Vehicle safety system and vehicle control method

Abstract

The invention discloses a vehicle safety system and a vehicle control method. The vehicle safety system comprises a distance sensor, a color RGB camera, an infrared IR camera and a processor. The method comprises the following steps: periodically transmitting a detection signal through a distance sensor so as to sense a first distance between the palm and the palm placed in the transmitting direction of the detection signal of the distance sensor; the processor controls the RGB camera to collect a first image by receiving a first distance sent by the distance sensor and under the condition that the first distance is smaller than a first threshold value, controls the IR camera to collect a second image at the same time, and generates a third image according to the offset of the first image and the second image. Based on the first image, the second image and the third image, biological characteristic information of the palm is extracted, and under the condition that a first matching value between the biological characteristic information of the palm and set user registration information is higher than a second threshold value, a first unlocking instruction is sent to a controller of the electric vehicle.

Description

Technical Field

[0001] The present application relates to the field of vehicle safety, and in particular to a vehicle safety system and a vehicle control method. Background Art

[0002] In modern society, two-wheeled or three-wheeled electric vehicles used for short-distance travel are generally equipped with keys or near field communication (NFC) cards for unlocking. However, in a busy life, people often forget to bring keys or NFC cards, which not only affects the user's travel, but also increases the risk of the vehicle being stolen. Summary of the invention

[0003] To solve the related technical problems, the embodiments of the present application provide a vehicle safety system and a vehicle control method.

[0004] The embodiment of the present application provides a vehicle safety system, which is applied to a two-wheeled or three-wheeled electric vehicle, and includes: a distance sensor, a color RGB camera, an infrared (IR, infrared) camera and a processor, wherein the distance sensor, the RGB camera and the IR camera are arranged together in the same body area of ​​the electric vehicle;

[0005] The distance sensor is used to periodically transmit a detection signal when the electric vehicle is in a locked state, so as to sense a first distance from a palm placed in a direction of the detection signal transmission of the distance sensor;

[0006] The processor is configured to receive the first distance sent by the distance sensor, and when the first distance is less than a first threshold, control the RGB camera to capture a first image, and control the IR camera to capture a second image; the first image includes surface feature information of the palm; the second image includes deep feature information of the palm;

[0007] The processor is further configured to calculate an offset between the plane positions of the same part of the palm in the first image and the second image, and generate a third image according to the offset, wherein the third image is characterized as a parallax image;

[0008] The processor is also used to extract biometric information of the palm based on the first image, the second image and the third image, and send a first unlocking instruction to the controller of the electric vehicle when a first matching value between the biometric information of the palm and the set user registration information is higher than a second threshold.

[0009] In the above vehicle system, the processor is further used for:

[0010] Matching the biometric information of the palm with the user registration information stored in the vehicle safety system to obtain the first matching value;

[0011] It is determined whether the first matching value is higher than the second threshold value to obtain a determination result.

[0012] In the above vehicle system, the processor is further used for:

[0013] Sending the biometric information of the palm to a first terminal, where the first terminal represents a terminal authenticated by the vehicle safety system, and the biometric information of the palm is used by the first terminal to determine whether the first matching value is higher than the second threshold value to obtain a determination result;

[0014] The determination result sent by the terminal is received.

[0015] In the above vehicle system, the step of sending the biometric information of the palm to the first terminal includes:

[0016] The encrypted biometric information of the palm is sent to the first terminal.

[0017] In the above vehicle system, extracting the biometric information of the palm based on the first image, the second image and the third image includes:

[0018] generating a fourth image based on the third image and parameter information of the RGB camera and the IR camera, wherein the fourth image represents a perceived depth map including stereoscopic information of the palm;

[0019] Based on the first image, the second image and the fourth image, biometric information of the palm is extracted.

[0020] In the above vehicle system, the processor is further used for:

[0021] When the first distance sent by the distance sensor within a first set time is greater than a third threshold, entering a low power consumption mode; and / or,

[0022] When the first distance sent by the distance sensor is smaller than the first threshold, the low power consumption mode is exited.

[0023] In the above vehicle system, the processor is further used for:

[0024] When the electric vehicle is in an unlocked state, configuration information associated with the biometric information of the palm is sent to a controller of the electric vehicle; the configuration information is at least used to adjust the seat height and / or the mirror angle of the electric vehicle.

