WO2021082194A1 - 用于车辆安全的管理方法、装置和计算机存储介质 - Google Patents

用于车辆安全的管理方法、装置和计算机存储介质 Download PDF

Info

Publication number
WO2021082194A1
WO2021082194A1 PCT/CN2019/124107 CN2019124107W WO2021082194A1 WO 2021082194 A1 WO2021082194 A1 WO 2021082194A1 CN 2019124107 W CN2019124107 W CN 2019124107W WO 2021082194 A1 WO2021082194 A1 WO 2021082194A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
data
image
environmental
warning
Prior art date
Application number
PCT/CN2019/124107
Other languages
English (en)
French (fr)
Inventor
时红仁
Original Assignee
上海博泰悦臻电子设备制造有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 上海博泰悦臻电子设备制造有限公司 filed Critical 上海博泰悦臻电子设备制造有限公司
Priority to US17/773,299 priority Critical patent/US20240157958A1/en
Priority to EP19950670.0A priority patent/EP4036890A4/en
Publication of WO2021082194A1 publication Critical patent/WO2021082194A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • 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
    • B60K35/00—Instruments specially adapted for vehicles; Arrangement of instruments in or on vehicles
    • B60K35/20—Output arrangements, i.e. from vehicle to user, associated with vehicle functions or specially adapted therefor
    • B60K35/28—Output arrangements, i.e. from vehicle to user, associated with vehicle functions or specially adapted therefor characterised by the type of the output information, e.g. video entertainment or vehicle dynamics information; characterised by the purpose of the output information, e.g. for attracting the attention of the driver
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • 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
    • B60K2360/00—Indexing scheme associated with groups B60K35/00 or B60K37/00 relating to details of instruments or dashboards
    • B60K2360/11—Instrument graphical user interfaces or menu aspects
    • B60K2360/119—Icons
    • 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
    • B60K2360/00—Indexing scheme associated with groups B60K35/00 or B60K37/00 relating to details of instruments or dashboards
    • B60K2360/16—Type of output information
    • B60K2360/166—Navigation
    • 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
    • B60K2360/00—Indexing scheme associated with groups B60K35/00 or B60K37/00 relating to details of instruments or dashboards
    • B60K2360/16—Type of output information
    • B60K2360/178—Warnings
    • 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
    • B60K2360/00—Indexing scheme associated with groups B60K35/00 or B60K37/00 relating to details of instruments or dashboards
    • B60K2360/55—Remote control arrangements
    • B60K2360/56—Remote control arrangements using mobile devices
    • B60K2360/577—Mirror link with mobile devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B60W2050/146—Display means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
    • B60W2555/20—Ambient conditions, e.g. wind or rain
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/10—Historical data

