Method and device for learning a facial recognition model for vehicles

Abstract

The present invention relates to a method and device for learning a facial recognition model for vehicles implemented as a neural network. To this end, supervised learning (25) of a pre-trained facial recognition model is implemented. The supervised learning comprises refining a set of parameters of the pre-trained facial recognition model from the labeled training dataset (202, 204). The supervised learning implements a learning method without backpropagation of errors by using, in each layer of a set of layers of the neural network, a target label vector for refining a subset of the parameters of the parameter set associated with each layer. The target label vector is obtained by multiplying the label vector by a random matrix associated with each layer. Figure 2

Description

Title of the invention: Method and device for learning a facial recognition model for vehicles. Technical field

[0001] The invention relates to methods and devices for training a facial recognition model for a vehicle, particularly but not exclusively a motor vehicle. The invention relates to methods and devices for controlling an embedded system in a vehicle implementing such a facial recognition model. Technological background

[0002] Modern vehicles incorporate various driver assistance systems, known as ADAS (Advanced Driver-Assistance System), to assist the driver of such a vehicle in controlling the driving of the vehicle, or even to replace the driver in an autonomous driving mode of the vehicle.

[0003] Some of these ADAS systems rely on predictive models implemented by neural networks. These predictive models need to be trained in a learning phase before they can be used in the vehicle. The learning phase of a neural network implementing a predictive model requires a large amount of data so that the neural network can then function in all the real-life situations encountered by the vehicle. The quality of the training data used in the learning phase is important for improving the relevance of the neural network and the predictions it makes. Therefore, it is necessary that the training data reflect as closely as possible all the real-life situations the vehicle will encounter once it is in operation.To this end, car manufacturers use data collected from test vehicles as well as from private vehicles driving on public roads in real-world conditions. For test vehicles, the data captured by the vehicle's various sensors (radar, lidar, cameras) is stored on dashcams, which are retrieved at the end of the tests to extract the data. For private vehicles, the data captured by the various onboard sensors is retrieved from one or more cloud servers to which the vehicles are connected wirelessly, for example, via a wireless cellular network.

[0004] However, collecting data from private vehicles presents certain problems. These vehicles must be equipped with specific and expensive equipment necessary for acquiring and recording data, such as than video encoders or extended flash memory. Furthermore, transmitting data acquired by vehicles via wireless communication requires very high bandwidth, which is particularly costly, as the risk of data packet loss is high in areas with limited wireless connectivity. Finally, the security of data transmitted over wireless network infrastructure, such as cellular wireless networks, is difficult to guarantee. Summary of the present invention

[0005] One object of the present invention is to solve at least one of the problems of the technological background described above.

[0006] An object of the present invention is, for example, to improve the learning of a facial recognition model implemented by a vehicle neural network.

[0007] Another objective is to reduce the costs associated with training such a facial recognition model, in particular by reducing the bandwidth required to transmit training data acquired by private vehicles.

[0008] According to a first aspect, the present invention relates to a method for learning a facial recognition model for vehicles implemented in the form of a neural network, the method being implemented by at least one computer embedded in the vehicle, the method comprising the following steps: - reception of image data representative of images of a vehicle's interior, the image data being acquired by a camera mounted in the vehicle; - detection of a set of faces by a pre-trained facial recognition model from image data, the detection including an association of a label to each face in the set of faces, face image data representative of the face set and label data representative of the associated labels feeding a training dataset; - control of the display of each face and the associated label on a screen mounted in the vehicle; - receiving validation data representative of a validation or correction of the label associated with each image; - generation of a labeled training dataset from the training dataset and the validation data, the labeled training dataset comprising a vector of labels associated with the face image data; - supervised learning of the facial recognition model by refining a set of parameters of the pre-trained facial recognition model from the labeled training dataset, the supervised learning implementing a learning method without backpropagation of errors by using, in each layer of a set of layers of the neural network, a vector target labels for refining a portion of the parameters in the parameter set associated with each layer, the target label vector being obtained by multiplying the label vector by a random matrix associated with each layer.

