WO2024221021A1

WO2024221021A1 - System and method for reporting offences

Info

Publication number: WO2024221021A1
Application number: PCT/ZA2024/050016
Authority: WO
Inventors: Kevin Lester OLINSKY; Ricardo DA FONSECA; Warren SWALES
Original assignee: Olinsky Kevin Lester; Da Fonseca Ricardo; Swales Warren
Priority date: 2023-04-20
Filing date: 2024-04-11
Publication date: 2024-10-24

Abstract

The present disclosure relates to a computer-implemented method for reporting offenses by endpoint computing devices (12.1) in data communication with a server (14). The method may comprise registering one or more of the endpoint computing devices (12.1) each having an associated unique identifier and a camera for capturing image data; receiving image data from one of the endpoint computing devices (12.1); accessing a machine learning (ML) module (30) trained by training images of offences; inputting the received image data to the ML-module (30) which automatically analyses the data to identify an offence therefrom; receiving an analysis result from the ML-module (30); and responsive to an identified offence, outputting an approval message to the endpoint computing device (12.1) that transmitted the image data. The present disclosure extends to a system for reporting offenses by endpoint computing devices (12.1) and to a computer program product for reporting offenses by endpoint computing devices (12.1) in data communication with a server (14).

Description

SYSTEM AND METHOD FOR REPORTING OFFENCES

CROSS-REFERENCE TO RELATED APPLICATION

This application claims priority from South African provisional patent application number 2023/04569 filed on 20 April 2023, which is incorporated by reference herein.

FIELD OF THE INVENTION

This present disclosure relates to a system and method for reporting offences. More particularly, but not exclusively, this present disclosure relates to a system and method for reporting traffic offenses or criminal offences.

BACKGROUND TO THE INVENTION

In South Africa, road safety is a huge problem. Violations of road traffic law that are often seen on South African roads include road users running red lights, speeding, reckless driving, driving over double lines or yellow lines, driving with expired licence discs, overloading vehicles, parking in non-designated parking zones, driving with unroadworthy vehicles, or driving without wearing a seatbelt. Criminal offences are also common on roads, such as driving under the influence of alcohol or other substances that impair driving ability. Most of these issues are overlooked, thus being taken advantage of. Perpetrators of many traffic infringements simply ignore traffic laws, sometimes in order to transport as many people as possible per day. This leads to an unpredictable and dangerous road environment where other drivers as well as pedestrians are unsafe, leading to a very large number of road deaths per year that can be attributed to offences.

In 2022, Mr. Simon Zwane of the Road Traffic Management Corporation made a press statement reporting that 8547 young people between 21 and 34 years of age had lost their lives on South African roads between 2019 and 2021 . In 2020, Statistics South Africa published a breakdown of the financial health of local municipalities. Fines are one of the largest sources of ‘other’ revenue for municipalities of which traffic fines make up the biggest portion. In 2020 alone, R4.6 billion in fines was collected due to road traffic law infringements, representing 1.1% of total revenue. The problem is exacerbated by a national shortage in traffic officers which means a lack of surveillance and enforcement of road traffic rules. Infringers can get away without being apprehended due to the current inefficient, expensive, environmentally unfriendly, and outdated methods of road traffic law enforcement. The current systems cost the South African Government billions per annum in damaged roads, barriers, traffic signs, traffic lights, static traffic cameras, traffic officers, emergency services, etc.

Several interventions to address this issue have been implemented over the years with varying results. These include the employment and training of more law enforcement officers and increasing traffic infrastructure. Current road traffic infrastructure includes traffic signs, traffic lights, static traffic and speeding cameras and traffic officers. The problem with most of these interventions is that they are very expensive to maintain and are predominantly static in nature or bulky. For example, where a speed camera has been set motorists eventually familiarise themselves with where these are and only abide by the law when passing that specific zone. While some areas are higher risk zones for traffic violations, all roads should be monitored to ensure safety and abidance of traffic rules. Similarly, motorists are aware of old speed cameras which remain unmaintained and out of order and abuse the lack of surveillance in such areas. The shortage of traffic officers on the ground as well as the lack of funds, resources or infrastructure means that police cannot set up cameras and monitor all the roads every day. Therefore, many violations of traffic law are not even seen by traffic officers. It will also be appreciated that these problems do not only occur in South Africa, but also in many other countries over the world.

The applicant considers there to be room for improvement.

The preceding discussion of the background to the invention is intended only to facilitate an understanding of the present invention. It should be appreciated that the discussion is not an acknowledgment or admission that any of the material referred to was part of the common general knowledge in the art as at the priority date of the application.

SUMMARY OF THE INVENTION

In accordance with an aspect of the present disclosure there is provided a computer-implemented method for reporting offenses by endpoint computing devices in data communication with a server, the method conducted at the server and comprising: registering one or more of the endpoint computing devices, each of the registered endpoint computing devices having at least an associated unique identifier and a camera for capturing image data; receiving image data from one of the registered endpoint computing devices; accessing a machine learning module which is trained by a plurality of training images of offences; inputting the received image data to the machine learning module which automatically analyses the received image data so as to identify an offence therefrom; receiving a result of the analysis from the machine learning module; and responsive to an identified offence, outputting an approval message to the registered endpoint computing device that transmitted the received image data.

The method may include, by the server, allocating a reward that is digitally linked to the unique identifier of the registered endpoint computing device from which the image data is received. The reward may be a monetary reward, a coupon or a voucher. The reward may be a digital reward, e.g., an e-gift card, which can be redeemed digitally, or the reward may be in the form of pre-paid airtime via a mobile network, or the reward may be a digital token or other digital asset. The method may include allocating or assigning the reward to the registered endpoint computing device.

The method may include uniquely associating the received image data with the unique identifier of the registered endpoint computing device from which the image data is received. The unique association may, optionally, be performed by the server.

The method may include establishing a secure communications session between the registered endpoint computing device and the server.

The method may include, by the registered endpoint computing device, encrypting or digitally signing the image data by way of an endpoint private key associated with the registered endpoint device. The endpoint private key may, alternatively, or in addition, be associated with the unique identifier of the registered endpoint computing device. The server may be arranged to decrypt encrypted image data received from the registered endpoint computing device, e.g., by way of a public key.

The server may be arranged to verify, authenticate, or confirm the authenticity of the received image data, e.g., by decrypting the encrypted received image data. Any cryptographic protocol, including asymmetric cryptography that utilises public and private key pairs may be implemented, or digital endpoint device certificates may be used. The encrypted image data may inhibit duplicate image data or fraudulent image data from being transmitted, or it may enable the server to detect these duplicates or fraud. The method may include, by the server, digitally verifying or digitally authenticating the received image data so as to confirm the authenticity thereof.

Alternatively, or in addition, the received image data may be encrypted by the server using a server-side private key. This may inhibit third parties from accessing the received image data. The method may include outputting a digital infringement notice, fine, or penalty, based on the result of the analysis received from the machine learning module.

