Method and system for generating map of a real-world scene

Abstract

A method (400) and a system (100) for generating a three-dimensional (3D) map associated with a real-world scene is disclosed. The method (400) includes obtaining CSI data and camera data corresponding to the real-world scene based on capturing the real-world scene via one or more pairs of wireless transmitter-receiver (30) and cameras (40), respectively. The method (400) includes identifying overlapping CSI regions based on the CSI data. The overlapping CSI regions indicate regions where CSI signals received from two pairs of wireless transmitter-receiver (30) overlap. The method (400) further includes identifying objects corresponding to the real-world scene based on the CSI data. Further, the method (400) includes generating a 2D layout associated based on the objects and the overlapping CSI regions. Furthermore, the method (400) includes modifying the 2D layout for generating 3D map associated with the real-world scene.

Description

DescriptionTitle of Invention :METHOD AND SYSTEM FOR GENERATING MAP OF A REAL-WORLD SCENETechnical Field

[0001] The present disclosure relates to map generation, and more particularly, to a method and a system for a three-dimensional (3D) map of a real-world scene.Background Art

[0002] The information in this section merely provides background information related to the present disclosure and may not constitute prior art(s) for the present disclosure.

[0003] Many map-based applications are available today and are designed for a variety of different devices (e.g., desktops, laptops, tablet devices, smartphones, handheld global positioning system (GPS) receivers, etc.) and different purposes. Most of these applications generate displays of a map based on map data that describes the relative position of various objects on the map.

[0004] The maps used in such applications are usually two-dimensional (2D) maps or three- dimensional (3D) maps. However, a large number of the applications use 2D maps due in part to the processing-intensive demands of viewing 3D maps. For the same reason, the applications that use 3D maps are often slow or inefficient to the point that renders the application useless.

[0005] Traditionally, some applications can be installed on devices such as mobile devices to enable a user to take a picture of a real-world scene, such as a home to generate a 2D map. The generated 2D map can provide an overall view of the home but is unable to provide a realistic view which degrades the user experience.

[0006] However, currently, existing applications provide various features which enable the user to create home layouts with different options like “take picture of home floor plan”, “hand-drawn structures picture”, “create map view with manual structure addition”, etc. For example, if the user selects an option to “create a map view” for the home, the user can arrange the devices and interiors of the home such as doors, windows, furniture, etc. Further, for creating map views, such as the 3D map view, human intervention is required to provide a floor plan and arrange devices and interiors. For example, the user may use a camera of the mobile device to capture a floor layoutto obtain a picture of a floor plan. In another scenario, the user can directly sketch a floor plan. Thereafter, the user can arrange interiors, such as rooms and walls, to represent the 3D map of the home. Once the 3D map is created, the user can connect the devices with the application to place the devices on the generated 3D map.

[0007] However, the current existing applications lead to many limitations due to human intervention, such as a lack of precession and incomplete generation of the 3D map. Furthermore, the current existing applications do not enable the users to capture home aesthetics while creating the map view. Moreover, there is no such technique that enables tracking the 3D map in case of any change in the interiors, which leads to confusion or errors when interacting with the devices.

[0008] In a nutshell, there is a need for an alternative solution that may overcome the abovediscussed limitations.

[0009] The drawbacks / difficulties / disadvantages / limitations of the conventional techniques explained in the background section are just for exemplary purposes and the disclosure would never limit its scope only such limitations. A person skilled in the art would understand that this disclosure and below mentioned description may also solve other problems or overcome the other drawbacks / disadvantages.Solution to Problem

[0010] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify essential inventive concepts of the invention nor is it intended for determining the scope of the invention.

[0011] According to an aspect of the present disclosure, a method for generating a three- dimensional (3D) map associated with a real-world scene is disclosed. The method includes obtaining channel state information (CSI) data and camera data corresponding to the real-world scene based on capturing the real-world scene via one or more pairs of wireless transmitter-receiver and one or more cameras, respectively, installed within the real-world scene. The method further includes identifying one or more overlapping CSI regions based on the obtained CSI data. The one or more overlapping CSI regions indicate regions where CSI signals received from at least two pairs of wireless transmitter-receiver overlap. Further, the method includes identifying one or more objects corresponding to the real -world scene based on the obtained CSI data. Furthermore, the method includes generating a two-dimensional (2D) layoutassociated with the real -world scene based on the one or more identified objects and the one or more overlapping CSI regions. Moreover, the method includes modifying the generated two-dimensional (2D) layout for generating a three-dimensional (3D) map associated with the real-world scene. In an embodiment, modifying the generated two-dimensional (2D) layout includes identifying dissimilarity between the obtained CSI data and the camera data associated with the one or more identified objects. Further, the modification includes normalizing at least one of a position and an orientation of the one or more identified objects based on the identified dissimilarity. Furthermore, the modification includes identifying one or more targeted zones among one or more predefined zones based on at least one of the normalized position and the normalized orientation. The one or more targeted zones are indicative of at least one of one or more isolated zones and one or more disconnected zones identified based on analyzing the generated 2D layout. Moreover, the modification includes applying one or more object-enhancing effects on the one or more identified objects associated with each of the one or more predefined zones in response to identifying the one or more targeted zones, thereby generating the 3D map associated with the real-world scene.

[0012] According to another aspect of the present disclosure, a system for generating a three- dimensional (3D) map associated with a real-world scene is disclosed. The system includes a memory. The system further includes at least one processor in communication with the memory. The at least one processor is configured to obtain channel state information (CSI) data and camera data corresponding to the real-world scene based on capturing the real-world scene via one or more pairs of wireless transmitter-receiver and one or more cameras , respectively, installed within the real- world scene. The at least one processor is further configured to identify one or more overlapping CSI regions based on the obtained CSI data. The one or more overlapping CSI regions indicate regions where CSI signals received from at least two pairs of wireless transmitter-receiver overlap. Further, the at least one processor is configured to identify one or more objects corresponding to the real -world scene based on the obtained CSI data. Furthermore, the at least one processor is configured to generate a two-dimensional (2D) layout associated with the real-world scene based on the one or more identified objects and the one or more overlapping CSI regions. Moreover, the at least one processor is configured to modify the generated two-dimensional (2D) layout for generating a three-dimensional (3D) map associated with the real-world scene, In an embodiment, to modify the generated two-dimensional (2D) layout, the atleast one processor configured to identify dissimilarity between the obtained CSI data and the camera data associated with the one or more identified objects. The at least one processor is configured to normalize at least one of a position and an orientation of the one or more identified objects based on the identified dissimilarity. Further, the at least one processor is configured to identify one or more targeted zones among one or more predefined zones based on at least one of the normalized position and the normalized orientation. The one or more targeted zones are indicative of at least one of isolated zones and disconnected zones identified based on analyzing the generated 2D layout. Furthermore, the at least one processor is configured to apply one or more object-enhancing effects on the one or more identified objects 50 associated with each of the one or more predefined zones in response to the identification of the one or more targeted zones, thereby generating the 3D map associated with the real-world scene

[0013] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail in the accompanying drawings.Brief Description of Drawings

[0014] These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0015] Figure 1 illustrates a schematic block diagram of an environment for generating a three-dimensional (3D) map associated with a real-world scene, in accordance with an embodiment of the present disclosure;

[0016] Figure 2 illustrates a schematic block diagram of a system for generating the 3D map, in accordance with an embodiment of the present disclosure;

[0017] Figure 3 illustrates a schematic block diagram depicting a plurality of modules of the system, in accordance with an embodiment of the present disclosure;

[0018] Figure 4 illustrates a flowchart depicting an exemplary method for generating the three-dimensional (3D) map, in accordance with an embodiment of the present disclosure;

[0019] Figure 5 illustrates a schematic flow diagram for a generation of a zonal map using camera data, in accordance with an embodiment of the present disclosure;

[0020] Figure 6A illustrates a flowchart depicting sub-steps for determining motion, using channel state information (CSI) data, in the real-world scene, in accordance with an embodiment of the present disclosure;

[0021] Figure 6B illustrates a schematic flow diagram depicting blocks for processing the CSI data, in accordance with an embodiment of the present disclosure;

[0022] Figure 7A illustrates a flowchart depicting sub-steps for identifying one or more overlapping CSI regions, in accordance with an embodiment of the present disclosure;

[0023] Figure 7B illustrates an example representation of the one or more overlapping CSI zones within one or more predefined zones, in accordance with an embodiment of the present disclosure;

[0024] Figure 8A illustrates an example representation of zones selected among the one or more predefined zones for boundary determination, in accordance with an embodiment of the present disclosure;

[0025] Figure 8B illustrates an example javascript object notation (JSON) representation of the one or more predefined zones, the one or more overlapping CSI regions, and the determined boundary for each zone, in accordance with an embodiment of the present disclosure;

[0026] Figure 9 illustrates a flowchart depicting sub-steps for identifying one or more objects corresponding to the real-world scene based on the CSI data, in accordance with an embodiment of the present disclosure;

