System and method for authenticating user
Patent Information
- Application Number
- PCT/EP2025/058341
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-03-26
- Publication Date
- 2026-10-01
Smart Images
Figure EP2025058341_01102026_PF_FP_ABST
Abstract
Description
[0001] 202404235
[0002] 1
[0003] SYSTEM AND METHOD FOR AUTHENTICATING USER TECHNICAL FIELD
[0004] The present disclosure in general relates to system and method for authentication. More particularly, the present disclosure relates to a system and a method for authenticating a user.
[0005] BACKGROUND
[0006] Current facial recognition solutions face significant challenges, particularly in scenarios requiring high accuracy, low-light performance, and depth estimation. Many systems rely on multiple sensors to achieve robust results, which increases complexity and cost. When mono cameras are used, facial detection accuracy suffers, and such systems are susceptible to being deceived by masks or similar countermeasures.
[0007] Further, facial recognition is increasingly employed for advanced applications, such as vehicle entry and ignition authentication. However, these systems struggle to detect faces accurately when the user moves or turns their head. The limitations of 2D recognition methods make it difficult to ensure consistent performance in dynamic environments, where facial orientation can vary significantly.
[0008] A notable vulnerability of 2D facial recognition systems is their susceptibility to spoofing with masks. To address this, many systems incorporate complex multi-sensor setups, such as Near-Infrared (NIR) dot projectors, illuminators, and image sensors, as seen in solutions like TRINAMIX. While effective, these approaches add to the cost and complexity. Alternatively, expensive stereo cameras can provide depth information, but they too are cost-prohibitive and cannot achieve low form factors for many applications. In summary, existing solutions are constrained by their reliance on multiple sensors and lack of robustness in low-light or dynamic conditions. Mono cameras fail to deliver accurate facial detection and remain vulnerable to simple spoofing methods. The industry must find a balance between cost, complexity, and performance to overcome these limitations effectively.
[0009] Thus, there is a need for an improved solution that is capable of solving the aforementioned problems of conventional face detection solutions.202404235
[0010] 2
[0011] SUMMARY
[0012] Though face detection solutions are widely known for authenticating user in the vehicle, however, the existing solutions are not efficient as they require multiple cameras and are complex in structure. Furthermore, the existing solutions are deceived due to their susceptibility to spoofing with masks. Also, the existing solutions are not efficient in detecting the face of the user accurately and precisely and thereby the existing solutions lack in proper and efficient authentication of the user while the user approaches the vehicle or about to start the vehicle.
[0013] Therefore, there is a need for an improved system and method for detecting face of the user that further facilitates efficient authentication of the user while the user approaches the vehicle or about to initiate the vehicle.
[0014] It is therefore an object of the present disclosure to provide a system to authenticate the user. The system of the present disclosure facilitates to provide a device-less access to the user in the vehicle. Another object of the present disclosure is to provide a method for authenticating the user.
[0015] This and other objects are achieved by means of a system, and a method defined in the appended claims. The term exemplary is in the present context to be understood as serving as an instance, example or illustration.
[0016] According to the first aspect of the present disclosure, a method for authenticating a user is disclosed. The method includes a step of detecting the user in a field of view (FOV) of at least one imaging device disposed at one or more locations of a vehicle. The method further includes a step of obtaining depth information and facial data for the detected user. The method further includes a step of generating an actuation signal for actuating the at least one imaging device. The method further includes a step of dynamically adjusting the field of view of the at least one imaging device in one or more directions to capture multi-dimensional facial data of the detected user. The method further includes a step of generating the three-dimensional facial model of the detected user based on the depth information and the multi-dimensional facial data. The method further includes a step of comparing the three-dimensional facial model of the detected user with a reference facial model. The method further includes a step of determining an authenticity of the detected user based on the comparison.202404235
[0017] 3
[0018] Optionally, the depth information comprises facial depth maps comprising one of: a two-dimensional representation of a distance of facial features of the user from one of: a reference plane and the at least one imaging device and three-dimensional representation facial coordinates, and facial surface normal representing orientation of facial surfaces of the user in three-dimensional space.
[0019] Optionally, the dynamically adjusting the field of view of the at least one imaging device comprises changing an orientation of the at least one imaging device in the one or more directions. The orientation is changed by tilting the at least one imaging device at one or more angles.
[0020] Optionally, the method further comprises a step of extracting three-dimensional points from the three-dimensional facial model. The method further comprises a step of mapping the three-dimensional points with three-dimensional points of the reference facial model.
[0021] Optionally, the method further comprises a step of authenticating the user when the extracted three-dimensional points are mapped with the three-dimensional points of the reference facial model. The method further comprises a step of disproving the user when the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model.
[0022] According to the second aspect of the present disclosure, a system to authenticate a user is disclosed. The system includes at least one imaging device that is disposed at one or more locations of a vehicle. The at least one imaging device is configured to detect the user in a field of view (FOV) of the at least one imaging device. The at least one imaging device is further configured to obtain depth information and facial data for the detected user. The system further includes processing circuitry that is coupled to the at least one imaging device. The processing circuitry is configured to generate an actuation signal to actuate the at least one imaging device. The system further includes an actuator that is coupled to the at least one imaging device and the processing circuitry. The actuator is adapted to, upon generation of the actuation signal, dynamically adjust the field of view of the at least one imaging device to capture multidimensional facial data for the detected user. The processing circuitry is further configured to generate a three-dimensional facial model of the user based on the depth information and the multi-dimensional facial data. The processing circuitry is further202404235
[0023] 4
[0024] configured to compare the three-dimensional facial model of the detected user with a reference facial model. The processing circuitry is further configured to determine an authenticity of the detected user based on the comparison.
