Description:BACKGROUND
Technical Field
[0001] The embodiments herein generally relate to edge computing, and more particularly, to a system and method for optimizing display area for monitoring security threats using concurrent artificial intelligence (AI) models.
Description of the Related Art
[0002] In traditional security surveillance systems, data overload poses a significant technical challenge, as the increasing number of sensors and devices collecting data can overwhelm security personnel at control centers. This makes it difficult to identify and respond to critical incidents in real-time. Traditional approaches demand an extensive amount of screen real-estate, often necessitating multiple screens, for effectively monitoring a large number of audio and video feeds. This presents a formidable challenge as security personnel struggle to efficiently process and respond to the abundance of information, leading to a risk of information overload and decreased situational awareness. In this context, the issue of change blindness further increases the problem, hampering ability of the security personnel to promptly detect potential security threats.
[0003] Change blindness, a phenomenon where individuals fail to perceive significant alterations in their visual field, becomes a substantial hindrance in traditional approaches. The constant monitoring of numerous feeds requires rapid identification of potential security threats, and the dynamic nature of urban environments necessitates a surveillance system that not only optimizes screen real-estate but also mitigates change blindness, ensuring that security personnel can promptly and accurately detect and respond to security incidents. The technical challenge lies in developing a solution that not only addresses the spatial constraints of monitoring large volumes of data but also enhances the perceptual capabilities of security personnel by minimizing change blindness.
[0004] Accordingly, there remains a need of addressing the technical problems using a system and method for optimizing display area for monitoring security threats using concurrent artificial intelligence (AI) models.
BRIEF DESCRIPTION OF THE DRAWINGS
[0005] The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:
[0006] FIG. 1 illustrates a system for optimizing display area for monitoring security threats using concurrent artificial intelligence (AI) models according to some embodiments herein;
[0007] FIG. 2 illustrates a block diagram of the real-time city surveillance server and edge nodes of FIG. 1 according to some embodiments herein;
[0008] FIG. 3 illustrates an interaction diagram for a method for anonymization of security threats in surveillance devices using concurrent AI models according to some embodiments herein;
[0009] FIG. 4 is a flow diagram that illustrates a method for optimizing display area for monitoring using concurrent AI models according to some embodiments herein; andFIG. 5 is a representative hardware environment for practicing the embodiments herein with respect to FIG. 1 through 4.
SUMMARY
[0010] In view of the foregoing, according to a first aspect, there is provided a method for optimizing display area for monitoring security threats using concurrent artificial intelligence (AI) models. The method comprising (a) mapping, based on user-defined rules that are configured at a real-time city surveillance server, the plurality of surveillance devices to at least one edge node, wherein the at least one edge device is communicatively connected to the real-time city surveillance server and the plurality of surveillance devices, wherein the plurality of surveillance devices are associated with owner entities, wherein the user-defined rules are associated with spatial boundaries that are covered by the plurality of surveillance devices, (b) receiving, at the at least one edge node, audio and visual data captured from the plurality of surveillance devices, (c) detecting in real-time, at the at least one edge node, movement of all entities in the audio and visual data to obtain movement data of entities, wherein the entities comprise moving objects including a vehicle, an individual or an animal, (d) detecting at least one potential security threat by concurrently running, at the at least one edge node, the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects, wherein the classification AI models comprise at least one of human detection models, animal detection models and vehicle detection models, (e) dynamically mapping the at least one potential security threat to at least one of a visual cue or an audio cue, and, (f) continuously updating a selection of real-time feeds of the plurality of surveillance devices that are displayed on a screen with M windows, wherein the selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat, thereby optimizing the display area for monitoring the movement data in the plurality of surveillance devices.
[0011] The method is of advantage that the method addresses the technical challenge of data overload and spatial constraints faced by security personnel in traditional surveillance systems. The concurrent use of artificial intelligence (AI) models for real-time movement data analysis at the edge nodes provides a solution to challenges posed by change blindness of security personnel. The integration of classification AI models, including human, animal, and vehicle detection models, enables accurate detection of potential security threats. The method enables prompt identification and classification of moving entities in audio and visual data, overcoming the hindrance of change blindness.
[0012] Dynamic mapping of potential security threats to visual or audio cues enables the security personnel to receive immediate and actionable cues, thereby effectively optimizing the display area for monitoring security threats. By providing prioritized information based on the detection of potential security threats, the method maximizes the utility of screen real-estate, allowing security personnel to focus on critical areas and respond promptly to security incidents.
[0013] In some embodiments, the method comprises encrypting, at the at least one edge node, the movement data using a secure hash algorithm (SHA) -3 encryption method and storing in a blockchain based distributed ledger.