The method may include inputting the received image data to the machine learning module which may be arranged to automatically analyse the received image data so as to identify an offender therefrom. Optionally, the method may include receiving an offender identifier from the machine learning module. The offender identifier may, for example, be a vehicle licence plate number, biometric data, facial recognition data relating to the offender, or other data relating to the offender. The offender identifier or other data relating to the offender may, for example, be derived from the image data by the machine learning module.

The received image may, alternatively or in addition, be input to an adjudication module by the server. An adjudicator computing device may be in data communication with the adjudicator module. The outputting of an approval message by the server may be preceded by, or succeeded by, an approval input facilitated by the adjudicator module and the adjudicator computing device.

The received image data or the encrypted received image data may be stored in a database accessible by the server.

The method may include, by the server, storing and/or updating a digital record of the received image data. This may facilitate the server to keep track of the received image data from a plurality of endpoint computing devices.

Each endpoint computing device may be a personal handheld electronic device, a security camera such as a closed-circuit television (CCTV) security camera, a dashboard camera, or a traffic camera. However, it will be appreciated that the present disclosure is not limited to any specific form of capturing device. Any type of image capturing device, or a data capturing device (e.g., forming part of an electronic device) may for example be used.

The method may include receiving geolocation data from the registered endpoint computing device that transmitted the image data. The geolocation data may be associated with the image data. The server may be arranged to uniquely associate the endpoint computing device that transmitted the image data with the geolocation data of the received image data.

The method may include associating the unique identifier of the endpoint computing device with the geolocation data. Alternatively, or in addition, the method may include associating the unique identifier of the endpoint computing device with the received image data.

The storing and/or updating may include storing and/or updating the geolocations associated with the received image data in the database accessible by the server.

The received image data may be photographic data or videographic data.

The method may include, by the server, receiving a user input which is indicative of whether the image data relates to a possible traffic offence, and/or to a possible criminal offence. Alternatively, or in addition, the machine learning module may be arranged to determine whether the image data relates to a possible traffic offence and/or to a possible criminal offence, and to output data relating to this determination to the server.

The method may include, during a registration process, prompting a user to input user details via the endpoint computing device, e.g., via a user interface provided at the endpoint computing device.

The method may include, by the server, storing the user details in the database accessible by the server. The user details may include a telephone number, an email address, an identification number, a physical address, an Internet Protocol (IP) address or another digital identifier, and the like.

The method may include, by a vetting component accessible by the server, using the user details to perform a background check of the user including but not limited to a credit check, a criminal record check, an address verification, and the like. The vetting component may be arranged to accept or reject the registration of the user based on a result of the background check.

In accordance with another aspect of the present disclosure there is provided a computer- implemented method for reporting offenses by endpoint computing devices in data communication with a server, the method conducted at a first one of the endpoint computing devices and comprising: registering at the server, the endpoint computing device which has at least an associated unique identifier and a camera for capturing image data; transmitting image data from the registered endpoint computing device to the server which has access to a machine learning module that is trained by a plurality of training images of offences so as to enable the server to input the received image data to the machine learning module which automatically analyses the received image data in order to identify an offence therefrom, the server receiving a result of the analysis from the machine learning module; and responsive to an identified offence, receiving an approval message from the server at the registered endpoint computing device.

Further features of the method may include carrying out (or at least partially carrying out), at the first one of the endpoint computing devices, one or more of the method steps defined above.

In accordance with another aspect of the present disclosure there is provided a system for reporting offenses by endpoint computing devices, the system comprising: a server computer in data communication with the endpoint computing devices, the server computer including or having access to a processor and a memory, said memory containing instructions executable by the processor, to execute functions of components including: an endpoint registration component that operatively registers one or more of the endpoint computing devices, each of the registered endpoint computing devices having at least an associated unique identifier and a camera for capturing image data; a receiving component that operatively receives image data from one of the registered endpoint computing devices; a machine learning module interface component that operatively accesses a machine learning module which is trained by a plurality of training images of offences; an inputting component that operatively inputs the received image data to the machine learning module which automatically analyses the received image data so as to identify an offence therefrom; a result receiving component that operatively receives a result of the analysis from the machine learning module; and an output component which, responsive to an identified offence, operatively outputs an approval message to the registered endpoint computing device that transmitted the received image data.

The system may include additional components for carrying out one or more of the method steps defined above.

In accordance with another aspect of the present disclosure there is provided a computer program product for reporting offenses by endpoint computing devices in data communication with a server, the computer program product comprising a non-transitory computer-readable medium having stored computer-readable program code for performing the steps of: registering one or more of the endpoint computing devices, each of the registered endpoint computing devices having at least an associated unique identifier and a camera for capturing image data; receiving image data from one of the registered endpoint computing devices; accessing a machine learning module which is trained by a plurality of training images of offences; inputting the received image data to the machine learning module which automatically analyses the received image data so as to identify an offence therefrom; receiving a result of the analysis from the machine learning module; and responsive to an identified offence, outputting an approval message to the registered endpoint computing device that transmitted the received image data.

The computer-readable medium may be a non-transitory computer-readable medium. The computer-readable program code may be executable by a processing circuit.

Embodiments of the present disclosure will now be described, by way of example only, with reference to the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

In the drawings:

Figure 1 is a schematic diagram which illustrates an exemplary embodiment of a system in accordance with aspects of the present disclosure;

Figure 2 is a high-level block diagram illustrating components of an exemplary server according to aspects of the present disclosure;

Figure 3 is a high-level block diagram illustrating components of an exemplary registered endpoint computing device according to aspects of the present disclosure;

Figure 4 is a schematic flow diagram illustrating an exemplary method in accordance with an aspect of the present disclosure for reporting offenses by an endpoint computing device in data communication with a server;

Figure 5 is another schematic diagram which illustrates an exemplary embodiment of a system in accordance with aspects of the present disclosure;

Figure 6 is a swim-lane flow diagram which illustrates an exemplary method in accordance with an aspect of the present disclosure for reporting offenses by an endpoint computing device in data communication with a server;

Figure 7 is a diagram showing an exemplary user interface that may be displayed by an endpoint device, as well as exemplary steps in a method in accordance with aspects of the present disclosure;

Figure 8 is a schematic diagram which illustrates an exemplary embodiment of a method in accordance with aspects of the present disclosure;

Figure 9 is another diagram illustrating an exemplary user interface that may be displayed by an endpoint device which may execute a method in accordance with aspects of the present disclosure;

Figure 10 is a yet further exemplary user interface that may be displayed by an endpoint device which may execute a method in accordance with aspects of the present disclosure; and

Figure 11 illustrates an example of a computing device in which various aspects of the disclosure may be implemented.