[0025] Optionally, the depth information comprises facial depth maps comprising one of: a two-dimensional representation of a distance of facial features of the user from one of: a reference plane and the at least one imaging device and three-dimensional representation facial coordinates, and facial surface normal representing orientation of facial surfaces of the user in three-dimensional space.
[0026] Optionally, the at least one imaging device is configured to capture a plurality of image frames of the user from the one or more directions to capture the multi-dimensional facial data of the user based on the dynamic adjustment of the FOV.
[0027] Optionally, the actuator is configured to change an orientation of the at least one imaging device in the one or more directions. The orientation is changed by tilting the at least one imaging device at one or more angles.
[0028] Optionally, the processing circuitry is configured to extract three-dimensional points from the three-dimensional facial model. The processing circuitry is further configured to map the three-dimensional points with three-dimensional points to the reference facial model.
[0029] Optionally, the processing circuitry is further configured to authenticate the user when the extracted three-dimensional points are mapped with the three-dimensional points of the reference facial model. The processing circuitry is further configured to disprove the user when the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model.
[0030] Optionally, the actuator comprises a microelectromechanical system (MEMS) actuator.
[0031] Optionally, the one or more locations comprising one of, inside a cabin of the vehicle and on a body of the vehicle.
[0032] Optionally, the actuator is adapted to dynamically adjust the field of view of the at least one imaging device in a range of 10 Degrees to 20 Degrees.202404235
[0033] 5
[0034] According to another aspect of the present disclosure, there is provided a computer program comprising instructions, which, when loaded and run on the system, causes processing circuitry to perform corresponding steps of the method for authenticating a user.
[0035] According to another aspect of the present disclosure, there is provided a computer-readable medium having stored thereon a computer program.
[0036] Some embodiments disclosed herein have one or more of the following advantages:
[0037] - With the proposed solution the user is effectively authenticated while the user approaches the vehicle or about to initiate the vehicle.
[0038] - The proposed system and method advantageously facilitate three-dimensional face detection / matching that can be achieved by way of single camera (i.e., at least one imaging device). There is no need of multi sensor NIR based cameras that are used in prior art technologies.
[0039] - The proposed system and method advantageously provide dynamic adjustment of FOV of the at least one imaging device that facilitates to increase coverage of the FOV. Thus, the user may advantageously be detected while the user is moving in the FOV of the at least one imaging device.
[0040] - The proposed system and method advantageously facilitate changing the orientation of the at least one imaging device in one or more directions to increase the FOV of the at least one imaging device. The proposed system and method facilitate to change the orientation of the at least one imaging device by tilting the imaging device by way of the actuator.
[0041] - The proposed system and method advantageously facilitate to generate the three- dimensional facial model based on the multi-dimensional facial data that is obtained upon dynamic adjustment of the field of view.
[0042] - The proposed system and method advantageously facilitate to authenticate the user by comparing the three-dimensional facial model of the detected user with the reference facial model.
[0043] - The proposed system and method require the MEMS actuator that enhances performance of deviceless access to the vehicle.
[0044] - The MEMS actuator advantageously facilitates the at least one imaging device to move in multiple directions to capture the multi-dimensional facial data of the user. Therefore, the at least one imaging device is advantageously configured to202404235
[0045] 6
[0046] capture facial points of the user from different directions to cover maximum portion of the face of the user. This advantageously enhances the authentication procedure while authenticating the user.
[0047] - The MEMS actuator facilitates the at least one imaging device to pitch, yaw, roll, and X&Y translation. Thus, the MEMS actuator advantageously allows the at least one imaging device to move in multiple directions to better capture facial features of the user.
[0048] Other advantages may be readily apparent to one having skill in the art. Certain embodiments may have none, some, or all of the recited advantages.
[0049] BRIEF DESCRIPTION OF THE DRAWINGS
[0050] The foregoing will be apparent from the following more particular description of the example embodiments, as illustrated in the accompanying drawings in which like reference characters refer to the same parts throughout the different views. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating the example embodiments.
[0051] FIG. 1 illustrates a block diagram of a system to authenticate a user, according to some embodiments;
[0052] FIG. 2 illustrates a block diagram of a processing circuitry of the system as illustrated in FIG. 1, according to some embodiments;
[0053] FIG. 3 illustrates a flowchart of a method for authenticating a user, according to some embodiments;
[0054] FIG. 4 illustrates a perspective view of at least one imaging device and an actuator of the system of FIG. 1, according to some embodiments;
[0055] FIG. 5 illustrates authentication of the user when at least one imaging device of the system is disposed inside a cabin of a vehicle, according to some exemplary embodiments;
[0056] FIG. 6A and FIG. 6B illustrates authentication of the user when the at least one imaging device of the system is disposed outside the cabin of the vehicle, according to some exemplary embodiments;202404235
[0057] 7
[0058] FIG. 7 illustrates a representation of the authentication of the user based on generation of the face model, according to some embodiments; and
[0059] FIG. 8 illustrates an example computing environment implementing the system according to some embodiments.
[0060] DETAILED DESCRIPTION
[0061] Aspects of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. The systems and methods disclosed herein can, however, be realized in many different forms and should not be construed as being limited to the aspects set forth herein. Like numbers in the drawings refer to like elements throughout.