[0025] The present application also provides a vehicle control method, including:

[0026] When the electric vehicle is in a locked state, the distance sensor periodically transmits a detection signal to sense a first distance from a palm placed in a direction in which the detection signal is transmitted by the distance sensor;

[0027] receiving the first distance sent by the distance sensor, and when the first distance is less than a first threshold, controlling the RGB camera to capture a first image and controlling the IR camera to capture a second image; the first image includes surface feature information of the palm; the second image includes deep feature information of the palm;

[0028] Calculating the offset between the plane positions of the same part of the palm in the first image and the second image, and generating a third image according to the offset, wherein the third image is characterized as a parallax image;

[0029] Based on the first image, the second image and the third image, the biometric information of the palm is extracted, and when a first matching value between the biometric information of the palm and the set user registration information is higher than a second threshold, a first unlocking instruction is sent to the controller of the electric vehicle.

[0030] The above solutions include:

[0031] Matching the biometric information of the palm with the user registration information stored in the vehicle safety system to obtain the first matching value;

[0032] It is determined whether the first matching value is higher than the second threshold value to obtain a determination result.

[0033] The above solutions include:

[0034] Sending the biometric information of the palm to a first terminal, where the first terminal represents a terminal authenticated by the vehicle safety system, and the biometric information of the palm is used by the first terminal to determine whether the first matching value is higher than the second threshold value to obtain a determination result;

[0035] The determination result sent by the terminal is received.

[0036] In the above solution, sending the biometric information of the palm to the first terminal includes:

[0037] The encrypted biometric information of the palm is sent to the first terminal.

[0038] In the above solution, extracting the biometric information of the palm based on the first image, the second image and the third image includes:

[0039] generating a fourth image based on the third image and parameter information of the RGB camera and the IR camera, wherein the fourth image represents a perceived depth map including stereoscopic information of the palm;

[0040] Based on the first image, the second image and the fourth image, biometric information of the palm is extracted.

[0041] The above solutions include:

[0042] When the first distance sent by the distance sensor within a first set time is greater than a third threshold, entering a low power consumption mode; and / or,

[0043] When the first distance sent by the distance sensor is smaller than the first threshold, the low power consumption mode is exited.

[0044] The above solutions include:

[0045] When the electric vehicle is in an unlocked state, configuration information associated with the biometric information of the palm is sent to a controller of the electric vehicle; the configuration information is at least used to adjust the seat height and / or the mirror angle of the electric vehicle.

[0046] In a vehicle safety system and a vehicle control method provided in an embodiment of the present application, the vehicle safety system includes: a distance sensor, a color RGB camera, an infrared IR camera, and a processor. First, the distance sensor periodically transmits a detection signal to sense a first distance between the palm placed in the detection signal emission direction of the distance sensor. Secondly, the processor receives the first distance sent by the distance sensor, and when the first distance is less than the first threshold, controls the RGB camera to capture the first image, and controls the IR camera to capture the second image, and calculates the offset between the plane positions of the same part of the palm in the first image and the second image, and generates a third image based on the offset. Finally, the processor extracts the biometric information of the palm based on the first image, the second image, and the third image, and sends a first unlocking instruction to the controller of the electric vehicle when the first matching value between the biometric information of the palm and the set user registration information is higher than the second threshold. Through the above-mentioned vehicle safety system and the corresponding vehicle control method, not only can the vehicle be unlocked by palm, avoiding the situation that the vehicle cannot be used due to not carrying a key or an NFC card, but also the method of unlocking the vehicle with the palm uses an RGB camera and an IR camera, which effectively improves the acquisition quality of the palm image, and image processing and palm recognition are performed based on the images collected by the RGB camera and the IR camera, which effectively improves the accuracy and safety of palm biometric recognition in unlocking two-wheeled or three-wheeled electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic diagram of a vehicle safety system according to an embodiment of the present application;

[0048] Figure 2 A schematic diagram of the vehicle safety system installation area according to an embodiment of the present application;

[0049] Figure 3 A schematic diagram of another vehicle safety system according to an embodiment of the present application;

[0050] Figure 4 A schematic flow chart of a vehicle control method according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] With the popularization of smart devices and mobile terminals, the advantages of biometric technology in terms of security and portability have gradually become apparent. Currently, widely used biometric methods include fingerprint recognition, face recognition, iris recognition, and palm print recognition. Among them, fingerprint recognition is a contact recognition and is not suitable for use under conditions where there are stains or water stains on the surface; when face recognition is used to unlock, the anti-counterfeiting ability is weak and it is easily affected by makeup and accessories; the cost of iris recognition is relatively high. For two-wheeled or three-wheeled electric vehicles, traditional key or NFC card unlocking faces the security risk of loss or theft, and a more convenient, safe and economical unlocking method is urgently needed.

