WO2020181801A1 - 基于人脸识别的车辆启动方法、装置、介质及终端设备 - Google Patents
基于人脸识别的车辆启动方法、装置、介质及终端设备 Download PDFInfo
- Publication number
- WO2020181801A1 WO2020181801A1 PCT/CN2019/116641 CN2019116641W WO2020181801A1 WO 2020181801 A1 WO2020181801 A1 WO 2020181801A1 CN 2019116641 W CN2019116641 W CN 2019116641W WO 2020181801 A1 WO2020181801 A1 WO 2020181801A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- detection
- child
- feature vector
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
- B60K28/02—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
- B60K28/08—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the cargo, e.g. overload
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
- B60K28/10—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
- B60K28/10—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the vehicle
- B60K28/12—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the vehicle responsive to conditions relating to doors or doors locks, e.g. open door
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R22/00—Safety belts or body harnesses in vehicles
- B60R22/48—Control systems, alarms, or interlock systems, for the correct application of the belt or harness
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/20—Means to switch the anti-theft system on or off
- B60R25/2018—Central base unlocks or authorises unlocking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/20—Means to switch the anti-theft system on or off
- B60R25/25—Means to switch the anti-theft system on or off using biometry
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R22/00—Safety belts or body harnesses in vehicles
- B60R22/48—Control systems, alarms, or interlock systems, for the correct application of the belt or harness
- B60R2022/4883—Interlock systems
- B60R2022/4891—Interlock systems preventing use of the vehicle when the seatbelt is not fastened
Definitions
- This application belongs to the field of computer technology, and in particular relates to a vehicle starting method, device, computer non-volatile readable storage medium and terminal equipment based on face recognition.
- the starting ignition of the vehicle is manually operated by the driver, but many drivers have not developed good driving habits.
- various safety items are not checked. For example, it may happen Forgetting to fasten the seat belt, the door is not closed, the overload, the tire pressure is insufficient, etc., in this case, traffic accidents are prone to occur, and the safety risk is great.
- the embodiments of the present application provide a vehicle starting method, device, computer non-volatile readable storage medium, and terminal equipment based on face recognition to solve the problem that the existing vehicle starting method is prone to traffic accidents. A problem with great security risks.
- the first aspect of the embodiments of the present application provides a vehicle starting method based on face recognition, which may include:
- the vehicle detection configuration file is retrieved from the preset database, and each vehicle detection entry is extracted from the vehicle detection configuration file. Each vehicle detection entry corresponds to an item before the vehicle starts.
- a second aspect of the embodiments of the present application provides a vehicle starting device, which may include a module for implementing the steps of the vehicle starting method described above.
- the third aspect of the embodiments of the present application provides a computer non-volatile readable storage medium, the computer non-volatile readable storage medium stores computer readable instructions, and the computer readable instructions are executed by a processor When realizing the steps of the vehicle starting method described above.
- the fourth aspect of the embodiments of the present application provides a terminal device, including a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, and the processor executes the computer
- the steps of the vehicle starting method described above are realized when the instructions are readable.
- the embodiment of the application has the beneficial effect that: the embodiment of the application first collects the facial image of the driver through the camera set in the vehicle, and performs face recognition on the facial image. If the face recognition is successful, the vehicle detection configuration file is retrieved from the preset database, and each vehicle detection entry is extracted from the vehicle detection configuration file. Each vehicle detection entry corresponds to an item before the vehicle starts. For safety matters, each vehicle detection item in the vehicle detection configuration file is sequentially executed on the vehicle according to a preset detection sequence, and the detection result of each vehicle detection item is recorded. Only when the detection results of each vehicle detection item meet the preset vehicle starting conditions, the vehicle is started, thereby eliminating safety hazards in time before starting the vehicle, reducing safety risks, and avoiding traffic accidents.
- FIG. 1 is a flowchart of an embodiment of a method for starting a vehicle based on face recognition in an embodiment of the application;
- Figure 2 is a schematic flow chart of the setting process of the vehicle detection configuration file
- FIG. 3 is a schematic flow chart of separately detecting whether each face image in the vehicle is a child face image
- FIG. 4 is a structural diagram of an embodiment of a vehicle starting device in an embodiment of the application.
- Fig. 5 is a schematic block diagram of a terminal device in an embodiment of the application.
- an embodiment of a method for starting a vehicle based on face recognition in an embodiment of the present application may include:
- Step S101 Collect a face image of the driver through a camera set in the vehicle, and perform face recognition on the face image.
- the camera in this embodiment may be located in front of the driving position of the vehicle, with the lens facing the driving position so as to facilitate collection of the driver's face image.
- the angle of the camera can be automatically adjusted according to the actual situation.
- the position of the eyes in the image can be used as a reference, and the height range of the eyes in the image can be set in advance. After a face image is collected, it is determined whether the eyes are within this height range. Within the range, the current angle of the camera is maintained and no further settings are made. If the eyes are higher than the height range, the camera is controlled to gradually rotate downwards until the required face image is collected. If the eyes are lower than the height range, Then control the camera to gradually rotate upwards until the face image that meets the requirements is collected.
- the trigger time point of the face image collection is when it is determined that the driver is in the driving position.
- the weight on the driving position can be obtained through a weight sensor arranged in the driving position. If the weight in the driving position is less than the preset first weight threshold, it is determined that the driving position is empty at this time, and no operation is required at this time. If the weight in the driving position is greater than or equal to the first weight threshold , It is determined that the driver is in place at this time, and the step of collecting the face image of the driver through the camera provided in the vehicle can be performed at this time.
- the first weight threshold may be set according to actual conditions, for example, it may be set to 30 kg, 40 kg, 50 kg or other values.
- step S102 After collecting the facial image of the driver, perform facial recognition on it and compare it with the facial image in the preset facial image library of legal drivers. If the facial recognition fails, a warning will be issued , Inform that the current driver is not a legal driver, ask the legal driver to drive the vehicle in the driver's seat, if the face recognition is successful, start to perform step S102 and subsequent steps.
- Step S102 If the face recognition is successful, the vehicle detection configuration file is retrieved from the preset database, and each vehicle detection entry is extracted from the vehicle detection configuration file.
- Each vehicle inspection item corresponds to a safety item before the vehicle starts, as shown in the following table:
- Test items Safety matters before starting the vehicle Detection item 1 Is the seat belt fastened?
- Test item 2 Is the door closed Test item 3 Whether overloaded Test item 4 Whether the tire pressure is normal Test item 5 Whether the child is in the safety seat Test item 6 Does the driver hold the steering wheel tightly ... ...
- the setting process of the vehicle detection configuration file may specifically include the following steps:
- Step S1021 obtain the detection mode of the vehicle.
- the detection mode of the vehicle may include a selected detection mode and a default detection mode, which are set in advance by the driver.
- Step S1022 it is determined whether the detection mode of the vehicle is the selected detection mode.
- step S1023 If the detection mode of the vehicle is the selected detection mode, step S1023 and subsequent steps are executed, and if the detection mode of the vehicle is the default detection mode, step S1025 is executed.
- Step S1023 Display each vehicle detection item in the preset global vehicle detection item set in a preset display area.
- the global vehicle detection item set is a complete set of vehicle detection items, including but not limited to seat belt detection items, door detection items, overload detection items, tire pressure detection items, child safety detection items, steering wheel detection items, etc.
- Step S1024 Receive the driver's selection of each vehicle detection item in the global vehicle detection item set through a preset user interaction interface, and add the selected vehicle detection item to the vehicle detection configuration file .
- the driver can select each vehicle detection item in the global vehicle detection item set through the user interaction interface. For example, the driver can select only the seat belt detection item, the door detection item, and the overload detection item according to actual needs. And so on, the driver can also select all vehicle detection items in the global vehicle detection item set according to actual needs.
- Step S1025 Add each vehicle detection item in the global vehicle detection item set to the vehicle detection configuration file.
- step S103 each vehicle detection item in the vehicle detection configuration file is sequentially executed on the vehicle according to a preset detection sequence, and the detection result of each vehicle detection item is recorded.