[0027] Figure 10 illustrates a flowchart depicting sub-steps for generating a 2D layout, in accordance with an embodiment of the present disclosure;

[0028] Figure 11A illustrates a flowchart depicting sub-steps for identifying a dissimilarity between the CSI data and the camera data associated with the one or more identified objects, in accordance with an embodiment of the present disclosure;

[0029] Figure 1 IB illustrates an example representation depicting a common reference frame associated with the one or more identified objects, in accordance with an embodiment of the present disclosure;

[0030] Figure 11C illustrates a flowchart depicting blocks for calculating a rotation matrix and a translational vector, in accordance with an embodiment of the present disclosure;

[0031] Figure 12 illustrates a flowchart depicting sub-steps for normalizing a position and / or an orientation of the one or more identified objects, in accordance with an embodimentof the present disclosure;

[0032] Figure 13 A illustrates an exemplary 2D layout of the home, in accordance with an embodiment of the present disclosure;

[0033] Figure 13B illustrates an exemplary shape and the orientation of an exemplary identified object, in accordance with an embodiment of the present disclosure;

[0034] Figure 13C illustrates an exemplary shape and the orientation of the identified object when captured by the one or more cameras, in accordance with an embodiment of the present disclosure;

[0035] Figure 13D illustrates an exemplary shape and the orientation of the identified object when captured by CSI signals of one or more pairs of transmitter-receiver, in accordance with an embodiment of the present disclosure;

[0036] Figure 13E illustrates an exemplary representation of the identified object of Figure 13D after calibration, in accordance with an embodiment of the present disclosure;

[0037] Figures 13F-13H illustrate exemplary representations of the identified object rotated to match the object captured by the one or more cameras, in accordance with an embodiment of the present disclosure;

[0038] Figure 14A illustrates an exemplary schematic diagram depicting a coordinate-to- geometry view of the 2D layout, in accordance with an embodiment of the present disclosure;

[0039] Figure 14B illustrates a schematic diagram of the 2D layout after identifying a presence or an absence of one or more parameters associated with the one or more predefined zones, in accordance with an embodiment of the present disclosure;

[0040] Figure 14C illustrates an example representation of the 2D layout depicting an aligned polygon of identified one or more targeted zones, in accordance with an embodiment of the present disclosure; and

[0041] Figure 15 illustrates an example representation of a first exemplary use case depicting a realistic home including one or more smart devices for rendering the generated 3D map, in accordance with an embodiment of the present disclosure;

[0042] Figures 16A-16B illustrate an example representation of a second exemplary use depicting wi-fi coverage and air quality index (AQI) in a map generated by existing methods and the present disclosure, respectively;

[0043] Figures 17A-17B illustrate example representations of a third exemplary use for locating and instructing a vacuum cleaner using the present disclosure and the existing methods, respectively; and

[0044] Figures 18A-18B illustrate an example representation of a fourth exemplary use case in which user navigates using the map generated by the present disclosure and the existing methods, respectively.

[0045] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help improve understanding of aspects of the present invention. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.Description of Embodiments

[0046] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the various embodiments and specific language will be used to describe the same. It should be understood at the outset that although illustrative implementations of the embodiments of the present disclosure are illustrated below, the present invention may be implemented using any number of techniques, whether currently known or in existence. The present disclosure is not necessarily limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary design and implementation illustrated and described herein, but may be modified within the scope of the present disclosure.

[0047] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the invention and are not intended to be restrictive thereof.

[0048] Reference throughout this specification to “an aspect”, “another aspect” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrase “in an embodiment”, “in another embodiment” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

[0049] It is to be understood that as used herein, terms such as, “includes,” “comprises,” “has,” etc. are intended to mean that the one or more features or elements listed are withinthe element being defined, but the element is not necessarily limited to the listed features and elements, and that additional features and elements may be within the meaning of the element being defined. In contrast, terms such as, “consisting of’ are intended to exclude features and elements that have not been listed.

[0050] 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 to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The term “or” as used herein, refers to a non-exclusive or unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0051] As is traditional in the field, embodiments may be described and illustrated in terms of blocks that carry out a described function or functions. These blocks, which may be referred to herein as units or modules or the like, are physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the invention. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the invention.

[0052] The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are notlimited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents, and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.

[0053] Figure 1 illustrates a schematic block diagram of an environment 1000 for generating a three-dimensional map of a real-world scene, in accordance with an embodiment of the present disclosure. In an embodiment, the real-world scene may herein refer to an indoor space, such as a home within the scope of the present disclosure. However, this should not be construed as a limitation of the present disclosure. In another embodiment, the real-world scene may also refer to an outdoor space.

[0054] The environment 1000 may include one or more receivers 10 that may be installed in the real -world scene. In an embodiment, the one or more receivers 10 may also refer to one or more smart devices, such as wash machines, televisions, fans, lights, etc. within the scope of the present disclosure. In an embodiment, the one or more receivers 10 may be in wireless communication with one or more transmitters 20. For example, the one or more transmitters 20 may be one or more routers. In an embodiment, the one or more transmitters 20 may also refer to channel state information (CSI) devices within the scope of the present disclosure. In an embodiment, the CSI may herein refer to information on the movement of signals from the one or more transmitters 20 to the one or more receivers 10. In an exemplary embodiment, the one or more transmitters 20 and the one or more receivers 10 in combination may be referred to as one or more pairs of wireless transmitter-receiver 30 within the scope of the present disclosure. The one or more pairs of wireless-transmitter-receiver 30 may be used to generate CSI signals with the real-world scene.

[0055] Further, the environment 1000 may include one or more cameras 40 which may be installed in the indoor space and may be communication with the one or more receivers 10 and / or the one or more transmitters 20. In one embodiment, the one or more cameras 40 may be inbuilt within the one or more receivers 10. In another embodiment, the one or more cameras 40 may be closed circuit television (CCTV) cameras. In an embodiment, the one or more cameras 40 may be installed to capture a floor area of the home. Further, the captured data which may also be referred to as camera data is used to obtain red, green, and blue (RGB) images / videos of the home for creating atwo-dimensional (2D) map of the home.

[0056] In one embodiment, the environment 1000 may further include a system 100 that may be in communication with the one or more pairs of wireless transmitter- receiver 30 and / or the one or more cameras 40. In an embodiment, the system 100 may obtain CSI data and camera data to generate the 3D map of the real-world scene.

[0057] Figure 2 illustrates a schematic block diagram of a system 100 for generating the 3D map, in accordance with an embodiment of the present disclosure.

[0058] In an embodiment, the system 100 may include a memory 102 including a database 104, a processor 106 communicatively coupled with the memory 102, an Input / Output (I / O) interface 110, and a plurality of modules 120. In an embodiment, the system 100 may be implemented at a User Equipment (UE). In a non-limiting example, the UE may be a smartphone, a laptop computer, a desktop computer, a Personal Computer (PC), a notebook, a tablet, or a smartwatch. In another embodiment, the system 100 may be implemented at the one or more smart devices.

[0059] In another embodiment, the system 100 may be implemented by a cloud-based system 100, that may include a server, specifically a cloud server. In yet another embodiment, the system 100 may be implemented by a combination of the UE and the server. More specifically, one or more steps may be performed in the UE and the remaining steps may be performed by the server.

[0060] In one embodiment, the memory 102 is configured to store instructions executable by the processor 106. In one embodiment, the memory 102 communicates via a bus within the system 100. The memory 102 includes but is not limited to, a non-transitory computer-readable storage media, such as various types of volatile and non-volatile storage media including, but not limited to, random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one example, the memory includes a cache or random-access memory (RAM) for the processor 106. In alternative examples, the memory 102 is separate from the processor 106 such as a cache memory of a processor, the system 100 memory, or other memory. The memory 102 is an external storage device or the memory 102 is for storing data. The memory 102 is operable to store instructions executable by the processor 106. The functions, acts, or tasks illustrated in the figures or described are performed by the programmed processor for executing the instructions stored in the memory 102. The functions, acts, or tasks are independent of theparticular type of instruction set, storage media, processor, or processing strategy and may be performed by software, hardware, integrated circuits, firmware, micro-code, and the like, operating alone or in combination. Likewise, processing strategies include multiprocessing, multitasking, parallel processing, and the like.

[0061] As a non-limiting example, the processor 106 may be a single processing unit or a set of units each including multiple computing units. The processor 106 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions (computer-readable instructions) stored in the memory 102. Among other capabilities, the processor 106 may be configured to fetch and execute computer-readable instructions and data stored in the memory 102. The processor 106 includes one or a plurality of processors. The plurality of processors is further implemented as a general- purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit, such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an Al-dedicated processor such as a neural processing unit (NPU). The plurality of processors controls the processing of the input data in accordance with a predefined operating rule or an artificial intelligence (Al) model stored in the memory 102. The predefined operating rule or the Al model is provided through training or learning.