[0052] In a vehicle safety system and a vehicle control method provided in an embodiment of the present application, the vehicle safety system includes: a distance sensor, a color RGB camera, an infrared IR camera, and a processor. First, the distance sensor periodically transmits a detection signal to sense a first distance between the palm placed in the detection signal emission direction of the distance sensor. Secondly, the processor receives the first distance sent by the distance sensor, and when the first distance is less than the first threshold, controls the RGB camera to capture the first image, and controls the IR camera to capture the second image, and calculates the offset between the plane positions of the same part of the palm in the first image and the second image, and generates a third image based on the offset. Finally, the processor extracts the biometric information of the palm based on the first image, the second image, and the third image, and sends a first unlocking instruction to the controller of the electric vehicle when the first matching value between the biometric information of the palm and the set user registration information is higher than the second threshold. Through the above-mentioned vehicle safety system and the corresponding vehicle control method, not only can the vehicle be unlocked by palm, avoiding the situation that the vehicle cannot be used due to not carrying a key or an NFC card, but also the method of unlocking the vehicle with the palm uses an RGB camera and an IR camera, which effectively improves the acquisition quality of the palm image, and image processing and palm recognition are performed based on the images collected by the RGB camera and the IR camera, which effectively improves the accuracy and safety of palm biometric recognition in unlocking two-wheeled or three-wheeled electric vehicles.

[0053] The present application embodiment provides a vehicle safety system, referring to Figure 1 The vehicle safety system is applied to a two-wheeled or three-wheeled electric vehicle, and the vehicle safety system includes: a distance sensor 101, a color RGB camera 102, an infrared IR camera 103 and a processor 104. The distance sensor 101, the RGB camera 102 and the IR camera 103 are arranged together in the same body area of ​​the electric vehicle.

[0054] A distance sensor 101, used for periodically transmitting a detection signal when the electric vehicle is in a locked state, so as to sense a first distance from a palm placed in a direction of the detection signal transmission of the distance sensor;

[0055] The processor 102 is configured to receive the first distance sent by the distance sensor, and when the first distance is less than a first threshold, control the RGB camera to capture a first image, and control the IR camera to capture a second image; the first image includes surface feature information of the palm; the second image includes deep feature information of the palm;

[0056] The processor 102 is further configured to calculate an offset between the plane positions of the same part of the palm in the first image and the second image, and generate a third image according to the offset, wherein the third image is characterized as a parallax image;

[0057] The processor 102 is also used to extract biometric information of the palm based on the first image, the second image and the third image, and to send a first unlocking instruction to the controller of the electric vehicle when a first matching value between the biometric information of the palm and the set user registration information is higher than a second threshold.

[0058] In the embodiments of the present application, two-wheeled or three-wheeled electric vehicles include two-wheeled or three-wheeled vehicles driven by electricity, such as electric motorcycles, electric power-assisted bicycles, and electric bicycles.

[0059] In an embodiment of the present application, the vehicle safety system includes a distance sensor, which may be an ultrasonic sensor, an infrared sensor, a lidar sensor, a time of flight (ToF) sensor, or a photoelectric sensor. In actual application, the distance sensor may be selected based on cost or convenience.

[0060] In the embodiment of the present application, the distance sensor is used to periodically transmit a detection signal when the electric vehicle is in a locked state to sense a first distance from a palm placed in the detection signal emission direction of the distance sensor. When the electric vehicle is in an unlocked state, the distance sensor may not transmit a detection signal to save vehicle energy consumption.

[0061] In the embodiment of the present application, the vehicle safety system includes an RGB camera and an IR camera. The RGB camera uses the standard three channels of red, green, and blue to capture color information and texture information within the visible light spectrum; the IR camera is a camera based on the reflective properties of infrared light, which can avoid interference from factors such as weak light, reflections, and colors.

