Temporary visual field adjusting method for electronic rearview mirror, electronic rearview mirror and equipment

Abstract

The invention relates to the field of electronic rearview mirrors, and discloses an electronic rearview mirror temporary visual field adjusting method, an electronic rearview mirror and equipment, and the method comprises the steps: collecting a temporary visual field through a camera device, and carrying out the temporary visual field display through a display screen; acquiring feature data of the face of the driver; estimating a first distance between the face of the driver and the display screen based on the feature data; when the first distance changes, correspondingly adjusting the amplification factor of the display screen; estimating the attention direction of the face of the driver based on the feature data; and when the attention direction changes, correspondingly adjusting the temporary view display range of the display screen. According to the electronic rearview mirror, the eye spot position and the observation direction of the driver are tracked through corresponding software and hardware, so that when the driver uses the electronic rearview mirror, the technical effects that the visual field can be changed by moving the head back and forth, and the visual angles in different ranges can be obtained by moving the attention direction are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electronic rearview mirror, in particular to an electronic rearview mirror temporary field of view adjustment method, an electronic rearview mirror and a device. BACKGROUND

[0002] The traditional physical rearview mirror has a history of more than 100 years, and the importance of the rearview mirror has been generally accepted by the public. However, in actual use, the physical rearview mirror has several disadvantages: large blind area, large wind resistance, far light and strong light glare, and interference in rainy and snowy weather. With the development of technology, electronic rearview mirrors have emerged as the times require.

[0003] The electronic rearview mirror, also known as a camera-monitor system (CMS), is an indirect field of view device that acquires a temporary field of view through a camera-monitor system. The CMS is composed of a high-definition camera, a system controller and a display. The existing automatic temporary field of view function cannot completely cover all scenarios of the original traditional rearview mirror, such as before the driver high-speed lane-changing turn, by stretching the face, changing the eye point position to translate the field of view range of the rearview mirror, observing the blind area that the rearview mirror cannot see, and ensuring the safety of lane-changing and turning. However, at this time, since the steering wheel angle has not changed, when the electronic rearview mirror is replaced, the driver cannot see the blind area by changing the eye point position to translate the field of view. SUMMARY

[0004] In order to solve the above technical problems, the present application provides an electronic rearview mirror temporary field of view adjustment method, an electronic rearview mirror and a device, which track the driver's eye point position and observation direction through corresponding software and hardware, so that when the driver uses the electronic rearview mirror, the front and rear movement of the head can change the field of view size, and the movement of the attention direction can obtain different ranges of visible angles.

[0005] Specifically, the technical scheme of the present application is as follows:

[0006] In a first aspect, the present application discloses an electronic rearview mirror temporary field of view adjustment method, comprising:

[0007] acquiring a temporary field of view through a camera device, and displaying the temporary field of view through a display screen;

[0008] acquiring feature data of the driver's face;

[0009] estimating a first distance between the driver's face and the display screen based on the feature data; and adjusting the magnification of the display screen when the first distance changes;

[0010] estimating a direction of attention of the driver's face based on the feature data; and adjusting a temporary field of view display range of the display screen when the direction of attention changes.

[0011] In some embodiments, the estimating the first distance between the driver's face and the display screen based on the feature data comprises:

[0012] calculating a pixel distance between any two feature points of the driver's face in real time based on the feature points and the coordinates of the feature points; and estimating the first distance based on the pixel distance.

[0013] In some embodiments, the estimating the first distance between the driver's face and the display screen based on the feature data comprises:

[0014] calculating an area of a specified region of the driver's face in real time based on the feature points and the coordinates of the feature points; and estimating the first distance based on the area of the specified region.

[0015] In some embodiments, the adjusting the magnification of the display screen when the first distance changes comprises:

[0016] obtaining a preset reference distance; and calculating a relative change amount of the first distance relative to the reference distance.

[0017] calculating the magnification of the display screen based on the relative change amount and a preset conversion function.

[0018] In some embodiments, the adjusting the temporary field of view display range of the display screen when the direction of attention changes comprises the following steps:

[0019] taking an angle at which the driver's face is parallel to the display screen as a reference angle;

[0020] detecting in real time whether there is an angle deviation between the driver's face and the reference angle based on the feature points and the coordinates of the feature points; and considering that the direction of attention of the driver changes if there is an angle deviation.