Definitions

  • the present disclosure generally relates to vehicle insurance and safety, and in particular, to management methods, devices, and computer storage media for vehicle safety.
  • the owner usually purchases insurance (such as auto insurance) in advance.
  • the purchased insurance generally has a certain validity period, and the coverage of the purchased auto insurance may not cover the vehicle due to sudden bad weather.
  • the risks to the safety of vehicles and personnel For example, in the face of sudden heavy rain, many vehicles driving or stored outside are easily submerged by standing water, resulting in varying degrees of loss. If the car owner only purchases car damage insurance and does not choose engine water damage insurance on the basis of car damage insurance, then the car owner may not be able to obtain corresponding compensation for the direct damage of the engine caused by the water entering the engine.
  • the validity period of the car insurance has expired, when severe weather occurs suddenly, even if the car owner anticipates the safety hazards faced by the vehicle and the driver and passengers of the vehicle, there is no way to purchase the insurance in time.
  • the present disclosure provides a management method, device, and computer storage medium method and equipment for vehicle safety, which can provide matching and timely warnings and safety guarantees for vehicles and vehicle personnel in sudden bad weather.
  • a management method for vehicle safety includes: acquiring at least one of meteorological data and environmental data, the environmental data being collected via on-board equipment at the vehicle; determining a warning weather type based on at least one of the meteorological data and environmental data; and in response to determining that the warning weather type conforms to Predetermined warning conditions, based on at least one of weather data and environmental data, and vehicle driving data, determine auto insurance data matching the vehicle; and present at least one of the mobile device and the vehicle’s on-board display screen that is associated with the auto insurance data
  • the mobile device is associated with the vehicle via the detection of a predetermined action on the mobile device.
  • an apparatus for managing vehicle safety includes: a memory configured to store one or more computer programs; and a processor coupled to the memory and configured to execute One or more programs cause the device to perform the method of the first aspect of the present disclosure.
  • non-transitory computer-readable storage medium stores machine-executable instructions, and when executed, the machine-executable instructions cause the machine to perform the method of the first aspect of the present disclosure.
  • the environmental data includes at least one of the following: environmental video data collected via a camera device of the vehicle, the environmental video data includes at least vehicle window image data and external environmental image data of the vehicle; via a humidity sensor of the vehicle Detected environmental humidity data; environmental air volume data detected by the vehicle’s air volume sensor; and rain volume data detected by the vehicle’s wiper sensor; environmental temperature data detected by the vehicle’s temperature sensor.
  • the environmental video data of the vehicle is acquired through the streaming media rearview mirror of the vehicle.
  • the environmental video data includes at least the vehicle window image data and the external environment image data of the vehicle, and the streaming media rearview mirror and multiple vehicles The camera device is connected.
  • the identification associated with the auto insurance data includes an operable icon for indicating an auto insurance type matching the vehicle.
  • the method further includes: in response to detecting an operation on the operable icon, obtaining personal information of the user associated with the mobile device; and generating an association with the auto insurance data based on the obtained personal information and auto insurance data Order data; send order data to cloud server via mobile device.
  • the method further includes: in response to detecting an operation on the operable icon, sending order data associated with the auto insurance data to a cloud server via the mobile device.
  • the method further includes: at the mobile device, in response to confirming that the distance of the mobile device from the vehicle is less than a predetermined value, acquiring environmental data and meteorological data for determining the warning weather type.
  • determining the warning weather type further includes: generating environmental image noise data based on the environmental image data of the vehicle; and determining whether the warning weather type indicates one of heavy rain, heavy snow, or hail based on the probability distribution of the environmental image noise data.
  • determining the warning weather type includes: generating a high-frequency image based on at least one of image data of the window image data and image data of the external environment of the vehicle, the high-frequency image including the high-frequency information in the at least one image data .
  • determining the warning weather type further includes: determining the ground image area at the rear of the vehicle based on the image data of the external environment of the vehicle; extracting image features of the ground image area at the rear of the vehicle; and determining the rear of the vehicle based on the extracted image features Whether there is one of snow and water in the ground image area; in response to determining that there is one of snow and water in the ground image area at the rear of the vehicle, based on the high-frequency image, and the environmental temperature data and the environmental humidity data At least one of the items to determine the warning weather type.
  • determining the warning weather type includes: selecting multiple sets of environmental image sequences in the environmental video data; determining background objects in the environmental image sequences based on the multiple sets of environmental image sequences; and determining that in response to at least one of the following conditions being met, determining Whether the warning weather type indicates low visibility: the edge strength of the background object is lower than the first predetermined threshold; the image sharpness of the background object is lower than the second predetermined threshold, the first predetermined threshold and the second predetermined threshold are based on the association with the background object And the speed at which the background object disappears in the environmental image sequence is higher than a third predetermined threshold, which is determined based on the historical image data associated with the background object and the driving speed of the vehicle.
  • the method further includes: in response to confirming that the warning weather type indicates heavy rain, determining whether there is a wading warning area in the path from the current location to the destination, the wading warning area being based on geographic features and roads associated with the path At least one of the attributes and historical data; and in response to determining that there is a wading warning area in the path, at least one of the on-board display screens of the mobile device and the vehicle is displayed for identifying the distance between the current location and the destination. Information about the path to be selected.
  • the method further includes: in response to detecting an operation on the path to be selected; determining the expected time to reach the destination via the path to be selected based on the navigation information and traffic information received by the mobile device; and The expected time is displayed in at least one of the on-board display screens of the vehicle.
  • determining that the warning weather type meets the predetermined warning condition includes at least one of the following: in response to determining that the warning weather type is indicated as at least one of low visibility, heavy snow, heavy rain, lightning, hail, and freezing, determining the warning weather type The predetermined warning condition is met, and the low visibility includes at least one of haze and sandstorm; and in response to determining that the current warning weather type changes relative to the warning weather type in the past predetermined time interval, the first predetermined condition is met.
  • FIG. 1 shows a schematic diagram of a system 100 for a management method of vehicle safety according to an embodiment of the present disclosure
  • FIG. 2 shows a flowchart of a management method 200 for vehicle safety according to an embodiment of the present disclosure
  • FIG. 3 shows a flowchart of a method 300 for generating an insurance order according to an embodiment of the present disclosure
  • FIG. 4 shows a flowchart of a method 400 for determining the type of warning weather according to an embodiment of the present disclosure
  • FIG. 5 shows a flowchart of a method 500 for determining the type of warning weather according to an embodiment of the present disclosure
  • FIG. 6 shows an overall schematic diagram of a method 600 for identifying warning weather types according to an embodiment of the present disclosure
  • FIG. 7 shows a schematic diagram of a process 700 for extracting high-frequency features according to an embodiment of the present disclosure
  • FIG. 8 shows a schematic diagram of an up-sampling process 800 according to an embodiment of the present disclosure
  • FIG. 9 shows a schematic diagram of a method 900 for determining a warning weather type according to an embodiment of the present disclosure.
  • FIG. 10 schematically shows a block diagram of an electronic device 1000 suitable for implementing embodiments of the present disclosure.
  • a user for example, a car owner
  • purchases a vehicle insurance with a certain validity period in advance it may be due to the coverage of the purchased insurance and the sudden bad weather of the vehicle.
  • the situation does not match, the validity period of the purchased insurance has expired, etc., and it is impossible to provide matching and timely warnings and safety guarantees to vehicles and personnel on the vehicles that suddenly experience bad weather.
  • example embodiments of the present disclosure propose a management solution for vehicle safety.
  • at least one of meteorological data and environmental data is acquired, and the environmental data is collected via on-board equipment at the vehicle; based on at least one of the meteorological data and environmental data, the warning weather type is determined; in response to the determination of the warning weather type Meet the predetermined warning conditions, determine the auto insurance data matching the vehicle based on at least one of weather data and environmental data and the driving data of the vehicle; and present the relevant auto insurance data in at least one of the mobile device and the on-board display screen of the vehicle
  • the mobile device is associated with the vehicle via detection of a predetermined action on the mobile device.
  • FIG. 1 shows a schematic diagram of a system 100 for a management method of vehicle safety according to an embodiment of the present disclosure.
  • the system 100 includes a vehicle 110, a mobile device 120 and a cloud server 130.
  • the mobile device 120 and the server 130 are connected through a network 140.
  • the system 100 further includes a road side unit (RSU, Road Side Unit, not shown) and the like.
  • RSU Road Side Unit
  • the vehicle 110 it at least includes: a vehicle machine, a vehicle-mounted data sensing device, and a vehicle-mounted T-BOX.
  • On-board data sensing equipment is used to perceive the vehicle's own data and the external environment data where the vehicle is located in real time.
  • the vehicle-mounted T-BOX it is used for data interaction between the vehicle, the mobile device 120, the roadside unit, and the cloud server 130.
  • the vehicle-mounted T-BOX includes, for example, a SIM card, GPS antenna, 4G or 5G antenna, and so on.
  • the application APP
  • the TSP background will send a monitoring request command to the vehicle T-BOX, and the vehicle After obtaining the control command, the control message is sent through the CAN bus to realize the control of the vehicle, and finally the operation result is fed back to the user's mobile phone APP.
  • the vehicle-mounted T-BOX communicates with the vehicle through the canbus to achieve data interaction, such as the transmission of vehicle status information, button status information, and control commands.
  • the vehicle-mounted T-BOX can collect bus data related to the vehicle 110 bus Dcan, Kcan, and PTcan.
  • the vehicle's own data sensed by the on-board data sensing device includes, for example, vehicle speed, acceleration, yaw rate, position, and so on.
  • the external environment data sensed by the vehicle-mounted data sensing device includes, for example, temperature, humidity, light, distance, and so on.
  • the data sensing device for sensing external environmental data includes, for example, a humidity sensor for detecting environmental humidity data, an air volume sensor for detecting environmental air volume data, a wiper sensor for detecting rain volume data, and an environment for detecting Temperature sensor for temperature data, multiple cameras for collecting environmental video data.
  • the data sensing device for sensing external environment data also includes a camera device of the vehicle 110, for example, multiple camera devices connected to a streaming media rearview mirror.
  • the streaming media rearview mirror passes through a front-end camera connected to the streaming media rearview mirror.
  • the environmental video data collected by the camera and the rear camera includes at least the image data of the vehicle window and the image data of the external environment of the vehicle (for example, the environmental image of the rear of the vehicle).
  • the vehicle 110 and the mobile device 120 may interact and share data through wireless communication means such as Wi-Fi, Bluetooth, and cellular.
  • the mobile device 120 is associated with the vehicle by detecting a predetermined action (for example, shaking) on the mobile device.
  • a predetermined action for example, shaking
  • the connection between the vehicle and the associated mobile device of a specific user can be established in a safe manner, so as to share data and computing resources.
  • the vehicle 110 may detect that the distance between the mobile device 120 and the vehicle 110 is less than a predetermined value (for example, but not limited to, it is detected that the mobile device 120 is inside the vehicle 110, or within a few meters outside the vehicle), and senses the vehicle data
  • the vehicle's own data and external environmental data (for example, including environmental video data) collected by the device are sent to the mobile device 120.
  • unnecessary data interaction between the vehicle and the mobile device can be reduced.
  • the vehicle and the mobile phone can be interconnected through USB communication technology.
  • the vehicle 110 and the cloud server 130 perform real-time data exchange through wireless communication technologies such as satellite wireless communication or mobile cellular.
  • the vehicle 110 directly obtains real-time weather data from the cloud server 130, or interacts with the cloud server 130 directly or via the mobile device 120 for insurance data.
  • the mobile device 120 is, for example, but not limited to, a mobile phone.
  • the terminal device 120 can directly carry out data interaction on the vehicle-mounted T-BOX.
  • the mobile device 120 may be a tablet computer.
  • the vehicle's own data, environmental data, and weather data can be obtained to determine the warning weather type at the mobile device 120, and when it is determined that the warning weather type matches When pre-determining warning conditions, determine the matching auto insurance data.
  • FIG. 2 shows a flowchart of a management method 200 for vehicle safety according to an embodiment of the present disclosure.
  • the method 200 may be executed at the electronic device 1000 described in FIG. 10, for example. It can also be executed at the mobile device 120 or the vehicle 110 described in FIG. 1. It should be understood that the method 200 may also include additional actions not shown and/or the actions shown may be omitted, and the scope of the present disclosure is not limited in this respect.
  • the mobile device 120 or the vehicle machine of the vehicle 110 may obtain at least one of meteorological data and environmental data, and the environmental data is collected via an on-board device at the vehicle.
  • environmental data and meteorological data are acquired for determining the warning weather type.
  • environmental data in some embodiments, it includes at least one of the following: environmental video data collected via the camera device of the vehicle, the environmental video data including at least vehicle window image data and vehicle external environmental image data; The environmental humidity data detected by the humidity sensor; the environmental air volume data detected by the vehicle’s air volume sensor; and the rainfall data detected by the vehicle’s wiper sensor; the environmental temperature data detected by the vehicle’s temperature sensor.
  • the vehicle window image data and the vehicle external environment image data of the vehicle are acquired via the streaming media rearview mirror of the vehicle.
  • the streaming media rearview mirror is, for example, connected to a plurality of camera devices (such as a front camera and a rear camera) of the vehicle.
  • a wiper sensor in the form of an optical sensor includes a plurality of light emitting diodes and a reflected light receiver.
  • the light emitting diode and the reflected light receiver are, for example, arranged inside the front windshield.
  • the light is reflected through the front windshield to the reflected light receiver.
  • the light will deviate, and the signal received by the reflected light receiver will change relative to the signal received in fine weather.
  • the amount of rainfall can be determined, for example, the number of raindrops per unit area can be determined.
  • the wiper sensor in the form of a capacitive sensor uses the difference between the dielectric constant of raindrops (for example, the dielectric constant of water is 80) and glass (for example, the dielectric constant of glass is 2), based on glass The change in the dielectric constant is used to determine the amount of rain falling on the glass. Therefore, the mobile device 120 or the vehicle 110 can obtain the rain volume data from the wiper sensor and use it to subsequently determine the warning weather type.
  • the mobile device 120 or the vehicle machine of the vehicle 110 determines the warning weather type based on at least one of weather data and environmental data.
  • the method for determining the type of warning weather can be implemented in a variety of ways.
  • O represents the input image with the influence of bad weather (for example, image data of car windows, image data of the external environment of the vehicle).
  • B represents the input image without the influence of severe weather
  • S represents the image noise data caused by the influence of severe weather (such as low visibility, heavy snow, heavy rain, lightning, hail, etc.). Therefore, S in formula (1) can be understood as image noise data in the traditional sense. Therefore, the impact of bad weather on the collected images can be regarded as the noise of the image data, and then the image noise data can be effectively classified through the classification network, and the warning weather type can be determined efficiently.
  • the method for determining the warning weather type includes, for example, the mobile device 120 or the vehicle machine of the vehicle 110 generates environmental image noise data based on the environmental image data of the vehicle; and determining the warning weather type based on the probability distribution of the environmental image noise data Whether the indication is one of heavy rain, heavy snow, and hail.
  • the vehicle's environmental image data such as car window image noise data
  • it is not only possible to efficiently determine the warning weather type.
  • it can classify low-resolution high-frequency image noise indicating severe weather more effectively, and at the same time significantly improve the calculation efficiency.
  • the car window image noise data can be used to identify the conditions of raindrops, snowflakes and hail, and then to identify whether the current weather belongs to the warning weather type of heavy precipitation weather, blizzard or hail.
  • the image information indicated in the window image data is simpler than the image information indicated by the environment image data of the vehicle, especially the front window image data, which usually includes the road and the vehicle ahead, therefore, use the window Image data, especially the front window image data, is more efficient in recognizing the current weather type.
  • the mobile device 120 or the vehicle machine of the vehicle 110 determines whether the warning weather type meets the predetermined warning condition.
  • the mobile device 120 or the vehicle machine of the vehicle 110 determines that the warning weather type meets the predetermined warning condition, then based on at least one of the weather data and environmental data and the driving data of the vehicle, determine the car insurance data matching the vehicle .
  • the warning weather type meets the predetermined warning condition, in some embodiments, it includes, for example, at least one of the following: if the mobile device 120 or the vehicle 110 determines that the warning weather type is indicated as low visibility, heavy snow, heavy rain, lightning, hail, freezing If at least one of the conditions is selected, it is determined that the warning weather type meets the predetermined warning conditions, where the low visibility includes at least one of smog and sandstorm. Or if the mobile device 120 or the vehicle 110 determines that the current warning weather type relative to the change of the warning weather type in the past predetermined time interval meets the first predetermined condition.
  • the mobile device 120 or the vehicle 110 combines the above two situations to determine whether it is in response to determining whether the current warning weather type belongs to the warning weather requiring insurance. By judging whether there is a sudden change in the current warning weather type, you can provide timely warnings for sudden severe weather so as to purchase insurance that matches the sudden severe weather type.
  • an identification associated with the car insurance data is displayed in at least one of the mobile device 120 and the on-board display screen of the vehicle 110, and the mobile device is associated with the vehicle via detecting a predetermined action on the mobile device.
  • the displayed logo is used to graphically remind the user of the type, insurance rights and expenses, and the user can enjoy related insurance services as long as the user simply confirms.
  • it includes an operable icon for indicating the type of auto insurance matching the vehicle. For example, if it is determined that the severe weather type is heavy rain (that is, heavy rain weather), the car insurance data is, for example, recommended vehicle wading insurance, and the identifier associated with the car insurance data is, for example, an operable icon indicating that the vehicle is wading. If it is determined that the type of severe weather is blizzard, the identifier associated with the car insurance data is, for example, an operable icon indicating that the vehicle is skidding.