[0062] In the embodiment of the present application, the distance sensor, the RGB camera and the IR camera are jointly arranged in the same body area of ​​the electric vehicle. Exemplarily, the distance sensor, the RGB camera and the IR camera can be jointly arranged on the left handle or the right handle of the electric vehicle, or in the same body area near the left handle or the right handle. Exemplarily, the distance sensor, the RGB camera and the IR camera can be jointly arranged in the area of ​​the electric vehicle where the key originally needs to be inserted and twisted to unlock, so as to replace the traditional key unlocking method, such as Figure 2 As shown, the electric motorcycle may be arranged in an area 201 framed by a dotted line.

[0063] In an embodiment of the present application, the vehicle safety system includes a processor, the processor is used to receive the first distance sent by the distance sensor, and when the first distance is less than a first threshold, control the RGB camera to capture a first image, and control the IR camera to capture a second image. Wherein, when the first distance is less than the first threshold, it indicates that an object or creature is recognized to be close to the distance sensor, so the RGB camera and the IR camera can be controlled to capture the first image and the second image respectively, so as to facilitate subsequent palm recognition or authentication.

[0064] In the embodiment of the present application, the first image includes surface feature information of the palm, including surface texture information and color information of the palm; the second image includes deep feature information of the palm, including deep line information, capillary information and pore information. The IR camera reduces interference under visible light conditions (such as background color, light shadow, etc.), focuses on the clear presentation of skin texture and deep features, and generates a second image with clear palm print information by specifically capturing reflected infrared light and absorbing and reflecting infrared light to different textures, bumps, blood vessels and other structures on the palm to different degrees.

[0065] In an embodiment of the present application, the processor is also used to calculate the offset of the same part of the palm between the plane positions of the first image and the second image, and generate a third image based on the offset, and the third image is characterized as a parallax image. Since the positions of the RGB camera and the IR camera are different, and images are captured from different angles, there may be a certain offset, so the processor can calculate the same part of the palm in the first image and the second image, such as the offset (or parallax value) of each pixel point in the same palm print in the two images, and generate a parallax map of the palm, that is, the third image. Among them, parallax refers to the offset of different positions of the same object seen in the two cameras. This offset is related to the distance of the object from the camera. The closer the object is, the greater the parallax is, and the farther the object is, the smaller the parallax is. The third image can reflect the ups and downs and texture depth of the palm, and can prevent deception of flat photos.

[0066] In an embodiment of the present application, the processor is further used to extract the biometric information of the palm based on the first image, the second image and the third image, and send a first unlocking instruction to the controller of the electric vehicle when the first matching value between the biometric information of the palm and the set user registration information is higher than a second threshold. The processor can extract the biometric information of the palm based on the first image, the second image and the third image. In some cases, the biometric information of the palm can also be extracted based only on the third image, but the extracted biometric information is relatively inaccurate. The biometric information is characteristic information unique to the user's palm and can include one or more feature vectors. Similarly, the set user registration information can also include one or more feature vectors. By calculating the first matching value between the biometric information of the palm and the set user registration information, when the first matching value is higher than the set second threshold, the characteristic information characterizing the palm is matched with the vehicle, and the vehicle can be unlocked using the information of the palm. In this case, the controller can send a first unlocking instruction to the controller of the electric vehicle.

[0067] In one embodiment, the processor is further configured to:

[0068] Matching the biometric information of the palm with the user registration information stored in the vehicle safety system to obtain the first matching value;

[0069] It is determined whether the first matching value is higher than the second threshold value to obtain a determination result.

[0070] In an embodiment of the present application, the user's registration information may be stored in the vehicle safety system. Moreover, the vehicle safety system may also receive the registration information sent by a terminal device authenticated by the vehicle safety system wirelessly or by wire, and then store the received registration information in the vehicle safety system. The registration information is used to match the biometric information of the palm to obtain the first matching value, and to judge the first matching value and the second threshold.

[0071] In the embodiment of the present application, the vehicle safety system itself stores the user's registration information, which can help the user unlock the vehicle directly with his palm when he does not carry the terminal device. Since the terminal device does not need to be involved in unlocking, the unlocking process can be accelerated, making it more convenient for the user to use.

[0072] In one embodiment, the processor is further configured to:

[0073] Sending the biometric information of the palm to a first terminal, where the first terminal represents a terminal authenticated by the vehicle safety system, and the biometric information of the palm is used by the first terminal to determine whether the first matching value is higher than the second threshold value to obtain a determination result;

[0074] The determination result sent by the terminal is received.