- the detection can be performed according to the following content:
- a pressure sensor can be installed on the seat belt buckle to detect the pressure on the seat belt buckle, obtain the pressure value on the seat belt buckle, and determine whether the pressure value reaches the preset pressure Threshold, if the pressure threshold is reached, it is determined that the seat belt has been fastened and the seat belt detection item passes the detection; if the pressure threshold is not reached, it is determined that the seat belt is not fastened and the seat belt detection item fails the detection.
- the state of the vehicle door can be detected by the level of the port. Place a magnetic object inside one end of the door, and place a magnetron switch at the corresponding position on the other end of the door. One end of the magnetron switch is grounded, and the other end is pulled up to a preset level through a preset resistor and connected to the detection port. When the door is opened, the magnetic object leaves the magnetic control switch, the magnetic control switch loses its magnetic force, and the switch is released.
- the level of the detection port is pulled up to the level through the resistor, showing a high level; when the door is closed.
- the magnetic control switch is closed, and the detection port level is pulled down to the ground, showing a low level, that is, by judging the level of the detection port, the opening and closing state of the car door can be detected.
- a distance sensor can be used to detect the state of the vehicle door.
- a miniature distance sensor is installed at both ends of the door, and the distance sensor is used to measure the distance between the two ends of the door. When the distance between the two is less than the preset distance threshold, the door is considered to be closed. The detection entry passes the detection, and if the distance between the two is greater than or equal to the distance threshold, the vehicle door is considered to be in an open state, and the detection entry for the door detection fails.
- the distance threshold can be set according to actual conditions, for example, it can be set to 0.2 cm, 0.5 cm, 1 cm or other values.
- the threshold of the number of people can be set according to actual conditions, for example, it can be set to 4, 7, 10 or other values.
- a pressure sensor can be installed on the outside of the tire to detect the tire pressure, obtain the current tire pressure value, and determine whether the current tire pressure value is within the preset tire pressure range. If the tire pressure is within the range, it is determined that the tire pressure is normal, and the tire pressure test item is passed. If the current tire pressure value is higher or lower than the tire pressure range, it is determined that the tire pressure is abnormal, and the tire pressure is abnormal. The pressure test item test failed.
- each face image in the vehicle is collected by the camera, and then it is detected whether each face image in the vehicle is a child face image.
- the weight of the preset safety seat is collected by a preset weight sensor, and the weight sensor is arranged inside the safety seat. If the weight on the safety seat is greater than the preset second weight threshold, it is determined that the child safety test item is passed; if the weight on the safety seat is less than or equal to the weight threshold, it is determined that the The child safety test item fails the test.
- the second weight threshold may be set according to actual conditions, for example, it may be set to 5 kg, 10 kg, 15 kg or other values. Generally, the second weight threshold is smaller than the first weight threshold.
- the step of separately detecting whether each face image in the vehicle is a child face image may include the following process:
- Step S1031 extract the n-th face feature vector in the vehicle.
- ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇
- FaceVec (FaceElm 1 ,FaceElm 2 ,...,FaceElm gn ,...,FaceElm GN )
- gn is the dimension number of the face feature vector, 1 ⁇ gn ⁇ GN, GN is the total number of dimensions of the face feature vector, FaceElm gn is the value of the nth face feature vector in the vehicle in the gnth dimension, FaceVec is the nth face feature vector in the vehicle.
- Step S1032 respectively select an adult sample set and a child sample set from the preset historical sample library.
- the number of samples contained in the two sample sets should be roughly equal to maintain the balance of the final result.
- the facial feature vector of each adult sample in the adult sample set is recorded as:
- m is the serial number of the adult sample, 1 ⁇ m ⁇ AdultNum, AdultNum is the total number of adult samples, AdultElm m,gn is the value of the face feature vector of the mth adult sample in the gnth dimension, and AdultVec m is the mth dimension Face feature vectors of three adult samples.
- the face feature vector of each child sample in the child sample set is recorded as:
- BabyVec f (BabyElm f,1 ,BabyElm f,2 ,...,BabyElm f,gn ,...,BabyElm f,GN )
- BabyNum is the total number of child samples
- BabyElm f,gn is the value of the face feature vector of the fth child sample in the gnth dimension
- BabyVec f is the fth The face feature vectors of two child samples.
- Step S1033 Calculate the average distances between the n-th face feature vector in the vehicle and the adult sample set and the child sample set.
- the average distance between the n-th face feature vector in the vehicle and the adult sample set and the child sample set can be calculated according to the following formula:
- AdultDis is the average distance between the nth face feature vector in the vehicle and the adult sample set
- BabyDis is the average distance between the nth face feature vector in the vehicle and the child sample set distance.
- Step S1034 Determine whether the nth face image in the vehicle is a child face image according to the average distance between the nth face feature vector in the vehicle and the adult sample set and the child sample set.
- a pressure sensor can be installed at the handle of the steering wheel to obtain the pressure value at the handle of the steering wheel, and determine whether the pressure value reaches the preset pressure threshold. If the pressure threshold is reached, it is determined that the driver has gripped the steering wheel firmly. The detection of the steering wheel detection item is passed, and if the pressure threshold is not reached, it is determined that the driver has not gripped the steering wheel firmly, and the detection of the steering wheel detection item fails.
- Step S104 If the detection result of each vehicle detection item meets the preset vehicle start condition, start the vehicle.
- each vehicle detection item If the detection result of each vehicle detection item meets the preset vehicle start condition, that is, each vehicle detection item passes the detection, the vehicle can be automatically started. Conversely, if there are vehicle detection items that fail the detection, for example, the seat belt is not fastened, the door is not closed, etc., a reminder can be issued to the driver to inform him of various safety hazards, so that the driver can start the vehicle. Eliminate these potential safety hazards in time to reduce safety risks.
- the embodiment of the present application first collects the facial image of the driver through the camera provided in the vehicle, and performs face recognition on the facial image. If the face recognition is successful, the vehicle detection configuration file is retrieved from the preset database, and each vehicle detection entry is extracted from the vehicle detection configuration file. Each vehicle detection entry corresponds to an item before the vehicle starts. For safety matters, each vehicle detection item in the vehicle detection configuration file is sequentially executed on the vehicle according to a preset detection sequence, and the detection result of each vehicle detection item is recorded. Only when the detection results of each vehicle detection item meet the preset vehicle starting conditions, the vehicle is started, thereby eliminating safety hazards in time before starting the vehicle, reducing safety risks, and avoiding traffic accidents.
- FIG. 4 shows a structural diagram of an embodiment of a vehicle starting device provided in an embodiment of the present application.
- a vehicle starting device may include:
- the face recognition module 401 is configured to collect a face image of the driver through a camera set in the vehicle, and perform face recognition on the face image;
- the vehicle detection entry extraction module 402 is configured to retrieve vehicle detection configuration files from a preset database if the face recognition is successful, and extract each vehicle detection entry from the vehicle detection configuration file, each vehicle detection entry All correspond to a safety item before the vehicle starts;
- the vehicle detection item execution module 403 is configured to sequentially execute each vehicle detection item in the vehicle detection configuration file on the vehicle according to a preset detection sequence, and record the detection result of each vehicle detection item;
- the vehicle start module 404 is configured to start the vehicle if the detection result of each vehicle detection item meets the preset vehicle start condition.
- vehicle starting device may further include:
- a detection mode acquisition module for acquiring the detection mode of the vehicle
- a vehicle detection item display module configured to display each vehicle detection item in the preset global vehicle detection item set in a preset display area if the detection mode of the vehicle is the selected detection mode;
- the selection receiving module is used to receive the driver's selection of each vehicle detection item in the global vehicle detection item set through a preset user interaction interface, and add the selected vehicle detection item to the vehicle detection In the configuration file;
- the vehicle detection entry adding module is configured to add each vehicle detection entry in the global vehicle detection entry set to the vehicle detection configuration file if the detection mode of the vehicle is the default detection mode.