  • the auto insurance data may be prompted by voice.
  • the mobile device 120 determines that the warning weather type is heavy fog based on the acquired weather data and/or environmental data, and the mobile device 120 Display the key card to display warnings or signs, for example, "Driving with caution today", and whether "you need to purchase additional insurance for 10 yuan or scratch insurance”. If the user clicks to buy, the screen of the vehicle 110 displays, for example, a "big icon for insurance today".
  • the mobile device 120 or the vehicle machine of the vehicle 110 may be further determined whether there is a wading warning area in the path from the current location to the destination.
  • the determination of the wading warning area may be determined based on at least one of geographic features, road attributes, and historical data associated with the route. If the mobile device 120 or the vehicle machine of the vehicle 110 confirms that there is indeed a wading warning area in the current path, at least one of the on-board display screens of the mobile device and the vehicle presents a path to be selected from the current location to the destination. information.
  • the mobile device 120 or the vehicle machine of the vehicle 110 can plan a better route for the user that does not involve the wading warning area. If the mobile device 120 or the vehicle machine of the vehicle 110 detects an operation on the planned route (for example, the user selects a planned route without a water warning area); the mobile device 120 or the vehicle machine of the vehicle 110 can be based on the mobile device 120 accepts To determine the expected time to reach the destination via the planned route through the navigation information and traffic information (such as traffic accident and congestion information provided by the Internet of Vehicles platform); then, for example, the expected time is displayed on the mobile device and/or the vehicle’s on-board display screen.
  • traffic information such as traffic accident and congestion information provided by the Internet of Vehicles platform
  • the method 200 may also include a method 300 for generating an insurance order.
  • the method for generating an insurance order will be described below in conjunction with FIG. 3.
  • FIG. 3 shows a flowchart of a method 300 for generating an insurance order according to an embodiment of the present disclosure. It should be understood that the method 300 may be executed at the electronic device 1000 described in FIG. 10, for example. It can also be executed at the mobile device 120 described in FIG. 1 or at the vehicle machine of the vehicle 110. It should be understood that the method 300 may further include additional actions not shown and/or the actions shown may be omitted, and the scope of the present disclosure is not limited in this respect.
  • the mobile device 120 or the vehicle machine of the vehicle 110 determines whether an operation for an operable icon is detected.
  • the personal information is, for example, personal data and payment information required for purchasing insurance.
  • the mobile device 120 or the car machine of the vehicle 110 generates order data associated with the car insurance data based on the acquired personal information and car insurance data.
  • the order data is sent to the cloud server via the mobile device 120.
  • the mobile device 120 or the vehicle machine of the vehicle 110 can determine whether an operation on an operable icon is detected; if an operation on an operable icon is detected, it can directly send the auto insurance data to the cloud server via the mobile device 120 The associated order data.
  • the insurance order can be directly sent through the user's operation of the operation icon. For example, in some cases where the insurance premium is low, and the user's personal information is already stored with the server, the insurance can be purchased conveniently and efficiently.
  • FIG. 4 shows a flowchart of a method 400 for determining a warning weather type according to an embodiment of the present disclosure. It should be understood that the method 400 may be executed at the electronic device 1000 described in FIG. 10, for example. It can also be executed at the mobile device 120 described in FIG. 1 or at the vehicle machine of the vehicle 110. It should be understood that the method 400 may also include additional actions not shown and/or the actions shown may be omitted, and the scope of the present disclosure is not limited in this respect.
  • the mobile device 120 or the vehicle machine of the vehicle 110 selects multiple sets of environmental image sequences in the environmental video data.
  • the mobile device 120 or the vehicle machine of the vehicle 110 determines the background object in the environmental image sequence based on the multiple sets of environmental image sequences.
  • the mobile device 120 or the vehicle 110 determines that at least one of the following conditions is met, it is determined whether the warning weather type is indicated as low visibility: the edge intensity of the background object is lower than the first predetermined threshold; the image of the background object The sharpness is lower than a second predetermined threshold, the first predetermined threshold and the second predetermined threshold are determined based on historical image data associated with the background object; and the speed at which the background object disappears in the environmental image sequence is higher than the third predetermined threshold
  • the third predetermined threshold is determined based on historical image data associated with the background object and the driving speed of the vehicle.
  • FIG. 5 shows a flowchart of a method 500 for determining a warning weather type according to an embodiment of the present disclosure. It should be understood that the method 500 may be executed at the electronic device 1000 described in FIG. 10, for example. It can also be executed at the mobile device 120 described in FIG. 1 or at the vehicle machine of the vehicle 110. It should be understood that the method 500 may also include additional actions not shown and/or the actions shown may be omitted, and the scope of the present disclosure is not limited in this respect.
  • the mobile device 120 or the vehicle machine of the vehicle 110 generates a high-frequency image based on at least one of the image data of the window image and the image data of the external environment of the vehicle, and the high-frequency image includes the window image data and/or the vehicle.
  • High-frequency information in image data of the external environment may be generated.
  • the mobile device 120 or the vehicle machine of the vehicle 110 may generate a high-frequency window image based on the window image data through frequency domain transformation.
  • the high-frequency image corresponds to the high-frequency component of the window image data
  • the low-frequency image corresponds to the low-frequency component of the window image data.
  • the low-frequency component (low-frequency signal) in the image generally represents the part of the image with small gradient changes, such as the area where the brightness or gray value changes slowly. Therefore, the low-frequency component can be used to comprehensively measure the intensity of the entire image.
  • the high-frequency components (high-frequency signals) in the image generally indicate the parts with sharp changes in the image, or the parts with large gradient changes, such as the edges (contours) or noise and details of the image. Therefore, the high-frequency components can be used to control the image. Measurement of edges and contours.
  • image noise data in the traditional sense is usually distributed in the high-frequency part of the image. Research has found that the impact of bad weather on the image is usually distributed in the high-frequency part.
  • the mobile device 120 or the vehicle machine of the vehicle 110 may divide the window image data or the image data of the external environment of the vehicle into high-frequency images (high-frequency images) and low-frequency images (low-frequency images) based on wavelet transform.
  • wavelet transform By using wavelet transform to obtain high-frequency images used to identify the effects of severe weather in the window image data, it can have good local characteristics in both the time domain and the frequency domain, so that high-frequency information can be extracted from the signal more effectively. In particular, it can better meet the needs of analyzing the influence of severe weather, which is a non-stationary signal.
  • the mobile device 120 or the vehicle machine of the vehicle 110 may also perform a two-dimensional Fourier transform on the window image data to generate a spectrogram of the window image data.
  • This spectrogram identifies the distribution of the image gradient of the window image data.
  • the mobile device 120 or the vehicle machine of the vehicle 110 may extract high-frequency features of the high-frequency image based on the recognition model.
  • the recognition model can be generated through machine learning of multiple training samples. There are many ways to extract the features of high-frequency images. The following describes how to extract features of high-frequency images with reference to FIGS. 6 to 8.
  • FIG. 6 shows an overall schematic diagram of a method 600 for identifying warning weather types according to an embodiment of the present disclosure.
  • the encoder-decoder neural network model can be used to extract high-frequency features of high-frequency images (for example, car window noise images).
  • the classification model is then used to classify the high-frequency features extracted by the encoder-decoder neural network model to determine the type of warning weather, that is, predict the value of the type that indicates the warning weather.
  • the identification method 600 for determining the warning weather type mainly includes encoder-decoder processing 602 and classification processing 604.
  • the encoder-decoder processing 602 is mainly used to implement the action at block 504.
  • the encoder-decoder processing 602 is used to extract high-frequency features based on input high-frequency images (for example, high-frequency images of car windows and/or high-frequency images of the external environment of the vehicle).
  • the classification processing 604 is used to determine the warning weather type based on the extracted high-frequency features.
  • the encoder-decoder processing 602 includes: inputting an input image 604 (for example, a high-frequency image of a car window and/or a high-frequency image of the external environment of the vehicle) into an encoder model 606, so as to generate a low-frequency feature 608 and a high-frequency Feature 610, and then input the low-frequency feature 608 and the high-frequency feature 610 processed by L2 regularization to the decoder model 612 for processing, so as to generate a composite image 614.
  • the generated composite image 614 can be used as a training sample for the encoder-decoder processing 602. Adjust the network structure parameters of the encoder-decoder neural network model in the process of training a large number of samples through reconstruction loss processing. It should be understood that, through the encoder-decoder processing 602, the high-frequency features of the high-frequency image can be extracted.
  • FIG. 7 shows a schematic diagram of a process 700 for extracting high-frequency features according to an embodiment of the present disclosure.
  • the aforementioned high-frequency images 702 for example, high-frequency images of car windows
  • the ResNet50 model has a convolutional layer of 50.
  • Product processing 706 and 708 to obtain low-frequency features 710 and high-frequency features 712, respectively, and then input the low-frequency features 710 and high-frequency features 712 into the up-sampling models 716 and 718, respectively, and then through the element operation layer summation processing 720 (Eltwise-sum ), the composite image 722 is output.
  • the up-sampling models 716 and 718, and the Eltwise-sum processing 720 constitute a decoder network structure 714.
  • ResNet50 includes three main parts: an input part, an output part, and an intermediate convolution part.
  • the intermediate convolution part is used to achieve the extraction of high-frequency features of the input high-frequency image through the stacking of convolutions, which includes, for example, Stage1 There are four stages in total to Stage4.
  • the ResNet50 model for encoder processing it is beneficial to improve the processing effect and efficiency of decomposing the low-frequency feature 710 and the high-frequency feature 612.
  • the number of convolution kernels is, for example, 256
  • the size of the convolution kernel is, for example, 3*3
  • the stride is, for example, 1.
  • the up-sampling model 716 or 718 in some embodiments, it is, for example, four sets of sampling models.
  • the decoder network structure 714 is used to restore the processed image to the original input image. Therefore, an up-sampling model is required to restore the image that has undergone the previous dimensionality reduction process to an image with the same size as the original input image. This can make reconstruction loss processing of the image relatively easy.
  • I represents the two-dimensional vector of the input image (for example, the high-frequency image 702).
  • I′ represents the two-dimensional vector of the synthesized image 722 processed by the decoder network structure 714.
  • l r stands for reconstruction loss. Generally, the smaller the reconstruction loss is, the better the encoder-decoder model fits. In some embodiments, the reconstruction loss function is the sum of the squares of the corresponding pixel points of the two-dimensional vector of the input image and the two-dimensional vector of the synthesized image.
  • I H represents a two-dimensional vector of high-frequency features.
  • l e stands for high frequency loss.
  • FIG. 8 shows a schematic diagram of an up-sampling process 800 according to an embodiment of the present disclosure.
  • the up-sampling processing 800 exemplifies one of the four groups of sampling models in the up-sampling model 716 or 718 mentioned above, for example.
  • the up-sampling process 800 includes, for example, a deconvolution process 802, a convolution process 804, and a convolution process 806.
  • the deconvolution process 802 there are 256 convolution kernels, the size of the convolution kernel is 4*4, and the stride is 2, for example.
  • the convolution process 804 there are 512 convolution kernels, the size of the convolution kernel is 1*1, and the stride is, for example, 1.
  • the convolution processing 806, there are 256 convolution kernels the size of the convolution kernel is 3*3, and the stride is, for example, 1.
  • the overall loss function of the encoder-decoder processing can be calculated by the following formula (4), for example.
  • l r represents reconstruction loss
  • l e represents high-frequency loss
  • ⁇ represents the coefficient, which is used to balance the importance of reconstruction loss and high-frequency loss in the overall loss of encoder-decoder processing.
  • the mobile device 120 or the vehicle machine of the vehicle 110 determines the warning weather type indicated by the high-frequency image based on the extracted high-frequency features.
  • the classification processing 604 includes, for example, inputting the high-frequency features 610 extracted through the encoder-decoder processing 602 into the classification model 624, and then through the normalized index processing 626 (Softmax) to obtain an output 628, and through the classification loss In processing 632, the network structure parameters of the classification model 622 are adjusted.
  • the finally determined warning weather type for the high-frequency feature 610 is, for example, the type indicated by the tag 630.
  • the ResNet18 classification network may be used to determine the warning weather type based on the extracted high-frequency features.
  • the ResNet18 classification network can, for example, be based on the input high-frequency features 610, through the downsampling of each stage, so that the input high-frequency feature maps are processed by dimensionality reduction until finally connected to the fully connected layer output, for example, the classification model 624
  • the number of output nodes is the same as the number of forecast warning weather types.
  • the loss function of the classification process at block 506 follows the following formula (5), for example.
  • N represents the number of samples
  • C represents the category
  • y i represents the output prediction value of the warning weather type
  • p c represents the output value of the normalized index processing 626. Represents the loss function of the classification process.
  • high-frequency images indicating the impact of severe weather are generated according to the difference in the distribution of severe weather such as rain, fog, and snow at high frequencies.
  • the classification network is used to classify high-frequency images, which can be efficiently and accurately Determine the type of weather warning.
  • FIG. 9 shows a schematic diagram of a method 900 for determining a warning weather type according to an embodiment of the present disclosure. It should be understood that the method 900 may be executed at the electronic device 1000 described in FIG. 10, for example. It can also be executed at the mobile device 120 described in FIG. 1 or at the vehicle machine of the vehicle 110. It should be understood that the method 900 may also include additional actions not shown and/or the actions shown may be omitted, and the scope of the present disclosure is not limited in this respect.
  • the mobile device 120 or the vehicle 110 of the vehicle is based on the image data of the external environment of the vehicle to determine the ground image area behind the vehicle.
  • the mobile device 120 or the vehicle machine of the vehicle 110 extracts the image features of the ground image area at the rear of the vehicle.
  • the mobile device 120 or the vehicle machine of the vehicle 110 determines whether there is one of snow and water in the ground image area at the rear of the vehicle based on the extracted image features.
  • the mobile device 120 or the vehicle machine of the vehicle 110 determines that there is one of snow and water in the ground image area at the rear of the vehicle, it may be based on the high-frequency image and the environmental temperature data and the environmental humidity data. At least one item, determine the type of warning weather.
  • the types of warning weather can be accurately identified, such as heavy precipitation. Weather, blizzard weather.
  • FIG. 10 schematically shows a block diagram of an electronic device 1000 suitable for implementing embodiments of the present disclosure.
  • the device 1000 may be a device for implementing the methods 200, 300, 400, 500, and 900 shown in FIGS. 2 to 5.
  • the device 1000 includes a central processing unit (CPU) 1001, which can be loaded into a random access memory (RAM) 1003 according to computer program instructions stored in a read-only memory (ROM) 1002 or loaded from a storage unit 1008.
  • RAM 1003 various programs and data required for the operation of the device 1000 can also be stored.
  • the CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004.
  • An input/output (I/O) interface 1005 is also connected to the bus 1004.
  • the processing unit 1001 executes the various methods and processes described above, such as executing the methods 200, 300, 400, 500, and 900.
  • the methods 200, 300, 400, 500, and 9000 may be implemented as computer software programs, which are stored in a machine-readable medium, such as the storage unit 1008.
  • part or all of the computer program may be loaded and/or installed on the device 1000 via the ROM 1002 and/or the communication unit 1009.
  • the CPU 1001 When the computer program is loaded into the RAM 1003 and executed by the CPU 1001, one or more operations of the methods 200, 300, 400, 500, and 900 described above can be executed.
  • the CPU 1001 may be configured to perform one or more actions of the methods 200, 300, 400, 500, and 900 in any other suitable manner (for example, by means of firmware).
  • the present disclosure may be a method, an apparatus, a system, and/or a computer program product.
  • the computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for executing various aspects of the present disclosure.
  • the computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a printer with instructions stored thereon
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • flash memory flash memory
  • SRAM static random access memory
  • CD-ROM compact disk read-only memory
  • DVD digital versatile disk
  • memory stick floppy disk
  • mechanical encoding device such as a printer with instructions stored thereon
  • the computer-readable storage medium used here is not interpreted as the instantaneous signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through fiber optic cables), or through wires Transmission of electrical signals.
  • the computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • the network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .
  • the computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or in one or more programming languages.
  • Source code or object code written in any combination, the programming language includes object-oriented programming languages-such as Smalltalk, C++, etc., and conventional procedural programming languages-such as "C" language or similar programming languages.
  • Computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as a stand-alone software package, partly on the user's computer and partly executed on a remote computer, or entirely on the remote computer or server carried out.
  • the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect to the user's computer) connection).
  • LAN local area network
  • WAN wide area network
  • an electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by using the status information of the computer-readable program instructions.
  • FPGA field programmable gate array
  • PDA programmable logic array
  • the computer-readable program instructions are executed to realize various aspects of the present disclosure.
  • These computer-readable program instructions can be provided to the processing unit of the processor, general-purpose computer, special-purpose computer, or other programmable data processing device in the voice interaction device, so as to produce a machine so that these instructions can be used by a computer or other programmable data processing device.
  • the processing unit of the data processing device When executed, it produces a device that implements the functions/actions specified in one or more blocks in the flowchart and/or block diagram.
  • These instructions make computers, programmable data processing apparatuses, and/or other devices work in a specific manner.
  • the computer-readable medium storing the instructions includes An article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction contains one or more options for realizing the specified logical function.
  • Execute instructions may also occur in a different order than the order marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Development Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Technology Law (AREA)
  • Analytical Chemistry (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Atmospheric Sciences (AREA)
  • Computing Systems (AREA)
  • Combustion & Propulsion (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Security & Cryptography (AREA)
  • Emergency Management (AREA)
  • Geology (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Environmental & Geological Engineering (AREA)