[0062] The terminology used herein is for the purpose of describing particular aspects of the disclosure only and is not intended to limit the invention. It should be emphasized that the term “comprises / comprising” when used in this specification is taken to specify the presence of stated features, integers, steps, or components, but does not preclude the presence or addition of one or more other features, integers, steps, components, or groups thereof. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
[0063] Embodiments of the present disclosure will be described and exemplified more fully hereinafter with reference to the accompanying drawings. The solutions disclosed herein can, however, be realized in many different forms and should not be construed as being limited to the embodiments set forth herein.
[0064] It will be appreciated that when the present disclosure is described in terms of a system and a method, it may also be embodied in one or more processors and one or more memories coupled to the one or more processors, wherein the one or more memories store one or more programs that perform the steps, services and functions disclosed herein when executed by the one or more processors.
[0065] The terms “field of view” and “FOV” are interchangeably referred herein context of the present disclosure.
[0066] FIG. 1 illustrates a block diagram of a system 100 to authenticate a user, according to some embodiments. In an example, the system 100 may be configured to authenticate the user when the user is approaching towards a vehicle (not shown in FIG. 1 ). In202404235
[0067] 8
[0068] another example, the system 100 may be further configured to authenticate the user when the user sits in the vehicle. The system 100 may require single camera to authenticate the user. The system 100 may adjust an orientation of the single camera to capture multi-dimensional facial data of the user.
[0069] The system 100 may comprise at least one imaging device 102 that may be disposed at one or more locations of the vehicle. The at least one imaging device 102 may be configured to detect the user in a field of view (FOV) of the at least one imaging device 102. The at least one imaging device 102 may be further configured to obtain depth information and facial data for the detected user.
[0070] The system 100 may further comprise processing circuitry 104 that may be coupled to the at least one imaging device 102. The processing circuitry 104 may be configured to generate an actuation signal to actuate the at least one imaging device 102. The system 100 may further comprise an actuator 106. The actuator 106 may be coupled to the at least one imaging device 102 and the processing circuitry 104. The actuator 106 may be adapted to, upon generation of the actuation signal, dynamically adjust the FOV of the at least one imaging device 102 to capture multi-dimensional facial data for the detected user. The processing circuitry 104 may be further configured to generate a three-dimensional facial model of the user based on the depth information and the multidimensional facial data. The processing circuitry 104 may be further configured to compare the three-dimensional facial model of the detected user with a reference facial model. The processing circuitry 104 may be further configured to determine an authenticity of the detected user based on the comparison.
[0071] In an example, the system 100 may further comprise a database 108. The at least one imaging device 102, the processing circuitry 104, and the database 108 may be communicatively coupled to each other. Specifically, the at least one imaging device 102, the processing circuitry 104, and the database 108 may be communicatively coupled to each other by way of a first communication channel 110. The first communication channel 110 may facilitate the at least one imaging device 102, the processing circuitry 104, and the database 108 to exchange information associated with the system 100 with each other.
[0072] In an example, the first communication channel 110 may be one of: a wired communication channel and a wireless communication channel. Embodiments of the202404235
[0073] 9
[0074] present disclosure are intended to include and / or otherwise cover any type of the first communication channel 110, without deviating from the scope of the present disclosure. The database 108 may be configured to store one or more reference facial models such that each reference facial model of the one or more reference facial models may correspond to one or more authentic users of the vehicle. The one or more authentic users may be users with which a digital key of the vehicle may be shared.
[0075] In some embodiments of the present disclosure, the depth information comprises facial depth maps comprising one of: a two-dimensional representation of a distance of facial features of the user from one of: a reference plane and the at least one imaging device 102 and three-dimensional representation facial coordinates, and facial surface normal representing orientation of facial surfaces of the user in a three-dimensional space. In some embodiments of the present disclosure, the at least one imaging device 102 may be further configured to capture a plurality of image frames of the user from the one or more directions to capture the multi-dimensional facial data of the user based on the dynamic adjustment of the FOV.
[0076] In some embodiments of the present disclosure, the actuator 106 may be configured to change an orientation of the at least one imaging device 102 in the one or more directions. The orientation may be changed by tilting the at least one imaging device 102 at one or more angles. In some examples of the present disclosure, the orientation may be changed by tipping the at least one imaging device 102 at the one or more angles. In some other examples of the present disclosure, the orientation may be changed by moving the at least one imaging device 102 in a direction perpendicular to the plane of the at least one imaging device 102 i.e., Z-direction. In such a scenario, the orientation of the at least one imaging device 102 may be changed by either moving the at least one imaging device 102 towards one or more components of the actuator 106 or moving the at least one imaging device 102 away from the one or more components of the actuator 106. In other words, to change the orientation of the at least one imaging device 102, the actuator 106 may be configured to (i) move the at least one imaging device 102 in an upward direction i.e., away from the actuator 106 and (ii) move the at least one imaging device 102 in a downward direction i.e., towards the actuator 106. In some embodiments of the present disclosure, the processing circuitry 104 may be configured to extract three-dimensional points from the three-dimensional facial model.202404235
[0077] 10
[0078] The processing circuitry 104 may be further configured to map the three-dimensional points with three-dimensional points of the reference facial model.
[0079] In some embodiments of the present disclosure, the processing circuitry 104 may be configured to generate the three-dimensional facial model of the user by way of one of, a hiface-high-fidelity-3D-face-reconstruction technique and a GhostFaceNetV2 technique. Embodiments of the present disclosure are intended to include and / or otherwise cover any type of technique that facilitates the processing circuitry 104 to generate the three-dimensional facial model, without deviating from the scope of the present disclosure.
[0080] In some embodiments of the present disclosure, the processing circuitry 104 may be further configured to authenticate the user when extracted three-dimensional points are mapped with the three-dimensional points of the reference facial model. The processing circuitry 104 may be further configured to disprove the user when the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model.