[0062] The processor 106 may be disposed in communication with one or more input / output (I / O) devices via the Input / Output (I / O) interface 110. The I / O interface 110 employs communication code-division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (LTE), WiMax, and the like, etc. In another embodiment of the present invention, the I / O interface 110 employs ethemet, industrial wireless Local Area Network (LAN), process field bus (PROFIBUS), actuator sensor (AS) Interface, and the like.

[0063] Figure 3 illustrates a schematic block diagram depicting a plurality of modules 120 of the system 100, in accordance with an embodiment of the present disclosure. The plurality of modules 120 may include the one or more instructions (stored in a memory) that may be executed to cause the system 100, in particular, the processor 106 of the system 100, to perform the one or more functions / methods, as discussed here in the present disclosure. In one embodiment, the plurality of modules 120 may be implemented at least in part as hardware, which may work in conjunction with theinstructions to perform the functions / methods discussed herein.

[0064] The plurality of modules 120 may include an identifying module 122, an obtaining module 124, a computing module 126, a correlating module 128, a generating module 130, a determining module 132, a classifying module 134, a modifying module 136, and a rendering module 138. In an embodiment, the identifying module 122, the obtaining module 124, the computing module 126, the correlating module 128, the generating module 130, the determining module 132, the classifying module 134, the modifying module 136, and the rendering module 138 may be in communication with each other. In an embodiment, the plurality of modules 120 may be configured to perform various operations or steps that may be discussed and explained in detail in conjunction with Figures 4-12.

[0065] Preferably, a detailed explanation of various functions of the processor 106, and / or the plurality of modules 120 may be explained in view of Figures 4-12.

[0066] Figure 4 illustrates a flowchart depicting an exemplary method 400 for generating the 3D map, in accordance with an embodiment of the present disclosure. In an embodiment, the method 400 is a computer-implemented method 400 that is explained in detail in the below paragraphs.

[0067] In an embodiment, the method 400 may begin with step 402 which may include obtaining the (CSI) data and the camera data corresponding to the real -world scene based on capturing the real-world scene via the one or more pairs of wireless transmitter-receiver 30 and the one or more cameras 40. In an embodiment, the camera data may be used to obtain a zonal map of the real-world scene which may be discussed in conjunction with Figure 5.

[0068] Figure 5 illustrates a schematic flow diagram for a generation of the zonal map using the camera data, in accordance with an embodiment of the present disclosure. In an embodiment, the zonal map generated by the camera data may also interchangeably be referred to as a predefined frame within the scope of the present disclosure. In an embodiment, the camara data may include the RGB images that may be captured by the one or more cameras 40.

[0069] More specifically, the system 100 may include a deep encoder to process the RGB images, specifically an RGB panorama with a predefined resolution. For example, the predefined resolution may be 512x 1024 (or 512x512 for perspective images), and manhattan line features lying on three orthogonal vanishing directions using an alignment method. The encoder may contain one or more convolution layers with apredefined kernel size, for example, the predefined kernel size of 3^3. Each convolution may be followed by a rectified linear unit (ReLU) operation and a max pooling layer with a predefined down-sampling factor. In an exemplary scenario, the predefined down-sampling factor is 2. The first convolution may contain one or more features, for example, 32 features, and a size may be doubled after each convolution.

[0070] Further, the system 100 may include a decoder that may include a layout boundary map predictor that may decode the one or more features into 2D features with the same resolution as the RGB panorama. In an embodiment, the layout boundary map predictor may predict a 3 -channel prediction of wall, ceiling- wall and wall-floor boundary on the RGB panorama, for both visible and occluded boundaries. The decoder may further include a comer map predictor, that may follow the same structure as the boundary map predictor and additionally may receive skip connections from a top branch for each convolution layer. More, specifically, the comer map predictor may predict corners along with the occluded comers for generation of the zonal map.

[0071] Again, referring to step 402 of Figure 4, the CSI data may be obtained from the one or more pairs of wireless transmitter-receiver 30 that may be utilized to determine motion in the real-world scene. In an embodiment, the determination of the motion associated with the real-world scene may be explained with reference to Figure 6A.

[0072] Figure 6A illustrates a flowchart depicting sub-steps for determining the motion, using the CSI data, in the real -world scene, in accordance with an embodiment of the present disclosure.

[0073] At sub-step 402a, the step 402 may include processing the obtained CSI data from each pair of wireless transmitter-receiver 30 using a predefined CSI processing model. In an embodiment, the CSI data may be processed using the following sub-steps which may be explained using blocks illustrated in Figure 6B.

[0074] At block 602, the CSI data may include CSI amplitude variations in a time domain that may be extracted and may be determined that amplitude may be different for different humans, activities, gestures, etc., which may be used for various tasks. In an embodiment, the amplitude may vary depending on factors such as distance and signal strength. For example, given a complex CSI value as shown in equation 1 below, the amplitude may be extracted as shown in equation 2 below: z= a+ib . (1) where a corresponds to amplitude component,where b corresponds to phase component, where z corresponds to the complex CSI valueA = Va2+ b2. (2),Where, A corresponds to the amplitude.

[0075] After that, at block 604, a phase value (a) of the CSI signals may be extracted. The phase value (a) may provide valuable information about channel characteristics, such as delay spread, and a doppler shift with proper processing. For the complex CSI value (z), the phase value (a) may be extracted using equation 3 as below:Im(z) corresponds to an imaginary part of the complex value (z)Re ( z ) corresponds to a real part ( real axis component ) of the complex CSI value ( z )

[0076] More specifically, a ratio between the imaginary part (Im(z)) and the real part (Re(z)) may be computed by dividing the imaginary part (Im(z)) by the real part (Re(z)). The computed ration may be used as an argument for an inverse tan function. Thereafter, the angle formed by the imaginary part (Im(z)) and the real part (Re(z)) of the complex CSI value (z) in a polar coordinate system may be determined using the inverse tan function.

[0077] Further, at block 606, a phase sanitization may be conducted to mitigate errors or distortions in the extracted phase value (a). More specifically, in this step, the effects of phase noise and random phase offsets may be mitigated by implementing a linear transformation as shown in equation 4 below: a = argmin S v=1Sj=i(y(k,v,y) + 2nf5(y - l)a + p)2. (4)Where fsis a frequency difference of adjacent subcarriers, y(k,v,y) is unwrapped phase of kthsubcarrier transmitted from vthtransmitter and received at ythreceiver,where o represents an optimal parameter set that minimizes the error,K represents number of classes,V represents number of features,Y represents number of samples, y(k, v, y): observed data point at class k, feature v, sample y, ffg (y-1) represent Kronecker delta function, which is 1 when y-1 = 5 and 0 otherwise, a represents weighting factor for the Kronecker delta function, andP represents offset term.

[0078] In an embodiment, a calibrated phase value (a) may be extracted using equation (5) as below: y'(k,v,y) = y(k,v,y) - 2nf5(y - 1)CT . ( 5 )

[0079] At block 608, outliers may be substituted from the calibrated phase value (a) using a hampel filter, as the outliers may have a significant impact on the accuracy of the features extracted and may cause significant errors in the estimation of channel frequency response. Therefore, the substitution of the outliers may lead to improving the performance of the system 100. In an embodiment, the hampel filter may be a configurable width sliding window that may be a slide across time series. For each window, the hampel filter may replace values that surpass a certain threshold based on median absolute deviation.

[0080] At block 610, long-term trends in the CSI data caused by various factors such as signal reflections, interference and hardware imperfections may be eliminated using a linear de-trending. The linear-de-trending may calculate a least-square linear regression of the CSI data and subtract a resulting line from the CSI data to de-trend. In an exemplary embodiment, the resulting line may herein refer to a fitted line obtained from the leastsquare linear regression of the CSI data. More particularly, the fitted line may represent a long-term trend present in the CSI data, which may be caused by factors such as signal reflections, interference, and hardware imperfections.

[0081] At block 612, the processing module may include a combination layer that may combine the preprocessed amplitude data and phase data.

[0082] Again, referring to Figure 6A, at sub-step 402b, the step 402 may include converting the amplitude data and the phase data associated with the processed CSI data to a first signal. In an embodiment, the amplitude data and the phase data may be converted using equation 6 as below:"z=|z|(cos(4>)+isin(4>))" . (6)Where , " | z | " is the magnitude andis Phase information .

[0083] At sub-step 402c, the step 402 may include obtaining a second signal based on correlating the CSI signals and the first signal using equation 7 as below: Xc=Xl*X2 . (7)

[0084] In an embodiment, Xc corresponds to the second signal alternatively referred to a cross-correlation signal which may be created by multiplying pre-processed Wi-Fi CSI signal (CSI signal) extracted from Tx-Rxl (first transmitter-receiver 30) with complex conjugate of Tx-Rx2 (second transmitter-receiver 30) signal extracted.

[0085] At sub-step 402d, the step 402 may include obtaining a doppler shift spectrogram based on applying one or more predefined doppler shift models on the second signal. In an embodiment, the doppler shift spectrogram may indicate a visual representation of change in frequency over time. More specifically, the doppler shift spectrogram may be obtained by applying a Butterworth band pass filter, and a short-time Fourier transform successively on the second signal. In an embodiment, the doppler shift spectrogram may capture a variation caused in the second signal due to dynamic components of the real-world scene being used so that static signals may be removed to reduce the impact of static environmental factors on activity signals.