[0014] In some embodiments, the method comprises determining anonymized movement data that comprises the movement data of non-owner entities by removing the movement data associated with the owner entities, at the at least one edge nodes, using a data anonymization technique, wherein the owner entities are entities that are linked to the plurality of surveillance devices, wherein the data anonymization technique comprises a combination of at least one of a k-anonymity technique, a differential privacy technique, a pseudo anonymization technique, a tokenization and a data masking technique.
[0015] In some embodiments, the potential security threat is based on the rules defined at the real-time city surveillance server, wherein the rules include at least one of a control access, a predefined threshold and a condition-based notification.
[0016] In some embodiments, the method comprises generating, upon detecting the at least one potential security threat, a rapid response notification and transmitting the rapid response notification to associated user devices.
[0017] In some embodiments, the method comprises cataloging data obtained from the plurality of surveillance devices for events that are characterized by user-defined rules. The cataloging of data enables optimization of storage resources that are required to store the data captured from the plurality of surveillance devices.
[0018] In some embodiments, the method comprises implementing a One M2M global standard to standardize collection and exchange of data from the plurality of surveillance devices and additional data sources.
[0019] In some embodiments, the method comprises implementing a mesh technology to create self-forming and self-healing networks for an efficient collection of the audio and visual data from the plurality of surveillance devices.
[0020] In a second aspect, there is provided a system for monitoring security threats in a plurality of surveillance devices based on concurrently running classification of artificial intelligence (AI) models, wherein the system comprises a plurality of surveillance devices, at least one edge node and a real-time city surveillance server that comprises a processor and a memory configured to perform (a) mapping, based on user-defined rules that are configured at a real-time city surveillance server, the plurality of surveillance devices to at least one edge node, wherein the at least one edge device is communicatively connected to the real-time city surveillance server and the plurality of surveillance devices, wherein the plurality of surveillance devices are associated with owner entities, wherein the user-defined rules are associated with spatial boundaries that are covered by the plurality of surveillance devices, (b) receiving, at the at least one edge node, audio and visual data captured from the plurality of surveillance devices, (c) detecting in real-time, at the at least one edge node, movement of all entities in the audio and visual data to obtain movement data of entities, wherein the entities comprise moving objects including a vehicle, an individual or an animal, (d) detecting at least one potential security threat by concurrently running, at the at least one edge node, the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects, wherein the classification AI models comprise at least one of human detection models, animal detection models and vehicle detection models, (e) dynamically mapping the at least one potential security threat to at least one of a visual cue or an audio cue, and, (f) continuously updating a selection of real-time feeds of the plurality of surveillance devices that are displayed on a screen with M windows, wherein the selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat, thereby optimizing the display area for monitoring the movement data in the plurality of surveillance devices.
[0021] The system is of advantage that the system addresses the technical challenge of data overload and spatial constraints faced by security personnel in traditional surveillance systems. The concurrent use of artificial intelligence (AI) models for real-time movement data analysis at the edge nodes provides a solution to challenges posed by change blindness of security personnel. The integration of classification AI models, including human, animal, and vehicle detection models, enables accurate detection of potential security threats. The system enables prompt identification and classification of moving entities in audio and visual data, overcoming the hindrance of change blindness.
[0022] Dynamic mapping of potential security threats to visual or audio cues enables the security personnel to receive immediate and actionable cues, thereby effectively optimizing the display area for monitoring security threats. By providing prioritized information based on the detection of potential security threats, the system maximizes the utility of screen real-estate, allowing security personnel to focus on critical areas and respond promptly to security incidents.
[0023] In some embodiments, the system includes encrypting, at the at least one edge nodes, the anonymized movement data using SHA-3 encryption method and storing in a blockchain based distributed ledger.
[0024] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.
DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS
[0025] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[0026] In the view of the foregoing, the need for a system and method for optimizing display area for monitoring security threats using concurrent AI models is fulfilled in the ongoing description by (a) mapping, based on user-defined rules that are configured at a real-time city surveillance server, the plurality of surveillance devices to at least one edge node, wherein the at least one edge device is communicatively connected to the real-time city surveillance server and the plurality of surveillance devices, wherein the plurality of surveillance devices are associated with owner entities, wherein the user-defined rules are associated with spatial boundaries that are covered by the plurality of surveillance devices, (b) receiving, at the at least one edge node, audio and visual data captured from the plurality of surveillance devices, (c) detecting in real-time, at the at least one edge node, movement of all entities in the audio and visual data to obtain movement data of entities, wherein the entities comprise moving objects including a vehicle, an individual or an animal, (d) detecting at least one potential security threat by concurrently running, at the at least one edge node, the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects, wherein the classification AI models comprise at least one of human detection models, animal detection models and vehicle detection models, (e) dynamically mapping the at least one potential security threat to at least one of a visual cue or an audio cue, and, (f) continuously updating a selection of real-time feeds of the plurality of surveillance devices that are displayed on a screen with M windows, wherein the selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat, thereby optimizing the display area for monitoring the movement data in the plurality of surveillance devices.