[0009] Implementing the training of the neural network parameters implementing the facial recognition model directly in the vehicle eliminates the need to transmit the data acquired by the vehicle to a remote device implementing the training. This reduces the costs associated with training by eliminating data transmission. Implementing training in the vehicle is made possible by using a pre-trained model, validating the training data through user feedback in the vehicle (via displaying an image of faces and their associated labels on a vehicle screen), and finally, implementing a supervised learning method that does not require backpropagation of errors, thus reducing the amount of computation required for training and consequently reducing processor and memory requirements.

[0010] Implementing neural network training within the vehicle also ensures the security of the data used during training, as this data is stored within the vehicle. The entire training and facial recognition cycle is carried out without the data being sent to a third party; therefore, individuals whose facial images are used for training do not need to give their consent for the processing of their personal data, and the risks of data leaks and other GDPR (General Data Protection Regulation) violations are minimized.

[0011] According to one variant, supervised learning is implemented by at least one processor of at least one computer when a load level of at least one processor induced by processing tasks other than supervised learning by at least one processor is below a determined threshold.

[0012] According to yet another variant, the refinement of the parameter set is implemented until a percentage error between a set of labels obtained from the facial recognition model from the image data and a set of labels from the label vector becomes less than a threshold.

[0013] According to a further variant, a different random matrix is ​​associated with each layer of the layer set.

[0014] According to another variant, the method further comprises the following steps: - compression of representative data from the labeled training dataset to obtain compressed data; and - recording of the compressed data in a vehicle memory.

[0015] According to an additional variant, the method further includes a step of decompressing the compressed data for implementation of the supervised learning step.

[0016] According to a second aspect, the present invention relates to a device for learning a facial recognition model for vehicles, the device comprising a memory associated with a processor configured for implementing the steps of the process according to the first aspect of the present invention.

[0017] According to a third aspect, the present invention relates to a vehicle, for example of the automobile type, comprising a device as described above according to the second aspect of the present invention.

[0018] According to a fourth aspect, the present invention relates to a computer program which includes instructions adapted for carrying out the steps of the process according to the first aspect of the present invention, in particular when the computer program is executed by at least one processor.

[0019] Such a computer program may use any programming language, and be in the form of source code, object code, or an intermediate form between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0020] According to a fifth aspect, the present invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the process according to the first aspect of the present invention.

[0021] On the one hand, the recording medium can be any entity or device capable of storing the program. For example, the medium can include a storage means, such as a ROM, a CD-ROM or a microelectronic circuit-type ROM, or a magnetic recording means or a hard disk drive.

[0022] On the other hand, this recording medium can also be a transmissible medium such as an electrical or optical signal, such a signal being able to be transmitted via an electrical or optical cable, by conventional or radio frequency, by self-directing laser beam, or by other means. The computer program according to the present invention can, in particular, be downloaded from an Internet-type network.

[0023] Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to execute or to be used in the execution of the process in question. Brief description of the figures

[0024] Other features and advantages of the present invention will become apparent from the description of the particular and non-limiting embodiments of the present invention below, with reference to the attached Figures 1 to 4, in which:

[0025] [Fig-1] schematically illustrates part of a vehicle passenger compartment, according to a example of a particular embodiment of the present invention;

[0026] [Fig.2] schematically illustrates a learning process of a neural network implementing a facial recognition model in the vehicle of [Fig.1], according to a particular embodiment of the present invention;

[0027] [Fig.3] schematically illustrates a device configured for training a neural network implementing a facial recognition model in the vehicle of [Fig.1], according to a particular and non-limiting embodiment of the present invention.

[0028] [Fig.4] illustrates a flowchart of the different stages of a process for learning a facial recognition model in the vehicle of [Fig.1], according to a particular and non-limiting embodiment of the present invention. Description of examples of achievements

[0029] A method and device for learning a facial recognition model for vehicles implemented in a neural network will now be described in what follows with joint reference to Figures 1 to 4. The same elements are identified with the same reference signs throughout the description that follows.