[0021] controlling the field of view range of the display screen to be translated to the direction of attention of the driver.

[0022] In some embodiments, after obtaining the feature data, the method further comprises the step of performing a smoothing filtering process on the feature data.

[0023] In a second aspect, the present application discloses an electronic rearview mirror, which comprises a camera, a display screen, a processor, and a memory, which are connected to the processor respectively.

[0024] The camera collects a temporary field of view and displays the temporary field of view on the display screen.

[0025] The processor executes a computer program stored on the memory to implement the following steps:

[0026] Obtain feature data of the driver's face.

[0027] Estimate a first distance between the driver's face and the display screen based on the feature data; when the first distance changes, the magnification of the display screen is adjusted accordingly.

[0028] Estimate the attention direction of the driver's face based on the feature data; when the attention direction changes, the display range of the temporary field of view of the display screen is adjusted accordingly.

[0029] In a third aspect, the application also discloses an electronic rearview mirror temporary field of view adjustment system, characterized in that it comprises an electronic rearview mirror and a driver monitoring system as described in the above embodiments; the driver monitoring system is used for detecting the features of the driver's face to obtain feature data and sending the feature data to the electronic rearview mirror.

[0030] In some embodiments, the driver monitoring system is also used for collecting the facial image of the driver in real time; inputting the facial image into a trained neural network model; and extracting the feature data, including the feature points of the driver's face and the coordinates of the feature points, by using the neural network model.

[0031] Compared with the prior art, the application has at least one of the following beneficial effects:

[0032] 1. The technical solution provided by the application obtains driver posture information by multiplexing a DMS (Driver Monitor System). The application mainly applies the estimation of driver posture information to simulate the optical characteristics of a traditional physical rearview mirror on an electronic rearview mirror, i.e. the forward and backward movement of the head can change the size of the field of view, and the movement of the attention direction can obtain different ranges of visible angles.

[0033] 2. When the driver uses the electronic rearview mirror, the driver can still retain the original operation and use habits of the traditional rearview mirror while obtaining the convenience of the electronic rearview mirror and the advantages of night imaging. On the basis of fixed adjustment of the temporary field of view, the field of view direction of the electronic rearview mirror is optimized by using the attention direction of the driver.

[0034] 3、The application further comprises the step of smoothing filtering the feature data after obtaining the feature data. Specifically, the application processes the feature data obtained by the driver monitoring system by designing a smoothing function. It can be used to ignore the rapidly changing area data to exclude the influence caused by blinking, jolting, etc. BRIEF DESCRIPTION OF DRAWINGS

[0035] The above features, technical characteristics, advantages and implementation ways of the present application will be further described in the following with reference to the preferred embodiments and the accompanying drawings.

[0036] Figure 1 The step flow chart of a method embodiment of the present application;

[0037] Figure 2 The model structure schematic diagram of attention direction recognition provided in the embodiments of the present application. DETAILED DESCRIPTION

[0038] In the following description, specific details are set forth such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, persons skilled in the art should understand that the present application can be implemented in other embodiments without these specific details. In other cases, well-known systems, devices, circuits, and methods have not been described in detail in order not to obscure the description of the present application with unnecessary details.

[0039] It should be understood that when used in the specification and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0040] For the sake of simplicity, only the parts of the drawings that are related to the application are shown in the drawings, and they do not represent the actual structure of the product. In addition, in order to make the drawings simple and easy to understand, in some drawings, only one of the components with the same structure or function is shown schematically, or only one of them is labeled. In this document, "one" not only means "only one", but also means "more than one" situation.

[0041] It should be further understood that the term "and / or" used in the specification and the appended claims means any combination of the associated listed items and all possible combinations, and includes these combinations.

[0042] In this document, unless otherwise indicated and / or unless the context clearly dictates otherwise, the terms "mounting", "connected", "connection" should be interpreted broadly, for example, can be fixed connection, can also be detachable connection, or integral connection; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in this application can be understood according to the specific circumstances.

[0043] In a particular implementation, the terminal device described in the embodiments of the present application includes, but is not limited to, other portable devices such as mobile phones, laptop computers, home teaching machines or tablet computers having a touch-sensitive surface (e.g., a touch screen display and / or a touchpad). It should also be understood that in some embodiments, the terminal device is not a portable communication device, but a desktop computer having a touch-sensitive surface (e.g., a touch screen display and / or a touchpad).