DETAILED DESCRIPTION WITH REFERENCE TO THE DRAWINGS

Embodiments of a system and method for managing offence reporting are disclosed. Suspected offenses may be any violation or infringement of traffic and/or criminal law. In embodiments of the present disclosure an endpoint computing device may also be referred to as a user device. Each endpoint device or user device may be registrable at a central server or backend with which it may be in data communication either constantly or intermittently. Each of the endpoint device(s) may be associated with a unique identifier, or each endpoint device may be uniquely identifiable by the backend or central server. Each endpoint device may be capable of capturing photos and/or videos of offences or suspected offences. These offences may, for example be witnessed by a user of the relevant endpoint device, or the image data relating to the suspected offence may be automatically captured by an un-manned endpoint device. The endpoint device need not be limited to any specific form of capturing device, and any image capturing device or data capturing device (e.g., forming part of an electronic device) can be used. Examples of image capturing devices that can be implemented by the present disclosure include (but are not limited to) an automated security camera, smart camera, Internet of Things (loT) device, smart traffic camera, or the like. Other examples of endpoint devices that may be implemented by aspects of the present disclosure may be, for example, a smartphone, dashboard camera, or the like. Data in the form of one or more photos or videos of a suspected offence may be uploaded to the server or backend from a registered endpoint device. Data received from an endpoint device may be encrypted to avoid duplication and fraudulent entries such as digitally altered photographs.

The offense data may be assessed to determine if an infringement or an offense has been committed. The assessment may be performed by an artificial intelligence model or machine learning (ML) model that may be trained, or pre-trained. The ML model may also be termed a trained classification machine learning model. The machine learning model or module may be a neural network (NN), and it may have a deep learning network architecture. The deep learning network may be a convolutional neural network (CNN), or a fully convolutional deep neural network (FCDNN or FCNN). Other types of artificial neural networks may also be implemented by the present disclosure. The server or backend may implement a machine learning model, or it may have access to a cloud-based machine learning model. An input image (such as image data received by the server or backend from the endpoint device) or a sequence of images may be input to the machine learning module or model according to aspects of the present disclosure. The machine learning model or module may be pre-trained or trained to provide an output that is indicative of whether or not the input image data relates to, or positively identifies, an offence in it. In other words, predefined images or image data may have been previously input into the machine learning model/module in order to train it to intelligently identify offences (whether criminal, traffic-related or other types of offences) from received image data, and to generate an output that indicates findings of the analysis performed by the machine learning module/model. The output of the machine learning model/module may be fed back to the central server or backend for further processing. The machine learning model may be trained using machine learning techniques (such as, but not limited to NN, CNN, DNN, FCDNN etc.) to improve accuracy of its predictions and/or the accuracy of the identified offences, or so as to increase efficiency whereby the offences are reported, managed or processed.

Hence, the received offense data may be analysed by the central server and/or by a machine learning model to automatically identify and verify offenses. The offender may also be identified from the received images or image data. E.g., the machine learning model/module may be trained to automatically perform facial recognition, or other biometric recognition, in order to identify an offender in the image data, e.g., from a database of known offenders. The result of the analysis of the adjudication may be sent to the server. If an offense is verified to have occurred, a reward may be sent to the device that transmitted the offense data and the offender may be issued a penalty. Such a penalty may be a fine or a warning.

In addition, or alternatively, assessment of the data may also be done by one or more trained and approved members or operators. The system and method of the present disclosure may be implemented for managing, capturing, and/or reporting offences. Traffic and criminal law violations may hence be alleviated by the present disclosure which may increase the safety of roads, and optionally also reward users for participating.

Figure 1 is a schematic diagram which illustrates an exemplary embodiment of a system (10) according to aspects of the present disclosure. Various combinations of the described features and aspects may be used in a given implementation.

Referring to Figure 1 , the system (10) may be implemented for reporting offenses by endpoint computing devices (12.1 , 12.2 to 12.n). The endpoint computing devices (12.1 to 12.n) may be in data communication with a server computer (14), and they may be registered at the server (14). Data communication between the server (14) and endpoint computing devices (12.1 to 12.n) may be by way of a communications network such as the Internet. The data communication may be intermittent or continuous. The server computer (14) may include, or it may have access to a processor (16) and a memory (18), said memory containing instructions executable by the processor, to execute functions of components of the system (10). The exemplary embodiment of Figure 1 is described in more detail below.

The server (14) may include the processor (16) for executing the functions of components described in the present disclosure, which may be provided by hardware or by software units executing on the processor. The software units may be stored in the memory component (18) and instructions may be provided to the processor (16) to carry out the functionality of the described components. In some cases, for example in a cloud computing implementation, software units arranged to manage and/or process data on behalf of the server (14) may be provided remotely.

Turning to Figure 2, there is shown a high-level block diagram of the server computer (14) with exemplary components of the server (14). In Figure 3 is shown a first one of the registered endpoint computing devices (12.1 , in this case) with exemplary components of the registered endpoint computing device (12.1 ). In certain embodiments of the present disclosure, the endpoint device may be termed a user device, and in the exemplary embodiment of Figure 1 , the first endpoint device (12.1) may be a user device such as a smartphone. However, it will be appreciated that the endpoint device may be any electronic device or computing device. The endpoint device may, for example, form part of an Internet of Things (loT) environment. In other words, the endpoint device may, or may not be associated with a specific user. The server computer (14) may include an endpoint registration component (20) which may be arranged to operatively register one or more of the endpoint computing devices (12.1 to 12.n). Each of the registered endpoint computing devices (e.g., 12.1) may have at least an associated unique identifier (22) and a camera (24) for capturing image data. In the various embodiments of the present disclosure, the camera (24) may also be referred to as an image capturing component, or another data capturing component may be implemented instead of a camera.

The server (14) may also include a receiving component (26) that may be arranged to operatively receive image data from one of the registered endpoint computing devices (e.g., from 12.1). The server computer (14) may also include a machine learning module interface component (28) that includes, or that operatively accesses a machine learning module (30) which is trained by a plurality of training images (32) of offences. Embodiments are possible in which the machine learning module may form part of the server, or it may be hosted by the server. However, embodiments are also possible in which the machine learning module may be accessible by the server, e.g., online over the Internet, or in a cloud computing implementation. The server computer (14) may further include an inputting component (34) that may be arranged to operatively input the received image data to the machine learning module (30). The machine learning module (30) may be arranged to automatically analyse the received image data so as to identify an offence therefrom. The machine learning (ML) module (30) may include an analysing component (36), e.g., for performing this automatic analysis of the received image data. In embodiments of the present disclosure, the ML module (30) may be pre-trained. However, embodiments are also envisaged in which the ML module is trained by the server.

The server computer (14) may further include a result receiving component (38) which may be arranged to operatively receive a result of the analysis from the machine learning module (30), or from the ML module interface component (28). The server computer (14) may also include an output component (40) which may also be termed a transmitting component. The output component (40) may be arranged, responsive to an identified offence, to operatively output an approval message to the registered endpoint computing device (e.g., 12.1 ) that transmitted the received image data. Optionally, the server may further include an encrypting component (42) and a database component (44), or the server (14) may have access to a database.