- vehicle detection entry execution module may include:
- a face image collection unit configured to collect various face images in the vehicle through the camera
- the child face image detection unit is configured to separately detect whether each face image in the vehicle is a child face image
- a weight collection unit configured to collect a preset weight on the safety seat through a preset weight sensor if a child's face image is detected in each face image in the vehicle;
- the first determining unit is configured to determine that the child safety test item is passed if the weight on the safety seat is greater than a preset weight threshold
- the second determining unit is configured to determine that the child safety test item fails to pass if the weight on the safety seat is less than or equal to the weight threshold.
- the child face image detection unit may include:
- the feature vector extraction subunit is used to extract the nth face feature vector in the vehicle
- the sample set selection subunit is used to select the adult sample set and the child sample set from the preset historical sample library
- the average distance calculation subunit is used to calculate the average distance between the n-th face feature vector in the vehicle and the adult sample set and the child sample set;
- the child face image detection subunit is used to determine whether the nth face image in the vehicle is a child face image.
- vehicle detection entry execution module may further include:
- a total number of face images statistics unit configured to collect various face images in the vehicle through the camera, and count the total number of face images in the vehicle
- the third determining unit is configured to determine that the detection of the overload detection item fails if the total number of face images in the vehicle is greater than a preset number of people threshold;
- the fourth determining unit is configured to determine that the overload detection entry is passed if the total number of face images in the vehicle is less than or equal to the number threshold.
- FIG. 5 shows a schematic block diagram of a terminal device provided by an embodiment of the present application. For ease of description, only parts related to the embodiment of the present application are shown.
- the terminal device 5 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
- the terminal device 5 may include: a processor 50, a memory 51, and computer-readable instructions 52 stored in the memory 51 and running on the processor 50, such as executing the aforementioned method for starting a vehicle based on face recognition Computer readable instructions.
- the processor 50 executes the computer-readable instructions 52, the steps in the aforementioned embodiments of the vehicle starting method based on face recognition are implemented.
- the computer-readable instructions 52 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 51 and executed by the processor 50, To complete this application.
- the one or more modules/units may be a series of computer-readable instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer-readable instructions 52 in the terminal device 5.
- the processor 50 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
- the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
- the memory 51 may be an internal storage unit of the terminal device 5, such as a hard disk or a memory of the terminal device 5.
- the memory 51 may also be an external storage device of the terminal device 5, for example, a plug-in hard disk equipped on the terminal device 5, a smart memory card (Smart Media Card, SMC), and a Secure Digital (SD) Card, Flash Card, etc. Further, the memory 51 may also include both an internal storage unit of the terminal device 5 and an external storage device.
- the memory 51 is used to store the computer-readable instructions and other instructions and data required by the terminal device 5.
- the memory 51 can also be used to temporarily store data that has been output or will be output.
- the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
- the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
- the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer non-volatile readable storage medium.
- the technical solution of this application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several computer-readable instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.
- the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks, etc., which can store computer-readable instructions. Medium.
- Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
