An onboard information management system for a motor vehicle and method thereof

Abstract

Method of obscuring faces and identifiers of vehicle occupants, comprising: receiving an image of a vehicle’s passenger compartment (102, Fig.1a); identifying an occupant face and / or identifier (104,

Description

TECHNICAL FIELD This disclosure relates to an information management system, in particular an onboard information management system for a motor vehicle to safeguard onboard data privacy. BACKGROUND There has been a significant increase in adaptation of in-vehicle monitoring systems for both commercial and passenger vehicles. There is an increasing concern, especially with breach of privacy of vehicle driver and vehicle occupants, which needs to be regulated and comply with national data privacy law. A typical mandate is to implement a closed loop system, where no camera data may be permanently stored or transmitted outside of the vehicle, such that the camera data does not contain any information by which individuals are identifiable. Nonetheless, preventive measures are required, for example in private vehicles, to prevent third party hacking into the system and obtaining camera data. There may also be concerns with car sharing providers, where data captured by onboard cameras does not belong to the driver and / or vehicle occupants. Existing in-vehicle camera systems often make exceptions from the close loop requirement discussed above. At times, camera data may even be transmitted to cloud for artificial intelligence or machine learning processing over distributed computing systems before the results are executed in-vehicle, as a result of the convenience of vehicle connectivity. The background description provided herein is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure. SUMMARY A purpose of this disclosure is to at least ameliorate some of the problems discussed above by providing the subject-matter of the independent claims. Further purposes of this disclosure are set out in the accompanying dependent claims. In an aspect of this disclosure, a method of managing onboard information for a motor vehicle is provided. The method may comprises receiving, by way of a processor, a digital image generated by an imaging module having a field of view of a passenger compartment of a motor vehicle. The method may further comprise identifying, by way of the processor, at least one occupant identifier contained in the digital image received. The method may further comprise blurring, by way of a privacy algorithm, the at least one occupant identifier identified in the digital image received. The method may further comprise producing, at least one resultant image, the at least one resultant image containing the at least one occupant identifier identified in the digital image blurred out. An advantage of the aforesaid method is to yield one or more resultant images with at least one occupant identifier blurred-out in the resultant images. In some embodiment, the at least one occupant identifier may comprise a region of interest of a face of the at least one occupant contained in the digital image received. In some embodiment, the at least one occupant identifier may comprise a body landmark of the at least one occupant contained in the digital image received. The privacy algorithm may comprise executing, by way of the processor, a Gaussian Kernal function for blurring the at least one occupant identifier identified in the digital image. In some embodiment, the method may further comprise streaming, by way of a video signal, multiple frames of the at least one resultant image containing the at least one occupant identifier identified in the digital image blurred out. In some embodiment, the method may further comprise storing, by way of the processor, the at least one resultant image containing the at least one occupant identifier identified in the digital image blurred out in a memory of the processor. In an aspect of this disclosure, an onboard information management system for a motor vehicle is provided. The system may comprise an imaging module having a field of view of a passenger compartment of a motor vehicle. The system may comprise a processor including a memory. The processor may be operable to receive a digital image generated by the imaging module. The processor may be operable to identify at least one occupant identifier contained in the digital image received. The processor may be operable to execute a privacy algorithm, the privacy algorithm operable to blur the at least one occupant identifier identified in the digital image received. The processor may be operable to produce at least one resultant image, the resultant image contains the at least one occupant identifier identified in the digital image blurred out. In some embodiment, the at least one occupant identifier may comprise a region of interest of a face of the at least one occupant contained in the digital image received. In some embodiment, the at least one occupant identifier may comprise a body landmark of the at least one occupant contained in the digital image received. The privacy algorithm may comprise a Gaussian Kernal function operable to blur the at least one occupant identifier identified in the digital image. In some embodiment, the processor may be operable to execute an instruction to stream multiple frames of the at least one resultant image containing the at least one occupant identifier identified in the digital image blurred out. In some embodiment, the processor may be operable to store the at least one resultant image containing the at least one occupant identifier identified in the digital image blurred out in a memory of the processor. In some embodiment, the imaging module may comprise a driver monitoring system. In some embodiment, the imaging module may comprise a cabin monitoring system. In an aspect of this disclosure, the onboard information management system and processor to execute the method of managing onboard information may be implemented in a motor vehicle. In an aspect of this disclosure, a computer program product is provided. The computer program product may comprise instructions to cause an onboard information system adapted with a processor to execute a method of managing onboard information for a motor vehicle. In an aspect of this disclosure, a non-transitory computer readable medium having stored thereon a computer program product as disclosed herein is provided. Other objects, features and characteristics, as well as the methods of operation and the functions of the related elements of the structure, the combination of parts and economics of manufacture will become more apparent upon consideration of the following detailed description and appended claims with reference to the accompanying drawings, all of which form a part of this specification. It should be understood that the detailed description and specific examples, while indicating the non-limiting embodiments of the disclosure, are intended for purposes of illustration only and are not intended to limit the scope of the disclosure. BRIEF DESCRIPTION OF DRAWINGS The present