Referring to Figure 3, as mentioned above, the endpoint computing device (12.1 ) may be registered at the server (14). The registered endpoint computing device (12.1 ) may for example be a portable electronic device, such as a mobile phone (or smart phone), tablet computer, wearable computing device, personal digital assistant, laptop computer, digital security camera (e.g., 12.2) or smart security camera, or the like. Any image capturing device or data capturing device (e.g., forming part of an electronic device) may be implemented by the present disclosure, and the present disclosure is not limited to any specific form of capturing device. The registered endpoint computing device (12.1 ) may for example be a mobile device of a first user (15, see Figure 1) which may have been pre-registered or enrolled by the user (15) for use of the system (10). A software application (46) may execute on the registered endpoint device (12.1) and in some implementations, registration of the registered endpoint device (12.1 ) may entail registration of the software application (46), or registration may be facilitated by the software application (46).

The registered endpoint device (12.1 ) and/or software application (46) may be associated with the unique identifier (22). The unique identifier may, for example, include or be derived from one or more hardware descriptors of hardware components in the device, such as an International Mobile Equipment Identity (IMEI) number, a central processor unit (CPU) serial number, a hard drive serial number, or the like. The unique identifier (22) may alternatively, or in addition, be a unique device identifier associated with the registered endpoint device (12.1 ) (or registered user device) such as, but not limited to a MAC (Media Access Control) address associated with the registered user device. Alternatively, or in addition, the identifier may be a communication address associated with the registered user device, such as an Internet Protocol (IP) address. The method may include, by the server, using the unique identifier to ensure that data relating to the offense or the image data is only transmitted once to the server, e.g., once per offence (or a sequence of images may only be transmitted once per offence, per geolocation, or per endpoint device, as the case may be). Stated differently, the server (14) may uniquely associate the received image data with the unique ID (22) of the registered endpoint computing device (12.1 ) so as to inhibit duplication, fraud or the like. A timing component (not shown) may be implemented by the server, or by the endpoint device, and the transmission of image data may be disabled for a set time period (e.g., after image data of a first suspected offence has been transmitted), before the server again allows the endpoint device to transmit image data (e.g., to prevent duplication or fraud).

The endpoint device (e.g., 12.1 , but also any one of the other endpoint device(s), e.g., 12.2) may include a processor (e.g., 50) for executing the functions of components described in the present disclosure, which may be provided by hardware or by software units executing on the endpoint device (12.1). The software units may be stored in the memory component (52) and instructions may be provided to the processor (50) to carry out the functionality of the described components. In some cases, for example in a cloud computing implementation, software units arranged to manage and/or process data on behalf of the endpoint device (12.1 ) may be provided remotely. Some or all of the components described may be provided by the software application downloadable onto and executable on the endpoint device (e.g. 12.1 ).

The server (14) may uniquely associate or link the registered endpoint device (12.1), or the unique device identifier (22), with a user record (48) of the user (15) by way of a suitable enrolment process, as is well known in the art. The user record (48) may be securely stored in a database (44) associated with the server or accessible by the server (14). The registered endpoint computing device (12.1 ) may further be associated with a communication address thereof, such as a mobile station international subscriber directory number (MSISDN) or other identifier or address by way of which messages, notifications, etc. may be transmitted from the server (14) to the registered endpoint device (12.1). The server (14) may be enabled to associate the registered endpoint device (12) with the user record (48), so as to be uniquely identifiable by the server. The endpoint computing device (12.1 ) may include the processor (50) and the memory (52), as well as a transmitting component (54) and a receiving component (56). A geolocation determining system (58) of the registered endpoint computing device (12.1 ) may optionally be implemented so as to determine a geolocation of the registered endpoint computing device (12.1) in use. The method (100) may include receiving geolocation data from the registered endpoint computing device (e.g., 12.1) that transmitted the image data. The geolocation data may be associated with the image data. The server may be arranged to uniquely associate the endpoint computing device that transmitted the image data with the geolocation data of the received image data. This may facilitate identification and/or verification of the offence. The ML module (30) may optionally be trained to take the geolocation data into account when analysing the received image data. The method (100) may include associating the unique identifier (22) of the endpoint computing device (12.1) with the geolocation data. Alternatively, or in addition, the method may include associating the unique identifier of the endpoint computing device with the received image data. The geolocation data may optionally be used by the server (14) to inhibit or prevent duplicate image data or fraudulent image data from being received. The method (100) may further include storing and/or updating the geolocations associated with the received image data in the database (44) accessible by the server (14).

The application (46) may have, or it may provide an endpoint interface (60) (which may also be termed a user interface in certain embodiments), e.g., which may be arranged to receive user input. A secure communication component (62) may be provided, e.g., by the application (46) and this may facilitate secure communications between the registered endpoint computing device

(12.1) and the server (14), e.g., over the Internet.

In Figure 4 there is shown a schematic flow diagram of an exemplary method (100) according to aspects of the present disclosure. The system (10) described above may implement a method (100) for reporting offenses by endpoint computing devices (12.1 to 12.n) in data communication with the server (14). One or more aspects of the method may be conducted at the server (14), and one or more aspects of the method may be conducted at the endpoint computing device

(12.1). Throughout the present disclosure, it should be appreciated that any one or more of the steps or processes of the method may be conducted either at the server (14), or at the endpoint computing device (e.g., 12.1 ).

The server (14) may provide the application (46) (“app”) to the endpoint computing device (12.1) e.g., by making it available to be downloadable and installable on the endpoint device. A web service (64) may optionally also be provided by the server (14) to the endpoint device (12.1). The server (14) may be arranged for registering one or more of the endpoint computing devices (12.1 to 12.n). In the present embodiment, a user (e.g., 15) may be prompted to register via the app, and a registration process (65) may be performed. Exemplary steps of the registration process (65) may include prompting the user to input their Name, Surname, Address, Cell phone number, email address, Identification (ID) Number. Optionally the registration process may also include prompting the user to scan their ID and/or drivers’ licence. It should be appreciated that these are mere examples of data input by the user for the registration process. Many other implementations of the registration process are possible. For example, embodiments are possible in which this registration process takes place by way of an automatic enrolment of the endpoint computing device (12.1 ) at the server (14) e.g., as also described elsewhere in the present disclosure. Optionally, the registration process (65) may be approved or declined (68) by the server (14) and an appropriate message may be transmitted to the endpoint computing device and/or displayed to the user (15). In an exemplary embodiment, the user may be enabled to open (70) the app. However, it will be appreciated that the app may also operate autonomously, and it may operate without requiring user input (e.g., on the smart security camera (12.2)).

In the present embodiment, the user may open (70) the app, and the user may be prompted (72) via the app to take a photo or a video of a suspected offence (preferably a digital photo or video) (or scan a license disk/plate, or take a photo thereof (see also Figure 4)). In the exemplary embodiment of Figure 1 , the user (15) may be prompted to take a photograph of a suspected offence, and the user may for example take a digital photograph that includes image data of an offence committed by a motor vehicle, e.g., a motor vehicle (17) that may have driven recklessly. It will be appreciated that numerous other types of offences may be witnessed, and/or the user may be enabled via the system to capture image data of various other types of offences, including criminal or traffic offences.