[0027] The term “spatial boundary” refers to a predefined geographic or physical demarcation within an area of coverage of surveillance devices. The spatial boundary may be defined based on physical features, coordinates, or specific criteria, and serve as reference points for managing data from the surveillance devices. For example, the spatial boundary may include, but is not limited to an entrance area that encompasses entry points to a building, a pathway area that encompasses specific walkways or roads, a public square, a park, or a traffic junction.
[0028] The term “artificial intelligence (AI) model” may be used to refer to a machine learning model or a deep learning model.
[0029] Referring now to the drawings, and more particularly to FIGS. 1 through 4, where similar reference characters denote corresponding features in a consistent manner throughout the figures, there are shown preferred embodiments.FIG. 1 illustrates a system for optimizing display area for monitoring security threats using concurrent AI models according to some embodiments herein. The system 100 includes plurality of surveillance devices 102A-N, one or more edge nodes 104A-N, a blockchain-based distributed ledger 110, a real-time city surveillance server 112, and one or more user devices 114A-N. The plurality of surveillance devices 102A-N are connected to the one or more edge nodes 104A-N that comprise the concurrent AI models 106A-N. The one or more edge nodes 104A-N, the blockchain based distributed ledger 110, the real-time city surveillance server 112, and the one or more user devices 114A-N are connected with each other using a data communication network 108.
[0030] The data communication network 106 may be one or more of a wired network, a wireless network, a combination of the wired network and the wireless network or the Internet. The plurality of surveillance devices 102A-N may include a collection of cameras, microphones, sensors, or any other devices that are utilized for capturing audio and visual data in the context of surveillance activities within a city. The user devices 112A-N include, but are not limited to, a mobile device, a smartphone, a smart watch, a notebook, a Global Positioning System (GPS) device, a tablet, a desktop computer, a laptop or any network enabled device.
[0031] The real-time city surveillance server 110 is configured map, based on user-defined rules that are configured at the real-time city surveillance server 110, the plurality of surveillance devices 102A-N to the one or more edge nodes 104A-N. The one or more edge nodes are communicatively connected to the real-time city surveillance server 110 and the plurality of surveillance devices 102A-N. The plurality of surveillance devices 102A-N is associated with owner entities. The user-defined rules are associated with spatial boundaries that are covered by the one or more of surveillance devices 102A-N.
[0032] The one or more edge nodes 104A-N are configured to receive audio and visual data captured from the plurality of surveillance devices 102A-N.
[0033] The one or more edge nodes 104A-N are configured to detect in real-time, movement of all entities in the audio and visual data to obtain movement data of entities, where the entities comprise moving objects including a vehicle, an individual or an animal. The entities may be linked to the plurality of surveillance devices 102A-N. The plurality of surveillance devices 102A-N may include, but are not limited to, closed-circuit television (CCTV) cameras, microphones, license plate recognition cameras, thermal imaging cameras, drones, motion sensors, environmental sensors, smart streetlights, vehicle-mounted cameras, body cameras, RFID and NFC sensors, smoke and fire detectors, biometric scanners, smart traffic lights, IoT sensors. The data anonymization technique includes a combination of one or more of a k-anonymity technique, a differential privacy technique, a pseudo anonymization technique, a tokenization and a data masking technique.
[0034] The one or more edge nodes 104A-N are configured to detect at least one potential security threat by concurrently running the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects. The classification AI models include human detection models, animal detection models and vehicle detection models.
[0035] The system 100 is configured to dynamically map the at least one potential security threat to at least one of a visual cue or an audio cue. The system 100 is configured to continuously update a selection of real-time feeds of the plurality of surveillance devices 102A-N that are displayed on a screen with M windows, where the selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat, thereby optimizing the display area for monitoring the at least one potential security threat in the plurality of surveillance devices 102A-N.
[0036] The system 100 is of advantage that the system 100 addresses the technical challenge of data overload and spatial constraints faced by security personnel in traditional surveillance systems. The concurrent use of artificial intelligence (AI) models for real-time movement data analysis at the edge nodes provides a solution to challenges posed by change blindness of security personnel. The integration of classification AI models, including human, animal, and vehicle detection models, enables accurate detection of potential security threats. The system 100 enables prompt identification and classification of moving entities in audio and visual data, overcoming the hindrance of change blindness.
[0037] Dynamic mapping of potential security threats to visual or audio cues enables the security personnel to receive immediate and actionable cues, thereby effectively optimizing the display area for monitoring security threats. By providing prioritized information based on the detection of potential security threats, the system 100 maximizes the utility of screen real-estate, allowing security personnel to focus on critical areas and respond promptly to security incidents.