- Volatile memory may include random access memory (RAM) or external cache memory.
- RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Transportation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
本申请属于计算机技术领域,尤其涉及一种基于人脸识别的车辆启动方法、装置、计算机非易失性可读存储介质及终端设备。所述方法通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对人脸图像进行人脸识别;若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项;按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果。只有在各条车辆检测条目的检测结果均满足预设的车辆启动条件,才启动所述车辆,从而在车辆启动前及时消除安全隐患,减少安全风险,避免交通事故的发生。
Description
本申请要求于2019年3月12日提交中国专利局、申请号为201910184439.7、发明名称为“基于人脸识别的车辆启动方法、装置、介质及终端设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请属于计算机技术领域,尤其涉及一种基于人脸识别的车辆启动方法、装置、计算机非易失性可读存储介质及终端设备。
在现有技术中,车辆的启动点火是由驾驶员人工操作的,但很多驾驶员并未养成良好的驾驶习惯,在启动点火之前,并未对各项安全事项进行检查,例如,可能出现忘记系好安全带、车门未关紧、超载、轮胎胎压不足等等情况,在这种情况下极易出现交通事故,安全风险极大。
有鉴于此,本申请实施例提供了一种基于人脸识别的车辆启动方法、装置、计算机非易失性可读存储介质及终端设备,以解决现有的车辆启动方式极易出现交通事故,安全风险极大的问题。
本申请实施例的第一方面提供了一种基于人脸识别的车辆启动方法,可以包括:
通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别;
若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项;
按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果;
若各条车辆检测条目的检测结果均满足预设的车辆启动条件,则启动所述车辆。本申请实施例的第二方面提供了一种车辆启动装置,可以包括用于实现上述车辆启动方法的步骤的模块。
本申请实施例的第三方面提供了一种计算机非易失性可读存储介质,所述计算机非易失性可读存储介质存储有计算机可读指令,所述计算机可读指令被处理器执行时实现上述车辆启动方法的步骤。
本申请实施例的第四方面提供了一种终端设备,包括存储器、处理器以及存储在 所述存储器中并可在所述处理器上运行的计算机可读指令,所述处理器执行所述计算机可读指令时实现上述车辆启动方法的步骤。
本申请实施例与现有技术相比存在的有益效果是:本申请实施例首先通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别。若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项,接着按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果。只有在各条车辆检测条目的检测结果均满足预设的车辆启动条件,才启动所述车辆,从而在车辆启动前及时消除安全隐患,减少安全风险,避免交通事故的发生。
图1为本申请实施例中一种基于人脸识别的车辆启动方法的一个实施例流程图;
图2为车辆检测配置文件的设置过程的示意流程图;
图3为分别检测车辆内的各个人脸图像是否为儿童人脸图像的示意流程图;
图4为本申请实施例中一种车辆启动装置的一个实施例结构图;
图5为本申请实施例中一种终端设备的示意框图。
请参阅图1,本申请实施例中一种基于人脸识别的车辆启动方法的一个实施例可以包括:
步骤S101、通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别。
本实施例中的摄像头可以位于车辆驾驶位的前方,镜头朝向驾驶位从而便于采集驾驶员的人脸图像。
为了保证可以采集到完整的人脸图像,摄像头的角度可以根据实际情况进行自动调节。一般地,可以以眼睛在图像中的位置作为参照,预先设置眼睛在图像中所应处于的高度范围,当采集到一张人脸图像后,判定眼睛是否处于该高度范围内,若处于该高度范围内,则保持摄像头当前的角度,不再进行设置,若眼睛高于该高度范围,则控制摄像头逐步向下转动,直至采集到符合要求的人脸图像为止,若眼睛低于该高度范围,则控制摄像头逐步向上转动,直至采集到符合要求的人脸图像为止。
人脸图像采集的触发时间点是在判定驾驶员在驾驶位上就位之时,具体地,可以通过设置在驾驶位内的重量传感器获取所述驾驶位上的重量。若所述驾驶位上的重量 小于预设的第一重量阈值,则判定此时驾驶位为空,此时无需进行任何操作,若所述驾驶位上的重量大于或等于所述第一重量阈值,则判定此时驾驶员已就位,此时可以执行所述通过设置在车辆内的摄像头采集驾驶员的人脸图像的步骤。所述第一重量阈值可以根据实际情况进行设置,例如,可以将其设置为30千克、40千克、50千克或者其它取值。
在采集到驾驶员的人脸图像之后,对其进行人脸识别,将其与预设的合法驾驶人员的人脸图像库中的人脸图像进行比对,若人脸识别失败,则发出警告,告知当前驾驶员并非合法驾驶人员,请合法驾驶人员到驾驶座驾驶车辆,若人脸识别成功,则开始执行步骤S102及其后续步骤。
步骤S102、若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目。
每条车辆检测条目均对应于一项车辆启动前的安全事项,如下表所示:
| 检测条目 | 车辆启动前的安全事项 |
| 检测条目1 | 安全带是否系好 |
| 检测条目2 | 车门是否关闭 |
| 检测条目3 | 是否超载 |
| 检测条目4 | 轮胎胎压是否正常 |
| 检测条目5 | 儿童是否位于安全座椅内 |
| 检测条目6 | 驾驶员是否紧握方向盘 |
| …… | …… |
如图2所示,所述车辆检测配置文件的设置过程具体可以包括如下步骤:
步骤S1021、获取所述车辆的检测模式。
在本实施例中,所述车辆的检测模式可以包括选择检测模式和默认检测模式,由驾驶员预先进行设置。
步骤S1022、判断所述车辆的检测模式是否为选择检测模式。
若所述车辆的检测模式为选择检测模式,则执行步骤S1023及其后续步骤,若所述车辆的检测模式为默认检测模式,则执行步骤S1025。
步骤S1023、将预设的全局车辆检测条目集合中的各条车辆检测条目在预设的显示区域进行显示。
所述全局车辆检测条目集合为车辆检测条目的全集,包括但不限于安全带检测条目、车门检测条目、超载检测条目、轮胎胎压检测条目、儿童安全检测条目、方向盘检测条目等等。
步骤S1024、接收所述驾驶员通过预设的用户交互界面对所述全局车辆检测条目集合中的各条车辆检测条目的选择,并将被选中的车辆检测条目添加入所述车辆检测配置文件中。
驾驶员可以通过所述用户交互界面对所述全局车辆检测条目集合中的各条车辆检测条目进行选择,例如,驾驶员可以根据实际需要只选择检测安全带检测条目、车门检测条目、超载检测条目等等,驾驶员也可以根据实际需要选择所述全局车辆检测条目集合中的所有车辆检测条目。
步骤S1025、将所述全局车辆检测条目集合中的各条车辆检测条目均添加入所述车辆检测配置文件中。
也即在默认检测模式下,无需进行车辆检测条目的选择,直接将所述全局车辆检测条目集合中的所有车辆检测条目均进行默认选择。
步骤S103、按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果。
对所述车辆检测配置文件中包括的各条车辆检测条目,可以按照下述内容分别进行检测:
(1)安全带检测条目。
在本实施例中,可以在安全带系扣上安装压力传感器来对安全带系扣上的压力进行检测,获取安全带系扣上的压力值,并判断该压力值是否达到预先设定的压力阈值,若达到该压力阈值,则判定安全带已系好,所述安全带检测条目检测通过,若未达到该压力阈值,则判定安全带未系好,所述安全带检测条目检测不通过。
(2)车门检测条目。
在本实施例的一种具体实现中,可以通过端口电平高低来检测车门状态。在车门一端的内部放置磁性物体,车门另一端对应的位置放置磁控开关,磁控开关一端接地,另一端通过预设的电阻上拉到一个预设的电平值,并连接到检测端口,当车门打开时,磁性物体离开磁控开关,磁控开关失去磁力,将开关释放,此时检测端口的电平通过该电阻被上拉到该电平值,呈现出高电平;当车门关闭时,磁性物体靠近磁控开关,磁控开关吸合,将检测端口电平下拉到地,呈现低电平,即通过判断检测端口的电平高低,可以检测车门的开闭状态。
在本实施例的另一种具体实现中,可以通过距离传感器来检测车门状态。在车门的两端均设置一个微型的距离传感器,使用该距离传感器来测量车门两端之间的距离,当两者的距离小于预设的距离阈值时,则认为车门为闭合状态,所述车门检测条目检测通过,若两者的距离大于等于该距离阈值,则认为车门为开启状态,所述车门检测 条目检测不通过。所述距离阈值可以根据实际情况进行设置,例如,可以将其设置为0.2厘米、0.5厘米、1厘米或者其它取值。
(3)超载检测条目。
首先,通过所述摄像头采集所述车辆内的各个人脸图像,并统计所述车辆内的人脸图像总数。若所述车辆内的人脸图像总数大于预设的人数阈值,则判定所述超载检测条目检测不通过;若所述车辆内的人脸图像总数小于或等于所述人数阈值,则判定所述超载检测条目检测通过。所述人数阈值可以根据实际情况进行设置,例如,可以将其设置为4、7、10或者其它取值。
(4)轮胎胎压检测条目。
在本实施例中,可以在轮胎外侧安装压力传感器来对轮胎胎压进行检测,获取到当前胎压值,判断当前的胎压值是否处在预设的胎压范围内,若当前胎压值处于该胎压范围内,则判定轮胎胎压正常,所述轮胎胎压检测条目检测通过,若当前胎压值高于或低于该胎压范围,则判定轮胎胎压异常,所述轮胎胎压检测条目检测不通过。
(5)儿童安全检测条目。
首先,通过所述摄像头采集所述车辆内的各个人脸图像,然后分别检测所述车辆内的各个人脸图像是否为儿童人脸图像。
若在所述车辆内的各个人脸图像中未检测到儿童人脸图像,则直接判定所述儿童安全检测条目检测通过。