In the current example embodiment, the user (15) may be prompted (73) by the app (46) to capture either a traffic offence (74), or a criminal offence (76). The system and method of the present disclosure may implement a first list (78) of offences for traffic offences, and a second list (80) of offences for criminal offences. These lists may include any number of traffic offences, or criminal offences, as the case may be, and the number 100 is merely shown for exemplary purposes. The first list (78) and the second list (80) may be pre-determined. The server (14) may also, for example, dynamically update or change these lists (78, 80) depending on practical considerations.

It should be appreciated that the selection or prompting (73) is optional, and this may be performed automatically, e.g., in the example embodiment where user input is not required. For example, the smart security camera, or traffic camera (e.g., 12.2) may automatically perform one or more of the steps (e.g., steps 65, 70, 72, 73), and the type of offence (e.g., traffic or criminal offence) may be preconfigured for that camera.

Still referring to the exemplary method (100) in Figure 4, image data may be received (82) at the server (14) from one of the registered endpoint computing devices (e.g., from endpoint device (12.1) in this case). The image data may also be uploaded by the endpoint computing device (12.1) to the server (14). Further image data (e.g., of or relating to further images) may also be added as may be required. The server (14) may be arranged to access the machine learning (“ML”) module (30) which is trained by the plurality of training images of offences. The ML module (30) is also described above with reference to Figure 2. The server (14) may be arranged for inputting the received image data to the machine learning module (30) which automatically analyses the received image data so as to identify an offence therefrom. The server (14) may optionally receive (84) a result of the analysis from the machine learning module (30). The server (14) may further be arranged, responsive to an identified offence, for outputting (86) an approval message to the registered endpoint computing device (e.g., 12.1) that transmitted the received image data. Optionally, the image data may be declined (90) by the server (14), e.g., based on the result received (84) from the ML module (30). A notification (92) of the declined image data may be transmitted by the server (14) to the endpoint device (12.1 ).

In an exemplary embodiment, an adjudication module (88) may be implemented by the server (14), or the server may have access to it. The adjudication module (88) may, for example, have access to an online traffic information system and/or a national traffic authority computing system. The received image data relating to the offence or infringement may additionally, or alternatively, be adjudicated by one or more trained and approved members (94) to ascertain and/or establish that the captured infringement is legitimate or to verify it. However, it will be appreciated that embodiments are possible in which one or more functions of these members (94) are performed automatically by the systems and methods of the present disclosure. Optionally, the offence, infringement or crime may be processed and approved by the adjudication team (94) based on the received image data. The adjudication module (88) may for example receive a user input from the adjudication team, or from one or more adjudication users. The adjudication team may for example include police personnel. The received user input may be indicative of the legitimacy of the offence, and it may be used by the server (14) to perform an optional or additional verification step relating to the suspected offence, e.g., before transmitting the approval or decline message(s) (86, 92) to the endpoint device(s) (12.1 to 12.n).

As a further optional step in the exemplary method (100), the police may approve or decline the image data, and an arrest (96) of a perpetrator, (e.g., a person driving the vehicle 17) if it was a criminal offence, may be performed. For example, the image data transmitted by the endpoint device (12.1 or 12.2) may include data relating to a pedestrian (21) which was the victim of a “hit- and-run” incident, or another type of incident that relates to a criminal offence, or a traffic offence. The ML module (30) may additionally, or alternatively be arranged to automatically identify the criminal offence from the image data. The ML module (30) may also be arranged to automatically identify other types of offences by analysing the image data, e.g., other traffic offences such as crossing a solid line, or running a red light as shown in the further exemplary implementation of the system (100) shown in Figure 5. Again, the endpoint device (12.1 ) may be in data communication with the server, and capable of uploading or transmitting image data relating to the offence to the server computer (14).

Referring again to the exemplary embodiment of Figure 4, the server (14) may be arranged to allocate (98) a reward, e.g., based on successfully approving the image data. The method (100) may include, by the server (14), allocating a reward that is digitally linked to the unique identifier (22) of the registered endpoint device (e.g., 12.1) from which the image data is received. The reward may be a monetary reward, a coupon or a voucher. The reward may be a digital reward, e.g., an e-gift card, which can be redeemed digitally, or the reward may be in the form of pre-paid airtime via a mobile network. The reward may be transmitted to the endpoint device (e.g., 12.1 ), or the reward may be redeemed by a user associated with the relevant endpoint device (12.1 , 12.2, to 12.n as the case may be) in another way. Alternatively, or in addition, the reward allocated by the server may be a digital token or other digital asset which may e.g., be allocated to the registered endpoint computing device by the server.

The method (100) may include uniquely associating the received image data with the unique identifier (22) of the registered endpoint computing device (e.g., 12.1) from which the image data is received. The unique association may, optionally, be performed by the server (14). The method (100) may, optionally, include establishing a secure communications session between the registered endpoint computing device (e.g., 12.1 ) and the server (14). The image data may for example be uploaded or transmitted from the registered endpoint computing device to the server computer during the secure communication session. These features may facilitate data security, and it may also inhibit fraudulent or duplicate image data from being received by the server. Duplication may also be avoided or alleviated by verification of the date, time, location and the like by the systems and methods of the present disclosure, e.g., to avoid any repeated reports of the infringement or offence on the same day, or during a predefined time period.

The method (100) may also include, by the registered endpoint computing device (e.g., 12.1 ), encrypting or digitally signing the image data, e.g., by way of an endpoint private key (23) associated with the registered endpoint device (12.1). An associated encryption/decryption component (53) may optionally be provided by the endpoint device (12.1 ). The server computer (14) may also have an associated encryption/decryption component (99), e.g., which may be arranged to decrypt the encrypted image data received from the endpoint computing device (e.g., 12.1 ), e.g., by way of a public key. The endpoint private key (23) may, alternatively, or in addition, be associated with the unique identifier (22) of the registered endpoint computing device (12.1 ). The server may be arranged to verify, authenticate, or confirm the authenticity of the received image data, e.g., by decrypting the encrypted received image data. Any cryptographic protocol, including asymmetric cryptography that utilises public and private key pairs may be implemented. The encrypted image data may inhibit duplicate image data or fraudulent image data from being transmitted.

Alternatively, or in addition, the received image data may be encrypted or digitally signed by the server (14) using a server-side private key, e.g., in order to uniquely associate the received image data with a specific endpoint computing device (e.g., 12.1) out of the plurality of endpoint computing devices (12.1 , 12.2, to 12.n as the case may be) forming part of (or connected to) the system (10). This may inhibit third parties from accessing or copying the received image data, i.e., to prevent fraud, duplication, etc.

The method (100) may further include outputting a digital infringement notice, fine, or penalty, based on the result of the analysis received from the machine learning module (30). In this case, a notification or message relating to the digital infringement notice, fine, or penalty, may optionally be transmitted by the server to a computing device associated with the relevant offender (e.g., the driver of the vehicle 17). The server may have access to a database having a list of computing devices associated with individuals. In an exemplary embodiment, the ML module (30) may receive image data relating to an image captured by the user (15) in Figure 5 in which a driver of a vehicle (18) speeds across a pedestrian crossing (27) while also running over a red light (29). The ML module may be trained by the plurality of training images (32) so as to automatically identify one or more of these offences from the image data. The ML module may further be trained to automatically identify a number plate (31 ) or other identification from the image data, which uniquely associates the vehicle (18) with an offender. The server (14) may access the database or list of computing devices associated with individuals and automatically identify the driver of the vehicle associated with the number plate (31 ) and transmit a notification, penalty or fine to an address associated with that offender.