[0038] In some embodiments, the system 100 performs encrypting, at the at least one edge node, the movement data using a secure hash algorithm (SHA) -3 encryption method and storing in a blockchain based distributed ledger.
[0039] In some embodiments, the system 100 performs determining anonymized movement data that comprises the movement data of non-owner entities by removing the movement data associated with the owner entities, at the at least one edge nodes, using a data anonymization technique, wherein the owner entities are entities that are linked to the plurality of surveillance devices, wherein the data anonymization technique comprises a combination of at least one of a k-anonymity technique, a differential privacy technique, a pseudo anonymization technique, a tokenization and a data masking technique.
[0040] In some embodiments, the potential security threat is based on the rules defined at the real-time city surveillance server, wherein the rules include at least one of a control access, a predefined threshold and a condition-based notification.
[0041] In some embodiments, the system 100 performs generating, upon detecting the at least one potential security threat, a rapid response notification and transmitting the rapid response notification to associated user devices.
[0042] In some embodiments, the system 100 is configured to catalog data obtained from the plurality of surveillance devices for events that are characterized by user-defined rules. For example, events may include, but are not limited to a blast, a malfunction of an appliance such as a streetlight, or a temperature increase.
[0043] In some embodiments, the system 100 integrates a digital map and a zooming capability to visualize and analyze the anonymized movement data on a geographical map.
[0044] In some embodiments, the system 100 implements a One M2M global standard to standardize collection and exchange of data from the plurality of surveillance devices and additional data sources.
[0045] In some embodiments, the system 100 implements a mesh technology to create self-forming and self-healing networks for an efficient collection of the audio and visual data from the plurality of surveillance devices.
[0046] FIG. 2 illustrates an exploded view of the real-time city surveillance server 110 of FIG. 1 according to some embodiments herein. The real-time personalized recommendation server 110 includes a memory 200 and a processor 202 that are connected with a database 204. The memory 200 and the processor 202 are communicatively connected to a device mapping module 206, a threat to cue mapping module 212 and a surveillance device feed updation module 214. The surveillance device feed updation module 214 is communicatively connected to the one or more user devices 114A-N. The one or more edge nodes 104A-N include a movement data detection module 208, a threat detection module 210and the concurrent AI models 106A-N.
[0047] The device mapping module 206 is configured to map, based on user-defined rules that are configured at the real-time city surveillance server 110, the plurality of surveillance devices 102A-N to the one or more edge nodes 104A-N that are communicatively connected between the real-time city surveillance server 110 and the plurality of surveillance devices 102A-N, where each of the plurality of surveillance devices (102A-N) are associated with owner entities. The user-defined rules are associated with spatial boundaries that are covered by the plurality of surveillance devices 102A-N.
[0048] The movement data detection module 208 is configured to receive audio and visual data captured from the plurality of surveillance devices 102A-N. The movement data detection module 208 is configured to detect, in real-time, movement of all entities in the audio and visual data to obtain movement data of entities, where the entities include moving objects including a vehicle, an individual or an animal.
[0049] The threat detection module 210 is configured to detect one or more potential security threats by concurrently running, at the at least one edge node 104A, the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects. The classification AI models may include at least one of human detection models, animal detection models and vehicle detection models.
[0050] The threat to cue mapping module 212 is configured to dynamically map the at least one potential security threat to at least one of a visual cue or an audio cue.
[0051] The surveillance device feed updation module 214 is configured to continuously update a selection of real-time feeds of the plurality of surveillance devices 102A-N that are displayed on a screen with M windows. The screen is of the user devices 114A-N. The selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat, thereby optimizing the display area for monitoring the movement data in the plurality of surveillance devices 102A-N.
[0052] In some embodiments, movement data associated with owner entities may be removed, using a data anonymization technique to determine anonymized movement data that comprises movement data of non-owner entities. The owner entities are entities that are linked to the plurality of surveillance devices 102A-N. The data anonymization technique includes a combination of one or more of a k-anonymity techniques, a differential privacy technique, a pseudo anonymization technique, a tokenization and a data masking technique. The classification AI models may be concurrently run on the anonymized movement data to determine binary classification of a presence or an absence of the moving objects to detect a potential security threat for anonymization of movement data in the surveillance devices 102A-N.
[0053] In some embodiments, at least one user is authorized to access the blockchain based distributed ledger for performing search, view, and analysis by incorporating a robust access management system to control access to the anonymized and encrypted audio and visual information.