若在所述车辆内的各个人脸图像中检测到儿童人脸图像,则通过预设的重量传感器采集预设的安全座椅上的重量,所述重量传感器设置在所述安全座椅内部。若所述安全座椅上的重量大于预设的第二重量阈值,则判定所述儿童安全检测条目检测通过;若所述安全座椅上的重量小于或等于所述重量阈值,则判定所述儿童安全检测条目检测不通过。所述第二重量阈值可以根据实际情况进行设置,例如,可以将其设置为5千克、10千克、15千克或者其它取值,一般地,所述第二重量阈值小于所述第一重量阈值。
如图3所示,所述分别检测所述车辆内的各个人脸图像是否为儿童人脸图像的步骤可以包括如下过程:
步骤S1031、提取所述车辆内的第n个人脸特征向量。
在本实施例中,可以使用加速段检测特征(Features from Accelerated Segment Test,FAST)、尺度不变特征变换(Scale-Invariant Feature Transform,SIFT)、加速稳健特征(Speeded Up Robust Features,SURF)等算法或者其它类似的算法来进行人脸特征向量的提取。每个人脸特征向量均对应于所述车辆内的一个人脸图像,例如,第n个人脸 特征向量即对应于所述车辆内的第n个人脸图像,将其记为:
FaceVec=(FaceElm
1,FaceElm
2,...,FaceElm
gn,...,FaceElm
GN)
其中,gn为人脸特征向量的维度序号,1≤gn≤GN,GN为人脸特征向量的维度总数,FaceElm
gn为所述车辆内的第n个人脸特征向量在第gn个维度上的取值,FaceVec为所述车辆内的第n个人脸特征向量。
步骤S1032、从预设的历史样本库中分别选取成人样本集以及儿童样本集。
这两个样本集中所包含的样本数量应当大致相等,以保持最终结果的均衡性。
所述成人样本集中的各个成人样本的人脸特征向量记为:
AdultVec
m=(AdultElm
m,1,AdultElm
m,2,...,AdultElm
m,gn,...,AdultElm
m,GN)
m为成人样本的序号,1≤m≤AdultNum,AdultNum为成人样本的总数,AdultElm
m,gn为第m个成人样本的人脸特征向量在第gn个维度上的取值,AdultVec
m为第m个成人样本的人脸特征向量。
所述儿童样本集中的各个儿童样本的人脸特征向量记为:
BabyVec
f=(BabyElm
f,1,BabyElm
f,2,...,BabyElm
f,gn,...,BabyElm
f,GN)
f为儿童样本的序号,1≤f≤BabyNum,BabyNum为儿童样本的总数,BabyElm
f,gn为第f个儿童样本的人脸特征向量在第gn个维度上的取值,BabyVec
f为第f个儿童样本的人脸特征向量。
步骤S1033、分别计算所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离。
例如,可以根据下式分别计算所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离:
其中,AdultDis为所述车辆内的第n个人脸特征向量与所述成人样本集之间的平均距离,BabyDis为所述车辆内的第n个人脸特征向量与所述儿童样本集之间的平均距离。
步骤S1034、根据所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离确定所述车辆内的第n个人脸图像是否为儿童人脸图像。
若AdultDis大于BabyDis,则可确定所述车辆内的第n个人脸图像不是儿童人脸图像,若AdultDis小于BabyDis,则可确定所述车辆内的第n个人脸图像是儿童人脸 图像。
(6)方向盘检测条目。
在本方案中,可以在方向盘把手处安装压力传感器来获取方向盘把手处的压力值,判断该压力值是否达到预先设定的压力阈值,若达到该压力阈值,则判定驾驶员已经紧握方向盘,所述方向盘检测条目检测通过,若未达到该压力阈值,则判定驾驶员尚未紧握方向盘,所述方向盘检测条目检测不通过。
步骤S104、若各条车辆检测条目的检测结果均满足预设的车辆启动条件,则启动所述车辆。
若各条车辆检测条目的检测结果均满足预设的车辆启动条件,也即各条车辆检测条目均检测通过,则可自动启动所述车辆。反之,若存在检测不通过的车辆检测条目,例如,安全带未系好,车门未关闭等等,则可以向驾驶员发出提示,告知其存在的各项安全隐患,以使驾驶员在车辆启动前及时消除这些安全隐患,减少安全风险。
综上所述,本申请实施例首先通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别。若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项,接着按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果。只有在各条车辆检测条目的检测结果均满足预设的车辆启动条件,才启动所述车辆,从而在车辆启动前及时消除安全隐患,减少安全风险,避免交通事故的发生。
对应于上文实施例所述的一种基于人脸识别的车辆启动方法,图4示出了本申请实施例提供的一种车辆启动装置的一个实施例结构图。
本实施例中,一种车辆启动装置可以包括:
人脸识别模块401,用于通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别;
车辆检测条目提取模块402,用于若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项;
车辆检测条目执行模块403,用于按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果;
车辆启动模块404,用于若各条车辆检测条目的检测结果均满足预设的车辆启动条件,则启动所述车辆。
进一步地,所述车辆启动装置还可以包括:
检测模式获取模块,用于获取所述车辆的检测模式;
车辆检测条目显示模块,用于若所述车辆的检测模式为选择检测模式,则将预设的全局车辆检测条目集合中的各条车辆检测条目在预设的显示区域进行显示;
选择接收模块,用于接收所述驾驶员通过预设的用户交互界面对所述全局车辆检测条目集合中的各条车辆检测条目的选择,并将被选中的车辆检测条目添加入所述车辆检测配置文件中;
车辆检测条目添加模块,用于若所述车辆的检测模式为默认检测模式,则将所述全局车辆检测条目集合中的各条车辆检测条目均添加入所述车辆检测配置文件中。
进一步地,所述车辆检测条目执行模块可以包括:
人脸图像采集单元,用于通过所述摄像头采集所述车辆内的各个人脸图像;
儿童人脸图像检测单元,用于分别检测所述车辆内的各个人脸图像是否为儿童人脸图像;
重量采集单元,用于若在所述车辆内的各个人脸图像中检测到儿童人脸图像,则通过预设的重量传感器采集预设的安全座椅上的重量;
第一判定单元,用于若所述安全座椅上的重量大于预设的重量阈值,则判定所述儿童安全检测条目检测通过;
第二判定单元,用于若所述安全座椅上的重量小于或等于所述重量阈值,则判定所述儿童安全检测条目检测不通过。
进一步地,所述儿童人脸图像检测单元可以包括:
特征向量提取子单元,用于提取所述车辆内的第n个人脸特征向量;
样本集选取子单元,用于从预设的历史样本库中分别选取成人样本集以及儿童样本集;
平均距离计算子单元,用于分别计算所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离;
儿童人脸图像检测子单元,用于确定所述车辆内的第n个人脸图像是否为儿童人脸图像。
进一步地,所述车辆检测条目执行模块还可以包括:
人脸图像总数统计单元,用于通过所述摄像头采集所述车辆内的各个人脸图像,并统计所述车辆内的人脸图像总数;
第三判定单元,用于若所述车辆内的人脸图像总数大于预设的人数阈值,则判定所述超载检测条目检测不通过;
第四判定单元,用于若所述车辆内的人脸图像总数小于或等于所述人数阈值,则 判定所述超载检测条目检测通过。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的装置,模块和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述或记载的部分,可以参见其它实施例的相关描述。
图5示出了本申请实施例提供的一种终端设备的示意框图,为了便于说明,仅示出了与本申请实施例相关的部分。
在本实施例中,所述终端设备5可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。该终端设备5可包括:处理器50、存储器51以及存储在所述存储器51中并可在所述处理器50上运行的计算机可读指令52,例如执行上述的基于人脸识别的车辆启动方法的计算机可读指令。所述处理器50执行所述计算机可读指令52时实现上述各个基于人脸识别的车辆启动方法实施例中的步骤。
示例性的,所述计算机可读指令52可以被分割成一个或多个模块/单元,所述一个或者多个模块/单元被存储在所述存储器51中,并由所述处理器50执行,以完成本申请。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机可读指令段,该指令段用于描述所述计算机可读指令52在所述终端设备5中的执行过程。
所述处理器50可以是中央处理单元(Central Processing Unit,CPU),还可以是其它通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field-Programmable Gate Array,FPGA)或者其它可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
所述存储器51可以是所述终端设备5的内部存储单元,例如终端设备5的硬盘或内存。所述存储器51也可以是所述终端设备5的外部存储设备,例如所述终端设备5上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,所述存储器51还可以既包括所述终端设备5的内部存储单元也包括外部存储设备。所述存储器51用于存储所述计算机可读指令以及所述终端设备5所需的其它指令和数据。所述存储器51还可以用于暂时地存储已经输出或者将要输出的数据。