[0044] In addition, in the description of the present application, the terms "first", "second", etc. are only used for differentiation and description, and cannot be understood as indicating or implying relative importance.

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the specific embodiments of the present application will be described below with reference to the drawings. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings and embodiments according to these drawings without creating any creative labor.

[0046] The electronic rearview mirror is an indirect vision device that acquires a specified field of view through a camera and a monitor system. It contains high-definition cameras, digital vision processing systems, safety systems, liquid crystal displays, and other electronic devices, and is a new type of rearview mirror that can replace traditional optical rearview mirrors. The existing electronic rearview mirror automatic temporary field of view function cannot completely cover all scenarios of the original traditional rearview mirror. For example, before the driver high-speed merges and turns, the driver can change the eye point position by stretching the head forward, thereby translating the field of view of the rearview mirror to observe the blind area that the rearview mirror cannot see, and ensure the safety of merging and turning. However, at this time, since the steering wheel angle has not changed, when the electronic rearview mirror is replaced, the driver cannot translate the field of view by changing the eye point position to see the blind area. Therefore, the driver's eye point position and observation direction need to be tracked by corresponding software and hardware, so that when the driver uses the electronic rearview mirror, in addition to the convenience of the electronic rearview mirror and the advantages of night imaging, the driver can still retain the original operation and use habits of the traditional rearview mirror.

[0047] Reference is made to the drawings accompanying the Figure 1An embodiment of the temporary field of view adjustment method of the electronic rearview mirror provided by the application comprises the following steps:

[0048] S100, collecting the temporary field of view by the camera device and displaying the temporary field of view on the display screen.

[0049] Specifically, the reflection image of the traditional optical rearview mirror is limited, depending on the curvature, shape and size of the mirror. The camera of the electronic rearview mirror can adjust the FOV (field of view) to obtain a larger field of view, and can also expand the field of view in the scene of turning and reversing.

[0050] S200, obtaining the feature data of the driver's face.

[0051] S300, estimating the first distance between the driver's face and the display screen based on the feature data. When the first distance changes, the magnification of the display screen is adjusted accordingly.

[0052] S400, estimating the attention direction of the driver's face based on the feature data. When the attention direction changes, the range of the temporary field of view displayed by the display screen is adjusted accordingly.

[0053] Another embodiment of the temporary field of view adjustment method of the electronic rearview mirror provided by the application is based on the above-mentioned embodiment, and the step S200 of obtaining the feature data of the driver's face comprises the following steps: receiving the feature data of the driver's face sent by the driver monitoring system. The feature data includes the feature points of the driver's face and the coordinates of the feature points.

[0054] Specifically, the feature data of the driver's face is obtained by multiplexing the DMS system. DMS (Driver Monitor System) is the abbreviation of driver monitoring system, also known as driver fatigue detection system or behavior analysis system. Initially, the main application of DMS system is to monitor the state of the driver to prevent dangerous behaviors such as driver fatigue and distraction. With the progress of machine vision technology, the functions of DMS system have become very rich, including supporting fatigue driving detection, distraction driving detection, driver line of sight detection, gesture recognition (for interaction with vehicle system), face recognition (for unlocking, personalized settings), and expression recognition.

[0055] Another embodiment of the temporary field of view adjustment method of the electronic rearview mirror provided by the application is based on the above-mentioned embodiment, and the step S300 comprises the following steps:

[0056] S311, estimating the first distance between the driver's face and the display screen based on the feature data.

[0057] Or, S312, based on the feature points and the coordinates of the feature points, the pixel distance between any two feature points on the driver's face is calculated in real time. The first distance is estimated based on the pixel distance.

[0058] Or, S313, based on the feature points and the coordinates of the feature points, the area of a specified region on the driver's face is calculated in real time. The first distance is estimated based on the area of the specified region.

[0059] S320, a preset reference distance is obtained. The relative change amount of the first distance relative to the reference distance is calculated.

[0060] S330, based on the relative change amount and a preset conversion function, the magnification of the display screen is calculated.

[0061] The following provides several embodiments to explain the present embodiment in detail.

