includes a position and/or dimension of a landmark located in the environment, wherein the landmark includes any one or more of: a table, chair and/or workstation.

6. A method including:

capturing, from each of two or more video monitors, one or more images of a plurality of users located in an environment and providing the images to a processor, wherein the two or more video monitors have overlapping fields of view of at least one workstation in the environment and view the workstation from substantially different view-points;

determining by a processor whether each user identified in the environment complies with one or more distancing requirements, wherein the determining is based on a) the processed captured images and b) correlating predetermined user data and/or predetermined environmental data with determined user data from the captured one or more images; and

in accordance with a determination of non-compliance with the one or more distancing requirements, causing by the processor generation of a social distancing violation for the user.

7. The method of claim 6, wherein the determining is based on predetermined user data and wherein the predetermined and determined user data includes any one or more of: a user's shoulder width, hip width or height.

8. The method of claim 6 or claim 7, wherein the determining is based on predetermined environmental data and wherein the predetermined environmental data includes a position and/or dimension of at least one landmark located in the environment, wherein the at least one landmark includes the workstation.

9. The method of any one of claims 7 to 8, wherein the determining further includes triangulation based on the substantially different view-points and wherein the relative contribution of determining based on triangulation is weighted by a fixed amount or a variable amount.

10. The method of claim 9, wherein the weighting was determined by machine learning.