WO2019128027A1 - 一种道路交通数据的处理方法及车载设备 - Google Patents

一种道路交通数据的处理方法及车载设备 Download PDF

Info

Publication number
WO2019128027A1
WO2019128027A1 PCT/CN2018/085875 CN2018085875W WO2019128027A1 WO 2019128027 A1 WO2019128027 A1 WO 2019128027A1 CN 2018085875 W CN2018085875 W CN 2018085875W WO 2019128027 A1 WO2019128027 A1 WO 2019128027A1
Authority
WO
WIPO (PCT)
Prior art keywords
traffic
vehicle
analysis result
data
abnormal
Prior art date
Application number
PCT/CN2018/085875
Other languages
English (en)
French (fr)
Inventor
刘均
刘新
周军
Original Assignee
深圳市元征软件开发有限公司
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 深圳市元征软件开发有限公司 filed Critical 深圳市元征软件开发有限公司
Publication of WO2019128027A1 publication Critical patent/WO2019128027A1/zh

Links

Classifications

    • 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]
    • 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

Definitions

  • the present invention relates to the field of data information technologies, and in particular, to a method for processing road traffic data and an in-vehicle device.
  • the driver generally judges the surrounding environment, and after an abnormality occurs, the management center is called to promptly report the alarm and wait for the management center to respond; or the abnormality alarm processing is passed through the person passing the accident or by traversing the government-set fixed-point camera. Manual search.
  • the prior art processing method is inefficient, and on the other hand, the data reported to the management center is not accurate enough to help the management center to prepare rescue measures in a targeted manner, resulting in slow rescue time and further increasing the losses caused by traffic anomalies.
  • the embodiment of the invention provides a method and a device for processing road traffic data, which is beneficial to solving the problems of low efficiency, inaccurate data and slow rescue time of the traffic accident alarm processing method in the prior art, and is beneficial to improving the processing efficiency of traffic anomalies. .
  • an embodiment of the present invention provides a method for processing road traffic data, the method being applied to an in-vehicle device having a driving record function, the in-vehicle device being mounted on a vehicle, the method comprising: acquiring the vehicle Position information; acquiring traffic environment data of the vehicle according to the location information; analyzing and calculating the traffic environment data to obtain a traffic environment data analysis result; determining, according to the traffic environment data analysis result, whether a traffic abnormality occurs; if yes, following the preset The algorithm analyzes the abnormal data to obtain the abnormal analysis result, and performs corresponding measures according to the abnormal analysis result.
  • the traffic environment data includes: vehicle information of the vehicle, within a preset distance from the vehicle The surrounding vehicle information and the surrounding road environment information; the traffic environment data analysis result includes a traffic vehicle data analysis result and a surrounding road environment analysis result; and the analyzing and calculating the traffic environment data includes: according to the vehicle information and the The surrounding vehicle information analysis calculates a distance between the vehicle and the surrounding vehicle, and obtains a traffic vehicle data analysis result according to the ambient sound; extracts the portrait data, the sound data, and the ambient brightness data according to the image data in the surrounding road environment information and performs Analyze and calculate the surrounding road environment analysis results.
  • the determining, according to the traffic environment data analysis result, whether a traffic abnormality occurs Specifically, when the distance of at least two vehicles in the traffic vehicle data analysis result is less than the first distance threshold and accompanied by an abnormal sound, it is determined that a traffic abnormality occurs; or, when the surrounding road environment analysis result is included At least two portraits, when the distance between the portraits is less than the second distance threshold and accompanied by an abnormal sound, it is judged that a traffic abnormality occurs; or, when the ambient brightness data in the surrounding road environment analysis result exceeds the normal brightness value, the traffic is judged to occur abnormal.
  • the abnormal analysis result includes a traffic anomaly type, a traffic abnormality level, a responsible party, and a loss value.
  • the performing the corresponding measures according to the abnormal analysis result specifically includes:
  • the traffic abnormality type determines a corresponding traffic abnormality management center; the abnormality analysis result and the location are sent to the corresponding traffic abnormality management center, so that the traffic abnormality management center takes measures to solve the traffic abnormality problem.