在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时, 可以存储在一个计算机非易失性可读存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干计算机可读指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储计算机可读指令的介质。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,是可以通过计算机可读指令来指令相关的硬件来完成,所述的计算机可读指令可存储于一计算机非易失性可读取存储介质中,该计算机可读指令在执行时,可包括如上述各方法的实施例的流程。其中,本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用,均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限,RAM以多种形式可得,诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
以上所述实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。
Claims (20)
- 一种基于人脸识别的车辆启动方法,其特征在于,包括:通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别;若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项;按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果;若各条车辆检测条目的检测结果均满足预设的车辆启动条件,则启动所述车辆。
- 根据权利要求1所述的车辆启动方法,其特征在于,所述车辆检测配置文件的设置过程包括:获取所述车辆的检测模式;若所述车辆的检测模式为选择检测模式,则将预设的全局车辆检测条目集合中的各条车辆检测条目在预设的显示区域进行显示,所述全局车辆检测条目集合为车辆检测条目的全集;接收所述驾驶员通过预设的用户交互界面对所述全局车辆检测条目集合中的各条车辆检测条目的选择,并将被选中的车辆检测条目添加入所述车辆检测配置文件中;若所述车辆的检测模式为默认检测模式,则将所述全局车辆检测条目集合中的各条车辆检测条目均添加入所述车辆检测配置文件中。
- 根据权利要求1所述的车辆启动方法,其特征在于,还包括:若所述车辆检测配置文件中包括儿童安全检测条目,则所述执行所述车辆检测配置文件中的各条车辆检测条目包括:通过所述摄像头采集所述车辆内的各个人脸图像;分别检测所述车辆内的各个人脸图像是否为儿童人脸图像;若在所述车辆内的各个人脸图像中检测到儿童人脸图像,则通过预设的重量传感器采集预设的安全座椅上的重量,所述重量传感器设置在所述安全座椅内部;若所述安全座椅上的重量大于预设的重量阈值,则判定所述儿童安全检测条目检测通过;若所述安全座椅上的重量小于或等于所述重量阈值,则判定所述儿童安全检测条目检测不通过。
- 根据权利要求3所述的车辆启动方法,其特征在于,分别检测所述车辆内的各 个人脸图像是否为儿童人脸图像包括:提取所述车辆内的第n个人脸特征向量,记为:FaceVec=(FaceElm 1,FaceElm 2,...,FaceElm gn,...,FaceElm GN)其中,每个人脸特征向量均对应于所述车辆内的一个人脸图像,gn为人脸特征向量的维度序号,1≤gn≤GN,GN为人脸特征向量的维度总数,FaceElm gn为所述车辆内的第n个人脸特征向量在第gn个维度上的取值,FaceVec为所述车辆内的第n个人脸特征向量;从预设的历史样本库中分别选取成人样本集以及儿童样本集,其中,所述成人样本集中的各个成人样本的人脸特征向量记为:AdultVec m=(AdultElm m,1,AdultElm m,2,...,AdultElm m,gn,...,AdultElm m,GN)m为成人样本的序号,1≤m≤AdultNum,AdultNum为成人样本的总数,AdultElm m,gn为第m个成人样本的人脸特征向量在第gn个维度上的取值,AdultVec m为第m个成人样本的人脸特征向量;所述儿童样本集中的各个儿童样本的人脸特征向量记为:BabyVec f=(BabyElm f,1,BabyElm f,2,...,BabyElm f,gn,...,BabyElm f,GN)f为儿童样本的序号,1≤f≤BabyNum,BabyNum为儿童样本的总数,BabyElm f,gn为第f个儿童样本的人脸特征向量在第gn个维度上的取值,BabyVec f为第f个儿童样本的人脸特征向量;根据下式分别计算所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离:其中,AdultDis为所述车辆内的第n个人脸特征向量与所述成人样本集之间的平均距离,BabyDis为所述车辆内的第n个人脸特征向量与所述儿童样本集之间的平均距离;根据所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离确定所述车辆内的第n个人脸图像是否为儿童人脸图像。
- 根据权利要求1至4中任一项所述的车辆启动方法,其特征在于,还包括:若所述车辆检测配置文件中包括超载检测条目,则所述执行所述车辆检测配置文件中的各条车辆检测条目包括:通过所述摄像头采集所述车辆内的各个人脸图像,并统计所述车辆内的人脸图像总数;若所述车辆内的人脸图像总数大于预设的人数阈值,则判定所述超载检测条目检测不通过;若所述车辆内的人脸图像总数小于或等于所述人数阈值,则判定所述超载检测条目检测通过。
- 一种车辆启动装置,其特征在于,包括:人脸识别模块,用于通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别;车辆检测条目提取模块,用于若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项;车辆检测条目执行模块,用于按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果;车辆启动模块,用于若各条车辆检测条目的检测结果均满足预设的车辆启动条件,则启动所述车辆。
- 根据权利要求6所述的车辆启动装置,其特征在于,所述车辆启动装置还包括:检测模式获取模块,用于获取所述车辆的检测模式;车辆检测条目显示模块,用于若所述车辆的检测模式为选择检测模式,则将预设的全局车辆检测条目集合中的各条车辆检测条目在预设的显示区域进行显示,所述全局车辆检测条目集合为车辆检测条目的全集;选择接收模块,用于接收所述驾驶员通过预设的用户交互界面对所述全局车辆检测条目集合中的各条车辆检测条目的选择,并将被选中的车辆检测条目添加入所述车辆检测配置文件中;车辆检测条目添加模块,用于若所述车辆的检测模式为默认检测模式,则将所述全局车辆检测条目集合中的各条车辆检测条目均添加入所述车辆检测配置文件中。
- 根据权利要求6所述的车辆启动装置,其特征在于,所述车辆检测条目执行模块可以包括:人脸图像采集单元,用于通过所述摄像头采集所述车辆内的各个人脸图像;儿童人脸图像检测单元,用于分别检测所述车辆内的各个人脸图像是否为儿童人脸图像;重量采集单元,用于若在所述车辆内的各个人脸图像中检测到儿童人脸图像,则 通过预设的重量传感器采集预设的安全座椅上的重量,所述重量传感器设置在所述安全座椅内部;第一判定单元,用于若所述安全座椅上的重量大于预设的重量阈值,则判定所述儿童安全检测条目检测通过;第二判定单元,用于若所述安全座椅上的重量小于或等于所述重量阈值,则判定所述儿童安全检测条目检测不通过。
- 根据权利要求8所述的车辆启动装置,其特征在于,所述儿童人脸图像检测单元包括:特征向量提取子单元,用于提取所述车辆内的第n个人脸特征向量,记为:FaceVec=(FaceElm 1,FaceElm 2,...,FaceElm gn,...,FaceElm GN)其中,每个人脸特征向量均对应于所述车辆内的一个人脸图像,gn为人脸特征向量的维度序号,1≤gn≤GN,GN为人脸特征向量的维度总数,FaceElm gn为所述车辆内的第n个人脸特征向量在第gn个维度上的取值,FaceVec为所述车辆内的第n个人脸特征向量;样本集选取子单元,用于从预设的历史样本库中分别选取成人样本集以及儿童样本集,其中,所述成人样本集中的各个成人样本的人脸特征向量记为:AdultVec m=(AdultElm m,1,AdultElm m,2,...,AdultElm m,gn,...,AdultElm m,GN)m为成人样本的序号,1≤m≤AdultNum,AdultNum为成人样本的总数,AdultElm m,gn为第m个成人样本的人脸特征向量在第gn个维度上的取值,AdultVec m为第m个成人样本的人脸特征向量;所述儿童样本集中的各个儿童样本的人脸特征向量记为:BabyVec f=(BabyElm f,1,BabyElm f,2,...,BabyElm f,gn,...,BabyElm f,GN)f为儿童样本的序号,1≤f≤BabyNum,BabyNum为儿童样本的总数,BabyElm f,gn为第f个儿童样本的人脸特征向量在第gn个维度上的取值,BabyVec f为第f个儿童样本的人脸特征向量;平均距离计算子单元,用于根据下式分别计算所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离:其中,AdultDis为所述车辆内的第n个人脸特征向量与所述成人样本集之间的平 均距离,BabyDis为所述车辆内的第n个人脸特征向量与所述儿童样本集之间的平均距离;儿童人脸图像检测子单元,用于根据所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离确定所述车辆内的第n个人脸图像是否为儿童人脸图像。
- 根据权利要求6至9中任一项所述的车辆启动装置,其特征在于,所述车辆检测条目执行模块还可以包括:人脸图像总数统计单元,用于通过所述摄像头采集所述车辆内的各个人脸图像,并统计所述车辆内的人脸图像总数;第三判定单元,用于若所述车辆内的人脸图像总数大于预设的人数阈值,则判定超载检测条目检测不通过;第四判定单元,用于若所述车辆内的人脸图像总数小于或等于所述人数阈值,则判定所述超载检测条目检测通过。
- 一种计算机非易失性可读存储介质,所述计算机非易失性可读存储介质存储有计算机可读指令,其特征在于,所述计算机可读指令被处理器执行时实现如下步骤:通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别;若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项;按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果;若各条车辆检测条目的检测结果均满足预设的车辆启动条件,则启动所述车辆。