Abstract

一种车辆安全的管理方法、装置和计算机存储介质。该方法包括：获取气象数据和环境数据中的至少一种，环境数据经由车辆处的车载设备采集（202）；基于气象数据和环境数据中的至少一种，确定警示天气类型（204）；确定警示天气类型是否符合预定警示条件（206），基于天气数据和环境数据中的至少一种以及车辆的行驶数据，确定与车辆相匹配的车险数据（208）；以及在移动设备和车辆的车载显示屏的至少一处呈现与车险数据相关联的标识，移动设备经由检测到在移动设备上的预定动作而与车辆相关联（210）。所述方法能够为突遭恶劣天气的车辆和车上人员提供匹配和及时的警示与安全保障。

Description

用于车辆安全的管理方法、装置和计算机存储介质 技术领域
本公开总体上涉及车辆保险与安全，并且具体地，涉及用于车辆安全的管理方法、装置和计算机存储介质。
背景技术
突遭恶劣天气，例如强降水天气、暴雪、长时间冰雹袭击、雷击、暴风能通常会给车辆带来损害，甚至是对车辆的驾驶人员和乘客带来人身安全威胁。
在传统的用于车辆安全的管理方案中，通常是车主事先购买保险(例如车险)，但是，所购保险一般存在一定的有效期，并且所购车险的赔付范围可能无法覆盖因突遭恶劣天气车辆所面临的车辆和人员安全方面的风险。例如、面临突遭暴雨的情形，很多在外行驶或者存放的车辆容易被积水淹没，从而导致不同程度的损失。如果车主只选购了车损险，没有在车损险基础上选择发动机涉水损失险，那么因发动机进水后导致的发动机的直接损毁，车主很可能无法获得相应赔偿。而且对于车险有效期已过的情形，当突遭恶劣天气，即便车主预见到车辆和车辆的驾驶人员和乘客所面临的安全隐患，也没办法及时购买保险。
因此，在传统的用于车辆安全的管理方案中，无法对突遭恶劣天气的车辆和车上人员提供匹配和及时的警示与安全保障。
发明内容
本公开提供一种用于车辆安全的管理方法、装置和计算机存储介质的方法和设备，能够为突遭恶劣天气的车辆和车上人员提供匹配和及时的警示与安全保障。
根据本公开的第一方面，提供了一种用于车辆安全的管理方法。该方法包括：获取气象数据和环境数据中的至少一种，环境数据经由车辆处的车载设备采集；基于气象数据和环境数据中的至少一种，确定警示天气类型；响应于确定警示天气类型符合预定警示条件，基于天气数据和环境数据中的至少一种以及车辆的行驶数据，确定与车辆相匹配的车险数据；以及在移动设备和车辆的车载显示屏的至少一处呈现与车险数据相关联的标识，移动设备经由检测到在移动设备上的预定动作而与车辆相关联。
根据本发明的第二方面，还提供了一种用于车辆安全的管理的装置，设备包括：存储器，被配置为存储一个或多个计算机程序；以及处理器，耦合至存储器并且被配置为执行一个或多个程序使装置执行本公开的第一方面的方法。
根据本公开的第三方面，还提供了一种非瞬态计算机可读存储介质。该非瞬态计算机可读存储介质上存储有机器可执行指令，该机器可执行指令在被执行时使机器执行本公开的第一方面的方法。
在一些实施例中，环境数据至少包括以下的至少一项：经由车辆的摄像装置所采集的环境视频数据，环境视频数据至少包括车辆车窗图像数据和车辆外部环境图像数据；经由车辆的湿度传感器所检测的环境湿度数据；经由车辆的风量传感器所检测的环境风量数据；以及经由车辆的雨刮器传感器所检测的雨量数据；经由车辆的温度传感器所检测的环境温度数据。
在一些实施例中，经由车辆的流媒体后视镜获取所述车辆的环境视频数据，环境视频数据至少包括车辆车窗图像数据和车辆外部环境图像数据，流媒体后视镜与车辆的多个摄像装置相连。
在一些实施例中，与车险数据相关联的标识包括用于指示与车辆相匹配的车险险种的可操作图标。
在一些实施例中，该方法还包括：响应于检测到针对可操作图标的操作，获取与移动设备相关联的用户的个人信息；基于所获取的个人信息和车险数据，生成与车险数据相关联的订单数据；经由 移动设备向云服务器发送订单数据。
在一些实施例中，该方法还包括：响应于检测到针对所述可操作图标的操作，经由所述移动设备向云服务器发送与所述车险数据相关联的订单数据。
在一些实施例中，该方法还包括：在移动设备处，响应于确认移动设备相对于车辆的距离小于预定值，获取环境数据和气象数据，以用于确定警示天气类型。
在一些实施例中，确定警示天气类型还包括：基于车辆的环境图像数据，生成环境图像噪声数据；基于环境图像噪声数据的概率分布，确定警示天气类型是否指示为大雨、大雪、冰雹中的一种。
在一些实施例中，确定警示天气类型包括：基于车窗图像数据和车辆外部环境图像数据中的至少一种图像数据，生成高频图像，高频图像包括至少一种图像数据中的高频信息。
在一些实施例中，确定警示天气类型还包括：基于车辆外部环境图像数据，确定车辆后部地面图像区域；提取车辆后部地面图像区域的图像特征；基于所提取的图像特征，确定车辆后部地面图像区域中是否存在积雪和积水中的一种；响应于确定车辆后部地面图像区域中存在积雪和积水中的一种，基于高频图像、以及环境温度数据和环境湿度数据中的至少一项，确定警示天气类型。
在一些实施例中，确定警示天气类型包括：在环境视频数据中选择多组环境图像序列；基于多组环境图像序列，确定环境图像序列中的背景对象；响应于以下至少一项条件满足，确定警示天气类型是否指示为低能见度：背景对象的边缘强度低于第一预定阈值；背景对象的图像锐度低于第二预定阈值，第一预定阈值和第二预定阈值是基于与背景对象相关联的历史图像数据而确定的；以及背景对象在环境图像序列中消失的速度高于第三预定阈值，第三预定阈值是基于与背景对象相关联的历史图像数据和车辆的行驶速度而确定的。
在一些实施例中，该方法还包括：响应于确认警示天气类型指 示大雨，确定当前位置至目的地的路径中是否存在涉水警示区域，涉水警示区域基于与路径相关联的地理特征、道路属性、以及历史数据中的至少一项而确定；以及响应于确定路径中存在涉水警示区域，在移动设备和车辆的车载显示屏的至少一处显示用于标识当前位置至目的地之间的待选路径的信息。
在一些实施例中，该方法还包括：响应于检测到关于待选路径的操作；基于移动设备所接收的导航信息和交通信息，确定经由待选路径到达目的地的预期时间；以及在移动设备和车辆的车载显示屏的至少一处呈现预期时间。
在一些实施例中，确定警示天气类型符合预定警示条件包括以下至少一项：响应于确定警示天气类型指示为低能见度、大雪、大雨、闪电、冰雹，冰冻中的至少一项，确定警示天气类型符合预定警示条件，低能见度包括雾霾、沙尘暴中的至少一种；以及响应于确定当前警示天气类型相对于过去预定时间间隔内的警示天气类型的变化情况符合第一预定条件。
提供发明内容部分是为了以简化的形式来介绍对概念的选择，它们在下文的具体实施方式中将被进一步描述。发明内容部分无意标识本公开的关键特征或主要特征，也无意限制本公开的范围。
附图说明
图1示出了根据本公开的实施例的用于车辆安全的管理方法的系统100的示意图；
图2示出了根据本公开的实施例的用于车辆安全的管理方法200的流程图；
图3示出了根据本公开的实施例的用于生成保险订单的方法300的流程图；
图4示出了根据本公开的实施例的用于确定警示天气类型的方法400的流程图；
图5示出了根据本公开的实施例的用于确定警示天气类型的方 法500的流程图；
图6示出了根据本公开的实施例的用于识别警示天气类型的方法600的整体示意图；
图7示出了根据本公开的实施例的提取高频特征的处理700的示意图；
图8示出了根据本公开的实施例的上采样处理800的示意图；
图9示出了根据本公开的实施例的用于确定警示天气类型的方法900的示意图；以及
图10示意性示出了适于用来实现本公开实施例的电子设备1000的框图。
在各个附图中，相同或对应的标号表示相同或对应的部分。
具体实施方式
下面将参照附图更详细地描述本公开的优选实施例。虽然附图中显示了本公开的优选实施例，然而应该理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了使本公开更加透彻和完整，并且能够将本公开的范围完整地传达给本领域的技术人员。
在本文中使用的术语“包括”及其变形表示开放性包括，即“包括但不限于”。除非特别申明，术语“或”表示“和/或”。术语“基于”表示“至少部分地基于”。术语“一个示例实施例”和“一个实施例”表示“至少一个示例实施例”。术语“另一实施例”表示“至少一个另外的实施例”。术语“第一”、“第二”等等可以指代不同的或相同的对象。下文还可能包括其他明确的和隐含的定义。
如上文所描述的，在传统的用于车辆安全的管理方法方案中，如果用户(例如是车主)事先购买具有一定有效期的车辆保险，可能因为所购保险的理赔范围与车辆突遭恶劣天气的情形不相匹配，所购保险的有效期已过等原因，无法对突遭恶劣天气的车辆和车上人员提供匹配和及时的警示与安全保障。
为了至少部分地解决上述问题以及其他潜在问题中的一个或者多个，本公开的示例实施例提出了一种用于车辆安全的管理方案。在该方案中，获取气象数据和环境数据中的至少一种，环境数据经由车辆处的车载设备采集；基于气象数据和环境数据中的至少一种，确定警示天气类型；响应于确定警示天气类型符合预定警示条件，基于天气数据和环境数据中的至少一种以及车辆的行驶数据，确定与车辆相匹配的车险数据；以及在移动设备和车辆的车载显示屏的至少一处呈现与车险数据相关联的标识，移动设备经由检测到在移动设备上的预定动作而与车辆相关联。。
在上述方案中，通过在基于所获的气象数据和车辆处所采集的环境数据中的至少一种，确定警示天气类型符合预定警示条件时，根据指示气象数据和实际环境数据的至少一种以及表征车况的车辆行驶数据来匹配保险数据，可以实现所确定的保险数据与车辆实际突遭的恶劣天气的情形相匹配，而且通过在与车辆关联的移动设备和车辆的至少一处显示匹配的保险标识，使得既可以给车辆驾驶人员和乘客以与警示天气类型相关的信号警示，而且以指示或标识的方式，而非直接显示保险数据的方式，有利于用户快速识别和发出关于保险的操作，而不会对安全驾驶带来不必要的干扰。
图1示出了根据本公开的实施例的用于车辆安全的管理方法的系统100的示意。如图1所示，系统100包括车辆110、移动设备120、云服务器130。移动设备120、服务器130通过网络140相连。在一些实施例中，系统100还包括路侧单元(RSU，Road Side Unit，未示出)等。
关于车辆110，其至少包括：车机、车载数据感知设备、车载T-BOX。车载数据感知设备用于实时感知车辆自身数据和车辆所在外部环境数据。
关于车载T-BOX，其用于车机、移动设备120、路侧单元、云服务器130进行数据交互。车载T-BOX例如包括SIM卡、GPS天线，4G或5G天线等。当用户通过移动设备120(例如手机)的应用程 序(APP)发送控制命令(远程启动车辆、打开空调、调整座椅至合适位置等)，TSP后台会发出监控请求指令到车载T-BOX，车辆在获取到控制命令后，通过CAN总线发送控制报文并实现对车辆的控制，最后反馈操作结果到用户的手机APP上。车载T-BOX与车机之间通过canbus通信，实现数据交互，例如传输车辆状态信息、按键状态信息、控制指令等。车载T-BOX可以采集车辆110总线Dcan、Kcan、PTcan相关的总线数据。
车载数据感知设备所感知的车辆自身数据例如包括：车辆行驶速度、加速度、横摆角速度、位置等。车载数据感知设备所感知的外部环境数据例如包括：温度、湿度、光线、距离等。用于感知外部环境数据的数据感知设备例如包括：用于检测的环境湿度数据的湿度传感器、用于检测的环境风量数据的风量传感器、用于检测的雨量数据的雨刮器传感器、用于检测的环境温度数据的温度传感器、用于采集环境视频数据的多个摄像头。用于感知外部环境数据的数据感知设备还包括车辆110的摄像装置，例如与流媒体后视镜相连的多个摄像装置，在一些实施例中，该流媒体后视镜通过与其相连的前置摄像头和后置摄像头所采集的环境视频数据至少包括车辆车窗图像数据和车辆外部环境图像数据(例如车辆后部环境图像)。
车辆110与移动设备120可以通过Wi-Fi、蓝牙、蜂窝等无线通信手段进行数据交互与共享。例如，移动设备120通过检测到移动设备上的预定动作(例如摇一摇)而与车辆相关联。通过移动设备120藉由预定动作(例如摇一摇)与车辆相关联，能够以安全方式，建立车辆与特定用户(如车主)的关联移动设备之间的联系，以便共享数据与计算资源。车辆110可以在检测到移动设备120相对于车辆110的距离小于预定值(例如而不限于是，检测到移动设备120在车辆110内部，或者处于车外几米的范围之内)，将车辆数据感知设备所采集的车辆自身数据和外部环境数据(例如包括环境视频数据)发给移动设备120。通过采用上述手段，可以减少在车辆与移动设备之间的不必要数据的交互。在一些实施例中，当检测到移动 设备120在车辆110内部，车机和手机可以通过USB通信技术进行互联。
车辆110与云服务器130之间例如通过卫星无线通信或移动蜂窝等无线通信技术进行实时数据交互。例如车辆110直接从云服务器130获取实时气象数据，或者直接或者经由移动设备120与云服务器130进行保险数据的交互。