The method (100) may include inputting the received image data to the machine learning module (30) which may be arranged to automatically analyse the received image data so as to identify an offender therefrom. Optionally, the method may include receiving an offender identifier from the machine learning module. The offender identifier may, for example, be a vehicle licence plate number, biometric data, facial recognition data relating to the offender, or other data relating to the offender. For example, the image data may include data relating to biometrics of the offender, e.g., a digital picture of the face of the offender. The ML module and/or the server may be arranged to automatically perform an analysis of the received image data to identify the offender from the image data. The offender identifier or other data relating to the offender may, for example, be derived from the image data by the machine learning module.

Referring to Figures 1 to 5, the received image may, alternatively or in addition, be input to the adjudication module (88) by the server (14). An adjudicator computing device (95) may be in data communication with the adjudicator module (88). The outputting of an approval message by the server may be preceded by, or succeeded by, an approval input facilitated by the adjudicator module (88) and the adjudicator computing device (95), e.g., when an adjudicator (94) inputs an approval to the adjudicator computing device (95) in order to approve the received image data. Similarly, a decline input may be inputted to the adjudicator computing device (95) and hence to the adjudication module (88) associated with the server (14).

The received image data or the encrypted received image data may be stored in the database (44) accessible by the server (14). The method (100) may include, by the server (14), storing and/or updating a digital record of the received image data. This may facilitate the server to keep track of the received image data from the plurality of endpoint computing devices (12.1 , 12.2 to 12. n).

It will be appreciated that various endpoint devices may be implemented by the systems and methods of the present disclosure. Each endpoint computing device may be a personal handheld electronic device, a security camera such as a closed-circuit television (CCTV) security camera, a vehicle mounted camera such as a dashboard camera, or a traffic camera. The received image data may be photographic data or videographic data. The method (100) may optionally include, by the server (14), receiving a user input which is indicative of whether the image data relates to a possible traffic offence (74), or to a possible criminal offence (76). The method (100) may also include, during the registration process (e.g., 65), prompting a user (e.g., 15) to input user details via the endpoint computing device (e.g., 12.1 ). This may be performed, e.g., via a user interface provided at the endpoint computing device (12.1). The method (100) may further include, by the server (14), storing the user details in the database (44) accessible by the server (14). The user details may include any one or more of: a telephone number, an email address, an identification number, a physical address, an Internet Protocol (IP) address or another digital identifier, and the like.

The method (100) may also include, by a vetting component (not shown) accessible by the server (14), using the user details to perform a background check of the user (e.g., 15). A verting process may be implemented by the server (14), and this vetting process may include, but need not be limited to, a credit check, a criminal record check, an address verification, and the like. The vetting component may be arranged to accept or reject the registration of the user based on a result of the background check. Embodiments of the present disclosure are possible in which the server includes the vetting component, or the server may access the vetting component, e.g., in a cloudcomputing or online environment.

The system (10) described above may implement an exemplary method for reporting offenses by endpoint computing devices (12.1 to 12.n) in data communication with the server (14). Another exemplary method (1000) for reporting offences is illustrated in the swim-lane flow diagram of Figure 6 (in which respective swim-lanes delineate steps, operations or procedures performed by respective entities or devices). One or more steps of the method (1000) may be performed by the endpoint device (e.g., 12.1 , 12.2, to 12.n) and one or more steps of the method (1000) may be performed by the server (14). The first endpoint device (12.1) is diagrammatically illustrated, but the corresponding steps may just as well be performed at one or more of the other endpoint devices (12.2, to 12.n). The endpoint device (e.g., 12.1) may be registered (1010) at the server (14). Image data may be captured (1012) by the endpoint device (12.1). Image data may be transmitted (1014) or uploaded from the registered endpoint computing device (12.1 ) to the server (14) where it may be received (1016). The server (14) may access (1018) the machine learning module (30) that is trained by a plurality of training images (32) of offences. The server (14) may input the received image data to the machine learning module (30). The ML module (30) may automatically analyse (1020) the received image data in order to identify an offence therefrom (if possible). The ML module may transmit (1022) a result of the analysis to the server (14), e.g., if an offence has been identified from the received image data. The server (14) may receive (1024) a result of the analysis from the machine learning module (30). The server may transmit (1026) an approval message to the endpoint device (12.1). Responsive to an identified offence, the endpoint device (e.g., 12.1 ) may receive (1028) the approval message (86) from the server (14). Optionally, the endpoint device (12.1) may also receive (1030) the (e.g., digital) reward.

The method may optionally include, by a notification component of the server (14), notifying the offender of the offense. The method may also include, providing for the offender a means of payment of the penalty issued by the system either through a payment component associated with the server (14) or one accessible to the server.

Referring to Figure 8, there is shown an exemplary method of reporting an offense according to aspects of the present disclosure. The app may be provided by the server to the endpoint device on which the app may be installed. In the exemplary embodiment, the app may be called the ‘UCANFINE Violation Management System’. An endpoint device may capture image data of a suspected infringement or offense (step 1). The endpoint device may be a smartphone operated by a user. The image data may be assigned as either a traffic or a criminal violation and the image or image data may be uploaded to the app. The endpoint device may present a display, e.g., as exemplified in Figure 9, for assigning the image data as either relating to a traffic offence or a criminal offence. In step 2, the received image data may be analysed by an adjudication module, or by the machine learning model/module so as to determine if a violation or offence has occurred. Means may be put in place to ensure that the user of the app is also not infringing traffic rules. If the violation/offence is approved, the offender may be identified (step 3), and the violation/offence may be processed as described in the present disclosure. Verification may be performed by the system, e.g., by analysing or digitally recognizing a vehicle licence plate number from the received image data, analysing biometric data, facial recognition data relating to the offender, or other data captured by the endpoint device (step 4). Alternatively, the system and method of the present disclosure may be digitally connected or linked to a government system such as eNATIS to verify the offender. Once identified, an infringement or fine may be sent to a metropolitan or traffic agency such as RTMC or RTIA (step 5). One of these entities may send the notice or fine to the offender (step 6), preferably transmitted digitally. The user who uploaded the image data may be notified of the successful reporting and may be rewarded e.g., by monetary means (step 7) or another type of reward such as a digital asset or other digital reward. Lastly, the app may provide means through which the offender may pay the fine or infringement fee (step 8).

It will be appreciated that there are a number of ways that the method could be implemented. Endpoint devices may be registered and use the app following vetting by a vetting component accessible by the server. Alternatively, or additionally, more officials may be employed and a new type and level of Traffic Policing Officials with the relevant training in Technology Law Enforcement may be created. It may be desirable for both means to be implemented in conjunction.