[0062] Embodiment one of the present embodiment:

[0063] The first distance between the driver's face and the display screen is estimated directly through an image ranging algorithm.

[0064] When the first distance changes, the magnification of the display screen is adjusted accordingly. When the first distance decreases, it means that the driver's face is close to the display screen, and at this time, the magnification of the display screen is increased accordingly. When the first distance increases, it means that the driver's face is away from the display screen, and the magnification of the display screen is decreased accordingly.

[0065] More preferably, a preset reference distance is obtained. The relative change amount of the first distance relative to the reference distance is calculated. Based on the relative change amount and a preset conversion function, the magnification of the display screen is calculated. When the first distance decreases, the relative change amount is less than 0, and the target magnification is obtained by dividing the existing display screen magnification by the relative change amount. Conversely, when the first distance increases, the relative change amount is greater than 0, and the target magnification is obtained by dividing the existing display screen magnification by the relative change amount.

[0066] Specifically, the image ranging algorithm includes monocular camera ranging algorithm, binocular camera ranging algorithm, method based on triangulation principle, or sensor ranging, etc. to calculate the distance from the target object in the photo to the camera. Other existing more complex but more accurate camera model parameters can also be used to realize this function.

[0067] Embodiment two of the present embodiment:

[0068] Based on the feature points and the coordinates of the feature points, a pixel distance between any two feature points on the driver's face is calculated in real time. The first distance is estimated based on the pixel distance.

[0069] Specifically, in this embodiment, a distance estimation algorithm based on deep learning is adopted. The pixel distance between any two feature points on the driver's face, such as the pixel distance between the driver's pupils, is calculated. The obtained pixel distance is input into a trained deep learning model to accurately estimate the distance of the driver from the screen.

[0070] When the first distance changes, the magnification of the display screen is adjusted accordingly. When the first distance decreases, it means that the driver's face is approaching the display screen, and at this time, the magnification of the display screen is increased accordingly. When the first distance increases, it means that the driver's face is moving away from the display screen, and the magnification of the display screen is decreased accordingly.

[0071] Embodiment three of the present embodiment:

[0072] Based on the feature points and the coordinates of the feature points, a pixel distance between any two feature points on the driver's face is calculated in real time. When the pixel distance changes, the magnification of the display screen is adjusted accordingly.

[0073] Specifically, the pixel distance is, for example, the pixel distance between the driver's pupils, the pixel distance between the driver's left and right corners of the mouth, or the pixel distance of the driver's cheek width. More preferably, when the pixel distance decreases, it means that the driver's face is moving away from the display screen, and the magnification of the display screen is decreased accordingly. When the pixel distance increases, it means that the driver's face is approaching the display screen, and at this time, the magnification of the display screen is increased accordingly.

[0074] More preferably, a preset reference pixel distance is obtained. The relative change amount of the pixel distance relative to the reference pixel distance is calculated. Based on the relative change amount and a preset conversion function, the magnification of the display screen is calculated. When the pixel distance decreases, the relative change amount is less than 0, and the target magnification is obtained by multiplying the existing display screen magnification by the relative change amount. Conversely, when the pixel distance increases, the relative change amount is greater than 0, and the target magnification is obtained by multiplying the existing display screen magnification by the relative change amount.

[0075] Embodiment four of the present embodiment:

[0076] Based on the feature points and the coordinates of the feature points, the area of a designated region on the driver's face is calculated in real time. The first distance is estimated based on the area of the designated region.

[0077] Specifically, in the embodiment, a distance estimation algorithm based on deep learning is adopted. The area of a specified region of the driver's face, such as the area of the driver's left eye region or the area of the driver's right eye region, is calculated. The obtained left eye / right eye region area is input into a trained deep learning model to accurately estimate the distance of the driver from the screen.

[0078] When the first distance changes, the magnification of the display screen is adjusted accordingly. When the first distance decreases, it means that the driver's face is closer to the display screen, and at this time, the magnification of the display screen is adjusted to increase. When the first distance increases, it means that the driver's face is farther away from the display screen, and the magnification of the display screen is adjusted to decrease.

[0079] Embodiment five of the present embodiment:

[0080] Based on the feature points and the coordinates of the feature points, the area of a specified region of the driver's face is calculated in real time. When the specified region area changes, the magnification of the display screen is adjusted accordingly.