移动设备120，其例如但不限于是手机。终端设备120可以直接车载T-BOX进行数据交互。在一些实施例中，移动设备120可以是平板电脑。在移动设备120处，当确认移动设备相对于车辆的距离小于预定值，可以获取车辆的自身数据、环境数据和气象数据，以在移动设备120处确定警示天气类型，以及在确定警示天气类型符合预定警示条件时，确定匹配的车险数据。通过采用上述手段，可以将充分利用移动设备120的更强计算资源、以及移动设备12与云服务器(或者车联网平台)之间的更便捷的通信能力以及云服务器(或者车联网平台)与第三方应用更好的兼容性进行警示天气类型和匹配车险数据的计算，以及进行车险数据的交互，进而减轻车机的计算负担和因配置带来的局限性。
以下将结合图2描述根据本公开的实施例的用于车辆安全的管理方法。图2示出了根据本公开的实施例的用于车辆安全的管理方法200的流程图。应当理解，方法200例如可以在图10所描述的电子设备1000处执行。也可以在图1所描述的移动设备120处或者车辆110车机处的执行。应当理解，方法200还可以包括未示出的附加动作和/或可以省略所示出的动作，本公开的范围在此方面不受限制。
在框202处，移动设备120或者车辆110的车机可以获取气象数据和环境数据中的至少一种，环境数据经由车辆处的车载设备采集。在一些实施例中，在移动设备120处，响应于确认移动设备相对于车辆的距离小于预定值，获取环境数据和气象数据，以用于确定警示天气类型。关于环境数据，在一些实施例中，其至少包括以 下的至少一项：经由车辆的摄像装置所采集的环境视频数据，环境视频数据至少包括车辆车窗图像数据和车辆外部环境图像数据；经由车辆的湿度传感器所检测的环境湿度数据；经由车辆的风量传感器所检测的环境风量数据；以及经由车辆的雨刮器传感器所检测的雨量数据；经由车辆的温度传感器所检测的环境温度数据。在一些实施例中，经由车辆的流媒体后视镜获取车辆的车辆车窗图像数据和车辆外部环境图像数据。该流媒体后视镜例如与车辆的多个摄像装置(例如前置摄像头和后置摄像头)相连。通过采用流媒体式的图像传输方式，可以实现车辆环境图像数据的高速率、低噪声、高准确度的传输。
关于雨刮器传感器，在一些实施例中，其例如而不限于是：光学式传感器或者是电容式传感器。例如，在光学式传感器形式的雨刮器传感器中包括：多个发光二极管和反射光接收器。该发光二极管和反射光接收器例如设置在前挡风玻璃内侧。当多个发光二极管发出多束光线，该光线穿过前挡风玻璃反射到反射光接收器。当前挡风玻璃上存在雨滴、雪花或者冰雹时，光线就会偏离，反射光接收器所接收的信号相对于晴好天气时所接收的信号发生变化。基于所接收的信号发生变化，可以确定出雨量，例如可以确定单位面积雨滴的多少。关于电容式传感器形式的雨刮器传感器，在一些实施例中，其例如是利用雨滴(例如水的介电常数为80)和玻璃(例如玻璃介电常数为2)的介电常数的差异，基于玻璃的介电常数的变化来确定落在玻璃上雨量数据。因此，移动设备120或者车辆110可以通过获得雨刮器传感器的雨量数据，将其用于后续确定警示天气类型。
在框204处，移动设备120或者车辆110的车机基于气象数据和环境数据中的至少一种，确定警示天气类型。关于其中确定警示天气类型的方法可以通过多种方式实现。
应当理解，恶劣天气下，所采集的图像的分辨率一般较低，因此利用一般的基于图像的机器学习算法来识别天气，准确率相对较 低。经研究发现，恶劣天气对所采集的图像数据的影响和一般图像数据存在概率分布上的差异。以下结合公式(1)来说明恶劣天气对所采集的图像数据的影响。
O＝B+S     (1)
在上述公式(1)中，O代表带有恶劣天气影响的输入图像(例如车窗图像数据、车辆外部环境图像数据)。B代表没有恶劣天气影响的输入图像，S代表恶劣天气(例如低能见度、大雪、大雨、闪电、冰雹等)影响所带来的图像噪声数据。因此，公式(1)中S可以理解被理解为传统意义上图像噪声数据。因而，可以将恶劣天气对所采集图像的影响视为图像数据的噪声，然后通过分类网络对图像噪声数据进行有效分类，进而高效率地确定警示天气类型。
在一些实施例中，确定警示天气类型的方法例如包括：移动设备120或者车辆110的车机基于车辆的环境图像数据，生成环境图像噪声数据；基于环境图像噪声数据的概率分布，确定警示天气类型是否指示为大雨、大雪、冰雹中的一种。通过利用车辆的环境图像数据(例如车窗图像噪声数据)来确定警示天气类型，不仅能够高效率高地确定警示天气类型。而且相较于一般基于图像识别天气的方法，其能够更为有效地在对低分辨率的指示恶劣天气的高频图像噪声进行分类的同时，明显地提高了计算效率。
应当理解，当车辆突然遭遇强降水天气、暴雪或者冰雹袭击时，在车辆车窗的图像中会出现具有一定密度的较大粒子半径的雨滴、雪花或者冰雹。这些车窗图像上出现雨滴、雪花或者冰雹构成了车窗图像数据的噪声点。因此可以利用车窗图像噪声数据来识别雨滴、雪花和冰雹的情况，进而识别当前天气是否属于强降水天气、暴雪或者冰雹的警示天气类型。因为车窗图像数据中所指示的图像信息相对于车辆的环境图像数据所指示的图像信息而言，更为简单，特别是前车窗图像数据，通常包括前方道路与车辆，因此，利用车窗 图像数据，特别是前车窗图像数据识别当前天气类型的计算效率更高。
以下会结合图6至图8描述确定警示天气类型的具体方法。在此不再赘述。
在框206处，移动设备120或者车辆110的车机确定警示天气类型是否符合预定警示条件。
在框208处，如果移动设备120或者车辆110的车机确定警示天气类型符合预定警示条件，则基于天气数据和环境数据中的至少一种以及车辆的行驶数据，确定与车辆相匹配的车险数据。
关于确定警示天气类型符合预定警示条件，在一些实施例中，其例如是包括以下至少一项：如果移动设备120或者车辆110确定警示天气类型指示为低能见度、大雪、大雨、闪电、冰雹，冰冻中的至少一项，则确定警示天气类型符合预定警示条件，其中低能见度包括雾霾、沙尘暴中的至少一种。或者如果移动设备120或者车辆110确定当前警示天气类型相对于过去预定时间间隔内的警示天气类型的变化情况符合第一预定条件。或者移动设备120或者车辆110综合上述两种情形来判断确定响应于确定当前警示天气类型是否属于需要购买保险的警示天气。通过判断当前警示天气类型是否发生突变，可以针对突遭恶劣天气的及时警示，以便购买与突遭恶劣天气类型匹配的保险。
在框210处，在移动设备120和车辆110的车载显示屏的至少一处显示与车险数据相关联的标识，移动设备经由检测到在移动设备上的预定动作而与车辆相关联。在一些实施例中，所显示的标识用于给以图形化方式提示用户的种类、保险权益和费用，用户只要简单的确定就可以享受相关保险的服务。例如包括用于指示与车辆相匹配的车险险种的可操作图标。例如，如果确定恶劣天气类型为大雨(即强降雨天气)，车险数据例如是推荐的车辆涉水险，与车险数据相关联的标识例如是指示车辆涉水的可操作图标。如果确定恶劣天气类型为暴雪，与车险数据相关联的标识例如是指示车辆侧 滑剐蹭的可操作图标。在一些实施例中，可以通过语音提示车险数据。
在上述方案中，通过在基于所获的气象数据和车辆处所采集的环境数据中的至少一种，确定警示天气类型符合预定警示条件时，根据指示气象数据和实际环境数据的至少一种以及表征车况的车辆行驶数据来匹配保险数据，可以实现所确定的保险数据与车辆实际突遭的恶劣天气的情形相匹配，而且通过在与车辆关联的移动设备和车辆的至少一处显示匹配的保险标识，使得即可以给车辆驾驶人员和乘客以与警示天气类型相关的信号警示，而且以标识的方式，而非直接显示保险数据的方式，有利于用户快速识别和发出关于保险的操作，而不会对安全驾驶带来不必要的干扰。
在一些实施例中，例如当用户通过摇一摇移动设备120打开车辆110的车门后，移动设备120基于所获取气象数据和/或环境数据确定警示天气类型为大雾时，移动设备120上所显示钥匙卡片显示警示或者标识，例如，“今天大雾，谨慎驾驶”，以及是否“需要购买10块钱额外险或者剐蹭险”。如果用户点击购买，车辆110的屏幕上例如显示“今天有保险的大图标”。
在一些实施例中，如果移动设备120或者车辆110的车机确认警示天气类型指示大雨，还可以进一步确定当前位置至目的地的路径中是否存在涉水警示区域。涉水警示区域的确定可以基于与路径相关联的地理特征、道路属性、以及历史数据中的至少一项而确定。如果移动设备120或者车辆110的车机确认当前路径中确实存在涉水警示区域，在移动设备和车辆的车载显示屏的至少一处呈现用于标识当前位置至目的地之间的待选路径的信息。
在一些实施例中，移动设备120或者车辆110的车机可以为用户规划一条较佳的不涉及涉水警示区域的路径。如果移动设备120或者车辆110的车机检测到关于该规划路径的操作(例如用户点选了没有涉水警示区域的规划路径)；移动设备120或者车辆110的车机可以基于移动设备120所接受的导航信息和交通信息(例如车 联网平台所提供的交通事故拥堵信息)，确定经由该规划路径到达目的地的预期时间；然后例如在移动设备和/或车辆的车载显示屏显示预期时间。
在一些实施例中，方法200还可以包括用于生成保险订单的方法300。以下将结合图3描述用于生成保险订单的方法。图3示出了根据本公开的实施例的用于生成保险订单的方法300的流程图。应当理解，方法300例如可以在图10所描述的电子设备1000处执行。也可以在图1所描述的移动设备120处或者车辆110的车机处的执行。应当理解，方法300还可以包括未示出的附加动作和/或可以省略所示出的动作，本公开的范围在此方面不受限制。
在框302处，移动设备120或车辆110的车机确定是否检测到针对可操作图标的操作。
在框304处，如果在移动设备120或车辆110的车机检测到针对可操作图标的操作，则获取与移动设备120相关联的用户的个人信息。该个人信息例如是用于购买保险所需的个人数据和支付信息。
在框306处，移动设备120或车辆110的车机基于所获取的个人信息和车险数据，生成与车险数据相关联的订单数据。
在框308处，经由移动设备120向云服务器发送订单数据。
在一些实施例中，移动设备120或车辆110的车机可以确定是否检测到针对可操作图标的操作；如果检测到针对可操作图标的操作，可以直接经由移动设备120向云服务器发送与车险数据相关联的订单数据。通过上述方式，可以经由用户对操作图标的操作，直接发送保险订单，例如在保费较少、与服务器已经存有用户个人信息等一些情形下，能够便捷与高效地购买保险的。
图4示出了根据本公开的实施例的用于确定警示天气类型的方法400的流程图。应当理解，方法400例如可以在图10所描述的电子设备1000处执行。也可以在图1所描述的移动设备120处或者车辆110的车机处的执行。应当理解，方法400还可以包括未示出的附加动作和/或可以省略所示出的动作，本公开的范围在此方面不受 限制。
在框402处，移动设备120或车辆110的车机在环境视频数据中选择多组环境图像序列。
在框404处，移动设备120或车辆110的车机基于多组环境图像序列，确定环境图像序列中的背景对象。
在框406处，如果在移动设备120或车辆110的车机确定以下至少一项条件满足，确定警示天气类型是否指示为低能见度：背景对象的边缘强度低于第一预定阈值；背景对象的图像锐度低于第二预定阈值，第一预定阈值和第二预定阈值是基于与背景对象相关联的历史图像数据而确定的；以及背景对象在环境图像序列中消失的速度高于第三预定阈值，第三预定阈值是基于与背景对象相关联的历史图像数据和车辆的行驶速度而确定的。通过采用上述手段，本公开能够快速、准确确定警示天气类型，特别是低能见度，以便及时指示与低能见度匹配的保险。
图5示出了根据本公开的实施例的用于确定警示天气类型的方法500的流程图。应当理解，方法500例如可以在图10所描述的电子设备1000处执行。也可以在图1所描述的移动设备120处或者车辆110的车机处的执行。应当理解，方法500还可以包括未示出的附加动作和/或可以省略所示出的动作，本公开的范围在此方面不受限制。
在框502处，移动设备120或者车辆110的车机基于车窗图像数据和车辆外部环境图像数据中的至少一种图像数据，生成高频图像，高频图像包括车窗图像数据和/或车辆外部环境图像数据中的高频信息。在一些实施例中，移动设备120或者车辆110的车机可以经由频域变换，基于车窗图像数据，生成车窗高频图像。例如，高频图像对应于车窗图像数据的高频分量，低频图像对应于车窗图像数据的低频分量。
应当理解，图像中的低频分量(低频信号)一般代表着图像中梯度变化较小的部分，例如是亮度或者灰度值变化缓慢的区域，因 此，低频分量可用于对整幅图像强度的综合度量。图像中的高频分量(高频信号)一般指示图像变化剧烈的部分，或者梯度变化较大的部分，例如是图像的边缘(轮廓)或者噪声以及细节部分，因此，高频分量可用于对图像边缘和轮廓的度量。正如前文，传统意义上的图像噪声数据通常分布在图像的高频部分。经研究发现，恶劣天气对图像的影响通常分布在高频部分。