[0030] The terms "first," "second" (or "firsts," "seconds"), etc., are used in this document by arbitrary convention to allow for the identification and distinction of different elements (such as operations, means, etc.) implemented in the embodiments described below. Such elements may be distinct or correspond to a single element, depending on the embodiment.

[0031] Fig. 1 schematically illustrates part of the passenger compartment of a vehicle 10, according to a particular and non-limiting embodiment of the present invention.

[0032] Vehicle 10 corresponds, for example, to a vehicle with an internal combustion engine, with electric motor(s), or even a hybrid vehicle with an internal combustion engine and one or more electric motors. Vehicle 10 thus corresponds, for example, to a land vehicle comprising a passenger compartment or at least equipped with a display screen, for example, a car, a truck, a bus.

[0033] The vehicle 10 advantageously carries one or more cameras 13 configured for the acquisition of image data of the passenger compartment of the vehicle 10, in particular for the acquisition of images of the faces of the driver and any passengers of the vehicle 10.

[0034] The camera 13 is, for example, arranged in the passenger compartment of the vehicle 10 at the level of the interior rearview mirror. Such a camera 13 has a field of vision corresponding to the front of the passenger compartment including the front seats and possibly one or more rear seats.

[0035] According to one embodiment, the vehicle 10 further comprises another camera arranged on the dashboard, for example in a space behind the steering wheel. Such a camera is configured for acquiring images of the face of the driver of the vehicle 10. Such a camera corresponds, for example, to the camera of a driver attention monitoring system, known as a DMS (Driver Monitoring System).

[0036] A camera includes, for example, the following elements: - a photosensitive sensor corresponding for example to a matrix of photoreceptors associated for example with a Bayer filter; - an optical assembly arranged in front of the sensor with respect to the scene to be acquired by the sensor, the optical assembly comprising, for example, an arrangement of one or more lenses; and - optionally one or more computers associated with memory and configured for processing images acquired by the sensor.

[0037] The image data received or obtained from each camera, in particular camera 13, are thus representative of one or more images of the interior of the vehicle 10, this image data corresponding for example to data representative of a pixel matrix, color values ​​being for example associated with each pixel, for example according to one or more color channels; for example, the pixel data are coded in the form of RGB values ​​(from the English "Red, Green, Blue" or "Rouge, vert, bleu" in French).

[0038] The vehicle 10 also includes a display system comprising one or more computers controlling one or more display devices belonging to the display system. The display system includes, for example, a touchscreen 12 and a computer configured to control the display of content from a graphical HMI on the touchscreen 12, for example, integrated into the dashboard 11.

[0039] The control units controlling the display system (such as the infotainment system control unit, also known as the IVI (In-Vehicle Infotainment) control unit), the various vehicle components 10, and a set of ADAS-type driver assistance systems, for example, form a multiplexed architecture for providing various services essential for the proper functioning of the vehicle. The control units communicate and exchange data with each other via one or more computer buses, for example a communication bus of the CAN data bus type (from the English "Controller Area Network" or in French "Réseau de contrôlers"), CAN FD (from the English "Controller Area Network Flexible Data-Rate" or in French "Réseau de contrôlers à débit de données flexible"), FlexRay (according to the ISO 17458 standard), LIN (from the English "Local Interconnect Network" or in French "Réseau interconnecté local") or Ethernet (according to the ISO / IEC 802-3 standard).

[0040] The vehicle 10 also includes, for example, a set of driver assistance systems, known as AD AS systems (from the English "Advanced Driver-Assistance System" or in French "Système d'aide à la conduite avancé").

[0041] A learning process for a facial recognition model for vehicles, implemented by a neural network, is carried out by one or more devices embedded in the vehicle 10, for example by one or more computers of the vehicle's embedded network 10, i.e., by one or more processors of the computer(s) in association with one or more memories, for example, a memory of the computer(s). Examples of implementations of such a process are described opposite [Fig. 3] below.

[0042] Fig. 2 schematically illustrates a process 1 of learning a facial recognition model for vehicles and implemented in the form of a neural network, according to particular and non-limiting embodiments of the present invention.