[0081] Specifically, the coordinates of the feature points include the coordinates of the eye area and the coordinates of the two corners of the mouth. The specified region area, for example, is the area of the driver's left eye region, the area of the driver's right eye region, or the area of the lips. More preferably, when the specified region area decreases, it means that the driver's face is farther away from the display screen, and the magnification of the display screen is adjusted to decrease. When the specified region area increases, it means that the driver's face is closer to the display screen, and the magnification of the display screen is adjusted to increase.

[0082] More preferably, a preset reference region area is obtained. The relative change amount of the specified region area relative to the reference region area is calculated. Based on the relative change amount and a preset conversion function, the magnification of the display screen is calculated. When the specified region area has a relative change amount less than 0, the target magnification is obtained by multiplying the existing display screen magnification by the relative change amount. Conversely, when the specified region area increases, the relative change amount is greater than 0, and the target magnification is obtained by multiplying the existing display screen magnification by the relative change amount.

[0083] In some other embodiments of the present embodiment, based on the above embodiments one to five, the method further comprises the steps of:

[0084] A conversion function of the display screen magnification is preset. The relative change amount of the distance between the driver's face and the display screen, or the relative change amount of the pixel distance, or the relative change amount of the specified region area is calculated.

[0085] Specifically, the relative change amount is calculated by the following formula: relative change amount = new value / old value.

[0086] In other embodiments, the percentage change can also be calculated by the following formula:

[0087] Percentage change = (new value - old value) / old value * 100%.

[0088] After obtaining the relative change, the change is mapped to a preset conversion function to obtain the magnification of the display screen. A device CMS system (Content Management System) adjusts the field of view according to different magnifications.

[0089] Another embodiment of the electronic rearview mirror temporary field of view adjustment method provided in the present application is based on the above-mentioned embodiment, and the step S400 comprises the following steps:

[0090] S410, taking the angle at which the driver's face is parallel to the display screen as a reference angle.

[0091] S420, based on the feature points and the coordinates of the feature points, detecting in real time whether there is an angle between the driver's face and the reference angle. If there is an angle, it is considered that the attention direction of the driver has changed.

[0092] S430, controlling the field of view of the display screen to translate to the attention direction of the driver.

[0093] Through face key point detection, the positions of the two pupils of the driver are integrated, a head pose estimation algorithm is input, the yaw angle of the head of the driver (the angle at which the head of the driver turns left and right) is obtained, and thus the attention direction of the driver is obtained. Refer to the accompanying drawings Figure 2 , Figure 2 The model structure for attention direction recognition in the present embodiment is shown in the figure. Among them, points A, B and C represent three facial features of the driver, including the left eye, the right eye and the mouth. The yaw angle φ of the driver's face plane is obtained through the coordinates of the two eyes and the mouth corner. According to this yaw angle φ, the driver's face is projected onto a plane parallel to the display. It is used to correct the calculation error caused by the head turning.

[0094] Specifically, once the correct positions of the eyes and the mouth are determined, the facial symmetry can be used to determine the angle between the plane defined by the three facial features (two eyes, mouth) and the image plane. The three facial features determine an isosceles triangle. If we consider that one side of the triangle is located on the image plane, we can calculate the estimated value of the line of sight direction angle through the trigonometric function of the angle between the connecting lines of the selected facial features, as Figure 2 shown.

[0095] Let α be the side of the triangle connecting an eye and the center of the mouth, and β be the orthogonal projection of the other equal side on the image plane.Figure 2 In this case, the projection of the isosceles triangle is represented by a solid line and denoted as triangle ABC, while the isosceles triangle ABE is represented by a dashed line.

[0096] This means that if the person in the image is looking directly at the observer, the projection triangle should coincide with the isosceles triangle. The dashed line represents triangle CDE, which lies on a plane that is perpendicular to both the image plane and the plane of the isosceles triangle.

[0097] Let θ be the angle between lines a and b, and φ be the angle between the image plane and the plane of the isosceles triangle. From triangle CDE, we have:

[0098]

[0099] where |CD| represents the length of segment CD, and |DE| represents the length of segment DE. Similarly, from triangle ACD, we have:

[0100] CD = |AC| sin θ;

[0101] AD = |AC| cos θ;

[0102] From triangle ADE, we have:

[0103] AD 2 + |DE 2 = |AE 2 ;

[0104] Since triangle ABE is an isosceles triangle, we have:

[0105] AE 2 = |AB 2 ;

[0106] Solving the above equations together, we get:

[0107]

[0108] Therefore, the angle φ can be calculated using the following formula:

[0109]

[0110] φ is the attention direction angle we need.