The present disclosure may also be used to generate several forms of revenue. There may be potential to sell advertising space on the app or via an associated website or web service provided by the systems and methods of the present disclosure. These sources of revenue may be facilitated through banners, videos and the like, e.g., see Figure 10. An agreed percentage commission or transactional fee may be charged when payment of infringements and fines are paid by offenders through the app. This may create a so-called “earn as you fine” system to reward any reported offence resulting in an infringement and incentivise continued reporting. The monetary reward may alleviate unemployment while also enhancing road safety. The system and method of the present disclosure may allow the registration of personal vehicles, notifications may be transmitted to endpoint device(s) regarding vehicle licence expiries, and this may facilitate the renewals of licence disks or vehicle licences. Multiple training facilities may be created for learnership programs to train existing traffic officers and approved public members on how to use the system. Individuals may attend a training course which may be funded through the government to increase the overall skilled workforce and create employment. The course may cost R10,000 per member, for example.

The present disclosure may increase surveillance of road traffic activity and enhance the reporting efficiency of road traffic law violations. The present disclosure may also incorporate the greater community through various already existing structures including private security entities, community security forums and trained community members. This may drastically reduce traffic infringements through the promotion of safe driving and the changing of road user behaviours due to the knowledge that road users are being monitored. This may save many lives lost on public roads and save government expenditure on health care, emergency services and road infrastructure repairs. Community involvement may also increase awareness of infringement of the law as well as create jobs.

The present disclosure may also contribute to the financial health of local government without having to incur additional costs since traffic fines are one of the largest sources of alternative revenue for municipalities. The present disclosure may benefit the government’s current systems with cheaper, more effective, paperless, and data-recorded reporting.

The present disclosure may enable traffic officers to easily capture evidence of violations, resulting in more fines. The present disclosure may reduce state expenses as it eliminates the need for manual handwritten fines, thereby creating an electronic, paperless, and eco-friendly system. Corporate Social Investment (CSI) projects may also be created to assist victims of traffic violations associated with the captured image data (e.g., the pedestrian victim (21 ) of Figure 1 ).

Figure 11 illustrates an example of a computing device (1 100) in which various aspects of the disclosure may be implemented, for example the server (14) or the endpoint device(s) (12.1 to 12.n). The computing device (1100) may be embodied as any form of data processing device including a personal computing device (e.g., laptop or desktop computer), a server computer (which may be self-contained, physically distributed over a number of locations), a client computer, or a communication device, such as a mobile phone (e.g., cellular telephone), satellite phone, tablet computer, personal digital assistant or the like. Different embodiments of the computing device may dictate the inclusion or exclusion of various components or subsystems described below.

The computing device (1100) may be suitable for storing and executing computer program code. The various participants and elements in the previously described system diagrams may use any suitable number of subsystems or components of the computing device (1100) to facilitate the functions described herein. The computing device (1100) may include subsystems or components interconnected via a communication infrastructure (1105) (for example, a communications bus, a network, etc.). The computing device (1100) may include one or more processors (1 110) and at least one memory component in the form of computer-readable media. The one or more processors (11 10) may include one or more of: CPUs, graphical processing units (GPUs), microprocessors, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs) and the like. In some configurations, a number of processors may be provided and may be arranged to carry out calculations simultaneously. In some implementations various subsystems or components of the computing device (1100) may be distributed over a number of physical locations (e.g., in a distributed, cluster or cloud-based computing configuration) and appropriate software units may be arranged to manage and/or process data on behalf of remote devices.

The memory components may include system memory (1 115), which may include read only memory (ROM) and random access memory (RAM). A basic input/output system (BIOS) may be stored in ROM. System software may be stored in the system memory (1115) including operating system software. The memory components may also include secondary memory (1120). The secondary memory (1120) may include a fixed disk (1121), such as a hard disk drive, and, optionally, one or more storage interfaces (1122) for interfacing with storage components (1123), such as removable storage components (e.g., magnetic tape, optical disk, flash memory drive, external hard drive, removable memory chip, etc.), network attached storage components (e.g., NAS drives), remote storage components (e.g., cloud-based storage) or the like.

The computing device (1100) may include an external communications interface (1130) for operation of the computing device (1100) in a networked environment enabling transfer of data between multiple computing devices (1100) and/or the Internet. Data transferred via the external communications interface (1 130) may be in the form of signals, which may be electronic, electromagnetic, optical, radio, or other types of signal. The external communications interface (1130) may enable communication of data between the computing device (1100) and other computing devices including servers and external storage facilities. Web services may be accessible by and/or from the computing device (1100) via the communications interface (1130).

The external communications interface (1 130) may be configured for connection to wireless communication channels (e.g., a cellular telephone network, wireless local area network (e.g., using Wi-Fi™), satellite-phone network, Satellite Internet Network, etc.) and may include an associated wireless transfer element, such as an antenna and associated circuitry. The external communications interface (1130) may include a subscriber identity module (SIM) in the form of an integrated circuit that stores an international mobile subscriber identity and the related key used to identify and authenticate a subscriber using the computing device (1100). One or more subscriber identity modules may be removable from or embedded in the computing device (1100).

The computer-readable media in the form of the various memory components may provide storage of computer-executable instructions, data structures, program modules, software units and other data. A computer program product may be provided by a computer-readable medium having stored computer-readable program code executable by the central processor (1110). A computer program product may be provided by a non-transient or non-transitory computer- readable medium, or may be provided via a signal or other transient or transitory means via the communications interface (1130).

Interconnection via the communication infrastructure (1105) allows the one or more processors (1110) to communicate with each subsystem or component and to control the execution of instructions from the memory components, as well as the exchange of information between subsystems or components. Peripherals (such as printers, scanners, cameras, or the like) and input/output (I/O) devices (such as a mouse, touchpad, keyboard, microphone, touch-sensitive display, input buttons, speakers and the like) may couple to or be integrally formed with the computing device (1100) either directly or via an I/O controller (1135). One or more displays (1145) (which may be touch-sensitive displays) may be coupled to or integrally formed with the computing device (1100) via a display or video adapter (1140). The computing device (1100), for example in the form of one or more of the endpoint device(s) (12.1 to 12.n), may include a geographical location element (1155) which is arranged to determine the geographical location of the computing device (1100). The geographical location element (1155) may for example be implemented by way of a global positioning system (GPS), or similar, receiver module. In some implementations the geographical location element (1155) may implement an indoor positioning system, using for example communication channels such as cellular telephone or Wi-Fi™ networks and/or beacons (e.g., Bluetooth™ Low Energy (BLE) beacons, iBeacons™, etc.) to determine or approximate the geographical location of the computing device (1100). In some implementations, the geographical location element (1155) may implement inertial navigation to track and determine the geographical location of the communication device using an initial set point and inertial measurement data.

The foregoing description has been presented for the purpose of illustration; it is not intended to be exhaustive or to limit the present disclosure to the precise forms disclosed. Persons skilled in the relevant art can appreciate that many modifications and variations are possible in light of the above disclosure.