在一些实施例中，移动设备120或者车辆110的车机可以基于小波变换，将车窗图像数据或者车辆外部环境图像数据分为高频图像(高频图像)和低频图像(低频图像)。通过采用小波变换来获得车窗图像数据分中用于标识恶劣天气影响的高频图像，可以在时域和频域都有良好的局部特性，因而能够更有效地从信号中提取高频信息。特别是能够更好地满足分析恶劣天气影响这一非平稳信号时的需要。
在一些实施例中，移动设备120或者车辆110的车机也可以将车窗图像数据进行二维傅立叶变换，以便生成车窗图像数据的频谱图。该频谱图中标识了车窗图像数据的图像梯度的分布。该车窗图像数据的频谱图上可能存在多个指示恶劣天气的高频分量。恶劣天气的类型不同，其导致的车窗图像数据的变化剧烈的高频分量的特征也会不同。如果车窗图像数据的各个位置的强度大小变化很小，则车窗图像数据只存在低频分量。则可能指示不存在恶劣天气。
在框504处，移动设备120或者车辆110的车机可以基于识别模型，提取高频图像的高频特征。该识别模型可以经由对多个训练样本的机器学习而生成。可以通过多种方式来提取高频图像的特征。以下结合图6至图8来说明如何提取高频图像的特征。
图6示出了根据本公开的实施例的用于识别警示天气类型的方法600的整体示意图。如图6所示，可以利用encoder-decoder神经网络模型来提取高频图像(例如是车窗噪声图像)的高频特征。再通过分类模型针对经由encoder-decoder神经网络模型所提取的高频特征进行分类，以确定警示天气类型，即预测指示警示天气的类型 值。
如图6所示，用于确定警示天气类型的识别方法600主要包括encoder-decoder处理602和分类处理604。其中，encoder-decoder处理602主要用于实现框504处动作。在一些实施例中，encoder-decoder处理602用于基于输入的高频图像(例如车窗高频图像和/或车辆外部环境高频图像)，提取高频特征。分类处理604用于基于所提取的高频特征，确定警示天气类型。
关于encoder-decoder处理602，在一些实施例中，其包括：将输入图像604(例如车窗高频图像和/或车辆外部环境高频图像)输入encoder模型606，以便生成低频特征608和高频特征610，然后将低频特征608和经由L2正则化处理的高频特征610输入decoder模型612进行处理，以便生成合成图像614。所生成合成图像614可以作为encoder-decoder处理602的训练样本。经由重建损失处理在大量样本训练的过程中调整encoder-decoder神经网络模型的网络结构参数。应当理解，通过encoder-decoder处理602可以实现提取高频图像的高频特征。
图7示出了根据本公开的实施例的提取高频特征的处理700的示意图。如图7所示，将前文提及的多个高频图像702(例如车窗高频图像)作为输入图像，输入至resNet50模型704(其中ResNet50模型所具有的卷积层为50)，经由卷积处理706和708，分别获得低频特征710和高频特征712，然后将低频特征710和高频特征712分别输入上采样模型716和718，之后经由按照元素操作层求和处理720(Eltwise-sum)，输出合成图像722。其中，上采样模型716和718、Eltwise-sum处理720构成decoder网络结构714。
关于ResNet50，其包括三个主要部分：输入部分、输出部分和中间卷积部分，中间卷积部分用于通过卷积的堆叠来实现输入的高频图像的高频特征的提取，其例如包括Stage1到Stage4共计四个stage。ResNet50将stage4中的步长(Stride＝2)改为1，因此经由ResNet50得到的特征图像为输入图像的1/16，利于提高处理效果和 效率，以及极大减少了存储所需空间大小。通过采用ResNet50模型进行encoder处理，利于提高分解低频特征710和高频特征612的处理效果和效率。
关于卷积处理706和708，在一些实施例中，其卷积核个数例如为256，卷积核的大小例如是3*3，步长(stride)例如为1。
关于上采样模型716或718，在一些实施例中，其例如是四组采样模型。decoder网络结构714用于将经处理的图像还原至原始输入图像，因此需要经由上采样模型使得经前道降维处理的图像被还原成与原始输入图像大小一致的图像。这样可以使得图像的重建损失处理(Reconstruction loss)相对容易。
关于重建损失处理，以下结合公式(2)来具体说明。
Figure PCTCN2019124107-appb-000001
在上述公式(2)中，I代表输入图像(例如高频图像702)的二维向量。I’代表经由decoder网络结构714处理合成图像722的二维向量。l r代表重建损失。一般重建损失越小，就代表encoder-decoder模型拟合的越好。在一些实施例中，重建损失函数为输入图像的二维向量与合成图像二维向量的对应像素点的平方求和。
关于高频特征610输出的高频损失处理，以下结合公式(3)来具体说明。
Figure PCTCN2019124107-appb-000002
在上述公式(3)中，I H代表高频特征的二维向量。l e代表高频损失。
图8示出了根据本公开的实施例的上采样处理800的示意图。 如图8所示，上采样处理800例如示例的是前文提及的上采样模型716或718中四组采样模型中的一组采样模型。上采样处理800例如包括反卷积处理802、卷积处理804和卷积处理806。在反卷积处理802中，卷积核为256个，卷积核大小为4*4，步长(stride)例如为2。在卷积处理804中，卷积核为512个，卷积核大小为1*1，步长(stride)例如为1。在卷积处理806中，卷积核为256个，卷积核大小为3*3，步长(stride)例如为1。
encoder-decoder处理的整体损失函数例如可以由以下公式(4)来进行计算。
Figure PCTCN2019124107-appb-000003
在上述公式(4)中，l r代表重建损失，l e代表高频损失，
Figure PCTCN2019124107-appb-000004
代表encoder-decoder处理的整体损失，λ代表系数，用于平衡重建损失和高频损失在encoder-decoder处理的整体损失中重要性。
在框506处，移动设备120或者车辆110的车机基于所提取的高频特征，确定高频图像所指示的警示天气类型。可以通过多种方式来确定车窗高频图像所指示的警示天气类型。以下结合图6中的分类处理604来具体说明如何确定高频图像所指示的警示天气类型。如图6所示，分类处理604例如包括：将经由encoder-decoder处理602提取的高频特征610输入分类模型624，然后经由归一化指数处理626(Softmax)，以便获得输出628，经由分类损失处理632，调整分类模型622的网络结构参数。应当理解，通过分类模型622的处理，最终针对高频特征610的所确定的警示天气类型例如是标签630所指示类型。
关于分类模型624，在一些实施例中，可使用ResNet18分类网络基于所提取的高频特征来确定警示天气类型。ResNet18分类网络例如可以基于输入的高频特征610，经由每个stage的下采样处理(downsample)，使得输入的高频特征图被降维处理，直至最后接 全连接层输出，例如，分类模型624输出节点个数与预测警示天气的类型个数一致。
框506处的分类处理的损失函数例如遵循以下公式(5)。
Figure PCTCN2019124107-appb-000005
在上述公式(5)中，N代表样本数量，C代表类别，y i代表关于警示天气类型的输出预测值，p c代表归一化指数处理626的输出值，
Figure PCTCN2019124107-appb-000006
代表分类处理的损失函数。
在上述方案中通过依据雨天、雾天、雪天等恶劣天气在高频上分布的差异，生成指示恶劣天气影响的高频图像，利用分类网络针对高频图像进行分类，可以高效率并且准确地确定警示天气的类型。
在一些实施例中，不仅可以利用车窗高频图像来警示天气的类型，还可以融合多种传感器的检测结果来综合确定警示天气的类型，使得确定结果更为准确。以下结合图9来说明如何融合多种传感器的检测结果来确定警示天气的类型。图9示出了根据本公开的实施例的用于确定警示天气类型的方法900的示意图。应当理解，方法900例如可以在图10所描述的电子设备1000处执行。也可以在图1所描述的移动设备120处或者车辆110的车机处的执行。应当理解，方法900还可以包括未示出的附加动作和/或可以省略所示出的动作，本公开的范围在此方面不受限制。
在框902处，移动设备120或者车辆110的车机基于车辆外部环境图像数据，确定车辆后部地面图像区域.
在框904处，移动设备120或者车辆110的车机提取车辆后部地面图像区域的图像特征。
在框906处，移动设备120或者车辆110的车机基于所提取的图像特征，确定车辆后部地面图像区域中是否存在积雪和积水中的一种。
在框908处，如果移动设备120或者车辆110的车机确定车辆后部地面图像区域中存在积雪和积水中的一种，可以基于高频图像、以及环境温度数据和环境湿度数据中的至少一项，确定警示天气类型。
在上述方案中，通过融合基于车窗高频图像的识别结果、基于车辆后部地面图像区域的识别结果，以及环境温度数据和环境湿度数据，能够准确地识别警示天气的类型，例如识别强降水天气、暴雪天气。
图10示意性示出了适于用来实现本公开实施例的电子设备1000的框图。设备1000可以是用于实现执行图2至5所示的方法200、300、400、500和900的设备。如图10所示，设备1000包括中央处理单元(CPU)1001，其可以根据存储在只读存储器(ROM)1002中的计算机程序指令或者从存储单元1008加载到随机访问存储器(RAM)1003中的计算机程序指令，来执行各种适当的动作和处理。在RAM 1003中，还可存储设备1000操作所需的各种程序和数据。CPU 1001、ROM 1002以及RAM1003通过总线1004彼此相连。输入/输出(I/O)接口1005也连接至总线1004。
设备1000中的多个部件连接至I/O接口1005，包括：输入单元1006、输出单元1007、存储单元1008，处理单元1001执行上文所描述的各个方法和处理，例如执行方法200、300、400、500和900。例如，在一些实施例中，方法200、300、400、500和9000可被实现为计算机软件程序，其被存储于机器可读介质，例如存储单元1008。在一些实施例中，计算机程序的部分或者全部可以经由ROM 1002和/或通信单元1009而被载入和/或安装到设备1000上。当计算机程序加载到RAM 1003并由CPU 1001执行时，可以执行上文描述的方法200、300、400、500和900的一个或多个操作。备选地，在其他实施例中，CPU 1001可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行方法200、300、400、500和900的一个或多个动作。
需要进一步说明的是，本公开可以是方法、装置、系统和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于执行本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是但不限于电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，该编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或 类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、设备(系统)、和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给语音交互装置中的处理器、通用计算机、专用计算机或其它可编程数据处理装置的处理单元，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理单元执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动 作。
附图中的流程图和框图显示了根据本公开的多个实施例的设备、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，该模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。
以上该仅为本公开的可选实施例，并不用于限制本公开，对于本领域的技术人员来说，本公开可以有各种更改和变化。凡在本公开的精神和原则之内，所作的任何修改、等效替换、改进等，均应包含在本公开的保护范围之内。