[0043] In a first operation 21 of the process, image data representative of a set of images 201 of the passenger compartment of the vehicle 10 are received.

[0044] The images are acquired by one or more cameras 13 of the vehicle 10. The images forming the image set 201 include one or more faces of one or more occupants of the vehicle 10, for example the driver and one or more passengers sitting in the seats of the vehicle 10.

[0045] Image data is received by the computer(s) implementing the process directly from the camera 13 as images are acquired by the camera 13 or from a vehicle memory 10 in which the image data is stored after acquisition for processing as explained below.

[0046] This image data feeds into a pre-trained facial recognition model implemented as a neural network, for example, a neural network comprising several layers of neurons. The neural network corresponds, for example, to a convolutional neural network, or CNN (Convolutional Neural Network).

[0047] The parameters of the neural network implementing the pre-trained facial recognition model were trained prior to its implementation in the process using a large amount of training data, for example, facial image data and other image data. The pre-trained facial recognition model corresponds to a model trained for face recognition in images or to a more generic model trained, for example, for object recognition in images, including faces.

[0048] The pre-trained facial recognition model processes the image data 201 provided as input to the pre-trained model to classify these images and associate one or more labels with them (a label being associated with each class of a set of classes forming the output of the pre-trained model).

[0049] An example of a pre-trained facial recognition model is described in the article entitled "MixFaceNets: Extremely Efficient Face Recognition Networks", by Fadi Boutros et al., published on July 27, 2021 under the reference arXiv:2107.13046vl.

[0050] The parameters of such a pre-trained model have been previously loaded into the memory of the vehicle 10 to which the computer(s) implementing the process have access.

[0051] The pre-trained facial recognition model detects the faces present in the images 201 and associates with each of these faces (or predicts for each of these faces) a label identifying each of these faces, the label being initially predicted randomly before converging with the acquisition of several images of the same face.

[0052] The output of the pre-trained facial recognition model is obtained from representative data of a set of faces 202 and their associated labels 203, these data 202, 203 forming or feeding a training dataset.

[0053] When the images 201 contain only one face, the data 202 of the face images correspond for example to the data of these images 201.

[0054] In a second operation 22 of the process, the display of the images of the faces 202 and the associated labels 203 is controlled so as to display each face and each label (i.e. a face identifier) ​​associated with that face on a screen of the vehicle 10, for example screen 12, to have the association between the displayed face and its label / identifier validated or corrected by the driver or a passenger of the vehicle 10.

[0055] Each face and associated label pair is, for example, displayed as a particular graphical content of a graphical human-machine interface of vehicle 10.

[0056] A display control for graphic content or any graphic object (text, pictogram, icon, etc.) includes rendering the graphic content or graphic object, such rendering corresponding to a set of operations performed by one or more processors on the pixels of one or more images of the graphic content to be displayed on the screen 12. For example, rendering consists of associating a set pixel data of an image pixel data (for example color data expressed in an RGB (Red, Green, Blue) type space) associated with each graphic object.

[0057] The display control of graphic content or an image thus includes the transmission of control signals to the touch screen 12 to modify the values ​​associated with the pixels of the touch screen 12 at the location intended to display the graphic content or the image.

[0058] In a third operation 23 of the process, validation data representative of a validation or correction of the label associated with each image displayed on the screen 12 are received.

[0059] These validation data are for example received from the touch interface of the touch screen 12 when the occupant of the vehicle 10 viewing the images of faces and the associated labels validates or corrects (by assigning another label to the displayed image, i.e. by assigning another identifier to the displayed image) the information displayed, i.e. the label associated with the image of the displayed face.

[0060] According to another embodiment, this validation data is received from a microphone arranged in the passenger compartment of the vehicle 10 when the occupant of the vehicle 10, validating or correcting the displayed information, uses a voice communication interface of the vehicle 10.

[0061] In a fourth operation 24 of the process, a labeled training dataset is generated from the training dataset and the validation data, the labeled training dataset comprising a label vector 204 associated with the face image data 202.