[0081] In some embodiments of the present disclosure, the actuator 106 may comprise a microelectromechanical system (MEMS) actuator. The MEMS actuator may be based on a comb drive. The comb drive of the MEMS actuator are capacitive actuators that utilize electrostatic forces. The electrostatic forces acting between two electrically conductive combs. The combs are arranged such that the combs never touch to each other. When voltage is applied, the voltage causes the combs to be drawn together, causing mechanical movement. The force (mechanical movement) is proportional to the square of the applied voltage between the combs.
[0082] In an example, the MEMS actuator may actuate the at least one imaging device 102 in multiple directions. For example, the MEMS actuator may be configured to facilitate the at least one imaging device 102 to exhibiting pitching, yawing, rolling, and X&Y translation. The MEMS actuator may be advantageously configured to provide 5-axis stabilization. The MEMS actuator may respond very quickly. In other words, the MEMS actuator may be configured to quickly change the orientation of the at least one imaging device 102 with reduced latency, whenever required. Embodiments of the present disclosure are intended to include and / or otherwise cover any type of actuator, without deviating from the scope of the present disclosure.202404235
[0083] 11
[0084] In some embodiments of the present disclosure, the one or more locations may comprise one of: inside a cabin of the vehicle and outside the cabin i.e., on a body of the vehicle.
[0085] In some embodiments of the present disclosure, the actuator 106 may be adapted to dynamically adjust the FOV of the at least one imaging device 102 in a range of 10 Degrees to 20 Degrees.
[0086] FIG. 2 illustrates a block diagram of processing circuitry 104 of the system 100 as illustrated in FIG. 1, according to some embodiments. The processing circuitry 104 may include one or more engines that may be configured to execute one or more functionalities associated with the system 100. Each engine of the one or more engines of the processing circuitry 104 may be a set of instructions that, when executed by a hardware circuitry of the processing circuitry 102, may be configured to perform a specific functionality of the system 100.
[0087] The processing circuitry 104 may comprise a data exchange engine 202, a signal generation engine 204, a model generation engine 206, and an authenticity determination engine 208. The data exchange engine 202, the signal generation engine 204, the model generation engine 206, and the authenticity determination engine 208 may be communicatively coupled to each other. Specifically, the data exchange engine 202, the signal generation engine 204, the model generation engine 206, and the authenticity determination engine 208 may be communicatively coupled to each other by way of a second communication channel 210. The second communication channel 210 may be one of, a wired communication channel and a wireless communication channel. Embodiments of the present disclosure are intended to include and / or otherwise cover any type of the second communication channel 210, without deviating from the scope of the present disclosure.
[0088] The data exchange engine 202 may facilitate the processing circuitry 104 to exchange data associated with the system 100 among various engines of the processing circuitry 104. Specifically, the data exchange engine 202 may facilitate the processing circuitry 104 to exchange the data among various engines by way of the second communication channel 210. The second communication channel 210 may be any type of the communication channel that may facilitate exchange of information between the engines of the processing circuitry 104.202404235
[0089] 12
[0090] The signal generation engine 204 may facilitate the processing circuitry 104 to generate the actuation signal to actuate the at least one imaging device 102. The actuator 106, upon generation of the actuation signal, may be adapted to actuate the at least one imaging device 102 to dynamically adjust the FOV of the at least one imaging device 102. The at least one imaging device 102, upon dynamic adjustment of the FOV, may be configured to capture the multi-dimensional facial data for the detected user.
[0091] The model generation engine 206 may facilitate the processing circuitry 104 to generate the three-dimensional facial model of the user. Specifically, the model generation engine 206 may facilitate the processing circuitry 104 to generate the three-dimensional facial model of the user based on the depth information and the multi-dimensional facial data.
[0092] The authenticity determination engine 208 may facilitate the processing circuitry 104 to determine the authenticity of the detected user. To determine the authenticity of the detected user, the authenticity determination engine 208 may facilitate the processing circuitry 104 to compare the three-dimensional facial model of the detected user with the reference facial model. The authenticity determination engine 208 may further facilitate the processing circuitry 104 to extract the three-dimensional points from the three-dimensional facial model. The authenticity determination engine 208 may further facilitate the processing circuitry 104 to map the three-dimensional points with three-dimensional points of the reference facial model. The authenticity determination engine 208 may further facilitate the processing circuitry 104 to authenticate the user when the extracted three-dimensional points are mapped with the three-dimensional points of the reference facial model. The authenticity determination engine 208 may further facilitate the processing circuitry 104 to disprove the user when the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model. FIG. 3 illustrates a flowchart of a method 300 for authenticating the user, according to some embodiments. The method 300 may comprise following steps for authenticating the user by way of the system 100 as shown in FIG. 1.
[0093] At step 302, the method 300 may comprise a step of detecting the user in the field of view (FOV) of the at least one imaging device 102. Specifically, the method 300 may comprise the step of detecting, by way of the at least one imaging device 102, the user in the FOV of the at least one imaging device 102.202404235
[0094] 13
[0095] At step 304, the method 300 may comprise a step of obtaining depth information and facial data for the detected user. Specifically, the method 300 may comprise the step of obtaining, by way of the at least one imaging device 102, the depth information and the facial data for the detected user.
[0096] At step 306, the method 300 may comprise a step of generating an actuation signal for actuating the at least one imaging device 102. Specifically, the method 300 may comprise the step of generating, by way of the processing circuitry 104, the actuation signal to actuate the at least one imaging device 102.