Claims (16)

  1. 一种用于车辆安全的管理方法，包括：
    获取气象数据和环境数据中的至少一种，所述环境数据经由车辆处的车载设备采集；
    基于所述气象数据和所述环境数据中的至少一种，确定警示天气类型；
    响应于确定所述警示天气类型符合预定警示条件，基于所述天气数据和所述环境数据中的至少一种以及车辆的行驶数据，确定与所述车辆相匹配的车险数据；以及
    在移动设备和所述车辆的车载显示屏的至少一处呈现与所述车险数据相关联的标识，所述移动设备经由检测到在所述移动设备上的预定动作而与所述车辆相关联。
  2. 根据权利要求1所述的方法，所述环境数据至少包括以下的至少一项：
    经由所述车辆的摄像装置所采集的环境视频数据，所述环境视频数据至少包括车辆车窗图像数据和车辆外部环境图像数据；
    经由所述车辆的湿度传感器所检测的环境湿度数据；
    经由所述车辆的风量传感器所检测的环境风量数据；
    经由所述车辆的雨刮器传感器所检测的雨量数据；以及
    经由所述车辆的温度传感器所检测的环境温度数据。
  3. 根据权利要求1所述的方法，经由所述车辆的流媒体后视镜获取所述车辆的环境视频数据，所述环境视频数据至少包括车辆车窗图像数据和车辆外部环境图像数据，所述流媒体后视镜与所述车辆的多个摄像装置相连。
  4. 根据权利要求1所述的方法，其中与所述车险数据相关联的标识包括用于指示与所述车辆相匹配的车险险种的可操作图标。
  5. 根据权利要求4所述的方法，还包括：
    响应于检测到针对所述可操作图标的操作，获取与所述移动设 备相关联的用户的个人信息；
    基于所获取的所述个人信息和所述车险数据，生成与所述车险数据相关联的订单数据；以及
    经由所述移动设备向云服务器发送所述订单数据。
  6. 根据权利要求4所述的方法，还包括：
    响应于检测到针对所述可操作图标的操作，经由所述移动设备向云服务器发送与所述车险数据相关联的订单数据。
  7. 根据权利要求1所述的方法，还包括：
    在所述移动设备处，响应于确认所述移动设备相对于所述车辆的距离小于预定值，获取所述环境数据和所述气象数据，以用于确定警示天气类型。
  8. 根据权利要求2或3所述的方法，其中确定警示天气类型包括：
    基于所述车辆的环境图像数据，生成环境图像噪声数据；以及
    基于所述环境图像噪声数据的概率分布，确定所述警示天气类型是否指示为大雨、大雪、冰雹中的一种。
  9. 根据权利要求2所述的方法，其中确定警示天气类型还包括：
    基于所述车窗图像数据和所述车辆外部环境图像数据中的至少一种图像数据，生成高频图像，所述高频图像包括所述至少一种图像数据中的高频信息；
    基于识别模型，提取所述高频图像的高频特征，所述识别模型经由对多个训练样本的机器学习而生成；以及
    基于所提取的所述高频特征，确定所述高频图像所指示的警示天气类型。
  10. 根据权利要求8所述的方法，其中确定警示天气类型还包括：
    基于所述车辆外部环境图像数据，确定车辆后部地面图像区域；
    提取所述车辆后部地面图像区域的图像特征；
    基于所提取的图像特征，确定所述车辆后部地面图像区域中是 否存在积雪和积水中的一种；以及
    响应于确定所述车辆后部地面图像区域中存在积雪和积水中的一种，基于所述高频图像、以及所述环境温度数据和所述环境湿度数据中的至少一项，确定所述警示天气类型。
  11. 根据权利要求2或3所述的方法，其中确定警示天气类型包括：
    在所述环境视频数据中选择多组环境图像序列；
    基于所述多组环境图像序列，确定所述环境图像序列中的背景对象；以及
    响应于确定以下至少一项条件满足，确定所述警示天气类型是否指示为低能见度：
    所述背景对象的边缘强度低于第一预定阈值；
    所述背景对象的图像锐度低于第二预定阈值，所述第一预定阈值和第二预定阈值是基于与所述背景对象相关联的历史图像数据而确定的；以及
    所述背景对象在所述环境图像序列中消失的速度高于第三预定阈值，所述第三预定阈值是基于与所述背景对象相关联的历史图像数据和所述车辆的行驶速度而确定的。
  12. 根据权利要求2或3所述的方法，还包括：
    响应于确认所述警示天气类型指示大雨，确定当前位置至目的地的路径中是否存在涉水警示区域，所述涉水警示区域基于与所述路径相关联的地理特征、道路属性、以及历史数据中的至少一项而确定；以及
    响应于确定所述路径中存在涉水警示区域，在所述移动设备和所述车辆的车载显示屏的至少一处显示用于标识所述当前位置至所述目的地之间的待选路径的信息。
  13. 根据权利要求12所述的方法，还包括：
    响应于检测到关于所述待选路径的操作；
    基于所述移动设备所接收的导航信息和交通信息，确定经由所 述待选路径到达目的地的预期时间；以及
    在所述移动设备和所述车辆的车载显示屏的至少一处呈现所述预期时间。
  14. 根据权利要求1所述的方法，其中确定所述警示天气类型符合预定警示条件包括以下至少一项：
    响应于确定所述警示天气类型指示为低能见度、大雪、大雨、闪电、冰雹，冰冻中的至少一项，确定警示天气类型符合预定警示条件，所述低能见度包括雾霾、沙尘暴中的至少一种；以及
    响应于确定当前警示天气类型相对于过去预定时间间隔内的警示天气类型的变化情况符合第一预定条件。
  15. 一种用于车辆安全的管理的装置，包括：
    存储器，被配置为存储一个或多个计算机程序；以及
    处理器，耦合至所述存储器并且被配置为执行所述一个或多个程序使所述装置执行根据权利要求1-14中任一项所述的方法。
  16. 一种非瞬态计算机可读存储介质，其上存储有机器可执行指令，所述机器可执行指令在被执行时使机器执行根据权利要求1-14中任一项所述的方法的步骤。
PCT/CN2019/124107 2019-10-30 2019-12-09 用于车辆安全的管理方法、装置和计算机存储介质 WO2021082194A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/773,299 US20240157958A1 (en) 2019-10-30 2019-12-09 Management method and apparatus for vehicle safety, and computer storage medium
EP19950670.0A EP4036890A4 (en) 2019-10-30 2019-12-09 VEHICLE SECURITY AND COMPUTER STORAGE MEDIUM MANAGEMENT METHOD AND APPARATUS