[0054] In some embodiments, a OneM2M global standard is implemented to standardize collection and exchange of data from the plurality of surveillance devices and additional data sources OneM2M is a widely adopted global standard for Internet of Things (IoT) communication, for example communication between the plurality of surveillance devices 102A-N. OneM2M offers a robust and versatile framework that can be effectively leveraged to gather information from the surveillance devices 102A-N, including those monitoring air quality and traffic conditions. The utilization of the OneM2M global standard allows seamless connectivity and communication with diverse IoT sensors, enabling efficient collection of data from a wide range of sources. For instance, an air quality monitoring sensor may be incorporated to capture relevant data on pollutant levels, particulate matter, and environmental conditions. Such sensors, operating in accordance with the OneM2M global standard, contribute to real-time monitoring of air quality, providing valuable insights into the environmental health of the city. The standardized interfaces and protocols offered by the OneM2M global standard enable efficient gathering and consolidation of sensor data within the blockchain-based distributed ledger 108.
[0055] Additionally, the blockchain-based distributed ledger 108 may capture real-time traffic data from strategically positioned cameras, which monitor traffic flow, congestion, and vehicle emissions. A video feed obtained from the cameras undergoes edge processing and analysis, extracting essential information such as vehicle count, speed, and patterns. Leveraging the capabilities of the OneM2M global standard, the collected air quality and traffic data may be seamlessly aggregated and correlated. Such integration empowers the real-time city surveillance server to identify correlations and patterns between air quality metrics and traffic conditions, facilitating a comprehensive understanding of how vehicular activities impact air quality in various areas and at specific times.
[0056] Incorporation of the OneM2M global standard enables a decision-maker to gain valuable insights to devise targeted strategies for improving air quality and traffic management. The real-time data analysis and correlation of enable informed decision-making, leading to the implementation of effective traffic control measures, route optimizations, and air pollution reduction initiatives in areas with significant correlations between traffic and air quality. Overall, the implementation of OneM2M enhances the efficiency and effectiveness of the smart city surveillance system, making it a powerful tool for addressing air pollution and traffic management challenges in a holistic manner.
[0057] FIG. 3 illustrates an interaction diagram for a method for anonymization of security threats in surveillance devices using concurrent AI models according to some embodiments herein. At step 302, a plurality of surveillance devices including a plurality of cameras, microphones, and sensors are mapped based on user-defined rules to at least one edge nodes that are communicatively connected between the real-time city surveillance server and the plurality of surveillance devices, wherein the plurality of surveillance devices are associated with owner entities, wherein the user-defined rules are associated with spatial boundaries that are covered by the plurality of surveillance devices. At step 304, the one or more encryption and storage nodes 104A-N receive in real-time audio and visual data captured from the plurality of surveillance devices 102A-N. At step 306, movement of all entities in the audio and visual data is detected in real-time to obtain movement data of entities, wherein the entities comprise moving objects including a vehicle, an individual or an animal. At step 308, at least one potential security threat is detected by concurrently running, at the at least one edge node 104A, the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects, wherein the classification AI models comprise at least one of human detection models, animal detection models and vehicle detection models. At step 310, the at least one potential security threat is dynamically mapped to at least one of a visual cue or an audio cue. At step 312, the selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat. At step 314, a selection of real-time feeds of the plurality of surveillance devices 102A-N that are displayed on a screen of the user devices 112A-N with M windows is continuously updated.
[0058] FIG. 4 is a flow diagram that illustrates a method for anonymization of security threats in surveillance devices using concurrent AI models according to some embodiments herein. At step 402, the method includes mapping, based on user-defined rules that are configured at a real-time city surveillance server, the plurality of surveillance devices to at least one edge node, wherein the at least one edge device is communicatively connected to the real-time city surveillance server and the plurality of surveillance devices, wherein the plurality of surveillance devices are associated with owner entities, wherein the user-defined rules are associated with spatial boundaries that are covered by the plurality of surveillance devices. At step 404, the method includes receiving, at the at least one edge node, audio and visual data captured from the plurality of surveillance devices. At step 406, the method includes detecting in real-time, at the at least one edge node, movement of all entities in the audio and visual data to obtain movement data of entities, wherein the entities comprise moving objects including a vehicle, an individual or an animal. At step 408, the method includes detecting at least one potential security threat by concurrently running, at the at least one edge node, the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects, wherein the classification AI models comprise at least one of human detection models, animal detection models and vehicle detection models. At step 410, the method includes dynamically mapping the at least one potential security threat to at least one of a visual cue or an audio cue. At step 412, the method includes continuously updating a selection of real-time feeds of the plurality of surveillance devices that are displayed on a screen with M windows, wherein the selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat, thereby optimizing the display area for monitoring the at least one potential security threat in the plurality of surveillance devices.
[0059] The method is of advantage that the method addresses the technical challenge of data overload and spatial constraints faced by security personnel in traditional surveillance systems. The concurrent use of artificial intelligence (AI) models for real-time analysis at the edge nodes provides a solution to challenges posed by change blindness of security personnel. The integration of classification AI models, including human, animal, and vehicle detection models, enables accurate detection of potential security threats. The method enables prompt identification and classification of moving entities in audio and visual data, overcoming the hindrance of change blindness.