[0111] More preferably, the currently commonly used method for obtaining the head posture angle includes face landmark detection and image classification. For the eyes, the opening and closing degree of the eyes can be determined by calculating the coordinates of the key points of the eyelids and the corners of the eyes, and the mouth is similar. The Perspective-n-Point (PnP) algorithm is used to directly fit the three-dimensional angle of the head. The advantage of the face landmark detection method is that the idea is relatively simple, and only the coordinates of the key points need to be calculated. However, the disadvantage is also obvious, that is, the accuracy of the algorithm depends on the accuracy of the key point positioning. If the key point positioning is accurate, the final calculation result will also be more accurate.

[0112] Other head posture estimation methods can also be used, such as using pre-labeled yaw, pitch, and roll angle face images to train a small neural network, and making the output layer of the network directly regress the three floating-point numbers. This method is simple and direct, and has high accuracy. The training data set can directly use the open source face data set without additional labeling.

[0113] Another embodiment of the method of the present application, based on any one of the above embodiments, further comprises the step of performing smoothing filtering on the feature data after obtaining the feature data.

[0114] Specifically, by designing a smoothing function (such as Gaussian filtering), the rapidly changing area data is ignored to exclude the influence caused by blinking and jolting. Through this step, the accuracy of the field of view adjustment can be improved.

[0115] Another embodiment of the method of the present application, based on any one of the above embodiments, uses a Support Vector Machine (SVM) to control the robustness of the field of view adjustment switch.

[0116] Specifically, SVM is a supervised learning model widely used in machine learning, especially in classification problems. SVM finds an optimal hyperplane to separate different classes of data. For face recognition, it is to distinguish the features of different faces.

[0117] In this embodiment, a polynomial kernel is selected for nonlinear mapping, and the optimization parameter C is set to 10. The SVM model determines the driver's intention to see a larger field of view through the electronic rearview mirror through the face key points, and simultaneously calculates the driver's attention direction at this time through the 3D face coordinates input by the DMS system.

[0118] The technical scheme provided by the application is also used for improving the angle of view adjustment for observing the trailer of a cargo box by a commercial vehicle type II electronic outside rearview mirror. The current commercial vehicle type II electronic outside rearview mirror mainly realizes the adjustment of a fixed angle of view (temporary field of view adjustment) by the rotation angle of a steering wheel when turning. The embodiment can optimize the field of view direction of the electronic outside rearview mirror based on the fixed adjustment of the temporary field of view by using the attention direction of the driver.

[0119] Based on the same technical concept, the application further discloses an electronic rearview mirror, characterized in that the electronic rearview mirror comprises a camera, a display screen, a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to realize the steps of the method in any one of the embodiments.

[0120] The camera is used for collecting a temporary field of view.

[0121] The display screen is used for displaying the temporary field of view.

[0122] The processor executes the computer program stored in the memory to realize the following steps:

[0123] Obtaining feature data of a driver's face;

[0124] Estimating a first distance between the driver's face and the display screen based on the feature data; when the first distance changes, the magnification of the display screen is adjusted correspondingly;

[0125] Estimating the attention direction of the driver's face based on the feature data; when the attention direction changes, the display range of the temporary field of view of the display screen is adjusted correspondingly.

[0126] More preferably, the processor is a device CMS system (Content Management System).

[0127] The electronic rearview mirror can be used for various types of vehicles, carriers, robots and monitoring devices.

[0128] Based on the same technical concept, the application further discloses an electronic rearview mirror temporary field of view adjustment system, which at least comprises an electronic rearview mirror and a driver monitoring system in the above embodiments.

[0129] The driver monitoring system is used for detecting the features of a driver's face to obtain feature data, and sending the feature data to the electronic rearview mirror.

[0130] Specifically, the driver monitoring system is further configured to collect a face image of the driver in real time, input the face image into the trained neural network model, and extract the feature data from the neural network model, including feature points of the face of the driver and coordinates of the feature points.