  • a second aspect of the present invention provides an in-vehicle device including: a memory storing executable program code; a processor coupled to the memory; the processor invoking the memory stored in the memory Executing the program code, performing the following steps: acquiring location information of the vehicle; acquiring traffic environment data of the vehicle according to the location information; analyzing and calculating the traffic environment data, obtaining a traffic environment data analysis result; and determining, according to the traffic environment data analysis result Whether there is traffic anomaly; if it is, the abnormal data is analyzed according to the preset algorithm to obtain the abnormal analysis result, and the corresponding measures are executed according to the abnormal analysis result.
  • the traffic environment data includes: vehicle information of the vehicle, within a preset distance from the vehicle The surrounding vehicle information and the surrounding road environment information; the traffic environment data analysis result includes a traffic vehicle data analysis result and a surrounding road environment analysis result; the processor performs the analysis to calculate the traffic environment data, and the specific manner is: Calculating the distance between the vehicle and the surrounding vehicle by using the vehicle information and the surrounding vehicle information, and obtaining the traffic vehicle data analysis result in combination with the environmental sound; extracting the portrait data and the sound data according to the image data in the surrounding road environment information And the ambient brightness data is analyzed and calculated to obtain the surrounding road environment analysis results.
  • the processor performs the data according to the traffic environment
  • the analysis result determines whether there is a traffic anomaly.
  • the specific way is: when there is at least two vehicles in the traffic vehicle data analysis result that the distance is less than the first distance threshold and accompanied by an abnormal sound, the traffic abnormality is judged; or There are at least two portraits in the surrounding road environment analysis result.
  • the abnormal analysis result includes a traffic anomaly type, a traffic abnormality level, a responsible party, and a loss value.
  • the processor performs the performing the corresponding measure according to the abnormal analysis result.
  • the specific manner is: determining a corresponding traffic anomaly management center according to the type of traffic anomaly; sending the abnormality analysis result and location to the corresponding traffic anomaly management center, so that the traffic abnormality management center takes measures to solve the traffic abnormality problem.
  • acquiring location information of the vehicle acquiring traffic environment data of the vehicle according to the location information; analyzing and calculating the traffic environment data, and obtaining a traffic environment data analysis result;
  • the traffic environment data analysis results determine whether there is a traffic anomaly; if yes, the abnormal data is analyzed according to a preset algorithm to obtain an abnormal analysis result, and corresponding measures are performed according to the abnormal analysis result.
  • the above method is used to realize the rapid reporting and timely processing of road traffic anomalies, which brings great convenience to alleviate the congestion caused by traffic anomalies, improves the processing efficiency of traffic anomalies, and ensures the timeliness of the rescue of the management center.
  • FIG. 1 is a schematic flowchart of a road traffic data processing method according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of an in-vehicle device according to an embodiment of the present invention.
  • FIG. 3 is a schematic structural diagram of another in-vehicle device according to an embodiment of the present invention.
  • references to "an embodiment” herein mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the invention.
  • the appearances of the phrases in various places in the specification are not necessarily referring to the same embodiments, and are not exclusive or alternative embodiments that are mutually exclusive. Those skilled in the art will understand and implicitly understand that the embodiments described herein can be combined with other embodiments.
  • Multiple means two or more. "and/or”, describing the association relationship of the associated objects, indicating that there may be three relationships, for example, A and/or B, which may indicate that there are three cases where A exists separately, A and B exist at the same time, and B exists separately.
  • the character "/" generally indicates that the contextual object is an "or" relationship.
  • the embodiment of the invention is applied to an in-vehicle device having a driving record function