[0086] Moreover, at sub-step 402e, the step 402 may include determining a static motion and a dynamic motion in the real-world scene based on analyzing the doppler shift spectrogram on the second signal using the Al model. In an embodiment, the obtained CSI data is analyzed while considering the static motion and the dynamic motion in the real-world scene. More specifically, the Al model such as a deep learning module may be used for feature extraction to differentiate between the static motion and the dynamic motion.

[0087] Referring back to Figure 4, at step 404, the method 400 may include identifying, viathe identifying module 122, one or more overlapping CSI regions based on the obtained CSI data while considering the static motion and the dynamic motion within the real -world scene. In an embodiment, the one or more overlapping CSI regions may indicate regions where CSI signals received from at least two pairs of wireless transmitter-receiver 30 may overlap. In an embodiment, the identification of the one or more overlapping CSI regions may be discussed in conjunction with Figure 7A.

[0088] Figure 7A illustrates a flowchart depicting sub-steps for identifying the one or more overlapping CSI regions, in accordance with an embodiment of the present disclosure.

[0089] At sub-step 404a, the step 404 may include obtaining, via the obtaining module 124, channel impulse response (CRI) data associated with each pair of wireless transmitterreceiver 30 based on the analyzed CSI data. In an embodiment, the obtained CSI data may be analyzed using a fourier transform for extracting frequency components and identifying multipath delays. However, this should be construed as a limitation of the present disclosure. In another embodiment, the obtained CSI data may be analyzed using other similar analyzing techniques.

[0090] In an embodiment, a received signal y(t)y(t) at the one or more receivers 10 may be expressed as a convolution of a transmitted signal x(t)x(t) and the CRI h(t)h(t) along with additive noise as shown using equation 8 below: n(t)n(t): y(t)=x(t)*h(t)+n(t)y(t)=x(t)*h(t)+n(t) . (8)

[0091] At sub-step 404b, the step 404 may include computing, via the computing module 126, a set of beamforming vectors (w) for each pair of wireless transmitter-receiver 30 based on the obtained CRI data. In an embodiment, the beamforming vectors (w) may help in focusing transmitted signals toward an intended receiver 10 and enhancing reception quality.

[0092] In an embodiment, the beamforming vectors (w) may maximize the signal power at the one or more receivers 10 and be computed using equation 9 as below: w=Hv||Hv . (9) where , "H" is a channel matrix and "v" is a desired signal vector

[0093] At sub-step 404c, the step 404 may include obtaining, via the obtaining module 124, directional CSI data for each pair of wireless transmitter-receiver 30 based on applying the computed beam-forming vectors to the obtained CSI data.

[0094] At sub-step 404d, the step 404 may include correlating, via the correlating module 128, the channel impulse response (CRI), beamforming vectors, and the obtained directional CSI data for identifying the one or more overlapping CSI regions. In an exemplary scenario, the one or more overlapping CSI regions may be illustrated in Figure 7B. More specifically, referring to Figure 7B, the one or more transmitters 20 may be shown which may be installed in different locations of the real-world scene. For example, the one or more transmitters 20 may include a first transmitter 20a, a second transmitter 20b, a third transmitter 20c, and so on. Further, the figure may also illustrate one or more predefined zones associated with the real -world scene. For example, the one or more predefined zones may include zone 1, zone 2, zone 3, and so on. The one or more predefined zones may be defined based on the range of CSI signals of the one or more pairs of wireless-transmitter-receiver 30.

[0095] In one embodiment, the one or more predefined zones may have a boundary that may be determined. In an embodiment, to determine the boundary associated with the one or more predefined zones, the generating module 130 may generate a first score for each of the one or more predefined zones while considering a set of predefined criteria. In an embodiment, the first score may herein refer to a priority score. In an embodiment, the set of predefined criteria may herein indicate at least one of signal strength, signal-to-noise ratio (SNR), and spatial coverage. In an exemplary scenario, the zone with a higher signal strength, higher SNR ratio, and larger spatial coverage may be assigned with a higher first score.

[0096] Further, the generating module 130 may generate a second score for each of the one or more predefined zones based on correlating the first score associated with each zone using equation 10 below:PTotai=wRSSI*PRSSI+wSNR*PSNR+wCoverage*PCoverage ... (10) where P otai corresponds to the second score which may also be referred to as an overall priority score within the scope of the present disclosure, where, wRSSI, wSNR, and wCoverage are weights representing the relative importance of each criterion.

[0097] Furthermore, the identifying module 122 may select each zone among the one or more predefined zones based on the second generated score. In an embodiment, the zone with a higher score is selected prior to selecting other zones. In an exemplary scenario,if zone 1 has an overall priority score of 9 and zone 2 has the overall priority score of 7. In this case, the zone 1 is prioritized and selected first, thereafter, the zone 2 is selected. In an exemplary representation, the selected zones are illustrated in Figure 8A.

[0098] Thereafter, the determining module 132 may be configured to determine a boundary associated with each zone based on the selected zones as illustrated in Figure 8A.

[0099] In one embodiment, a number of one or more predefined zones may be calculated based on the identified one or more overlapping CSI regions. In an embodiment, the determining module 132 may determine a union of one or more overlapping CSI regions and intersect the one or more overlapping CSI regions with each determined boundary. This may enable the calculation of the number of the one or more predefined zones, and provide insights into the spatial organization of the home with respect to WiFi coverage.

[0100] In an exemplary scenario, let “O” be the one or more overlapping CSI regions and “B” be the determined boundary of each zone. The combination or union of the one or more overlapping CSI regions (U) may be represented using equation 11 below: U=Uo£OoU . (11)

[0101] For each boundary biGB, calculate the intersection with the union of overlapped regions (U) which is shown in equation 12 below:Bi=binU . (12)

[0102] Thereafter, the number of the one or more predefined zones may be calculated as the number of non-empty sets in a set of zone boundaries {Bi}.N=£i= 1 IB 11 (Bi 0)N=£i= 1 (B 1 =0) . (13)Where N represents the number of the one or more predefined zones,IB I is a number of boundaries associated with the one or more predefined zones, l(-) represents an indicator function, which returns 1 if a condition inside the parentheses is true and otherwise 0

[0103] In various embodiments, a JSON representation of the one or more predefined zones, the one or more overlapping CSI regions, and the determined boundary for each zone is generated. The JSON representation may include information such as zone IDs, and boundary coordinates, and the one or more transmitters 20 associations for each zoneare illustrated in Figure 8B.

[0104] Again, referring to Figure 4, at step 406, the method 400 may include identifying, via the identifying module 122, one or more objects 50 corresponding to the real -world scene based on the obtained CSI data. In an exemplary scenario, the one or more objects 50 may include but are not limited to sofas, chairs, tables, beds, or any other objects present in the real-world scene. However, this should not be construed as a limitation of the present disclosure. In another scenario, the one or more objects 50 may depend on a type of the real-world scene. In an embodiment, the identification of the one or more objects 50 may be explained in conjunction with Figure 9.

[0105] Figure 9 illustrates a flowchart depicting sub-steps for identifying the one or more objects 50 corresponding to the real-world scene based on the obtained CSI data, in accordance with an embodiment of the present disclosure.

[0106] At sub-step 406a, the step 406 may include extracting, via the obtaining module 124, features based on the obtained CSI data. In an embodiment, the features may be indicative of a presence of the one or more objects 50. In an exemplary embodiment, the features may include but are not limited to changes in signal strength, multipath reflections, and attenuation patterns.

[0107] At sub-step 406b, the step 406 may include generating, via the generating module 130, point clouds based on the extracted features. In an embodiment, the generated point clouds may be indicative of a spatial distribution of the one or more objects 50 in the one or more predefined zones. More specifically, each point cloud may correspond to a location where the one or more objects 50 may be detected, thereby identifying the one or more objects 50.

[0108] In an embodiment, after identifying the one or more objects 50, the classifying module 134 may use the Al model such as the deep learning model to classify the one or more identified objects 50 into or more categories based on the generated point clouds. For example, the one or more identified objects 50 may be classified as sofas, tables, etc.

[0109] Further, the correlating module 128 may correlate the generated point clouds associated with the one or more classified objects associated with the one or more predefined zones and the one or more overlapping CSI regions for generating the 2D layout. In another embodiment, other relevant information such as the boundary of each zone, and the signal strength in each zone may also be incorporated to generate the 2D layout.

[0110] Again, referring to Figure 4, at step 408, the method 400 may include generating, viathe generating module 130, generating the 2D layout associated with the real -world scene based on the one or more identified objects 50 and the one or more overlapping CSI regions. In an embodiment, the generated 2D layout may include a spatial distribution of the classified one or more identified objects 50. More specifically, the generation of the 2D layout may be explained in conjunction with Figure 10.