[0075] In the embodiment of the present application, the vehicle safety system itself may not store the user's registration information, but send the palm biometric information to the first terminal authenticated by the vehicle safety system. The first terminal may enter the user's palm biometric information in advance, or delete the palm biometric information of a certain user. Since the first terminal may have better computing power than the vehicle safety system, it may be more convenient to calculate the first matching value of the biometric information and the registration information.

[0076] In an embodiment of the present application, the vehicle safety system can send the biometric information of the palm to the first terminal authenticated by the vehicle safety system through wireless communication, and the wireless communication can adopt the following technologies: Bluetooth technology, Wi-Fi technology and ZigBee technology.

[0077] In the embodiment of the present application, the biometric information of the palm is sent to the first terminal, so that the first terminal determines whether the matching value is higher than the second threshold value. Since the above judgment is performed in the first terminal, the registration information in the first terminal can be updated in time, and the judgment process in the first terminal can be further encrypted, so the user's palm can be authenticated more accurately and securely.

[0078] In one embodiment, sending the biometric information of the palm to the first terminal includes:

[0079] The encrypted biometric information of the palm is sent to the first terminal.

[0080] In an embodiment of the present application, the vehicle safety system can encrypt the biometric information of the palm. The encryption method can be to convert the biometric information into a string of numbers or a code stream without retaining other information, and then send the encrypted biometric information to the first terminal. The first terminal can decrypt the encrypted biometric information after receiving it, and then calculate the first matching value.

[0081] In the embodiment of the present application, by encrypting the biometric information before sending it to the first terminal, the biometric information can be prevented from being stolen during the transmission process, further ensuring the safety of the user's palm information and the vehicle.

[0082] In one embodiment, after the processor in the vehicle safety system sends the encrypted or unencrypted biometric information to the first terminal, the first terminal can use image recognition or artificial intelligence related technologies to analyze the biometric to obtain the health status information of the palm, thereby realizing the health status reminder function; alternatively, the processor in the vehicle safety system can also directly use image recognition or artificial intelligence related technologies to analyze the biometric to obtain the health status information of the palm, and send the health status information to the first terminal, which can also realize the health status reminder function of the first terminal.

[0083] In one embodiment, extracting the biometric information of the palm based on the first image, the second image, and the third image includes:

[0084] generating a fourth image based on the third image and parameter information of the RGB camera and the IR camera, wherein the fourth image represents a perceived depth map including stereoscopic information of the palm;

[0085] Based on the first image, the second image and the fourth image, biometric information of the palm is extracted.

[0086] In the embodiment of the present application, the processor controls the RGB camera to capture the first image, controls the IR camera to capture the second image, and the processor may include a disparity map generation algorithm module for generating a disparity map of the palm using the first image and the second image, i.e., a third image. The processor may also include a perception depth map generation algorithm module (or a disparity map addition algorithm module) for using the third image, the parameter information of the RGB and IR cameras, and using triangulation to generate a perception depth map including stereoscopic information of the palm, i.e., a fourth image. The fourth image reflects the physical distance information of each point on the palm surface from the camera obtained after the conversion from disparity to distance, and the fourth image can provide physical depth information of the palm, including features such as the concavity and convexity of the palm and the depth of the texture.

[0087] In an embodiment of the present application, the processor can also control the image self-calibration circuit (or calibration board) of the RGB or IR camera to perform calibration processing on the first image or the second image to improve the anti-counterfeiting performance; the processor can also control the palm image enhancement circuit of the RGB or IR camera, that is, perform circuit detection through the image sensor inside the camera, enhance image exposure, and make the first image or the second image clearer.

[0088] In the embodiment of the present application, by generating a perceived depth map, i.e., the fourth image, and using the first image, the second image, and the fourth image together to extract the biometric information of the palm, the detailed texture feature information and deep biological information (such as the blood vessel structure under the skin, etc.) on the palm surface can be more effectively captured, the recognition accuracy can be improved, and the interference of factors such as lighting and image quality can be effectively reduced, thereby greatly reducing the risk of deception of flat photos or fake palms.

[0089] In one embodiment, the processor is further configured to:

[0090] When the first distance sent by the distance sensor within a first set time is greater than a third threshold, entering a low power consumption mode; and / or,

[0091] When the first distance sent by the distance sensor is smaller than the first threshold, the low power consumption mode is exited.