- 根据权利要求11所述的计算机非易失性可读存储介质,其特征在于,所述车辆检测配置文件的设置过程包括:获取所述车辆的检测模式;若所述车辆的检测模式为选择检测模式,则将预设的全局车辆检测条目集合中的各条车辆检测条目在预设的显示区域进行显示,所述全局车辆检测条目集合为车辆检测条目的全集;接收所述驾驶员通过预设的用户交互界面对所述全局车辆检测条目集合中的各条车辆检测条目的选择,并将被选中的车辆检测条目添加入所述车辆检测配置文件中;若所述车辆的检测模式为默认检测模式,则将所述全局车辆检测条目集合中的各 条车辆检测条目均添加入所述车辆检测配置文件中。
- 根据权利要求11所述的计算机非易失性可读存储介质,其特征在于,还包括:若所述车辆检测配置文件中包括儿童安全检测条目,则所述执行所述车辆检测配置文件中的各条车辆检测条目包括:通过所述摄像头采集所述车辆内的各个人脸图像;分别检测所述车辆内的各个人脸图像是否为儿童人脸图像;若在所述车辆内的各个人脸图像中检测到儿童人脸图像,则通过预设的重量传感器采集预设的安全座椅上的重量,所述重量传感器设置在所述安全座椅内部;若所述安全座椅上的重量大于预设的重量阈值,则判定所述儿童安全检测条目检测通过;若所述安全座椅上的重量小于或等于所述重量阈值,则判定所述儿童安全检测条目检测不通过。
- 根据权利要求13所述的计算机非易失性可读存储介质,其特征在于,分别检测所述车辆内的各个人脸图像是否为儿童人脸图像包括:提取所述车辆内的第n个人脸特征向量,记为:FaceVec=(FaceElm 1,FaceElm 2,...,FaceElm gn,...,FaceElm GN)其中,每个人脸特征向量均对应于所述车辆内的一个人脸图像,gn为人脸特征向量的维度序号,1≤gn≤GN,GN为人脸特征向量的维度总数,FaceElm gn为所述车辆内的第n个人脸特征向量在第gn个维度上的取值,FaceVec为所述车辆内的第n个人脸特征向量;从预设的历史样本库中分别选取成人样本集以及儿童样本集,其中,所述成人样本集中的各个成人样本的人脸特征向量记为:AdultVec m=(AdultElm m,1,AdultElm m,2,...,AdultElm m,gn,...,AdultElm m,GN)m为成人样本的序号,1≤m≤AdultNum,AdultNum为成人样本的总数,AdultElm m,gn为第m个成人样本的人脸特征向量在第gn个维度上的取值,AdultVec m为第m个成人样本的人脸特征向量;所述儿童样本集中的各个儿童样本的人脸特征向量记为:BabyVec f=(BabyElm f,1,BabyElm f,2,...,BabyElm f,gn,...,BabyElm f,GN)f为儿童样本的序号,1≤f≤BabyNum,BabyNum为儿童样本的总数,BabyElm f,gn为第f个儿童样本的人脸特征向量在第gn个维度上的取值,BabyVec f为第f个儿童样本的人脸特征向量;根据下式分别计算所述车辆内的第n个人脸特征向量与所述成人样本集以及所述 儿童样本集之间的平均距离:其中,AdultDis为所述车辆内的第n个人脸特征向量与所述成人样本集之间的平均距离,BabyDis为所述车辆内的第n个人脸特征向量与所述儿童样本集之间的平均距离;根据所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离确定所述车辆内的第n个人脸图像是否为儿童人脸图像。
- 根据权利要求11至14中任一项所述的计算机非易失性可读存储介质,其特征在于,还包括:若所述车辆检测配置文件中包括超载检测条目,则所述执行所述车辆检测配置文件中的各条车辆检测条目包括:通过所述摄像头采集所述车辆内的各个人脸图像,并统计所述车辆内的人脸图像总数;若所述车辆内的人脸图像总数大于预设的人数阈值,则判定所述超载检测条目检测不通过;若所述车辆内的人脸图像总数小于或等于所述人数阈值,则判定所述超载检测条目检测通过。
- 一种终端设备,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令,其特征在于,所述处理器执行所述计算机可读指令时实现如下步骤:通过设置在车辆内的摄像头采集驾驶员的人脸图像,并对所述人脸图像进行人脸识别;若人脸识别成功,则从预设的数据库中调取车辆检测配置文件,并从所述车辆检测配置文件中提取各条车辆检测条目,每条车辆检测条目均对应于一项车辆启动前的安全事项;按照预设的检测顺序对所述车辆依次执行所述车辆检测配置文件中的各条车辆检测条目,并记录各条车辆检测条目的检测结果;若各条车辆检测条目的检测结果均满足预设的车辆启动条件,则启动所述车辆。
- 根据权利要求16所述的终端设备,其特征在于,所述车辆检测配置文件的设 置过程包括:获取所述车辆的检测模式;若所述车辆的检测模式为选择检测模式,则将预设的全局车辆检测条目集合中的各条车辆检测条目在预设的显示区域进行显示,所述全局车辆检测条目集合为车辆检测条目的全集;接收所述驾驶员通过预设的用户交互界面对所述全局车辆检测条目集合中的各条车辆检测条目的选择,并将被选中的车辆检测条目添加入所述车辆检测配置文件中;若所述车辆的检测模式为默认检测模式,则将所述全局车辆检测条目集合中的各条车辆检测条目均添加入所述车辆检测配置文件中。
- 根据权利要求16所述的终端设备,其特征在于,还包括:若所述车辆检测配置文件中包括儿童安全检测条目,则所述执行所述车辆检测配置文件中的各条车辆检测条目包括:通过所述摄像头采集所述车辆内的各个人脸图像;分别检测所述车辆内的各个人脸图像是否为儿童人脸图像;若在所述车辆内的各个人脸图像中检测到儿童人脸图像,则通过预设的重量传感器采集预设的安全座椅上的重量,所述重量传感器设置在所述安全座椅内部;若所述安全座椅上的重量大于预设的重量阈值,则判定所述儿童安全检测条目检测通过;若所述安全座椅上的重量小于或等于所述重量阈值,则判定所述儿童安全检测条目检测不通过。
- 根据权利要求18所述的终端设备,其特征在于,分别检测所述车辆内的各个人脸图像是否为儿童人脸图像包括:提取所述车辆内的第n个人脸特征向量,记为:FaceVec=(FaceElm 1,FaceElm 2,...,FaceElm gn,...,FaceElm GN)其中,每个人脸特征向量均对应于所述车辆内的一个人脸图像,gn为人脸特征向量的维度序号,1≤gn≤GN,GN为人脸特征向量的维度总数,FaceElm gn为所述车辆内的第n个人脸特征向量在第gn个维度上的取值,FaceVec为所述车辆内的第n个人脸特征向量;从预设的历史样本库中分别选取成人样本集以及儿童样本集,其中,所述成人样本集中的各个成人样本的人脸特征向量记为:AdultVec m=(AdultElm m,1,AdultElm m,2,...,AdultElm m,gn,...,AdultElm m,GN)m为成人样本的序号,1≤m≤AdultNum,AdultNum为成人样本的总数, AdultElm m,gn为第m个成人样本的人脸特征向量在第gn个维度上的取值,AdultVec m为第m个成人样本的人脸特征向量;所述儿童样本集中的各个儿童样本的人脸特征向量记为:BabyVec f=(BabyElm f,1,BabyElm f,2,...,BabyElm f,gn,...,BabyElm f,GN)f为儿童样本的序号,1≤f≤BabyNum,BabyNum为儿童样本的总数,BabyElm f,gn为第f个儿童样本的人脸特征向量在第gn个维度上的取值,BabyVec f为第f个儿童样本的人脸特征向量;根据下式分别计算所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离:其中,AdultDis为所述车辆内的第n个人脸特征向量与所述成人样本集之间的平均距离,BabyDis为所述车辆内的第n个人脸特征向量与所述儿童样本集之间的平均距离;根据所述车辆内的第n个人脸特征向量与所述成人样本集以及所述儿童样本集之间的平均距离确定所述车辆内的第n个人脸图像是否为儿童人脸图像。
- 根据权利要求16至19中任一项所述的终端设备,其特征在于,还包括:若所述车辆检测配置文件中包括超载检测条目,则所述执行所述车辆检测配置文件中的各条车辆检测条目包括:通过所述摄像头采集所述车辆内的各个人脸图像,并统计所述车辆内的人脸图像总数;若所述车辆内的人脸图像总数大于预设的人数阈值,则判定所述超载检测条目检测不通过;若所述车辆内的人脸图像总数小于或等于所述人数阈值,则判定所述超载检测条目检测通过。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910184439.7 | 2019-03-12 | ||
| CN201910184439.7A CN110065471A (zh) | 2019-03-12 | 2019-03-12 | 基于人脸识别的车辆启动方法、装置、介质及终端设备 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020181801A1 true WO2020181801A1 (zh) | 2020-09-17 |
Family
ID=67366188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/116641 Ceased WO2020181801A1 (zh) | 2019-03-12 | 2019-11-08 | 基于人脸识别的车辆启动方法、装置、介质及终端设备 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110065471A (zh) |
| WO (1) | WO2020181801A1 (zh) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110065471A (zh) * | 2019-03-12 | 2019-07-30 | 平安科技(深圳)有限公司 | 基于人脸识别的车辆启动方法、装置、介质及终端设备 |
| CN110588562A (zh) * | 2019-09-27 | 2019-12-20 | 深圳市元征科技股份有限公司 | 一种儿童安全乘车提醒方法、装置、车载设备及存储介质 |
| CN112937435B (zh) * | 2019-12-11 | 2022-11-25 | 博泰车联网科技(上海)股份有限公司 | 一种关闭车辆启动系统的提醒装置及具有其的车辆 |
| CN111038446B (zh) * | 2019-12-26 | 2021-11-19 | 深圳市德塔防爆电动汽车有限公司 | 一种防爆汽车启动方法及系统 |
| CN114844764B (zh) * | 2021-01-30 | 2023-12-08 | 华为技术有限公司 | 一种网络安全功能检测的方法及相关设备 |
| CN113246908A (zh) * | 2021-04-22 | 2021-08-13 | 新疆爱华盈通信息技术有限公司 | 一种车辆启动方法及计算机设备 |