disclosure will become more fully understood from the detailed description and the accompanying drawings, wherein: FIG. 1 a shows a flowchart of a method of managing onboard information for a motor vehicle. FIG. 1 b shows a flowchart for a privacy algorithm. FIG. 2 shows a block diagram of an onboard information management system for a motor vehicle. FIG. 3a shows an image captured by an imaging module. FIG. 3b shows an image captured by the imaging module with at least one occupant identifier. FIG. 3c shows an image executed by a privacy algorithm. FIG. 3d shows an image containing a pixelated portion. FIG. 3e shows an image containing a blurred-out portion. In various embodiments described by reference to the above figures, like reference signs refer to like components in several perspective views and / or configurations. DETAILED DESCRIPTION It should be understood that like reference numerals identify corresponding or similar elements throughout the several drawings. It should be understood that although a particular component arrangement is disclosed and illustrated in these exemplary embodiments, other arrangements could also benefit from the teachings of this disclosure. Hereinafter, the term ““processor” may also refer to a “computer” and the term “processor” used herein may broadly encompass a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, and so forth. The “computer“may comprise one or more computer-readable storage media or memory modules, which may comprise transitory and non-transitory memory. The computer-readable storage media may encompass any electronic component capable of storing electronic information. The computer-readable storage media or memory may include transitory processor-readable media such as random-access memory (RAM) or cache memory. The computer-readable storage media or memory may include non-transitory processor-readable media such as read-only memory (ROM), non-volatile random-access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, etc. The memory is in electronic communication with a processor as disclosed herein and / or other processors of the computer. Computer-readable instructions, such as an operating system, middleware, firmware or other software framework, may reside in the non-transitory computer-readable storage medium. Computer-readable instructions may be implemented as a program or a code that can be read by the processor. The disclosed method may be implemented as a program or a code that can be read by the processor of the unmanned moving object. Accordingly, in an embodiment, there is provided a computer of an unmanned moving object operable to perform the method as disclosed herein. Exemplary processor(s) of the computer include a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, programmable gate arrays, systems-on-chip (SoC), programmable SoCs, or other suitable devices. The term "processor" may include a combination of processing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration suitable for the disclosed computer. Referring to FIG. 1a of the accompanying drawings which shows a flowchart of a method 100 of managing onboard information for a motor vehicle, at step 102, a digital image generated by an imaging module having a field of view of a passenger compartment of a motor vehicle may be received by a processor. In a next step 104, at least one occupant identifier contained in the digital image received may be being identified by the processor. At step 106, a privacy algorithm 110 may be executed by the processor, for blurring the at least one occupant identifier identified in the digital image received, determined from step 104. At least one resultant image containing the at least one occupant identifier identified in the digital image blurred out may be produced at a next step 108. The privacy algorithm 110 may include steps which may identify the at least one occupant identifier. The at least one occupant identifier may include region of interest on a face of the occupant or a landmark of a body, also known as body landmark, of the at least one occupant contained in the digital image received. The privacy algorithm 110 may execute a Gaussian Kemal function for blurring the at least one occupant identifier identified in the digital image at step 118, as shown in FIG. 1b, which illustrate a flowchart process for privacy algorithm 110. At step 112, the at least one resultant image containing the at least one occupant identifier identified in the digital image blurred out may be produced at a next step 108 may be streamed in multiple frames, in the form of video signals. By way of an example, this feature may be a streaming the resultant images as videos on a display apparatus, for an occupant to consent whether to use or keep such resultant images produced at step 114. In a next step 116, the at least one resultant image containing the at least one occupant identifier identified in the digital image blurred out may be stored in a memory of the processor either automatically or by way of consent from the occupant. FIG. 2 shows a block diagram of an onboard information management system 200 for a motor vehicle 208. The onboard information management system 200 may include an imaging module 202 having a field of view of a passenger compartment of a motor vehicle 208. The imaging module 202 may be an in-vehicle camera. The imaging module 202 may be a subsystem of the motor vehicle 208 comprising an in-vehicle camera function, for example a driver monitoring system or a cabin monitoring system. The system 200 may comprise a processor 204 having a memory 206 operable to store and retrieve a set of computer program instructions for execution. The processor 204 may be a single processor or a system on chip. In some embodiment, the processor 204 may receive data information from other subsystems in the motor vehicle 208. By way of an example, image processing may be executed by the imaging module 202 and the digital images are transmitted to the processor 204, but not limited thereto. The processor 204 may be operable to receive a digital image generated by the imaging module 202. The processor 204 may be operable to identify at least one occupant identifier contained in the digital image received. The processor may be further operable to execute a privacy algorithm 110. The privacy algorithm 110 may be operable to blur the at least one occupant identifier identified in the digital image received. The processor 204 may be further operable to produce at least one resultant image 306, 308, 310 as shown in FIG. 3c - e which will be explained in further details below, the resultant image contains the at least one occupant identifier identified in the digital image blurred out. FIG. 3a shows a digital image 302 captured by an imaging module 202. As can be observed from digital image 302, the imaging module 202 may be operable to capture an entire passenger compartment of a motor vehicle and at least partially an external surrounding of the motor vehicle 208. FIG. 3b shows a digital image 304 captured by the imaging module 202 with at least one occupant identifier 312. As shown in