[0092] In the embodiment of the present application, when the first distance sent by the distance sensor within the first set time is greater than the third threshold, it can be considered that there is no palm for recognition within the first set time, so only the detection distance function of the distance sensor can be retained, and the processor enters a low power consumption mode to save energy consumption of the vehicle safety system; when the first distance sent by the distance sensor is less than the first threshold, the processor exits the low power consumption mode. The third threshold is greater than or equal to the first threshold.

[0093] In an embodiment of the present application, by setting the low power consumption mode to be entered when the first distance sent by the distance sensor is greater than a third threshold within a first set time, and / or exiting the low power consumption mode when the first distance sent by the distance sensor is less than the first threshold, on the one hand, the energy consumption of the vehicle control system can be saved, and on the other hand, the low power consumption mode can be exited in time to speed up the acquisition speed of the palm image. Furthermore, the third threshold is greater than or equal to the first threshold, which can also avoid too frequent switching between the normal mode and the low power consumption mode of the vehicle safety system.

[0094] In one embodiment, the processor is further configured to:

[0095] When a first number of matching failure instructions received from the first terminal within a second set time is greater than a set number, an alarm instruction is sent to the controller of the vehicle, or an alarm instruction is sent to the first terminal.

[0096] In an embodiment of the present application, once the processor detects multiple failed unlocking behaviors, that is, when the first number of matching failure instructions received from the first terminal is greater than a set number, an alarm instruction can be sent to the controller of the vehicle, or an alarm instruction can be sent to the first terminal. This can not only improve the user experience, but also improve the vehicle's anti-theft capability.

[0097] In the embodiment of the present application, other detection devices may be provided in the system. When abnormal vibration or destructive behavior is detected, an alarm instruction is immediately sent to the first terminal to ensure the safety of the vehicle.

[0098] In the embodiment of the present application, the vehicle safety system can also directly receive the unlocking command from the first terminal to unlock the vehicle, but the vehicle safety system and the first terminal must authenticate each other in advance. Furthermore, the first terminal can also include the functions of automatic positioning and / or navigation and / or remote control related to the vehicle; the display panel of the vehicle can also include a logo pattern indicating whether the vehicle is unlocked, as well as other vehicle driving information, such as power level and mileage.

[0099] In one embodiment, the processor is further configured to:

[0100] When the electric vehicle is in an unlocked state, configuration information associated with the biometric information of the palm is sent to a controller of the electric vehicle; the configuration information is at least used to adjust the seat height and / or the mirror angle of the electric vehicle.

[0101] In an embodiment of the present application, the vehicle safety system may store configuration information associated with the biometric information of the palm, and the configuration information includes configuration information of the seat height and / or the mirror angle. For example, within a period of time after the vehicle safety system is in a locked state, the vehicle safety system actively stores the configuration information associated with the biometric information of the palm that was last unlocked. In addition, the user can also set his or her own biometric information and the configuration information of the associated seat and / or mirror in the terminal device, and then send the configuration information to the vehicle safety system wirelessly or wiredly.

[0102] In the embodiment of the present application, when the user unlocks the electric vehicle with the palm, that is, when the electric vehicle is in the unlocked state, the processor sends configuration information associated with the biometric information of the palm to the controller of the electric vehicle. The controller is a controller that can control the seat height and / or the mirror angle. When the controller receives the configuration information, it actively controls the seat to adjust the height and / or the mirror to adjust the angle.

[0103] In an embodiment of the present application, when the electric vehicle is in an unlocked state, the processor sends configuration information associated with the biometric information of the palm to the controller of the electric vehicle. The configuration information is at least used to adjust the seat height and / or mirror angle of the electric vehicle, which can help the user to make personalized settings, save the user's adjustment time after unlocking the electric vehicle, and facilitate the user's travel.

[0104] The vehicle safety system can be designed in a modular way, that is, the distance sensor, RGB and IR cameras, and the processor are integrated into one module. It can also be installed by snap-on accessories, which is convenient for manufacturers to install the vehicle safety system into two-wheeled or three-wheeled electric vehicles. Through modular design, the scalability and compatibility of the vehicle safety system can be increased, so as to adapt to the vast majority of electric-driven two-wheeled or three-wheeled vehicles on the market.

[0105] The present application is further described in detail below in conjunction with application examples.

[0106] like Figure 3 As shown in the figure, in order to identify the user's palm, a distance detection sensor is used to identify the distance. In addition, in a binocular camera, the camera sensor usually refers to an image sensor, which can convert the light captured by the lens into an electrical signal, and then convert it into a digital signal through an internal analog-to-digital converter (AD). Among them, the mainstream image sensors on the market are CCD (charge-coupled device) and CMOS (complementary metal oxide semiconductor). In order to capture a better image, an infrared fill light is also used for fill light.