Any of the steps, operations, components or processes described herein may be performed or implemented with one or more hardware or software units, alone or in combination with other devices. Components or devices configured or arranged to perform described functions or operations may be so arranged or configured through computer-implemented instructions which implement or carry out the described functions, algorithms, or methods. The computer- implemented instructions may be provided by hardware or software units. In one embodiment, a software unit is implemented with a computer program product comprising a non-transient or non- transitory computer-readable medium containing computer program code, which can be executed by a processor for performing any or all of the steps, operations, or processes described. Software units or functions described in this application may be implemented as computer program code using any suitable computer language such as, for example, Java™, C++, or Perl™ using, for example, conventional or object-oriented techniques. The computer program code may be stored as a series of instructions, or commands on a non-transitory computer-readable medium, such as a random access memory (RAM), a read-only memory (ROM), a magnetic medium such as a hard-drive, or an optical medium such as a CD-ROM. Any such computer-readable medium may also reside on or within a single computational apparatus, and may be present on or within different computational apparatuses within a system or network.

Flowchart illustrations and block diagrams of methods, systems, and computer program products according to embodiments are used herein. Each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, may provide functions which may be implemented by computer readable program instructions. In some alternative implementations, the functions identified by the blocks may take place in a different order to that shown in the flowchart illustrations.

Some portions of this description describe the embodiments of the present disclosure in terms of algorithms and symbolic representations of operations on information. These algorithmic descriptions and representations, such as accompanying flow diagrams, are commonly used by those skilled in the data processing arts to convey the substance of their work effectively to others skilled in the art. These operations, while described functionally, computationally, or logically, are understood to be implemented by computer programs or equivalent electrical circuits, microcode, or the like. The described operations may be embodied in software, firmware, hardware, or any combinations thereof.

The language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the present disclosure be limited not by this detailed description, but rather by any claims that issue on an application based hereon. Accordingly, the disclosure of the embodiments of the present disclosure is intended to be illustrative, but not limiting, of the scope of the present disclosure set forth in any accompanying claims.

Finally, throughout the specification and any accompanying claims, unless the context requires otherwise, the word ‘comprise’ or variations such as ‘comprises’ or ‘comprising’ will be understood to imply the inclusion of a stated integer or group of integers but not the exclusion of any other integer or group of integers.

Claims

CLAIMS:

1 . A computer-implemented method for reporting offenses by endpoint computing devices in data communication with a server, the method conducted at the server and comprising: registering one or more of the endpoint computing devices, each of the registered endpoint computing devices having at least an associated unique identifier and a camera for capturing image data; receiving image data from one of the registered endpoint computing devices; accessing a machine learning module which is trained by a plurality of training images of offences; inputting the received image data to the machine learning module which automatically analyses the received image data so as to identify an offence therefrom; receiving a result of the analysis from the machine learning module; and responsive to an identified offence, outputting an approval message to the registered endpoint computing device that transmitted the received image data.

2. The method as claimed in claim 1 , wherein the method includes, by the server, allocating a reward that is digitally linked to the unique identifier of the registered endpoint computing device from which the image data is received.

3. The method as claimed in claim 1 or claim 2, wherein the method includes, by the server, uniquely associating the received image data with the unique identifier of the registered endpoint computing device from which the image data is received.

4. The method as claimed in any one of claims 1 to 3, wherein the method includes, by the registered endpoint computing device, encrypting the image data by way of an endpoint private key associated with the registered endpoint computing device.

5. The method as claimed in claim 4, wherein the method includes, by the server, decrypting encrypted image data received from the registered endpoint computing device by way of a public key.

6. The method as claimed in any one of the preceding claims, wherein the method includes, by the server, digitally verifying or digitally authenticating the received image data so as to confirm the authenticity thereof.

7. The method as claimed in any one of the preceding claims, wherein the method includes, by the server, encrypting the received image data using a server-side private key.

8. The method as claimed in any one of the preceding claims, wherein the method includes, by the server, outputting a digital infringement notice, fine, or penalty, based on the result of the analysis received from the machine learning module.

9. The method as claimed in any one of the preceding claims, wherein the method includes, by the server, inputting the received image data to the machine learning module which automatically analyses the received image data so as to identify an offender therefrom.

10. The method as claimed in any one of the preceding claims, wherein the method includes, by the server, receiving an offender identifier from the machine learning module.

11 . The method as claimed in claim 10, wherein the method includes, by the machine learning module, deriving the offender identifier or other data relating to the offender from the image data.

12. The method as claimed in any one of the preceding claims, wherein the method includes, by the server, inputting the received image to an adjudication module.

13. The method as claimed in claim 12, wherein the outputting of an approval message by the server is preceded by, or succeeded by, an approval input facilitated by the adjudicator module.

14. The method as claimed in any one of the preceding claims, wherein the method includes, by the server, receiving geolocation data from the registered endpoint computing device that transmitted the image data.

15. The method as claimed in claim 14, wherein the method includes, by the server, uniquely associating the unique identifier of the endpoint computing device that transmitted the image data with the geolocation data, and/or uniquely associating the geolocation data with the received image data.

16. A computer-implemented method for reporting offenses by endpoint computing devices in data communication with a server, the method conducted at a first one of the endpoint computing devices and comprising: registering at the server, the endpoint computing device which has at least an associated unique identifier and a camera for capturing image data; transmitting image data from the registered endpoint computing device to the server which has access to a machine learning module that is trained by a plurality of training images of offences so as to enable the server to input the received image data to the machine learning module which automatically analyses the received image data in order to identify an offence therefrom, the server receiving a result of the analysis from the machine learning module; and responsive to an identified offence, receiving an approval message from the server at the registered endpoint computing device.

17. A system for reporting offenses by endpoint computing devices, the system comprising: a server computer in data communication with the endpoint computing devices, the server computer including or having access to a processor and a memory, said memory containing instructions executable by the processor, to execute functions of components including: an endpoint registration component that operatively registers one or more of the endpoint computing devices, each of the registered endpoint computing devices having at least an associated unique identifier and a camera for capturing image data; a receiving component that operatively receives image data from one of the registered endpoint computing devices; a machine learning module interface component that operatively accesses a machine learning module which is trained by a plurality of training images of offences; an inputting component that operatively inputs the received image data to the machine learning module which automatically analyses the received image data so as to identify an offence therefrom; a result receiving component that operatively receives a result of the analysis from the machine learning module; and an output component which, responsive to an identified offence, operatively outputs an approval message to the registered endpoint computing device that transmitted the received image data.

18. A computer program product for reporting offenses by endpoint computing devices in data communication with a server, the computer program product comprising a non-transitory computer-readable medium having stored computer-readable program code for performing the steps of: registering one or more of the endpoint computing devices, each of the registered endpoint computing devices having at least an associated unique identifier and a camera for capturing image data; receiving image data from one of the registered endpoint computing devices; accessing a machine learning module which is trained by a plurality of training images of offences; inputting the received image data to the machine learning module which automatically analyses the received image data so as to identify an offence therefrom; receiving a result of the analysis from the machine learning module; and responsive to an identified offence, outputting an approval message to the registered endpoint computing device that transmitted the received image data.