FIG. 3b, the at least one occupant identifier 312 is a face of an occupant. Example of techniques that may be used for identifying at least one occupant identifier may include extraction of face region of interest (ROI) using artificial intelligence (Al) such as convolution neural network (CNN) which supports image processing. Other examples may include cellular analysis, feature localization or computer vision, but not limited thereto. It shall be understood by a skilled practitioner, suitable techniques involving extraction of facial features using image processing may be applicable to achieve the same objective of extracting regions of interest. The at least one occupant identifier may include body landmarks, which may be identifiable using appropriate techniques such as Al technique involving CNN for image processing as discussed above or body pose identification using semantic labelling, a process of involves assigning a label or class to each pixel or region in an image or video to represent the underlying objects or scenes. Another suitable body landmark identification method may be a descriptor, which may be a compact and distinctive representation of a set of landmarks or features that are used to describe the shape or appearance of an object, such as a face or a body. Descriptors are known to be used in computer vision for tasks such as object recognition, face recognition, and body tracking. It shall be understood by a skilled practitioner, suitable techniques involving extraction of facial features using image processing are applicable to achieve the same objective of extracting body landmarks. In response to identifying at least one occupant identifier the processor 204 may be operable to blur the at least one occupant identifier identified in the digital image 304, to produce at least one resultant image 306 as shown in FIG. 3c, with at least a portion of the at least one occupant identifier blurred out. The blurring of the at least one occupant identifier by the privacy algorithm 110 may involve a Gaussian Kernal function and the computational logic may be designed by applying Gaussian distribution mathematical concept. In some embodiment, the size of kernel may be set to odd numbers only and positive, for example 3, 5, 7, but not limited thereto, to apply the Gaussian Kernel function. In the event the Gaussian standard deviation is non-positive, the size of kernel may be computed using the following computational logic: ksize as sigma = 0.3*((ksize-1)*0.5 -1) + 0.8 where: ksize refers to the size of Kemal sigma refers to Gaussian standard deviation. In some embodiment, the type of filter coefficient may be selected. In some embodiment, sigma X (Zx) may be designed as standard deviation in X direction. In some embodiment, the sigma Y (ZY) may be zero. In some embodiment, the sigma Y (ZY) may be equal to sigma X (Zx). While the type of filter coefficient selected and computational logic of Gaussian standard deviation may vary and yield slight difference in appearance of the resultant image, it shall be understood by a skilled practitioner the selection of the type of filter coefficient does not deviate from the inventive concept of this disclosure, i.e. to yield resultant images with occupant identifier masked or blurred out. The blurring may be achieved by using Gaussian blurring with varying kernel sizes or pixelation using varying block sizes to achieve best results. By way of example, in an embodiment as shown in FIG 3d, is a digital image 312’ containing at least one occupant identifier identified by the processor 204. Applying the Gaussian Kernal function executable by the privacy algorithm 110, to blur a portion of the at least one occupant identifier identified by the processor 204, the at least one resultant image 308 produced may contain a blurred-out portion which appears pixelated. In an embodiment as shown in FIG 3e, is a digital image 312’ containing at least one occupant identifier identified by the processor 204. Applying the Gaussian Kernal function executable by the privacy algorithm 110, to blur a portion of the at least one occupant identifier identified by the processor 204, the at least one resultant image 310 produced may contain a blurred-out portion. Compared with FIG. 3d, the at least one resultant image 310 appears blurrier rather than pixelated. The at least one resultant image 306, 308, 310 containing the at least one occupant identifier identified in the digital image blurred out produced may be streamed as a video, using multiple frames of the at least one resultant image 306, 308, 310. The resultant image 306, 308, 310 may be stored in a memory 206 of the processor 204. In some embodiment, the at least one resultant image 306, 308, 310 containing the at least one occupant identifier identified in the digital image blurred out produced may be an automated process of an imaging module 202 of the motor vehicle 208. The automated feature may be part of a selection of services for the motor vehicle 208. In some embodiment, onboard information management system 202 operable to produce the at least one resultant image 306, 308, 310 containing the at least one occupant identifier identified in the digital image blurred out produced may be a plugin feature in the form of a computer program product, for a vehicle subsystem having an imaging module 202, for example an independent in-vehicle camera for use in conjunction with a driver monitoring system or a cabin monitoring system. In some embodiment, the method 100 may implemented as a platform service or an operating system. The foregoing description shall be interpreted as illustrative and not be limited thereto. One of ordinary skill in the art would understand that certain modifications may come within the scope of this disclosure. Although the different non-limiting embodiments are illustrated as having specific components or steps, the embodiments of this disclosure are not limited to those combinations. Some of the components or features from any of the non-limiting embodiments may be used in combination with features or components from any of the other non-limiting embodiments. For these reasons, the appended claims should be studied to determine the true scope and content of this disclosure. List of Reference Signs 100 Method 102 Receiving a digital image generated by an imaging module 104 Identifying at least one occupant identifier 106 Blurring the at least one occupant identifier identified 108 Producing at least one resultant image with portion(s) blurred out 110 Privacy algorithm 112 Streaming the at least one resultant image with portion(s) blurred out 114 Consent from occupant 116 Storing the at least one resultant image with portion(s) blurred out 118 Executing a Gaussian Kernal function 200 System 202 Imaging module 204 Processor 206 Memory 208 Motor vehicle 302 Digital image received from imaging module 304 Digital image with at least one occupant identifier 306 At least one resultant image with a blurred-out portion 308 At least one resultant image with a blurred-out (pixelated) portion 310 At least one resultant image with a blurred-out portion