[0107] like Figure 3 As shown, the processor includes a CPU (central processing unit) and a single-chip microcomputer, and is connected to other driver modules, such as a crystal oscillator, an infrared fill light driver, and a red or green status light, through a general purpose input / output (GPIO) or IIC (Inter-Integrated Circuit) interface or protocol. The processor is also connected to the camera sensor through a mobile industry processor interface (MIPI). In addition, the processor communicates with the terminal device through a WiFi module, such as wireless communication with a mobile phone.

[0108] An embodiment of the present application also provides a vehicle control method, which can be applied to the vehicle safety systems of the above-mentioned embodiments. Figure 4 The flowchart of the method includes:

[0109] Step 401: When the electric vehicle is in a locked state, the distance sensor periodically transmits a detection signal to sense a first distance from a palm placed in a detection signal transmission direction of the distance sensor.

[0110] Step 402: Receive the first distance sent by the distance sensor, and when the first distance is less than a first threshold, control the RGB camera to capture a first image, and control the IR camera to capture a second image.

[0111] The first image includes surface feature information of the palm; the second image includes deep feature information of the palm.

[0112] Step 403: Calculate the offset between the plane positions of the same part of the palm in the first image and the second image, and generate a third image according to the offset, wherein the third image is characterized as a parallax image.

[0113] Step 404: Extract the biometric information of the palm based on the first image, the second image and the third image, and send a first unlocking instruction to the controller of the electric vehicle when a first matching value between the biometric information of the palm and the set user registration information is higher than a second threshold.

[0114] In one embodiment, the method further comprises:

[0115] Matching the biometric information of the palm with the user registration information stored in the vehicle safety system to obtain the first matching value;

[0116] It is determined whether the first matching value is higher than the second threshold value to obtain a determination result.

[0117] In one embodiment, the method further comprises:

[0118] Sending the biometric information of the palm to a first terminal, where the first terminal represents a terminal authenticated by the vehicle safety system, and the biometric information of the palm is used by the first terminal to determine whether the first matching value is higher than the second threshold value to obtain a determination result;

[0119] The determination result sent by the terminal is received.

[0120] In one embodiment, sending the biometric information of the palm to the first terminal includes:

[0121] The encrypted biometric information of the palm is sent to the first terminal.

[0122] In one embodiment, extracting the biometric information of the palm based on the first image, the second image, and the third image includes:

[0123] generating a fourth image based on the third image and parameter information of the RGB camera and the IR camera, wherein the fourth image represents a perceived depth map including stereoscopic information of the palm;

[0124] Based on the first image, the second image and the fourth image, biometric information of the palm is extracted.

[0125] In one embodiment, the method further comprises:

[0126] When the first distance sent by the distance sensor within a first set time is greater than a third threshold, entering a low power consumption mode; and / or,

[0127] When the first distance sent by the distance sensor is smaller than the first threshold, the low power consumption mode is exited.

[0128] In one embodiment, the method further comprises:

[0129] When the electric vehicle is in an unlocked state, configuration information associated with the biometric information of the palm is sent to a controller of the electric vehicle; the configuration information is at least used to adjust the seat height and / or the mirror angle of the electric vehicle.

[0130] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0131] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0132] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A vehicle safety system, characterized in that: The vehicle safety system is applied to a two-wheeled or three-wheeled electric vehicle, and the vehicle safety system comprises: a distance sensor, a color RGB camera, an infrared IR camera and a processor, wherein the distance sensor, the RGB camera and the IR camera are arranged together in the same body area of ​​the electric vehicle; The distance sensor is used to periodically transmit a detection signal when the electric vehicle is in a locked state, so as to sense a first distance from a palm placed in a direction of the detection signal transmission of the distance sensor; The processor is configured to receive the first distance sent by the distance sensor, and when the first distance is less than a first threshold, control the RGB camera to capture a first image, and control the IR camera to capture a second image; the first image includes surface feature information of the palm; the second image includes deep feature information of the palm; The processor is further configured to calculate an offset between the plane positions of the same part of the palm in the first image and the second image, and generate a third image according to the offset, wherein the third image is characterized as a parallax image; The processor is also used to extract biometric information of the palm based on the first image, the second image and the third image, and send a first unlocking instruction to the controller of the electric vehicle when a first matching value between the biometric information of the palm and the set user registration information is higher than a second threshold.