[0097] At step 308, the method 300 may comprise a step of dynamically adjusting the FOV of the at least one imaging device 102 in the one or more directions to capture the multidimensional facial data of the detected user. Specifically, the method 300 may comprise the step of dynamically adjusting, by way of the actuator 106, the FOV of the at least one imaging device 102 in the one or more directions to capture the multi-dimensional facial data of the detected user.
[0098] At step 310, the method 300 may comprise a step of generating the three-dimensional facial model of the detected user based on the depth information and the multidimensional facial data. Specifically, the method 300 may comprise the step of generating, by way of the processing circuitry 104, the three-dimensional facial model of the detected user based on the depth information and the multi-dimensional facial data. At step 312, the method 300 may comprise a step of comparing the three-dimensional facial model of the detected user with the reference facial model. Specifically, the method 300 may comprise the step of comparing, by way of the processing circuitry 104, the three-dimensional facial model of the detected user with the reference facial model.
[0099] At step 314, the method 300 may comprise a step of determining the authenticity of the detected user based on the comparison. Specifically, the method 300 may comprise a step of determining, by way of the processing circuitry 104, the authenticity of the detected user based on the comparison.
[0100] Details of the method 300 are similar to the details of the system 100 as discussed above and hence are not repeated for the sake of brevity.202404235
[0101] 14
[0102] In some embodiments of the present disclosure, the depth information comprises facial depth maps comprising one of: a two-dimensional representation of a distance of facial features of the user from one of: a reference plane and the at least one imaging device 102 and three-dimensional representation facial coordinates, and facial surface normal representing orientation of facial surfaces of the user in the three-dimensional space. In some embodiments of the present disclosure, the step 308 of dynamically adjusting the FOV of the at least one imaging device 102 may comprise changing the orientation of the at least one imaging device 102 in the one or more directions. The orientation may be changed by tilting the at least one imaging device 102 at the one or more angles.
[0103] In some embodiments of the present disclosure, the method 300 may further comprise a step of extracting the three-dimensional points from the three-dimensional facial model. Specifically, the method 300 may further comprise the step of extracting, by way of the processing circuitry 104, the three-dimensional points from the three-dimensional facial model.
[0104] In some embodiments of the present disclosure, the method 300 may further comprise a step of mapping the three-dimensional points with the three-dimensional points of the reference facial model. Specifically, the method 300 may further comprise the step of mapping the three-dimensional points with the three-dimensional points of the reference facial model.
[0105] In some embodiments of the present disclosure, the method 300 may further comprise a step of authenticating the user when the extracted three-dimensional points are mapped with the three-dimensional points of the reference facial model. Specifically, the method 300 may comprise the step of authenticating, by way of the processing circuitry 104, the user when the extracted three-dimensional points are mapped with the three-dimensional points of the reference facial model.
[0106] In some embodiments of the present disclosure, the method 300 may further comprise a step of disproving the user when the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model. Specifically, the method 300 may comprise the step of, by way of the processing circuitry 104,202404235
[0107] 15
[0108] disproving the user when the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model.
[0109] FIG. 4 illustrates a perspective view of the at least one imaging device 102 and the actuator 106 of the system 100, according to some embodiments. In some embodiments of the present disclosure, the at least one imaging device 102 may include an optical lens assembly 402 and an image sensor 404. The actuator 106 may include a stage 406 and a frame 408.
[0110] In some embodiments of the present disclosure, the optical lens assembly 402 may include one or more optical lenses (not shown). The one or more optical lenses may be stacked in an arrangement that the one or more lenses facilitates the at least one imaging device 102 to focus on the user. The arrangement of the one or more optical lenses may be adjusted to adjust resolution associated with the FOV of the at least one imaging device 102.
[0111] In some embodiments of the present disclosure, the image sensor 404 may be disposed behind the optical lens assembly 402 when seen from a side of an object / user. The image sensor 404 may be disposed behind the optical lens assembly 402 such that the image sensor 404 may be configured to sense signals associated with presence of the user. Since, the one or more optical lenses are arranged to provide clear focus and clear resolution, therefore, the image sensor 404 is configured to capture clear image frames that shows clear visibility about the presence of the user.
[0112] In some embodiments of the present disclosure, the image sensor 404 may be disposed on the stage 406. The stage 406 may be supported on or carried by the frame 408. The stage 406 and the frame 408 forms the part of the actuator 106. The stage 406 may be configured to actuate upon generation of the actuation signal. The stage 406 may be configured to tilt at the one or more angles such that an orientation of the stage 406 may be changed upon generation of the actuation signal. The stage 406 may therefore facilitate to change the orientation of the image sensor 404 upon generation of the actuation signal. Specifically, to dynamically adjust the FOV of the at least one imaging device 102, the stage 406 may facilitate to change the orientation of the image sensor 404. In other words, the stage 406 may be configured to tilt at the one or more angles, consequently, changing the orientation of the image sensor 404 in the one or202404235
[0113] 16
[0114] more directions. This facilitates adjustment of the FOV of the at least one imaging device 102 in the one or more directions.
[0115] In some examples of the present disclosure, the actuator 106 may be configured to change the orientation by tipping the at least one imaging device 102 at the one or more angles. In some other examples of the present disclosure, the actuator 106 may be configured to change the orientation by moving the at least one imaging device 102 in a direction perpendicular to the plane of frame 408. Specifically, the actuator 106 may be configured to change the orientation of the at least one imaging device 102 by moving the at least one imaging device 102 either towards the frame 408 or away from the frame 408.