[0062] Such an operation 24 makes it possible to correct the training dataset formed from the image data 202 and the associated labels 203 by correcting the erroneous labels to generate a new set of labels 204 (for example in the form of a vector) associated with the face image data 202 on the basis of the corrections (or validations) made by the person who viewed the face image / associated label pairs displayed on the screen 12. The new set of labels 204, called the label vector, is representative of the ground truth since it represents the identifiers associated with the face image data 202 validated by one (or more) users of the vehicle 10 whose face images were acquired by the camera 13 and used to generate the training dataset.

[0063] The labeled training dataset is stored in a memory of the vehicle 10 and forms a database that can be used to implement supervised learning of the parameters of the neural network forming the facial recognition model that will be used in the production or inference phase.

[0064] The representative data of the labeled training dataset are for example recorded in a compressed form, a compression operation being applied to this data according to any method known to a person skilled in the art.

[0065] When this data is recorded in compressed format, a data decompression operation is implemented before any processing operation is carried out on this data, for example during supervised learning as described in the fifth operation 25.

[0066] In a fifth operation 25 of the process, supervised learning of the parameters (or weights) of the neural network implementing the facial recognition model that will be used in the production or inference phase is refining the parameters (or weights) of the pre-trained facial recognition model.

[0067] Supervised learning corresponds to supervised fine-tuning, known as SFT (from the English "Supervised Fine-Tune" or in French "affinage surveillé").

[0068] Supervised learning is implemented based on the labeled training dataset, i.e. on the face images 202 and associated labels 204.

[0069] The method used for supervised learning corresponds to a method requiring fewer resources (in particular processor computing resources and memory resources) than a prior art method implemented on a server or computer comprising higher resources than those available on a vehicle computer (for example, low memory budget and limited number of operations (FLOPS, from the English "Floating-point Operations Per Second") available).

[0070] The method implemented in the present process corresponds to a method that does not implement the usual error backpropagation operation well known to the person skilled in the art.

[0071] The implemented method replaces error backpropagation by using a different so-called random matrix for each layer of the neural network. A matrix is ​​said to be random when its constituent elements are randomly generated. Thus, a different random matrix is ​​associated with each layer of the neural network.

[0072] A target label vector is used for refining the parameters of each neural network layer. The target label vector used for a given layer of the neural network is obtained by multiplying the label vector of the 204 labeled training dataset by the random matrix associated with the data layer of the neural network. Thus, a different target label vector is obtained for each layer of the neural network. The target label vector comprises the labels, called targets, that the parameters of the considered layer of the neural network must predict from the data that this layer receives as input.

[0073] Several refinement iterations are implemented, for example until the error between the predicted labels and the target labels is less than a threshold, for example for each layer. In other words, the supervised learning operation 25 is repeated until a percentage error between a set of labels obtained from the facial recognition model from the image data 202 and a set of labels from the label vector 204 becomes less than a threshold.

[0074] An example of such a method without backpropagation of error is described in more detail in the article entitled “Learning with Local Gradients at the Edge”, by Michael Lomnitz et al., published on September 16, 2022 under the reference arXiv:2208.08503v2.

[0075] According to a particular embodiment, the operations of the process, in particular but not exclusively the fifth supervised learning operation 25, is implemented by the processor(s) of the computer(s) in charge of the process only when the load level of these processors induced or due to the processing of tasks other than that relating to supervised learning is less than a determined threshold (for example when the load level is less than 25, 30, 40 or 50%).

[0076] This particular embodiment allows the processor(s) to be allocated to supervised learning when they are not heavily used for their assigned routine tasks (for example, controlling and executing one or more functions of an AD / AS system). This ensures that the processors are not used for supervised learning when they are being used to implement the functions necessary for the proper operation of the vehicle 10. It also ensures that the resource required for supervised learning is available when the computations associated with supervised learning are being performed.

[0077] According to another particular embodiment, the process further includes receiving confirmation data indicating the end of supervised learning. This data is, for example, received from the touchscreen interface of screen 12 when the driver (or a passenger) confirms and validates the completion of the facial recognition model's training for production use of the model, for example by pressing a virtual button displayed on the screen.