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911043704.6A CN112750323A (zh) 2019-10-30 2019-10-30 用于车辆安全的管理方法、装置和计算机存储介质
CN201911043704.6 2019-10-30

Publications (1)

Publication Number Publication Date
WO2021082194A1 true WO2021082194A1 (zh) 2021-05-06

Family

ID=75640526

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/124107 WO2021082194A1 (zh) 2019-10-30 2019-12-09 用于车辆安全的管理方法、装置和计算机存储介质

Country Status (4)

Country Link
US (1) US20240157958A1 (zh)
EP (1) EP4036890A4 (zh)
CN (1) CN112750323A (zh)
WO (1) WO2021082194A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113571906A (zh) * 2021-06-09 2021-10-29 武汉格罗夫氢能汽车有限公司 一种氢能汽车隐藏式杆式天线保护方法
CN113741460A (zh) * 2021-09-06 2021-12-03 东风汽车集团股份有限公司 一种防止车辆被暴雨浸没的系统及方法
CN113938300A (zh) * 2021-10-12 2022-01-14 湖北亿咖通科技有限公司 分级控制方法及装置
CN114022899A (zh) * 2021-10-29 2022-02-08 上海商汤临港智能科技有限公司 检测车辆乘员的身体部位伸出车窗外的方法、装置及车辆
CN114114464A (zh) * 2021-11-12 2022-03-01 北京三快在线科技有限公司 天气提醒方法、装置、设备及介质
CN116279113A (zh) * 2023-01-12 2023-06-23 润芯微科技(江苏)有限公司 一种极端天气预警方法、系统及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113570739B (zh) * 2021-07-06 2023-03-21 奇瑞新能源汽车股份有限公司 新能源汽车不停车收费系统及其收费方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9183176B2 (en) * 2012-04-25 2015-11-10 Electronics And Telecommunications Research Institute Method and apparatus for providing driver-customized vehicle service
CN105405306A (zh) * 2015-12-24 2016-03-16 小米科技有限责任公司 车辆告警方法及装置
CN107909839A (zh) * 2017-11-21 2018-04-13 北京华油信通科技有限公司 车辆安全处理方法及装置
CN108924253A (zh) * 2018-08-02 2018-11-30 成都秦川物联网科技股份有限公司 基于车联网的天气预告方法及车联网系统
CN108909656A (zh) * 2017-04-18 2018-11-30 宝沃汽车（中国）有限公司 一种车辆预警方法、装置以及车辆
CN109326134A (zh) * 2018-12-03 2019-02-12 北京远特科技股份有限公司 谨慎驾驶提醒方法及装置

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104345355B (zh) * 2014-09-30 2016-05-18 天青公司 一种采集与处理天气数据和图像的装置、方法和系统
CN104318477A (zh) * 2014-11-11 2015-01-28 西红柿科技（武汉）有限公司 一种基于大数据的车辆保险评估的方法
US10007263B1 (en) * 2014-11-13 2018-06-26 State Farm Mutual Automobile Insurance Company Autonomous vehicle accident and emergency response
CN104834912B (zh) * 2015-05-14 2017-12-22 北京邮电大学 一种基于图像信息检测的天气识别方法及装置
CN105196910B (zh) * 2015-09-15 2018-06-26 浙江吉利汽车研究院有限公司 一种雨雾天气下的安全驾驶辅助系统及其控制方法
CN105651293A (zh) * 2015-12-30 2016-06-08 联动优势科技有限公司 一种路径规划的导航方法及装置
JP6962316B2 (ja) * 2016-03-29 2021-11-05 ソニーグループ株式会社 情報処理装置、情報処理方法、プログラム、およびシステム
CN109426977A (zh) * 2017-08-28 2019-03-05 北京嘀嘀无限科技发展有限公司 一种信息处理方法、信息处理系统及计算机装置
CN109325856A (zh) * 2018-08-29 2019-02-12 广州巨时信息科技有限公司 一种基于物联网大数据的车险精准推送方法
CN109617942B (zh) * 2018-10-22 2022-05-17 平安科技（深圳）有限公司 产品数据推送方法、装置、计算机设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9183176B2 (en) * 2012-04-25 2015-11-10 Electronics And Telecommunications Research Institute Method and apparatus for providing driver-customized vehicle service
CN105405306A (zh) * 2015-12-24 2016-03-16 小米科技有限责任公司 车辆告警方法及装置
CN108909656A (zh) * 2017-04-18 2018-11-30 宝沃汽车（中国）有限公司 一种车辆预警方法、装置以及车辆
CN107909839A (zh) * 2017-11-21 2018-04-13 北京华油信通科技有限公司 车辆安全处理方法及装置
CN108924253A (zh) * 2018-08-02 2018-11-30 成都秦川物联网科技股份有限公司 基于车联网的天气预告方法及车联网系统
CN109326134A (zh) * 2018-12-03 2019-02-12 北京远特科技股份有限公司 谨慎驾驶提醒方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4036890A4 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113571906A (zh) * 2021-06-09 2021-10-29 武汉格罗夫氢能汽车有限公司 一种氢能汽车隐藏式杆式天线保护方法
CN113741460A (zh) * 2021-09-06 2021-12-03 东风汽车集团股份有限公司 一种防止车辆被暴雨浸没的系统及方法
CN113741460B (zh) * 2021-09-06 2023-11-10 东风汽车集团股份有限公司 一种防止车辆被暴雨浸没的系统及方法
CN113938300A (zh) * 2021-10-12 2022-01-14 湖北亿咖通科技有限公司 分级控制方法及装置
CN113938300B (zh) * 2021-10-12 2023-08-15 亿咖通(湖北)技术有限公司 分级控制方法及装置
CN114022899A (zh) * 2021-10-29 2022-02-08 上海商汤临港智能科技有限公司 检测车辆乘员的身体部位伸出车窗外的方法、装置及车辆
CN114114464A (zh) * 2021-11-12 2022-03-01 北京三快在线科技有限公司 天气提醒方法、装置、设备及介质
CN116279113A (zh) * 2023-01-12 2023-06-23 润芯微科技(江苏)有限公司 一种极端天气预警方法、系统及存储介质

Also Published As

Publication number Publication date
EP4036890A4 (en) 2024-01-24
CN112750323A (zh) 2021-05-04
US20240157958A1 (en) 2024-05-16
EP4036890A1 (en) 2022-08-03

Similar Documents

Publication Publication Date Title
WO2021082194A1 (zh) 用于车辆安全的管理方法、装置和计算机存储介质
US11118923B2 (en) Data processing system communicating with a map data processing system to determine or alter a navigation path based on one or more road segments
US10147004B2 (en) Automatic image content analysis method and system
CN109358612B (zh) 智能驾驶控制方法和装置、车辆、电子设备、存储介质
Negru et al. Image based fog detection and visibility estimation for driving assistance systems
US9076045B2 (en) Automatic content analysis method and system
US10223910B2 (en) Method and apparatus for collecting traffic information from big data of outside image of vehicle
US10814815B1 (en) System for determining occurrence of an automobile accident and characterizing the accident
CN111094095B (zh) 自动地感知行驶信号的方法、装置及运载工具
JP2021536648A (ja) ドライバの挙動を分類するためのシステムおよび方法
US11734880B2 (en) Sensor calibration with environment map
US11615551B2 (en) Assessing visibility of a target object with autonomous vehicle fleet
US11748664B1 (en) Systems for creating training data for determining vehicle following distance
Vaibhav et al. Real-time fog visibility range estimation for autonomous driving applications
US11137256B2 (en) Parking area map refinement using occupancy behavior anomaly detector
WO2023173699A1 (zh) 基于机器学习的辅助驾驶方法、装置和计算机可读介质
CN114998863A (zh) 目标道路识别方法、装置、电子设备以及存储介质
US11989949B1 (en) Systems for detecting vehicle following distance
US20230110464A1 (en) Vehicle occupant gaze detection system and method of using
US20240087092A1 (en) Method, apparatus, user interface, and computer program product for identifying map objects or road attributes based on imagery
Tian Identification of Weather Conditions Related to Roadside LiDAR Data
ApinayaPrethi et al. Fog detection and visibility measurement using SVM
CN115690719A (zh) 用于车辆周围的对象接近监测的系统和方法
CN114581615A (zh) 一种数据处理方法、装置、设备和存储介质
JP2021004923A (ja) 地図データ管理装置及び地図データ管理方法

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: 19950670

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 17773299

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2019950670

Country of ref document: EP

Effective date: 20220428

NENP Non-entry into the national phase

Ref country code: DE