[0116] FIG. 5 illustrates authentication of a user 502 through the system 100 when at least one imaging device 102 of the system 100 is disposed inside a cabin 500 of the vehicle, according to some exemplary embodiments. FIG. 5 shows an example of authentication of the user 502 when the user 502 is about to initiate the vehicle and start for a ride. The at least one imaging device 102 may be disposed inside the cabin 500. In some examples of the present disclosure, the at least one imaging device 102 may be disposed at a dashboard 504 inside the cabin 500. In some other examples of the present disclosure, the at least one imaging device 102 may be disposed at an infotainment panel 506 inside the cabin 500. The at least one imaging device 102 may be configured to capture the plurality of image frames of the user 502 when the user 502 sits inside the cabin 500. Preferably, the at least one imaging device 102 may be configured to capture the plurality of image frames of the user 502 when the user 502 sits inside the cabin 500 on a driver seat. The at least one imaging device 102 may be configured to capture the plurality of image frames from the one or more directions to capture the multi-dimensional facial data of the user 502. The user 502 may sit on a seat of the vehicle and start for the ride.
[0117] FIG. 6A and FIG. 6B illustrate authentication of a user 602 through the system 100 when the at least one imaging device 102 of the system 100 is disposed outside the cabin 500 of a vehicle 600 (as shown in FIG. 6B), according to some exemplary embodiments. The vehicle 600 may be same vehicle as disclosed / explained in context to the preceding FIGs 1-5 hereinabove in the present disclosure. Specifically, FIG. 6A shows a field of view 604 of the at least one imaging device 102. The field of view 604 of the at least one imaging device 102 may be a region that may be near to the vehicle202404235
[0118] 17
[0119] 600. The field of view 604 may show that the user 602 is approaching the vehicle 600. FIG. 6A and FIG. 6B further illustrate the authentication of the user 602 when the user 602 is approaching towards the vehicle 600. In other words, FIG. 6A and FIG. 6B illustrate the authentication of the user 602 when the user 602 is present in surroundings of the vehicle 600. In this embodiment, the system 100 may include multiple imaging devices 102a, 102b. The first imaging device 102a may have a first field of view 606a and the second imaging device 102b may have a second field of view 606b. Each imaging device of the multiple imaging devices 102a, 102b may be configured to detect the user 602 in their respective field of views.
[0120] For example, while the user 602 approaches towards the vehicle 600, the user 602 enters the first field of view 606a. The first imaging device 102a may be configured to detect the user 602 while the user 602 is moving in the first field of view 606a. The first imaging device 102a may be further configured to obtain the depth information and the facial data of the user 602 while the user 602 is moving the first field of view 606a. As the user 602 is approaching towards the vehicle 600 and is moving in the first field of view 606a, the first imaging device 102a may be configured to be tilted by the actuator 106 that facilitates the dynamic adjustment of the first field of view 606a in the one or more directions. This dynamic adjustment facilitates to increase range of the first field of view 606a and thereby compensates for the motion of the user 602 in the first field of view 606a while the user 602 approaches towards the vehicle 600. The dynamic adjustment of the first field of view 606a further facilitates the first field of view 606a to overlap with the second field of view 606b. Once the user 602 exits the dynamically adjusted first field of view 606a, the user 602 enters the second field of view 606b.
[0121] The second imaging device 102b may be configured to detect the user 602 while the user 602 is moving in the second field of view 606b. The second imaging device 102b may be further configured to obtain the depth information and the facial data of the user 602 while the user 602 is moving the second field of view 606b. As the user 602 is approaching towards the vehicle 600 and is moving in the second field of view 606b, the second imaging device 102b may be configured to be tilted by the actuator 106 that facilitates the dynamic adjustment of the second field of view 606b in the one or more directions. This dynamic adjustment facilitates to increase the range of the second field of view 606b and thereby compensates for the motion of the user 602 in the second field of view 606b while the user 602 approaches towards the vehicle 600.202404235
[0122] 18
[0123] Thus, the first and second imaging devices 102a, 102b may be configured to capture the plurality of image frames of the user 602 from the one or more directions to capture the multi-dimensional facial data of the user 602 based on the dynamic adjustments of the first and second fields of view 606a, 606b. The first and second imaging devices 102, 102b may therefore facilitate in authentication of the user 602 when the user 602 is present in the surroundings of the vehicle 600.
[0124] In some embodiments of the present disclosure, the processing circuitry 104 may be configured to train a machine learning model for facial features. The processing circuitry 104 may be configured to receive the plurality of image frames from the first and second imaging devices 102a, 102b. The first and second imaging devices 102a, 102b may be configured to record or capture activities that may occur near the vehicle 600. The first and second imaging devices 102a, 102b may be configured to record or capture facial features of multiple persons and the user 602 that may be present near to the vehicle. The first and second imaging devices 102a, 102b may be configured to transmit the captured data to the processing circuitry 104. The processing circuitry 104, by using the captured data, may be configured to train the machine learning model. The trained model may facilitate the processing circuitry 104 to classify authenticated users from non-authenticated users.
[0125] In some embodiments of the present disclosure, the processing circuitry 104 may be configured to facilitate enrolment of the authenticated user 602 in the system 100.