[0078] According to this other particular embodiment, the process as described in operations 21 to 25 is repeated at the request or command of the driver (or a passenger), for example for the acquisition and recognition of new faces.

[0079] The neural network obtained from the supervised learning described above is, for example, implemented by one or more AD AS systems of the vehicle 10, for example by a system controlling the identity of the person sitting in the seat driver of vehicle 10, for example to control the starting of the vehicle (only for the authorized person(s)) and / or to control the adjustment of the driver's seat, mirrors or any personalized element of vehicle 10 according to control parameters stored in memory and associated with the person thus identified.

[0080] Fig. 3 schematically illustrates a device 3 configured for learning a facial recognition model for vehicles implemented in the form of a neural network, according to examples of embodiments of the invention.

[0081] Device 3 advantageously corresponds to a data processing device embedded in a vehicle, for example a computer.

[0082] Device 3 is, for example, configured to carry out the operations described opposite Figures 1 and 2 and / or the steps of the process described opposite [Fig. 4]. Examples of such a device 3 include, but are not limited to, embedded electronic equipment such as a vehicle's on-board computer or an electronic control unit such as an ECU (Electronic Control Unit). The elements of device 3, individually or in combination, may be integrated into a single integrated circuit, into several integrated circuits, and / or into discrete components. Device 3 may be implemented in the form of electronic circuits or software (or computer) modules, or a combination of electronic circuits and software modules.

[0083] The device 3 comprises one (or more) processor(s) 30 configured to execute instructions for carrying out the steps of the process and / or for executing instructions from the software embedded in the device 3. The processor 30 may include integrated memory, an input / output interface, and various circuits known to those skilled in the art. The device 3 further comprises at least one memory 31, for example, volatile and / or non-volatile memory, and / or includes a memory storage device that may include volatile and / or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic disk, or optical disk.

[0084] The computer code of the embedded software(s) including the instructions to be loaded and executed by the processor is for example stored on memory 31.

[0085] According to various particular and non-limiting embodiments, the device 3 is coupled in communication with other similar devices or systems and / or with communication devices, for example a TCU (Telematic Control Unit), for example via a communication bus or through dedicated input / output ports.

[0086] According to a particular and non-limiting embodiment, the device 3 comprises a block 32 of interface elements for communicating with external devices. The interface elements of the block 32 comprise one or more of the following interfaces: - radio frequency RF interface, for example of the Wi-Fi® type (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or of the Bluetooth® type (according to IEEE 802.15.1), in the 2.4 GHz frequency band, or of the Sigfox type using UBN (Ultra Narrow Band) radio technology, or LoRa in the 868 MHz frequency band, LTE (Long-Term Evolution), LTE-Advanced; - USB interface (from the English "Universal Serial Bus" or "Universal Serial Bus" in French); - HDMI interface (from the English "High Definition Multimedia Interface", or "High Definition Multimedia Interface" in French); - LIN interface (from the English "Local Interconnect Network", or in French "Réseau interconnecté local").

[0087] According to another particular and non-limiting embodiment, the device 3 includes a communication interface 33 which allows communication to be established with other devices (such as other computers in the embedded system) via a communication channel 330. The communication interface 33 corresponds, for example, to a transmitter configured to transmit and receive information and / or data via the communication channel 330. The communication interface 33 corresponds, for example, to a wired network of the CAN (Controller Area Network) type, CAN FD (Controller Area Network Flexible Data-Rate), FlexRay (standardized by ISO 17458) or Ethernet (standardized by ISO / IEC 802-3).

[0088] Internal parameters (weights) of the pre-trained neural network can, for example, be received via the communication interface 33.

[0089] According to a particular and non-limiting embodiment, the device 3 can provide output signals to one or more external devices, such as a display screen 340, touch or not, one or more speakers 350 and / or other peripherals 360 (projection system) via output interfaces 34, 35 and 36 respectively. According to a variant, one or more of the external devices is integrated into the device 3.