Claims

1. A method (100) of managing onboard information for a motor vehicle, the method comprising:receiving (102), by way of a processor, a digital image generated by an imaging module having a field of view of a passenger compartment of a motor vehicle;identifying (104), byway of the processor, at least one occupant identifier(312) contained in the digital image received,characterised by that the method (100) further comprises:blurring (106), by way of a privacy algorithm (110), the at least one occupant identifier identified in the digital image received (302);andproducing (108), by way of the processor, at least one resultant image, the at least one resultant image (306, 308, 310) containing the at least one occupant identifier identified in the digital image blurred out.

2. The method (100) according to claim 1, characterised by that the at least one occupant identifier (312) comprises:a region of interest of a face of the at least one occupant contained in the digital image received;a body landmark of the at least one occupant contained in the digital image received (302), or combination thereof.

3. The method (100) according to claim 1, characterised by that the privacy algorithm (110) comprises:executing (118), by way of the processor (204), a Gaussian Kemal function for blurring the at least one occupant identifier (312) identified in the digital image.

4. The method (100) according to claim 1 - 2, characterised by that the method (100) further comprises:streaming (112), by way of a video signal, multiple frames of the at least one resultant image (306, 308, 310) containing the at least one occupant identifier (312) identified in the digital image blurred out;storing (116), by way of the processor, the at least one resultant image (306, 308, 310) containing the at least one occupant identifier (312) identified in the digital image blurred out in a memory (206) of the processor (204), or combination thereof.

5. An onboard information management system (202) for a motor vehicle (208) comprising:an imaging module (202) having a field of view of a passenger compartment of a motor vehicle (208); anda processor (204) including a memory (206);characterised in thatthe processor (204) is operable toreceive a digital image (302) generated by the imaging module (202);identify at least one occupant identifier (312) contained in the digital image received;execute a privacy algorithm (110), the privacy algorithm (110) operable to blur the at least one occupant identifier (312) identified in the digital image received;andproduce at least one resultant image (306, 308, 310), the resultant image contains the at least one occupant identifier identified in the digital image blurred out.

6. The system of claim 5, characterised in that the at least one occupant identifier (312) comprises:a region of interest of a face of the at least one occupant contained in the digital image received;a body landmark of the at least one occupant contained in the digital image received,or combination thereof.

7. The system according to claims 5- 6, characterised in that the privacy algorithm (110) comprises a Gaussian Kernal function operable to blur the at least one occupant identifier identified in the digital image (306).

8. The system according to any one of claims 5 to 7, characterised in that the processor is operable to:execute an instruction to stream multiple frames of the at least one resultant image (306, 308, 310) containing the at least one occupant identifier identified in the digital image blurred out;store the at least one resultant image (306, 308, 310) containing the at least one occupant identifier identified in the digital image blurred out in a memory (206) of the processor (204), or combination thereof.

9. The system according to any one of claims 5 to 8, characterised in that the imaging module (202) comprises:a driver monitoring system;ora cabin monitoring system.

10. A motor vehicle having an onboard information management system (200) and a processor (204) adapted to execute the steps (100) of claims 1-4.

11. A computer program product comprising instructions to cause the system (200) of claims 5 - 9 to execute the steps of the method (100) of managing onboard vehicle information defined in claims 1-4.12.A non-transitory computer readable medium having stored thereon the computer program product of claim 11.

Images