[0126] Specifically, the processing circuitry 104 may be configured to facilitate enrolment of multiple authenticated users among which, the digital key of the vehicle 600 may be shared. To enrol multiple authenticated users in the system 100, the processing circuitry 104 may be configured to receive the plurality of image frames from the first and second imaging devices 102a, 102b. Initially, during enrolment of the multiple authenticated users, the first and second imaging devices 102a, 102b may be configured to record or capture the plurality of image frames for multiple authenticated users. Specifically, the first and second imaging devices 102a, 102b may be configured to capture the plurality of image frames from multiple directions. The first and second imaging devices 102a, 102b may be configured to tilt in the one or more directions that facilitate the first and second imaging devices 102a, 102b to capture the plurality of image frames of multiple authenticated users from the one or more directions. In other words, upon tilting, the first and second imaging devices 102a, 102b may be configured to capture the plurality202404235
[0127] 19
[0128] of image frames that correspond to facial features of the multiple authenticated users from different directions. The processing circuitry 104 may be configured to receive the plurality of image frames of the multiple authenticated users from the first and second imaging devices 102a, 102b that facilitate enrolment of the multiple authenticated users in the system 100.
[0129] Although, the embodiments (of FIG. 6A and FIG. 6B) of the present disclosure are intended to include and / or otherwise cover only two imaging devices i.e., the first imaging device 102a and the second imaging device 102b, however the scope of the present disclosure is not limited to it. The present disclosure intends to cover any number of imaging devices, without deviating from the scope of the present disclosure, wherein each imaging device is structurally and functionally same or substantially similar to the first and second imaging devices 102a, 102b.
[0130] FIG. 7 illustrates a representation 700 of the authentication of the user 502, 602 based on generation of the face model, according to some embodiments. FIG. 7 shows a three-dimensional facial model 702 of the user 502, 602. The three-dimensional facial model 702 may be same three-dimensional facial model as explained / disclosed in context to the preceding FIGs 1-6 hereinabove in the present disclosure. The processing circuitry 104 may be configured to generate the three-dimensional facial model 702 of the user 502, 602 based on the depth information and the multidimensional facial data of the user 502, 602. The processing circuitry 104 may be further configured extract a mesh 704 of the three-dimensional points. Specifically, the processing circuitry 104 may be configured to extract the mesh 704 of the three-dimensional points from the three-dimensional facial model 702. To authenticate the user 502, 602, the processing circuitry 104 may be further configured to compare the three-dimensional facial model 702 of the detected user 502, 602 with a reference facial model 706. The reference facial model 706 may be same reference facial model as explained / disclosed in context to the preceding FIGs 1-6 hereinabove in the present disclosure. The reference facial model 706 may be stored in a suitable repository of the database 108. To compare the three-dimensional facial model with the reference facial model 706, the processing circuitry 104 may be configured to map the mesh 704 of the three-dimensional points with the three-dimensional points of the reference facial model 706. The processing circuitry 104 may be configured to authenticate the user 502, 602 when the mesh 704 of the extracted three-dimensional points are mapped with the202404235
[0131] 20
[0132] three-dimensional points of the reference facial model 706. The processing circuitry 104 may be further configured to disprove the user 502, 602 when the mesh 704 of the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model 706.
[0133] FIG. 8 illustrates an example computing environment 800 implementing the system 100, according to some embodiments. The example-computing environment 800 further implements the system 100 and the method 300 as shown in FIGs 1 and 3 to authenticate the user 502, 602. As depicted in FIG. 8, the computing environment 800 comprises at least one data processing unit 806 that is equipped with a control unit 802 and an Arithmetic Logic Unit (ALU) 804, a plurality of networking devices 808 and a plurality Input output, I / O devices 810, a memory 812, a storage 814. The data processing unit 806 may be responsible for implementing the system 100 and method 300 described in FIGs 1 to 4. For example, the data processing unit 806 in some embodiments be equivalent to the processing circuitry of the platform described above in conjunction with FIG. 2. For another example, the data processing unit 806 in some embodiments be equivalent to the processing circuitry 104 of the platform described above in conjunction with FIG. 2. The data processing unit 806 is capable of executing software instructions stored in memory 812. The data processing unit 806 receives commands from the control unit 802 in order to perform its processing. Further, any logical and arithmetic operations involved in the execution of the instructions are computed with the help of the ALU 804.
[0134] The computer program is loadable into the data processing unit 806, which may, for example, be comprised in an electronic apparatus (such as the platform). When loaded into the data processing unit 806, the computer program may be stored in the memory 812 associated with or comprised in the data processing unit 806. According to some embodiments, the computer program may, when loaded into and run by the data processing unit 806, cause execution of method steps according to, for example, the method illustrated in FIG. 3 as described herein.
[0135] The overall computing environment 800 may be composed of multiple homogeneous and / or heterogeneous cores, multiple CPUs of different kinds, special media and other accelerators. Further, the plurality of data processing unit 806 may be located on a single chip or over multiple chips.202404235
[0136] 21
[0137] The algorithm comprising of instructions and codes required for the implementation are stored in either the memory 812 or the storage 814 or both. At the time of execution, the instructions may be fetched from the corresponding memory 812 and / or storage 814 and executed by the data processing unit 806.
[0138] In case of any hardware implementations various networking devices 808 or external I / O devices 810 may be connected to the computing environment to support the implementation through the networking devices 808 and the I / O devices 810.
[0139] 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 shown in FIG. 8 include blocks which can be at least one of a hardware device, or a combination of hardware device and software module.