[0111] Figure 10 illustrates a flowchart depicting sub-steps for generating the 2D layout, in accordance with an embodiment of the present disclosure. At sub-step 408a, the step 408 may include splitting the real-world scene into a grid of cells. In an embodiment, the size of the cells may be determined based on a resolution required for the representation of the 2D layout to be generated.

[0112] At sub-step 408b, the step 408 may include generating, via the generating module 130, a signal strength value associated with each grid cell based on the split frame. In an embodiment, the signal strength value is indicative of signal strength and multipath effects. In an embodiment, each grid cell may herein represent a specific location within the real-world scene and an index of a specific grid cell corresponds to a position of the specific grid cell in a grid.

[0113] At sub-step 408c, the step 408 may include estimating, via the determining module 132, the signal strength at each of the one or more predefined zones based on interpolating the signal strength value for each grid cell. In an embodiment, the directional CSI data may be utilized to interpolate the signal strength values for each grid cell. Thereafter, the determining module 132 may use an inverse distance weighting (IDW) technique to estimate the signal strength at locations of the one or more predefined zones where direct measurements may not be available. In another embodiment, similar techniques may be used to estimate the signal strength.

[0114] Furthermore, at sub-step 408d, the step 408 may include detecting, via the determining module 132, a presence of one or more components associated with the signal strength based on the estimated signal strength. In an embodiment, the one or more components are indicative of obstacles, reflectors, diffraction phenomena, and signal-occluded areas. Further, the determining module 132 may apply a Friis transmission equation loss model to account for signal attenuation due to distance and environmental factors. In an embodiment, the determining module 132 may apply an edge detection technique to identify significant changes in the signal strength, thereby indicating the presence of the one or more components.

[0115] In addition, at sub-step 410e, the step 408 may include assigning one or more attributesto the one or more detected components based on categorizing the one or more detected components. In an embodiment, the one or more attributes may include an angle of arrival (AoA) and / or a time of flight (ToF) associated with the one or more detected components.

[0116] Further, at sub-step 41 Of, the step 408 may include computing, via the computing module 126, coordinates corresponding to the one or more detected components, and each grid cell based on the assigned attributes associated with the one or more detected components. In an exemplary embodiment, in any specific zone among the one or more predefined zones, a router (transmitter 20) may be considered as a reference point as the coordinates of the router (transmitter 20) may serve as a starting point for computing the coordinates of the one or more detected components within the real- world scene. Further, the coordinates of each grid cell with respect to the router (transmitter 20) may be defined based on the extracted features.

[0117] Moreover, at sub-step 410g, the step 408 may include converting coordinates associated with each grid cell to coordinates of the real-world scene using premeasured data (known dimensions and scale of the real-world scene) associated with the real- world scene, thereby generating the 2D layout. In an embodiment, the 2D layout along with the assigned attributes may be stored in the database 104 in the JSON format. In the JSON format, each zone may be represented with a unique identification (ID), coordinates of the one or more transmitters 20, and a collection of the coordinates with associated signal strength values. In an embodiment, the coordinates may be relative to the positions of the one or more transmitters 20, providing a spatially referenced layout.

[0118] Again, referring to Figure 4, at step 410, the method 400 may include modifying, via the modifying module 136, the 2D layout for generating the three-dimensional (3D) map associated with the real-world scene. In an embodiment, the modification of the generated 2D layout is explained in the below paragraphs.

[0119] At sub-step-410a, the step 410 may include identifying, via the identifying module 122, dissimilarity between the obtained CSI data and the camera data associated with the one or more identified objects 50. In an embodiment, the identification of the dissimilarity may be carried out using steps explained in the paragraphs below with reference to Figure 11 A.

[0120] Figure 11 A illustrates a flowchart depicting sub-steps for identifying the dissimilarity between the obtained CSI data and the camera data associated with the one or moreidentified objects 50, in accordance with an embodiment of the present disclosure.

[0121] At sub-step 410a-l, the determining module 132 may determine a common reference frame associated with the one or more identified objects 50. Referring to Figure 1 IB, in an exemplary scenario, the television is installed within a distance (d) meter from an identified object i.e., a sofa, and the one or more cameras 40 may be installed in the television. In an embodiment, the television may be determined as the common frame for capturing the sofa using the CSI signals and the one or more cameras 40, respectively.

[0122] At sub-step 410a-2, the determining module 132 may determine a first set of coordinates and a second set of coordinates corresponding to the one or more identified objects 50. In an embodiment, the first set of coordinates may be obtained by utilizing the obtained CSI data. In another embodiment, the second set of coordinates may be obtained by utilizing the camera data. For example, the first set of coordinates may be represented as (xCSI,SI) and the second set of coordinates may be represented as (xc,yc).

[0123] At sub-step 410a-3, the computing module 126 may compute a transforming matrix using a calibration technique based on the determined first set of coordinates and the determined second set of coordinates. In an embodiment, the transforming matrix may be indicative of the dissimilarity in the position and the orientation of the one or more identified objects 50, thereby identifying the dissimilarity between the obtained CSI data and the camera data. In an embodiment, the transformation matrix may be represented using equation 14 as below:Where R corresponds to a rotation matrix representing an orientation di fference ,T corresponds to a translational vector representing a position dif ference ,Where xcsi, ycsi corresponds to the first set of coordinatesWhere, xc, yccorresponds to the second set of coordinates, and

[0124] In an embodiment, the rotation matrix (R) and the translational vector (T) may becalculated using the calibration technique discussed using blocks illustrated in Figure 11C.

[0125] Figure 11C illustrates a flowchart depicting blocks for calculating the rotation matrix (R) and the translational vector (T), in accordance with an embodiment of the present disclosure.

[0126] At block 1102, the identifying module 122 may identify corresponding coordinates for the one or more identified objects 50 as shown in equations 15 and 16 below: Pi = (xci. yci) . (15)Where, xCi, yCicorresponds to the second set of coordinatesQi = (xcsii, ycsii) . (16)Where xcsii, ycsii corresponds to the first set of coordinates

[0127] At block 1104, the computing module 126 may be configured to compute centroids associated with the identified corresponding coordinates as shown in equations 17 and 18 below:

[0128] At block 1106, the computing module 126 may be configured to subtract centroids using equations 19 and 20 below:Pi' = Pi - P . (19)Q'i = Qi - Q . (20)

[0129] Further, at block 1108, the computing module 126 may a compute covariance matrix using equation 21 as below:

[0130] Further, at block 1110, the computing module 126 may compute a singular value decomposition (SVD) based on the covariance matrix (H) using equation 22 as below:

[0131] Furthermore, at block 1112, the computing module 126 may compute the rotationmatrix (R) based on the SVD using equation 23 as below:R = VUT. (23)

[0132] At step 1114, the computing module 126 may compute the translational vector (T) based on the rotation matrix (R) using equation 24 as below:T= Q - RP . (24)Where Q corresponds to a coordinate matrix of coordinates of the object(s) coordinates with respect to the CSI,P corresponds to a coordinate matrix of coordinates of the object(s) coordinates with respect to the cameras 40

[0133] Again, referring to Figure 4, at sub-step 410b, the step 410 may include normalizing, via the normalizing module, at least one of a position and an orientation of the one or more identified objects 50 based on the identified dissimilarity. In an embodiment, the normalization may be carried out using steps explained in the paragraphs below with reference to Figure 12.

[0134] Figure 12 illustrates a flowchart depicting sub-steps for normalizing the position and / or the orientation of the one or more identified objects 50, in accordance with an embodiment of the present disclosure.

[0135] At sub-step 410b-l, the modifying module 136 may adjust external calibration of the one or more identified objects 50 based on the computed transforming matrix.

[0136] At sub-step 41 Ob-2, the determining module 132 may be configured to estimate a co- spatial shift in the first set of coordinates using linear regression using equation 25 as shown below:(Axi, Ayl ) = ( f ( ( xci- Xcsii' ) , di, 01 ) , f ( ( yci- ycsii' ) , di, 0i ) ) . ( 25 )Where , ( Axi , Ayi ) corresponds to the co-spatial shi ft

[0137] At sub-step 410b-3, an orientation alignment may be validated. In an embodiment, the orientation alignment may be associated with the one or more identified objects 50 with respect to the objects identified in a predefined frame associated with the real- world scene captured by the one or more cameras 40.

[0138] At sub-step 41 Ob-4, the first set of coordinates associated with the one or more identified objects 50 may be calibrated based on the validation, thereby normalizingthe position of the one or more identified objects 50 in the generated 2D layout.

[0139] Figure 13 A illustrates an exemplary 2D layout of the home, in accordance with an embodiment of the present disclosure. In an exemplary embodiment, the 2D layout may include the one or more predefined zones such as zone 1, zone 2, and zone 3. Further, the 2D layout may be incorporated with the one or more pairs of wireless transmitter-receiver 30 and the one or more objects 50. For example, the one or more objects 50 may include a first object 50a, a second object 50b, and a third object 50c. In an exemplary scenario, the first object 50a may be captured through both the CSI signals of the one or more pairs of wireless transmitter-receiver 30 and the one or more cameras 40.