[0060] Dynamic mapping of potential security threats to visual or audio cues enables the security personnel to receive immediate and actionable cues, thereby effectively optimizing the display area for monitoring security threats. By providing prioritized information based on the detection of potential security threats, the method maximizes the utility of screen real-estate, allowing security personnel to focus on critical areas and respond promptly to security incidents.
[0061] In some embodiments, the method comprises encrypting, at the at least one edge node, the movement data using a secure hash algorithm (SHA) -3 encryption method and storing in a blockchain based distributed ledger.
[0062] In some embodiments, the method comprises determining anonymized movement data that comprises the movement data of non-owner entities by removing the movement data associated with the owner entities, at the at least one edge nodes, using a data anonymization technique, wherein the owner entities are entities that are linked to the plurality of surveillance devices, wherein the data anonymization technique comprises a combination of at least one of a k-anonymity technique, a differential privacy technique, a pseudo anonymization technique, a tokenization and a data masking technique.
[0063] In some embodiments, the potential security threat is based on the rules defined at the real-time city surveillance server, wherein the rules include at least one of a control access, a predefined threshold and a condition-based notification.
[0064] In some embodiments, the method comprises generating, upon detecting the at least one potential security threat, a rapid response notification and transmitting the rapid response notification to associated user devices.
[0065] In some embodiments, the method comprises catalog data obtained from the plurality of surveillance devices for events that are characterized by user-defined rules.
[0066] In some embodiments, the method comprises integrating a digital map and a zooming capability to visualize and analyze the anonymized movement data on a geographical map.
[0067] In some embodiments, the method comprises implementing a One M2M global standard to standardize collection and exchange of data from the plurality of surveillance devices and additional data sources.
[0068] In some embodiments, the method comprises implementing a mesh technology to create self-forming and self-healing networks for an efficient collection of the audio and visual data from the plurality of surveillance devices.
[0069] The various systems and corresponding components described herein and/or illustrated in the figures may be embodied as hardware-enabled modules and may be a plurality of overlapping or independent electronic circuits, devices, and discrete elements packaged onto a circuit board to provide data and signal processing functionality within a computer. An example might be a comparator, inverter, or flip-flop, which could include a plurality of transistors and other supporting devices and circuit elements. The systems that include electronic circuit’s process computer logic instructions capable of providing digital and/or analog signals for performing various functions as described herein. The various functions can further be embodied and physically saved as any of data structures, data paths, data objects, data object models, object files, database components. For example, the data objects could include a digital packet of structured data. Example data structures may include any of an array, tuple, map, union, variant, set, graph, tree, node, and an object, which may be stored and retrieved by computer memory and may be managed by processors, compilers, and other computer hardware components. The data paths can be part of a computer CPU or GPU that performs operations and calculations as instructed by the computer logic instructions. The data paths could include digital electronic circuits, multipliers, registers, and buses capable of performing data processing operations and arithmetic operations (e.g., Add, Subtract, etc.), bitwise logical operations (AND, OR, XOR, etc.), bit shift operations (e.g., arithmetic, logical, rotate, etc.), complex operations (e.g., using single clock calculations, sequential calculations, iterative calculations, etc.). The data objects may be physical locations in computer memory and can be a variable, a data structure, or a function. Some examples of the modules include relational databases (e.g., such as Oracle® relational databases), and the data objects can be a table or column, for example. Other examples include specialized objects, distributed objects, object-oriented programming objects, and semantic web objects. The data object models can be an application programming interface for creating HyperText Markup Language (HTML) and Extensible Markup Language (XML) electronic documents. The models can be any of a tree, graph, container, list, map, queue, set, stack, and variations thereof, according to some examples. The data object files can be created by compilers and assemblers and contain generated binary code and data for a source file. The database components can include any of tables, indexes, views, stored procedures, and triggers.
[0070] In an example, the embodiments herein can provide a computer program product configured to include a pre-configured set of instructions, which when performed, can result in actions as stated in conjunction with various figures herein. In an example, the pre-configured set of instructions can be stored on a tangible non-transitory computer readable medium. In an example, the tangible non-transitory computer readable medium can be configured to include the set of instructions, which when performed by a device, can cause the device to perform acts similar to the ones described here.
[0071] The embodiments herein may also include tangible and/or non-transitory computer-readable storage media for carrying or having computer-executable instructions or data structures stored thereon. Such non-transitory computer readable storage media can be any available media that can be accessed by a general purpose or special purpose computer, including the functional design of any special purpose processor as discussed above. By way of example, and not limitation, such non-transitory computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions, data structures, or processor chip design. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or combination thereof) to a computer, the computer properly views the connection as a computer-readable medium. Thus, any such connection is properly termed a computer-readable medium. Combinations of the above should also be included within the scope of the computer-readable media.