[0140] Reference signs
[0141] • System 100
[0142] • Imaging device 102
[0143] • First imaging device 102a
[0144] • Second imaging device 102b
[0145] • Processing circuitry 104
[0146] • Actuator 106
[0147] • Database 108
[0148] • First communication channel 110
[0149] • Data exchange engine 202
[0150] • Signal generation engine 204
[0151] • Model generation engine 206
[0152] • Authenticity determination engine 208
[0153] • Second communication channel 210
[0154] • Method 300
[0155] • Optical lens assembly 402
[0156] • Image sensor 404
[0157] • Stage 406202404235
[0158] 22 • Frame 408
[0159] Cabin 500
[0160] User 502, 602
[0161] Dashboard 504
[0162] Infotainment panel 506
[0163] Vehicle 600
[0164] Field of view 604
[0165] First field of view 606a
[0166] Second field of view 606b Graphical representation 700 Three-dimensional facial model 702 Mesh of three-dimensional points 704 Reference facial model 706 Computing environment 800 Control unit 802
[0167] Arithmetic Logic Unit 804
[0168] Data processing unit 806 Networking devices 808 Input / output devices 810
[0169] Memory 812
[0170] Storage 814
Claims
20240423523Claims:
1. A method (300) for authenticating a user (502, 602), characterized in that, the method (300) comprising:detecting (302) the user (502, 602) in a field of view (FOV) (604) of at least one imaging device (102) disposed at one or more locations of a vehicle (600);obtaining (304) depth information and facial data for the detected user (502, 602);generating (306) an actuation signal for actuating the at least one imaging device (102);dynamically adjusting (308) the field of view (604) of the at least one imaging device (102) in one or more directions to capture multi-dimensional facial data of the detected user (502, 602);generating (310) a three-dimensional facial model (702) of the detected user (502, 602) based on the depth information and the multi-dimensional facial data;comparing (312) the three-dimensional facial model (702) of the detected user (502, 602) with a reference facial model (706); anddetermining (314) an authenticity of the detected user (502, 602) based on the comparison.
2. The method (300) according to claim 1, wherein the depth information comprises facial depth maps comprising one of: a two-dimensional representation of a distance of facial features of the user (502, 602) from one of: a reference plane and the at least one imaging device (102) and three-dimensional representation facial coordinates, and facial surface normal representing orientation of facial surfaces of the user (502, 602) in a three-dimensional space.
3. The method (300) according to any of the claims 1 or 2, wherein the dynamically adjusting (308) the field of view (604) of the at least one imaging device (102) comprises:20240423524changing an orientation of the at least one imaging device (102) in the one or more directions, wherein the orientation is changed by tilting the at least one imaging device (102) at one or more angles.
4. The method (300) according to any of the claims from 1 to 3, further comprises:extracting three-dimensional points from the three-dimensional facial model (702); andmapping the three-dimensional points with three-dimensional points of the reference facial model (706).
5. The method (300) according to any of the claims from 1 to 4, further comprises:authenticating the user (502, 602) when the extracted three-dimensional points are mapped with the three-dimensional points of the reference facial model (706); anddisproving the user (502, 602) when the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model (706).
6. A system (100) to authenticate a user (502, 602), characterized in that, the system (100) comprising:at least one imaging device (102) disposed at one or more locations of a vehicle (600), and configured to:detect the user (502, 602) in a field of view (FOV) (604) of the at least one imaging device (102); andobtain depth information and facial data for the detected user (502, 602);processing circuitry (104) coupled to the at least one imaging device (102), and configured to generate an actuation signal to actuate the at least one imaging device (102);an actuator (106) coupled to the at least one imaging device (102) and the processing circuitry (104), and adapted to, upon generation of the actuation signal, dynamically adjust the field of view (604) of the at least one imaging device (102) to capture multi-dimensional facial data for the detected user (502, 602),20240423525wherein the processing circuitry (104) is further configured to:generate a three-dimensional facial model (702) of the user (502, 602) based on the depth information and the multi-dimensional facial data;compare the three-dimensional facial model (702) of the detected user (502, 602) with a reference facial model (706); anddetermine an authenticity of the detected user (502, 602) based on the comparison.
7. The system (100) according to claim 6, wherein the depth information comprises facial depth maps comprising one of: a two-dimensional representation of a distance of facial features of the user (502, 602) from one of: a reference plane and the at least one imaging device (102) and three-dimensional representation facial coordinates, and facial surface normal representing orientation of facial surfaces of the user (502, 602) in three-dimensional space.
8. The system (100) according to any of the preceding claims, wherein the at least one imaging device (102) is configured to:capture a plurality of image frames of the user (502, 602) from the one or more directions to capture the multi-dimensional facial data of the user (502, 602) based on the dynamic adjustment of the FOV.
9. The system (100) according to any of the preceding claims, wherein the actuator (106) is configured to:change an orientation of the at least one imaging device (102) in the one or more directions, wherein the orientation is changed by tilting the at least one imaging device (102) at one or more angles.
10. The system (100) according to any of the preceding claims, wherein the processing circuitry (104) is configured to:extract three-dimensional points from the three-dimensional facial model (702); and20240423526map the three-dimensional points with three-dimensional points of the reference facial model (706).
11. The system (100) according to any of the preceding claims, the processing circuitry (104) is further configured to:authenticate the user (502, 602) when the extracted three-dimensional points are mapped with the three-dimensional points of the reference facial model (706); anddisprove the user (502, 602) when the extracted three-dimensional points are unmapped with the three-dimensional points of the reference facial model (706).
12. The system (100) according to any of the preceding claims, wherein the actuator (106) comprises a microelectromechanical system (MEMS) actuator.
13. The system (100) according to any of the preceding claims, wherein the one or more locations comprising one of: inside a cabin of the vehicle (600) and on a body of the vehicle (600).
14. The system (100) according to any of the preceding claims, wherein the actuator (106) is adapted to dynamically adjust the field of view (604) of the at least one imaging device (102) in a range of 10 Degrees to 20 Degrees.
15. A computer program comprising instructions, which, when the program is executed by a computer, cause the computer to carry out the method (300) of any one of the claims 1 to 5.