[0140] Figure 13B illustrates an exemplary shape and the orientation of an identified object 50, in accordance with an embodiment of the present disclosure. Figure 13C illustrates an exemplary shape and the orientation of an exemplary identified object when captured by the one or more cameras 40, in accordance with an embodiment of the present disclosure.

[0141] Figure 13D illustrates an exemplary shape and the orientation of the identified object 50 when captured by the CSI signals of the one or more pairs of transmitter-receiver 30, in accordance with an embodiment of the present disclosure. In an exemplary embodiment, the first set of coordinates may be illustrated in Figure 13D. For example, the first set of coordinates are (xCSIl, yCSIl), (xCSI2, yCSI2), (xCSI3, yCSI3) and (xCSI4, yCSI4).

[0142] Figure 13E illustrates an exemplary representation of the identified object 50 of Figure 13D after calibration, in accordance with an embodiment of the present disclosure. From the figure, the first set of coordinates may be changed after the calibration. For example, (xCSIl, yCSIl) has been shifted to (xCSIl + Axl, yCSIl + Ayl).

[0143] At sub-step 410b-5, the modifying module 136 may rotate the one or more identified objects 50 by a predefined degree for a predefined number of times based on the calibrated first set of coordinates. In an embodiment, the one or more identified objects 50 may be rotated for matching the orientation of the one or more identified objects 50 with the objects captured by the one or more cameras 40, thereby normalizing the orientation of the one or more identified objects 50 in the generated 2D layout. In an exemplary scenario, the one or more identified objects 50 that may be identified by the CSI signals may be rotated by 1 degree each time and then matched with the objects that may be captured by the one or more cameras 40. This procedure may be repeatedtill the one or more identified objects 50 may complete full rotation or may match with the objects captured by the one or more cameras as illustrated in Figures 13F and 13H. Referring to Figure 13F, the identified object 50 captured by the CSI signals rotated by 1 degree clockwise to update the first set of coordinates as illustrated in Figure 13G. In an embodiment, the identified object 50 is rotated to match the object captured by the one or more cameras as illustrated in Figure 13H.

[0144] In one embodiment, the identifying module 122 may be configured to identify whether the one or more identified objects 50 may be common that are identified in the generated 2D layout and the predefined frame. In an embodiment, the predefined frame herein refers to the zonal map that may be generated using the one or more cameras 40. More specifically, the predefined frame may interchangeably be termed the zonal map within the scope of the present disclosure. For example, if the first object 50a may be similar in the one of the one or more cameras 40 and the CSI signals.

[0145] Further, the determining module 132 may determine one or more convergence zones associated with the one or more identified objects 50 that may be common. In an embodiment, the one or more convergence zones may be determined based on merging boundaries captured by the CSI signals and the one or more cameras 40 associated with the one or more identified objects 50 that may be common. More, specifically, the one or more identified objects 50 matched may be considered to be inside merged boundaries.

[0146] Again, referring to Figure 4, at sub-step 410c, the step 410 may include identifying, via the identifying module 122, one or more targeted zones among one or more predefined zones based on the normalized position and / or the normalized orientation. In an embodiment, the one or more targeted zones may be indicative of one or more isolated zones and / or one or more disconnected zones identified based on analyzing the generated 2D layout. More specifically, the identification module may include a partial zone reconciliation module that may contain geometric extrapolation verification check for closed shapes, and graph-based techniques to identify the one or more isolated zones and / or disconnected zones. In an embodiment, the one or more isolated zones and / or disconnected zones may highlight boundary inconsistencies, connectivity issues, and aesthetic misalignments.

[0147] In one embodiment, to identify the one or more targeted zones, the identifying module 122 may identify the presence or the absence of one or more parameters corresponding to the one or more predefined zones based on analyzing each zone. In an embodiment,the one or more parameters may indicate a closed polygon and / or straight boundaries of the one or more identified zones. Thereafter, the identifying module 122 may identify the one or more targeted zones among the one or more predefined zones upon identifying the absence of one or more parameters.

[0148] Figure 14A illustrates an exemplary schematic diagram depicting a coordinate-to- geometry view of the 2D layout, in accordance with an embodiment of the present disclosure. In an embodiment, a query for identifying the presence or absence of the one or more parameters associated with the 2D layout shown in Figure 14A may be generated as below: zonal_correction[] is closed geometry _polygon(z []: coordinates) : geometry _polygon =linestring(z[]. ’coordinates) return geometry polygon, is ring

[0149] Further, a response to the query may be generated as:Zone returns non- geometry polygon: Zone gets marked for Correction(zonal correction [Zx CSGVcorr])Zones which contains geometry _polygon: This signifies zone is closed (move to next stage)

[0150] In an embodiment, an updated javascript object notation (JSON) tag may be represented as below:“zone l geometry validation" : true;" zone 2 geometry validation" : true ;" zone 3 geometry validation" : false

[0151] Figure 14B illustrates a schematic diagram of the 2D layout after identifying the presence and / or the absence of the one or more parameters, in accordance with an embodiment of the present disclosure. In an exemplary embodiment, the zone 1 among the one or more predefined zones has a closed polygon. Further, the zone 2 also has the closed polygon, and the zone 3 does not have the geometry of the closed polygon. Thereafter, the identifying module 122 may identify the zone 3 as a targeted zone.

[0152] In one embodiment, the identifying module 122 may identify one or more multi subzones associated with the identified one or more targeted zones. More specifically, the identifying module 122 may iterate through metadata associated with each of the one or more targeted zones to determine if the one or more targeted zones may contain multi-functional zones symptoms like (kitchen, bedroom, walls, etc). Thereafter, the identifying module 122 may be configured to identify the one or more multi sub-zonesassociated with the one or more targeted zones. In an exemplary scenario, in the JSON format, the identification may be represented as below:Zl (metada ta [ ] ) => Itera tor (Z1 Obj [ ] )Z1 obj [ ] => Functional zone / sDetermines Ki tchen / Wall Segmen t which transla te in to mul ti -zone .Metada ta upda te => Zl [ Zl SubZl [ ] , Zl subZ2 [ ] ]

[0153] In another embodiment, the identifying module 122 may further identify misaligned coordinates corresponding to the one or more multi sub-zones. In an embodiment, the identifying module 122 may use a slope and reverse half validation technique for identifying the misaligned coordinates. slopes = [] for i in range(len(coordinates) - 1): xl, yl = coordinates [i] x2, y2 = coordinates [i + 1] slope = (y2 - yl) / (x2 - xl) slopes.append(slope)# Check if the slopes are consistent within the tolerance return all(abs(slopes[i] - slopes[i - 1]) < Tfmal for i in range(l, len(slopes)))Here Tfmal => Tolerance Point

[0154] In an embodiment, the tolerance unit (Tfmal) may be determined in a global context. The calculation of the tolerance unit (Tfmal) in the JSON format may be represented as: deviations[]=iterate(deviation = abs(cooord[0] - central axis) Tcb = np.mean(deviations)Tp = (map width + map height) / 200Tolerance unit => Tfmal = (Tcb + Tp) / 2Where, Tcb represents standard deviation from central boundary, and Tp represents proportional tolerance

[0155] In an embodiment, the one or more targeted zones and the associated multi-subzones may be selected for correction which may be represented in the JSON format as:Zone returns non- geometry _polygon: Zone gets marked for Correction (zonal correction [Zx CSG Vcorr ] )Zone returns Tolerance Invalidator zones: Zone gets marked for Correction(zonal correction [Zx BSMcorr ] )

[0156] In an embodiment, the modifying module 136 may include a geometry alignment model that may be adapted to modify the one or more parameters i.e., to make an aligned polygon with the straight boundaries associated with the identified one or more targeted zones. More specifically, the geometry alignment model may extend the boundary of the identified one or more targeted zones to touch and close the loop without causing overlaying another zone boundary. In an embodiment, the JSON format for making the aligned polygon may be represented as: ga s = [] for i in range (len(data)) polyl = Polygon(data.loc[i, 'coordinates]' ) for j in range (i + 1, len(data)) poly 2 = Polygon(data.loc[], 'coordinates'])# Check for gaps between polygons if not polyl.touches(poly2): gaps.append((i, ])) for (zone 1 idx, zone2_idx) in gaps polyl = Polygon(data.loc [zone 1 idx, 'coordinates]' ) poly 2 = Polygon(data.loc[zone2_idx, 'coordinates]' )

[0157] In an embodiment, the extension of the boundary of the identified one or more targeted zones may be represented as below: data . loc [ zonel idx' coordina tes ' ] . append (polyl . exterior . interpola te (1 . 0, normal! zed=True) ) da ta . loc [ zone2 idx,' coordina tes ' ] . append (poly 2 . exterior . interpola te (1 . 0, normal! zed=True) ) return updated coordinates