| CN116714546B (zh) * | 2023-06-02 | 2026-01-30 | 长城汽车股份有限公司 | 一种安全提示方法、系统、电子设备及车辆 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009227098A (ja) * | 2008-03-24 | 2009-10-08 | Tcm Corp | 作業車両 |
| CN104859448A (zh) * | 2015-04-16 | 2015-08-26 | 深圳市华宝电子科技有限公司 | 一种客车超载监控系统及其监控方法 |
| CN105150846A (zh) * | 2015-09-29 | 2015-12-16 | 武汉理工大学 | 一种汽车安全启动系统及其方法 |
| US20160280230A1 (en) * | 2015-03-26 | 2016-09-29 | Mitac International Corp. | Detecting method and detecting system for performing a driving safety evaluation, and an in-vehicle computer and a wearable device included in the detecting system |
| CN108108663A (zh) * | 2017-11-29 | 2018-06-01 | 安徽四创电子股份有限公司 | 一种视频人脸识别系统与方法 |
| CN108394374A (zh) * | 2018-04-26 | 2018-08-14 | 奇瑞汽车股份有限公司 | 乘车保护方法、装置及计算机可读存储介质 |
| CN108437933A (zh) * | 2018-02-10 | 2018-08-24 | 深圳智达机械技术有限公司 | 一种汽车启动系统 |
| CN109327735A (zh) * | 2018-09-07 | 2019-02-12 | 惠科股份有限公司 | 显示方法及显示装置 |
| CN110065471A (zh) * | 2019-03-12 | 2019-07-30 | 平安科技(深圳)有限公司 | 基于人脸识别的车辆启动方法、装置、介质及终端设备 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103043003B (zh) * | 2012-12-24 | 2016-02-03 | 朱佩芬 | 车载儿童安全保障系统 |
| CN103434484B (zh) * | 2013-08-20 | 2016-04-27 | 安科智慧城市技术(中国)有限公司 | 车载识别认证装置、移动终端、智能车钥控制系统及方法 |
| CN105083218B (zh) * | 2015-07-16 | 2018-10-19 | 浙江吉利汽车研究院有限公司 | 车辆启动方法 |
| CN105774708B (zh) * | 2016-03-22 | 2018-03-02 | 重庆长安汽车股份有限公司 | 一种基于随身智能设备的汽车个性化设置系统及方法 |
| CN107244306A (zh) * | 2017-07-27 | 2017-10-13 | 深圳小爱智能科技有限公司 | 一种启动汽车的装置 |
| CN108068761A (zh) * | 2017-12-20 | 2018-05-25 | 申娟 | 一种无钥匙启动方法及装置 |
| CN108545039B (zh) * | 2018-04-11 | 2021-07-06 | 航天科技控股集团股份有限公司 | 基于汽车仪表can总线信号的行车信息自动检测系统及检测方法 |
-
2019
- 2019-03-12 CN CN201910184439.7A patent/CN110065471A/zh active Pending
- 2019-11-08 WO PCT/CN2019/116641 patent/WO2020181801A1/zh not_active Ceased
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009227098A (ja) * | 2008-03-24 | 2009-10-08 | Tcm Corp | 作業車両 |
| US20160280230A1 (en) * | 2015-03-26 | 2016-09-29 | Mitac International Corp. | Detecting method and detecting system for performing a driving safety evaluation, and an in-vehicle computer and a wearable device included in the detecting system |
| CN104859448A (zh) * | 2015-04-16 | 2015-08-26 | 深圳市华宝电子科技有限公司 | 一种客车超载监控系统及其监控方法 |
| CN105150846A (zh) * | 2015-09-29 | 2015-12-16 | 武汉理工大学 | 一种汽车安全启动系统及其方法 |
| CN108108663A (zh) * | 2017-11-29 | 2018-06-01 | 安徽四创电子股份有限公司 | 一种视频人脸识别系统与方法 |
| CN108437933A (zh) * | 2018-02-10 | 2018-08-24 | 深圳智达机械技术有限公司 | 一种汽车启动系统 |
| CN108394374A (zh) * | 2018-04-26 | 2018-08-14 | 奇瑞汽车股份有限公司 | 乘车保护方法、装置及计算机可读存储介质 |
| CN109327735A (zh) * | 2018-09-07 | 2019-02-12 | 惠科股份有限公司 | 显示方法及显示装置 |
| CN110065471A (zh) * | 2019-03-12 | 2019-07-30 | 平安科技(深圳)有限公司 | 基于人脸识别的车辆启动方法、装置、介质及终端设备 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110065471A (zh) | 2019-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020181801A1 (zh) | 基于人脸识别的车辆启动方法、装置、介质及终端设备 | |
| CN110020592B (zh) | 物体检测模型训练方法、装置、计算机设备及存储介质 | |
| US11259718B1 (en) | Systems and methods for automated body mass index calculation to determine value | |
| US10056096B2 (en) | Electronic device and method capable of voice recognition | |
| EP3028184B1 (en) | Method and system for searching images | |
| US9917848B2 (en) | Method and system for identifying a human or machine | |
| WO2019200782A1 (zh) | 样本数据分类方法、模型训练方法、电子设备及存储介质 | |
| CN110717407B (zh) | 基于唇语密码的人脸识别方法、装置及存储介质 | |
| CN107958230B (zh) | 人脸表情识别方法及装置 | |
| US10748217B1 (en) | Systems and methods for automated body mass index calculation | |
| WO2019062721A1 (zh) | 语音身份特征提取器、分类器训练方法及相关设备 | |
| US20110194779A1 (en) | Apparatus and method for detecting multi-view specific object | |
| WO2019184518A1 (zh) | 一种音频检索识别方法及装置 | |
| CN109817339B (zh) | 基于大数据的患者分组方法和装置 | |
| CN109910819B (zh) | 一种车内环境设置方法、装置、可读存储介质及终端设备 | |
| US20170004378A1 (en) | Method and system for preprocessing images | |
| US9824313B2 (en) | Filtering content in an online system based on text and image signals extracted from the content | |
| CN110555346A (zh) | 驾驶员情绪检测方法、装置、电子设备及存储介质 | |
| CN115053300A (zh) | 从受试者声音诊断呼吸疾病 | |
| CN112508062B (zh) | 一种开集数据的分类方法、装置、设备及存储介质 | |
| CN106056083A (zh) | 一种信息处理方法及终端 | |
| KR20210089340A (ko) | 문서 내 텍스트를 분류하는 방법 및 장치 | |
| JP2013117861A (ja) | 学習装置、学習方法およびプログラム | |
| WO2019218482A1 (zh) | 基于大数据的人群筛选方法、装置、终端设备及可读存储介质 | |
| Amid et al. | Unsupervised feature extraction for multimedia event detection and ranking using audio content |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19918770 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19918770 Country of ref document: EP Kind code of ref document: A1 |