[0131] The electronic rearview mirror temporary field of view adjustment method, the electronic rearview mirror and the device have the same technical concept, and the technical details of the embodiments of the three can be applicable to each other. To avoid repetition, the technical details of the embodiments of the three will not be described again.

[0132] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above program modules is taken as an example, and in actual application, the above functions can be completed by different program modules according to needs, that is, the internal structure of the device is divided into different program units or modules to complete all or part of the functions described above. Each program module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one processing unit. The above integrated units can be realized in the form of hardware or software program units. In addition, the specific names of each program module are only for easy distinction, and do not limit the protection scope of the application.

[0133] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0134] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0135] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the modules or units is only a logical function division, and there can be another division in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0136] The units described as separate components may or may not be physically separate, and the components displayed as separate components may or may not be physical separate, and may be located in one position, or distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0137] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0138] Although the preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including all the preferred embodiments and all the changes and modifications falling within the scope of the present application.

[0139] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A method for temporarily adjusting the field of view of an electronic rearview mirror, characterized in that, Includes the following steps: A temporary field of view is captured by a camera device and displayed on a screen. Obtain facial feature data of the driver; The first distance between the driver's face and the display screen is estimated based on the feature data; when the first distance changes, the magnification of the display screen is adjusted accordingly. The driver's facial attention direction is estimated based on the feature data; when the attention direction changes, the temporary field of view of the display screen is adjusted accordingly.

2. A method for temporarily adjusting the field of view of an electronic rearview mirror as described in claim 1, characterized in that, The estimation of the first distance between the driver's face and the display screen based on the feature data includes: Based on the feature points and their coordinates, the pixel distance between any two feature points on the driver's face is calculated in real time; the first distance is estimated based on the pixel distance.

3. The method for temporarily adjusting the field of view of an electronic rearview mirror as described in claim 1, characterized in that, The estimation of the first distance between the driver's face and the display screen based on the feature data includes: Based on the feature points and their coordinates, the area of ​​a specified region on the driver's face is calculated in real time; the first distance is estimated based on the area of ​​the specified region.

4. A method for temporarily adjusting the field of view of an electronic rearview mirror as described in any one of claims 1, 2, and 3, characterized in that, The aforementioned adjustment of the magnification of the display screen when the first distance changes specifically includes: Obtain a preset reference distance; calculate the relative change of the first distance relative to the reference distance; The magnification of the display screen is calculated based on the relative change and a preset conversion function.

5. The method for temporarily adjusting the field of view of an electronic rearview mirror as described in claim 1, characterized in that, The method of adjusting the temporary field of view of the display screen when the direction of attention changes includes the following steps: The reference angle is the angle at which the driver's face is parallel to the display screen; Based on the feature points and their coordinates, the system detects in real time whether there is an angle of deviation between the driver's face and the reference angle. If a deflection angle exists, it is assumed that the driver's attention direction has changed; The field of view of the display screen is shifted to the direction of the driver's attention.

6. The method for temporarily adjusting the field of view of an electronic rearview mirror as described in claim 1, characterized in that, After obtaining the feature data, the process further includes the step of performing a smoothing filter on the feature data.

7. An electronic rearview mirror, characterized in that, include: The camera device, display screen, processor, and memory are respectively connected to the processor; The camera device captures a temporary field of view and displays the temporary field of view on the display screen; The processor executes a computer program stored in the memory to perform the following steps: Obtain facial feature data of the driver; The first distance between the driver's face and the display screen is estimated based on the feature data; when the first distance changes, the magnification of the display screen is adjusted accordingly. The driver's facial attention direction is estimated based on the feature data; when the attention direction changes, the temporary field of view of the display screen is adjusted accordingly.

8. A temporary field-of-view adjustment system for an electronic rearview mirror, characterized in that, Including the electronic rearview mirror and driver monitoring system as described in claim 7; The driver monitoring system is used to detect the driver's facial features, obtain feature data, and send the feature data to the electronic rearview mirror.

9. The electronic rearview mirror temporary field of view adjustment system as described in claim 8, characterized in that: The driver monitoring system is also used to collect facial images of the driver in real time; input the facial images into a trained neural network model; and use the neural network model to extract the feature data, including: feature points of the driver's face and the coordinates of the feature points.

Images