[0158] Figure 14C illustrates an example representation of the 2D layout depicting the aligned polygon of the identified one or more targeted zones, in accordance with an embodiment of the present disclosure. Referring to Figure, the zone 3 has been corrected to make the aligned polygon with updated coordinates represented in the JSON format as below:[zone_3_bottom_right_X, zone_3_bottom_right_Y]

[0159] In one embodiment, the modifying module 136 may correct the identified misaligned coordinates by utilizing one or more geometric factors to obtain the aligned coordinates associated with the one or more multi sub-zones. In an exemplary embodiment, the correction of the misaligned coordinates may be represented in the J SON format as below: correct_misaligned_deviation(coordinates, deviations): for i, slope, prev slope in deviations:- Calculate the corrected coordinate for the current segment- Use linear interpolation or a similar method to correct the deviation xl, yl = coordinates [i - 1] x2, y2 = coordinates [i] corrected_x2 = xl + (x2 -xl) * abs (prev slope / slope) corrected_y2 =yl + (y2 - yl) * abs (prev slope / slope)- Update the coordinates to correct the deviation coordinates [i] = (corrected _x2, corrected_y2) return coordinates

[0160] Again, referring to Figure 4, at sub step 410d, the step 410 may include applying, via the modifying module 136, one or more object-enhancing effects on the one or more identified objects 50 associated with each of the one or more predefined zones. More specifically, thematic modifications and / or exposure modifications may be applied to the one or more identified objects 50 associated with each zone of the generated 2D layout. This may help in accurately representing colour, textures and lighting conditions of the one or more identified objects 50 in the real -world scene, thereby leading to a more realistic and immersive 3D map that accurately reflects the real- world scene such as home, office etc.

[0161] In an embodiment, the thematic modifications may include colour modifications, shape modifications, and / or texture corrections. In the colour modifications, colour of the one or more identified objects 50 may be adjusted to make them more visually appealing or to match a specific colour scheme. This may involve changing a hue, a saturation, a brightness of a texture associated with the one or more identified objects 50. In the shape modifications, the shape of the one or more identified objects 50 may be modified using scaling, stretching, or reshaping a geometry of the one or more identified objects 50. This may improve the visual appearance or match specific design requirements. Furthermore, in the texture modifications, a texture of the one or moreidentified objects 50 may be enhanced or modified by applying filters, overlays, or texture mapping techniques. This may lead to improving realism or achieving specific visual effects.

[0162] In an embodiment, the exposure modifications may affect an object-level theme rendering in the 3D map. More specifically, the exposure modification may affect a perceived colour and texture of the one or more identified objects 50 in the real -world scene. Further, the exposure modifications may also affect the contrast and level of detail in the one or more identified objects 50. Moreover, adjusting exposure may highlight or obscure certain features of the one or more identified objects 50, which may impact how these features may perceive and render the 3D map via the rendering module 138. Furthermore, the exposure modifications may change the overall lighting of the real -world scene, which may in turn affect how the one or more identified obj ects 50 may illuminate and how themes may be rendered. In various embodiments, the exposure modifications may interchangeably be termed as exposure compensation within the scope of the present disclosure.

[0163] In various embodiments, for each zone a spatial transformation may be performed i.e. object wise theme extraction from the source image and distribution on the target image objects. In an exemplary embodiment, the image that may be captured by the one or more cameras 40 may not cover the entire indoor map and the objects. Therefore, the theme and exposure extrapolation may be performed on new zones and new objects where source objects may not be mapped one on one.

[0164] In various embodiments, the generating module 130 may generate the 3D map associated with the real-world scene based on the modifications. In an exemplary embodiment, the generating module 130 may use integration of exposure modification constraints and texture synthesis which is explained in the below paragraphs. A network may include one or more parallel streams, specifically two parallel streams, each focusing on a specific task related to the 3D map generation.

[0165] In an embodiment, the parallel streams may include a texture synthesis stream that may be responsible for generating realistic textures for the one or more identified objects 50 in the real-world scene. The texture synthesis stream may take 2D images as input of the real-world scene and may synthesize textures that may be visually appealing and contextually relevant.

[0166] Further, the parallel streams may include an exposure modification reconstruction stream that may focus on reconstructing exposure compensation values for each objectin the real-world scene. The exposure modification reconstruction stream may use synthesized textures and other contextual information to determine the appropriate exposure modification / compensation for each object 50 of the one or more identified objects.

[0167] Further, the system 100 may include a learning model that may couple learning between the above-discussed parallel streams. In an exemplary embodiment, the texture synthesis stream may take into account the exposure compensation constraints provided by the reconstruction stream, and vice versa. The coupling may allow the two parallel streams to better leverage each other's outputs and improve the overall plausibility of the generated 3D map.

[0168] In various embodiments, the 3D map may be associated with the real-world scene such as the home, and rendered in the one or more smart devices or the UE. For example, the 3D map specifies walls and openings (i.e., doors and windows) as line segments, provides a category for each room (e.g., bedroom), and contains structurally fixed objects (e.g., toilets), each of which is given a position. Further, floor map coordinates may be stored in JSON format. Additionally, the thematic modifications that may be applied on the one or more identified objects 50 may be stored as feature vectors in the database 104.

[0169] In various embodiments, exemplary use cases may be illustrated with reference to Figures 15-18B.

[0170] Figure 15 illustrates an example representation of a first exemplary use case depicting a realistic home including the one or more smart devices for rendering the generated 3D map, in accordance with an embodiment of the present disclosure. In an embodiment, the 3D map shows the realistic view of the one or more identified objects 50 which are rendered in the one or more smart devices such as a refrigerator, and the television as illustrated in Figure 15.

[0171] Figures 16A-16B illustrate example representations of a second exemplary use depicting wi-fi coverage and air quality index (AQI) in the map generated by existing methods and the present disclosure, respectively. More specifically, Figure 16A illustrates an example representation of the 2D map depicting the wi-fi coverage and the AQI. In an embodiment, the user finds it difficult to access the home and take corrective actions using the 2D map generated by the existing methods. More specifically, the user may not decide in which area of the home, an air purifier needs to be turned on. Figure 16B illustrates an example representation of the 3D mapgenerated, in accordance with an embodiment of the present disclosure. In the embodiment, the user may be able to access the home easily and may be able to take the corrective actions to purify the air in a particular area based on the air quality index (AQI) rendered in the 3D map generated and turn on the air purifier accordingly.

[0172] Figure 17A illustrates an example representation of a third exemplary use for locating and instructing a vacuum cleaner using the 3D map generated, in accordance with an embodiment of the present disclosure. In an embodiment, the user may locate the vacuum cleaner easily with the 3D map generated. Further, the user may easily identify dirty areas and instruct the vacuum cleaner accordingly. For example, the user may provide instructions to make the vacuum clear to clean the area under the table. However, in the 2D map generated by the existing methods, the user has to think and correlate with the real-world scene to locate the vacuum cleaner as illustrated in Figure 17B.

[0173] Figure 18A illustrates an example representation of a fourth exemplary use case in which the user navigates using the 3D map generated, in accordance with an embodiment of the present disclosure. In an embodiment, the 3D map is generated of the indoor space as a building in which a conference is going to be held. Therefore, the user may easily navigate the location of the conference with the help of the 3D map generated. However, in the 2D map generated by the existing methods, the user may not be able to navigate the location of the conference due to the path created by the 2D map being very intuitive as illustrated in Figure 18B.

[0174] In various embodiments, the present disclosure enables the generation of the 3D map that represents the realistic view of the real-world scene, thereby eliminating human intervention in creating the map. More specifically, the present disclosure enables the generation of the 3D map incorporating home aesthetics. Furthermore, the present disclosure enables tracking of the 3D map generated, in case of any changes in the real-world scene, thereby updating the 3D map accordingly. Moreover, the present disclosure enables modifications of the one or more predefined zones including the thematic and the exposure modifications of the one or more objects, leading to a more realistic view of the real -world scene in the 3D map rendered.

[0175] The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the elements. The elements can be at least one of a hardware device or a combination of hardware devices and software modules.

[0176] It is understood that terms including “unit” or “module” at the end may refer to the unit for processing at least one function or operation and may be implemented in hardware, software, or a combination of hardware and software.

[0177] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0178] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein.

[0179] Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

[0180] Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.

[0181] 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 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 at least one embodiment, those skilled in the art will recognize that the embodiments herein canbe practiced with modification within the spirit and scope of the embodiments as described herein.