[0072] Computer-executable instructions include, for example, instructions and data which cause a special purpose computer or special purpose processing device to perform a certain function or group of functions. Computer-executable instructions also include program modules that are executed by computers in stand-alone or network environments. Generally, program modules include routines, programs, components, data structures, objects, and the functions inherent in the design of special-purpose processors, etc. that perform particular tasks or implement particular abstract data types. Computer-executable instructions, associated data structures, and program modules represent examples of the program code means for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps.
[0073] The techniques provided by the embodiments herein may be implemented on an integrated circuit chip (not shown). The chip design is created in a graphical computer programming language and stored in a computer storage medium (such as a disk, tape, physical hard drive, or virtual hard drive such as in a storage access network. If the designer does not fabricate chips or the photolithographic masks used to fabricate chips, the designer transmits the resulting design by physical means (e.g., by providing a copy of the storage medium storing the design) or electronically (e.g., through the Internet) to such entities, directly or indirectly. The stored design is then converted into the appropriate format (e.g., GDSII) for the fabrication of photolithographic masks, which typically include multiple copies of the chip design in question that are to be formed on a wafer. The photolithographic masks are utilized to define areas of the wafer (and/or the layers thereon) to be etched or otherwise processed.
[0074] The resulting integrated circuit chips can be distributed by the fabricator in raw wafer form (that is, as a single wafer that has multiple unpackaged chips), as a bare die, or in a packaged form. In the latter case, the chip is mounted in a single chip package (such as a plastic carrier, with leads that are affixed to a motherboard or other higher-level carrier) or in a multichip package (such as a ceramic carrier that has either or both surface interconnections or buried interconnections). In any case, the chip is then integrated with other chips, discrete circuit elements, and/or other signal processing devices as part of either (a) an intermediate product, such as a motherboard, or (b) an end product. The end product can be any product that includes integrated circuit chips, ranging from toys and other low-end applications to advanced computer products having a display, a keyboard or other input device, and a central processor.
[0075] Furthermore, the embodiments herein can take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system. For the purposes of this description, a computer-usable or computer-readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[0076] The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation medium. Examples of a computer-readable medium include a semiconductor or solid-state memory, magnetic tape, a removable computer diskette, a random-access memory (RAM), a read-only memory (ROM), a rigid magnetic disk and an optical disk. Current examples of optical disks include compact disk - read only memory (CD-ROM), compact disk - read/write (CD-R/W) and DVD.
[0077] A data processing system suitable for storing and/or executing program code will include at least one processor coupled directly or indirectly to memory elements through a system bus. The memory elements can include local memory employed during actual execution of the program code, bulk storage, and cache memories which provide temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during execution.
[0078] Input/output (I/O) devices (including but not limited to keyboards, displays, pointing devices, etc.) can be coupled to the system either directly or through intervening I/O controllers. Network adapters may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modem and Ethernet cards are just a few of the currently available types of network adapters.
[0079] A representative hardware environment for practicing the embodiments herein is depicted in FIG. 5, with reference to FIGS. 1 through 4. This schematic drawing illustrates a hardware configuration of a software development device /computer system 500 in accordance with the embodiments herein. The system 500 comprises at least one processor or central processing unit (CPU) 10. The CPUs 10 are interconnected via system bus 12 to various devices such as a random-access memory (RAM) 14, read-only memory (ROM) 16, and an input/output (I/O) adapter 18. The I/O adapter 18 can connect to peripheral devices, such as disk units 11 and tape drives 13, or other program storage devices that are readable by the system. The system 500 can read the inventive instructions on the program storage devices and follow these instructions to execute the methodology of the embodiments herein. The system 500 further includes a user interface adapter 19 that connects a keyboard 15, mouse 17, speaker 24, microphone 22, and/or other user interface devices such as a touch screen device (not shown) to the bus 12 to gather user input. Additionally, a communication adapter 20 connects the bus 12 to a data processing network, and a display adapter 21 connects the bus 12 to a display device 23, which provides a graphical entity interface (GUI) 36 of the output data in accordance with the embodiments herein, or which may be embodied as an output device such as a monitor, printer, or transmitter, for example. Further, a transceiver 26, a signal comparator 27, and a signal converter 28 may be connected with the bus 12 for processing, transmission, receipt, comparison, and conversion of electric signals.
[0080] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope.