2. The vehicle safety system according to claim 1, characterized in that: The processor is further configured to: Matching the biometric information of the palm with the user registration information stored in the vehicle safety system to obtain the first matching value; It is determined whether the first matching value is higher than the second threshold value to obtain a determination result.

3. The vehicle safety system according to claim 1, characterized in that: The processor is further configured to: Sending the biometric information of the palm to a first terminal, where the first terminal represents a terminal authenticated by the vehicle safety system, and the biometric information of the palm is used by the first terminal to determine whether the first matching value is higher than the second threshold value to obtain a determination result; The determination result sent by the terminal is received.

4. The vehicle safety system according to claim 3, characterized in that: The sending the biometric information of the palm to the first terminal includes: The encrypted biometric information of the palm is sent to the first terminal.

5. The vehicle safety system according to claim 1, characterized in that: The step of extracting biometric information of the palm based on the first image, the second image, and the third image includes: generating a fourth image based on the third image and parameter information of the RGB camera and the IR camera, wherein the fourth image represents a perceived depth map including stereoscopic information of the palm; Based on the first image, the second image and the fourth image, biometric information of the palm is extracted.

6. The vehicle safety system according to claim 1, characterized in that: The processor is further configured to: When the first distance sent by the distance sensor within a first set time is greater than a third threshold, entering a low power consumption mode; and / or, When the first distance sent by the distance sensor is smaller than the first threshold, the low power consumption mode is exited.

7. The vehicle safety system according to claim 1, characterized in that: The processor is further configured to: When the electric vehicle is in an unlocked state, configuration information associated with the biometric information of the palm is sent to a controller of the electric vehicle; the configuration information is at least used to adjust the seat height and / or the mirror angle of the electric vehicle.

8. A vehicle control method, characterized in that: The method is applied to a two-wheeled or three-wheeled electric vehicle, and the method comprises: When the electric vehicle is in a locked state, the distance sensor periodically transmits a detection signal to sense a first distance from a palm placed in a direction in which the detection signal is transmitted by the distance sensor; receiving the first distance sent by the distance sensor, and when the first distance is less than a first threshold, controlling the RGB camera to capture a first image and controlling the IR camera to capture a second image; the first image includes surface feature information of the palm; the second image includes deep feature information of the palm; Calculating the offset between the plane positions of the same part of the palm in the first image and the second image, and generating a third image according to the offset, wherein the third image is characterized as a parallax image; Based on the first image, the second image and the third image, the biometric information of the palm is extracted, and when a first matching value between the biometric information of the palm and the set user registration information is higher than a second threshold, a first unlocking instruction is sent to the controller of the electric vehicle.

9. The method according to claim 8, characterized in that The method further comprises: Matching the biometric information of the palm with the user registration information stored in the vehicle safety system to obtain the first matching value; It is determined whether the first matching value is higher than the second threshold value to obtain a determination result.

10. The method according to claim 8, characterized in that The method further comprises: Sending the biometric information of the palm to a first terminal, where the first terminal represents a terminal authenticated by the vehicle safety system, and the biometric information of the palm is used by the first terminal to determine whether the first matching value is higher than the second threshold value to obtain a determination result; The determination result sent by the terminal is received.

11. The method according to claim 10, characterized in that The sending the biometric information of the palm to the first terminal includes: The encrypted biometric information of the palm is sent to the first terminal.

12. The method according to claim 8, characterized in that The step of extracting biometric information of the palm based on the first image, the second image, and the third image includes: generating a fourth image based on the third image and parameter information of the RGB camera and the IR camera, wherein the fourth image represents a perceived depth map including stereoscopic information of the palm; Based on the first image, the second image and the fourth image, biometric information of the palm is extracted.

13. The method according to claim 8, characterized in that The method further comprises: When the first distance sent by the distance sensor within a first set time is greater than a third threshold, entering a low power consumption mode; and / or, When the first distance sent by the distance sensor is smaller than the first threshold, the low power consumption mode is exited.

14. The method according to claim 8, characterized in that The method further comprises: When the electric vehicle is in an unlocked state, configuration information associated with the biometric information of the palm is sent to a controller of the electric vehicle; the configuration information is at least used to adjust the seat height and / or the mirror angle of the electric vehicle.

Images