Claims

Claims

1. A method (400) for generating a three-dimensional (3D) map associated with a real- world scene, the method (400) comprising: obtaining channel state information (CSI) data and camera data corresponding to the real-world scene based on capturing the real-world scene via one or more pairs of wireless transmitter-receiver (30) and one or more cameras (40), respectively, installed within the real- world scene; identifying one or more overlapping CSI regions based on the obtained CSI data, wherein the one or more overlapping CSI regions indicate regions where CSI signals received from at least two pairs of wireless transmitter-receiver (30) overlap; identifying one or more objects corresponding to the real -world scene based on the obtained CSI data; generating a two-dimensional (2D) layout associated with the real-world scene based on the one or more identified objects and the one or more overlapping CSI regions; and modifying the generated two-dimensional (2D) layout for generating the 3D map associated with the real-world scene, wherein modifying the generated two-dimensional (2D) layout comprises: identifying dissimilarity between the obtained CSI data and the camera data associated with the one or more identified objects; normalizing at least one of a position and an orientation of the one or more identified objects based on the identified dissimilarity; identifying one or more targeted zones among one or more predefined zones based on at least one of the normalized position and the normalized orientation, wherein the one or more targeted zones are indicative of at least one of one or more isolated zones and one or more disconnected zones identified based on analyzing the generated 2D layout; and applying one or more object-enhancing effects on the one or more identified objects associated with each of the one or more predefined zones in response to identifying the one or more targeted zones, thereby generating the 3D map associated with the real-world scene.

2. The method (400) as claimed in claim 1, wherein prior to identifying the one or more overlapping CSI regions, the method (400) comprises: processing the obtained CSI data from each pair of wireless transmitter-receiver (30) using a predefined CSI processing model; converting amplitude and phase data associated with the processed CSI data to a first signal; obtaining a second signal based on correlating CSI signals and the first signal; obtaining a Doppler shift spectrogram based on applying one or more predefined Doppler shift models on the second signal, wherein the Doppler shift spectrogram indicates a visual representation of change in frequency over time; and determining a static motion and a dynamic motion in the real-world scene based on analyzing the Doppler shift spectrogram on the second signal using the Al model, wherein the obtained CSI data is analyzed while considering the static motion and the dynamic motion in the real -world scene.

3. The method (400) as claimed in claim 1, wherein identifying the one or more overlapping CSI regions comprises: obtaining channel impulse response (CRI) data associated with each pair of wireless transmitter-receiver (30) based on the analyzed CSI data, wherein the obtained CSI data isanalyzed using Fourier Transform for extracting frequency components and identifying multipath delays; computing a set of beamforming vectors for each pair of wireless transmitter-receiver (30) based on the obtained CRI data; obtaining directional CSI data for each pair of wireless transmitter-receiver (30) based on applying the computed beam-forming vectors to the obtained CSI data; and correlating the channel impulse response (CRI), beamforming vectors, and the obtained directional CSI data for identifying the one or more overlapping CSI regions.

4. The method (400) as claimed in claim 3 further comprising: generating a first score for each of one or more predefined zones while considering a set of predefined criteria, wherein the set of predefined criteria indicates at least one of signal strength, signal-to-noise ratio, and spatial coverage; generating a second score for each of the one or more predefined zones based on correlating the first score associated with each zone; selecting each zone among the one or more predefined zones based on the second generated score, wherein a zone with a higher score zone is selected prior to selecting other zones; and determining a boundary associated with each zone based on the selected zones.

5. The method (400) as claimed in claim 1, wherein identifying the one or more objects comprises: extracting features based on the obtained CSI data, wherein the features are indicative of a presence of the one or more objects; and generating point clouds based on the extracted features, wherein the generated point clouds are indicative of a spatial distribution of the one or more objects in the one or more predefined zones, thereby identifying the one or more objects.

6. The method (400) as claimed in claim 5 further comprising: classifying the one or more identified objects into one or more categories using the Al model based on the generated point clouds; and correlating the generated point clouds associated with the one or more classified objects associated with the one or more predefined zones and the one or more overlapping CSI regions for generating the 2D layout.

7. The method (400) as claimed in claim 1, wherein generating the 2D layout associated with the real-world scene comprises: splitting the real-world scene into a grid of cells; generating a signal strength value associated with each grid cell based on the split frame, wherein the signal strength value is indicative of a signal strength and multipath effects; estimating signal strength at each of the one or more predefined zones based on interpolating the signal strength value for each grid cell; detecting a presence of one or more components associated with the signal strength based on the estimated signal strength, wherein the one or more components are indicative of obstacles, reflectors, diffraction phenomena and signal occluded areas; assigning one or more attributes to the one or more detected components based on categorizing the one or more detected components; computing coordinates corresponding to the one or more detected components and each grid cell based on the assigned attributes; andconverting coordinates associated with each grid cell to coordinates of the real-world scene using premeasured data associated with the real -word scene for generating the 2D layout.

8. The method (400) as claimed in claim 7, wherein detecting the presence of the one or more components comprises: identifying a first change in the signal strength based on correlating multipath effects with each grid cell; and analyzing the interpolated signal strength value associated with each grid cell for identifying a second change associated with the signal strength, thereby detecting the presence of the one or more components.

9. The method (400) as claimed in claim 1, wherein identifying the dissimilarity between the obtained CSI data and the camera data associated with the one or more identified objects comprises: determining a common reference frame associated with the one or more identified objects; determining a first set of coordinates and a second set of coordinates corresponding to the one or more identified objects, wherein the first set of coordinates is obtained by utilizing the obtained CSI data and the second set of coordinates is obtained by utilizing the camera data; and computing a transforming matrix using a calibration technique based on the determined first set of coordinates and the determined second set of coordinates, wherein the transforming matrix is indicative of the dissimilarity in the position and the orientation of the one or more identified objects, thereby identifying the dissimilarity between the obtained CSI data and the camera data associated with the one or more identified objects.

10. The method (400) as claimed in claim 9 further comprising: adjusting external calibration of the one or more identified objects based on the transforming matrix; estimating a co-spatial shift in the first set of coordinates using linear regression; validating an orientation alignment associated with the one or more identified objects with respect to objects identified in a predefined frame associated with the real -world scene captured by the one or more cameras (40); calibrating the first set of coordinates associated with the one or more identified objects based on the validation, thereby normalizing the position of the one or more identified objects in the generated 2D layout; and rotating the one or more identified objects by a predefined degree for a predefined number of times based on the calibrated first set of coordinates for matching the orientation of the one or more identified objects with the objects captured by the one or more cameras (40), thereby normalizing the orientation of the one or more identified objects in the generated 2D layout.

11. The method (400) as claimed in claim 10 further comprising: identifying that the one or more identified objects are common that are identified in the generated 2D layout and the predefined frame; and determining one or more convergence zones associated with the one or more identified objects that are common, wherein the one or more convergence zones are determined based on merging boundaries captured by the CSI signals and the one or more cameras (40) associated with the one or more identified objects that are common.

12. The method (400) as claimed in claim 1 comprising: identifying one of, a presence or absence of one or more parameters corresponding to the one or more predefined zones based on analyzing each zone, wherein the one or more parameters indicate at least one of a closed polygon and straight boundaries; identifying the one or more targeted zones among the one or more predefined zones upon identifying the absence of one or more parameters; and correcting the one or more parameters corresponding to the one or more identified targeted zones.

13. The method (400) as claimed in claim 12 further comprising: identifying one or more multi-zones associated with the one or more identified targeted zones; identifying misaligned coordinates corresponding to the one or more multi-zones; and correcting the identified misaligned coordinates by utilizing one or more geometric factors to obtain the aligned coordinates associated with the one or more multi-zones.

14. The method (400) as claimed in claim 1, wherein applying the one or more objectenhancing effects on the one or more identified objects comprises: applying at least one of thematic modifications and exposure modifications to the one or more identified objects associated with each zone of the generated 2D layout, wherein the thematic modifications are indicative of at least one of colour modifications, shape modifications, and texture corrections.

15. A system (100) for generating a three-dimensional (3D) map associated with a real- world scene, the system (100) comprising: a memory (102); and at least one processor (106) in communication with the memory (102), wherein the at least one processor (106) configured to: obtain channel state information (CSI) data and camera data corresponding to the real-world scene based on capturing the real-world scene via one or more pairs of wireless transmitter-receiver (30) and one or more cameras (40), respectively, installed within the real- world scene; identify one or more overlapping CSI regions based on the obtained CSI data, wherein the one or more overlapping CSI regions indicate regions where CSI signals received from at least two pairs of wireless transmitter-receiver (30) overlap; identify one or more objects corresponding to the real -world scene based on the obtained CSI data; generate a two-dimensional (2D) layout associated with the real-world scene based on the one or more identified objects and the one or more overlapping CSI regions; and modify the generated two-dimensional (2D) layout for generating the 3D map associated with the real-world scene, wherein to modify the generated two-dimensional (2D) layout, the at least one processor (106) configured to: identify dissimilarity between the obtained CSI data and the camera data associated with the one or more identified objects; normalize at least one of a position and an orientation of the one or more identified objects based on the identified dissimilarity; identify one or more targeted zones among one or more predefined zones based on at least one of the normalized position and the normalized orientation, wherein the one or moretargeted zones are indicative of at least one of isolated zones and disconnected zones identified based on analyzing the generated 2D layout; and apply one or more object-enhancing effects on the one or more identified objects associated with each of the one or more predefined zones in response to identification of the one or more targeted zones, thereby generating the 3D map associated with the real -world scene.

Images