[0081] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. , Claims:I/We Claim:


1. A method for optimizing display area required for monitoring security threats in a plurality of surveillance devices (102A-N) based on concurrently running classification of artificial intelligence (AI) models, said method comprising:
mapping, based on user-defined rules that are configured at a real-time city surveillance server (110), the plurality of surveillance devices (102A-N) to at least one edge node (104A), wherein the at least one edge device (104A) is communicatively connected to the real-time city surveillance server (110) and the plurality of surveillance devices (102A-N), wherein the plurality of surveillance devices (102A-N) are associated with owner entities, wherein the user-defined rules are associated with spatial boundaries that are covered by the plurality of surveillance devices (102A-N);
receiving, at the at least one edge node (104A), audio and visual data captured from the plurality of surveillance devices (102A-N);
detecting in real-time, at the at least one edge node (104A), movement of all entities in the audio and visual data to obtain movement data of entities, wherein the entities comprise moving objects including a vehicle, an individual or an animal;
detecting at least one potential security threat by concurrently running, at the at least one edge node (104A), the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects, wherein the classification AI models comprise at least one of human detection models, animal detection models and vehicle detection models;
dynamically mapping the at least one potential security threat to at least one of a visual cue or an audio cue; and
characterized in that;
continuously updating a selection of real-time feeds of the plurality of surveillance devices (102A-N) that are displayed on a screen with M windows, wherein the selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat, thereby optimizing the display area for monitoring the at least one potential security threat in the plurality of surveillance devices (102A-N).

2. The method as claimed in claim 1, wherein the method comprises encrypting, at the at least one edge node (104A), the movement data using a secure hash algorithm (SHA) -3 encryption method and storing in a blockchain based distributed ledger (108).

3. The method as claimed in claim 2, wherein the method comprises determining anonymized movement data that comprises the movement data of non-owner entities by removing the movement data associated with the owner entities, at the at least one edge nodes (104A-N), using a data anonymization technique, wherein the owner entities are entities that are linked to the plurality of surveillance devices (102A-N), wherein the data anonymization technique comprises a combination of at least one of a k-anonymity technique, a differential privacy technique, a pseudo anonymization technique, a tokenization and a data masking technique.


4. The method as claimed in claim 1, wherein the potential security threat is based on the rules defined at the real-time city surveillance server (110), wherein the rules include at least one of a control access, a predefined threshold and a condition-based notification.

5. The method as claimed in claim 4, wherein the method comprises generating, upon detecting the at least one potential security threat, a rapid response notification and transmitting the rapid response notification to associated user devices (112A-N).

6. The method as claimed in claim 1, further comprising cataloging data obtained from the plurality of surveillance devices (102A-N) for events that are characterized by user-defined rules.

7. The method as claimed in claim 1, wherein the method comprises implementing a One M2M global standard to standardize collection and exchange of data from the plurality of surveillance devices (102A-N) and additional data sources.

8. The method as claimed in claim 1, wherein the method comprises implementing a mesh technology to create self-forming and self-healing networks for an efficient collection of the audio and visual data from the plurality of surveillance devices (102A-N).

9. A system for optimizing display area required for monitoring security threats in a plurality of surveillance devices (102A-N) based on concurrently running classification of artificial intelligence (AI) models, said system comprising:
a plurality of surveillance devices (102A-N);
at least one edge node (104A); and
a real-time city surveillance server (110), comprising:
a memory comprising one or more instructions; and
a processor that executes the one or more instructions, wherein the processor is configured to:
mapping, based on user-defined rules that are configured at a real-time city surveillance server (110), the plurality of surveillance devices (102A-N) to at least one edge node (104A), wherein the at least one edge device (104A) is communicatively connected to the real-time city surveillance server (110) and the plurality of surveillance devices (102A-N), wherein the plurality of surveillance devices (102A-N) are associated with owner entities, wherein the user-defined rules are associated with spatial boundaries that are covered by the plurality of surveillance devices (102A-N);
receiving, at the at least one edge node (104A), audio and visual data captured from the plurality of surveillance devices (102A-N);
detecting in real-time, at the at least one edge node (104A), movement of all entities in the audio and visual data to obtain movement data of entities, wherein the entities comprise moving objects including a vehicle, an individual or an animal;
detecting at least one potential security threat by concurrently running, at the at least one edge node (104A), the classification AI models on the movement data to determine binary classification of a presence or an absence of moving objects, wherein the classification AI models comprise at least one of human detection models, animal detection models and vehicle detection models;
dynamically mapping the at least one potential security threat to at least one of a visual cue or an audio cue; and
characterized in that;
continuously updating a selection of real-time feeds of the plurality of surveillance devices (102A-N) that are displayed on a screen with M windows, wherein the selection of the real-time feeds is dynamically determined based on the detection of the at least one potential security threat, and the updating is performed based on a priority assigned to the at least one potential security threat, thereby optimizing the display area for monitoring the at least one potential security threat in the plurality of surveillance devices (102A-N).

10. The system as claimed in claim 9, further comprising encrypting, at the at least one edge nodes (104A-N), the anonymized movement data using SHA-3 encryption method and storing in a blockchain based distributed ledger (108).

Dated this 09th February , 2024

Arjun Karthik Bala
IN/PA - 1021