[0090] Figure 4 illustrates a flowchart of the different stages of a learning process for a vehicle facial recognition model implemented in the form of a neural network, according to a particular and non-limiting embodiment of the present invention. The method is implemented, for example, by device 3 in [Fig. 3].

[0091] In a first step 41, image data representative of images of a vehicle interior are received, the image data being acquired by a camera mounted in the vehicle.

[0092] In a second step 42, a set of faces is detected by a pre-trained facial recognition model from image data, the detection comprising an association of a label to each face in the set of faces, face image data representative of the face set and label data representative of the associated labels feeding a training dataset.

[0093] In a third step 43, the display of each face and associated label is controlled so that each face and associated label are displayed on a screen mounted in the vehicle.

[0094] In a fourth step 44, validation data representative of a validation or correction of the label associated with each image are received.

[0095] In a fifth step 45, a labeled training dataset is generated from the training dataset and the validation data, the labeled training dataset comprising a label vector associated with the face image data.

[0096] In a sixth step 46, supervised learning of the facial recognition model is implemented, such supervised learning comprising a refinement of a set of parameters of the pre-trained facial recognition model from the labeled training dataset, the supervised learning implementing a learning method without backpropagation of error by using, in each layer of a set of layers of the neural network, a target label vector for the refinement of a part of the parameters of the parameter set associated with each layer, the target label vector being obtained by multiplying the label vector by a random matrix associated with each layer.

[0097] According to one variant, the variants and examples of the operations described in relation to [Fig.1] and / or 2 apply to the steps of the process in [Fig.4].

Claims

1. Demands A method for learning a facial recognition model for a vehicle (10) implemented in the form of a neural network, said method being implemented by at least one computer embedded in said vehicle (10), said method comprising the following steps: - reception (41) of image data (201) representative of images of a passenger compartment of said vehicle (10), said image data being acquired by a camera mounted in said vehicle (10); - detection (42) of a set of faces by a pre-trained facial recognition model from said image data (201), said detection comprising an association of a label to each face of said set of faces (202), face image data (202) representative of said face set and label data (203) representative of the associated labels feeding a training dataset; - control (43) of displaying said face and associated label on a screen (12) mounted in said vehicle; - receipt (44) of validation data representative of a validation or correction of the label associated with said each image; - generation (45) of a labeled training dataset from said training dataset and validation data, said labeled training dataset comprising a label vector (204) associated with said face image data (202); - supervised learning (46) of said facial recognition model by refining a set of parameters of said pre-trained facial recognition model from said labeled training dataset, said supervised learning implementing a learning method without backpropagation of error by using, in each layer of a set of layers of the neural network, a target label vector for refining a part of the parameters of said parameter set associated with said each layer, said target label vector being obtained by multiplying said label vector (204) by a random matrix associated with said each layer.

2. A method according to claim 1, wherein said supervised learning is implemented by at least one processor of said at least one computer when a load level of said at least one processor induced by processing tasks different from said supervised learning by said at least one processor is below a determined threshold.

3. A method according to any one of claims 1 to 2, wherein the refinement of said parameter set is carried out until a percentage error between a set of labels obtained from said facial recognition model from said image data and a set of labels from said label vector (204) becomes less than a threshold.

4. A method according to any one of claims 1 to 3, wherein a different random matrix is ​​associated with each layer of said set of layers.

5. A method according to any one of claims 1 to 4, further comprising the following steps: - compression of representative data of said labeled training dataset to obtain compressed data; and - recording of said compressed data in a memory of said vehicle (10).

6. A method according to claim 5, further comprising a step of decompressing said compressed data for implementation of said supervised learning step.

7. A computer program comprising instructions for carrying out the method according to any one of the preceding claims, when such instructions are executed by at least one processor.

8. A computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the process according to any one of claims 1 to 6

9. 1 d U. Device (3) for learning a facial recognition model for a vehicle, said device (3) comprising a memory (31) associated with at least one processor (30) configured for carrying out the steps of the method according to any one of claims 1 to 4.

10. Vehicle comprising device (3) according to claim 9.

Images