  • the in-vehicle device may be an in-vehicle terminal, an in-vehicle recorder, an OBD box, or the like, or may be another in-vehicle device having a computing function and a driving record function.
  • the above examples are only used to illustrate the possible embodiments of the embodiments of the present invention, and should not be construed as limiting the embodiments of the present invention.
  • FIG. 1 is a schematic flowchart diagram of a road traffic data processing method according to an embodiment of the present invention. As shown in Figure 1, the method includes:
  • the in-vehicle device can acquire the vehicle location information through the base station positioning technology of the mobile communication network, and can also acquire the location information of the vehicle through a satellite navigation system (such as GPS, Beidou, etc.).
  • a satellite navigation system such as GPS, Beidou, etc.
  • the in-vehicle device can obtain the traffic environment data of the vehicle according to the location information.
  • the traffic environment data of the vehicle includes: vehicle information of the vehicle, surrounding vehicle information and surrounding road environment information within a preset distance from the vehicle.
  • the in-vehicle device can use various built-in sensors (camera sensor, acceleration sensor, gravity sensor, light sensor, etc.) to acquire traffic environment data of the vehicle, such as vehicle information of the vehicle itself, and surrounding vehicles within a preset distance from the vehicle. Information and surrounding road environment information.
  • the preset distance can be 100m, 500m, or other distances. There is no limit here.
  • the preset distance can be set according to the preferences of the vehicle user, or it can be fixed at the factory when the vehicle is installed.
  • the traffic environment data can be classified into vehicle data and surrounding road environment data. After analyzing and calculating the traffic environment data, the traffic environment data analysis results are obtained according to the classification, and the vehicle data analysis results and the surrounding road environment analysis results are obtained.
  • analyzing and calculating the traffic environment data specifically includes: calculating, according to the vehicle information and the surrounding vehicle information, a distance between the vehicle and the surrounding vehicle, and obtaining a traffic vehicle data analysis result according to the ambient sound;
  • the image data in the surrounding road environment information extracts portrait data, sound data, and environmental brightness data, and performs analysis and calculation to obtain a surrounding road environment analysis result.
  • the image data therein analyze the distance between the vehicle and the vehicle according to the image recognition algorithm or the artificial intelligence analysis algorithm, extract the portrait data and analyze the number of the calculation crowd, The type of the crowd, extracting the ambient brightness and calculating the brightness data; extracting the sound related to the vehicle, obtaining the decibel range of the sound, extracting the sound related to the crowd, and obtaining the decibel range of the sound and the type of the sound.
  • the distance between the vehicle and the vehicle and the sound decibel value related to the vehicle are taken as the traffic vehicle data analysis result;
  • the result of the portrait analysis (the number of people, the type of the crowd), the sound decibel range of the crowd, the sound type, and the ambient brightness data are taken as the periphery.
  • Road environment analysis results are taken as the distance between the vehicle and the vehicle and the sound decibel value related to the vehicle.
  • the first distance threshold may be a safety distance threshold, such as 0.5 m, or other values.
  • the abnormal sound may be abnormal noise generated by a vehicle collision or the like.
  • the decibel value can be used to judge whether there is abnormal sound. For example, the noise of heavy vehicles such as trucks and buses is 89-92. Decibels, while light vehicles such as cars and jeeps have a noise of about 82-85 decibels. When the sound decibel value associated with the vehicle exceeds the above range, an abnormal sound is considered to occur.
  • the distance of at least two vehicles in the result of the traffic vehicle data analysis is less than the safety distance threshold of 0.5 m, and the sound generated by the two vehicles exceeds 92 decibels, it can be judged that a traffic abnormality occurs, that is, a road vehicle traffic accident occurs.
  • the second distance threshold may be fixedly set in advance. For example, if the second distance threshold is set to 1.2 m (the safety distance between people is 1.2 m), the second distance threshold may be dynamically adjusted according to the intimacy of the crowd. For example, set to 0.45m and so on.
  • the abnormal sound can be the noise generated by the crowd quarrel.
  • the decibel value can be used to determine whether there is an abnormal sound. The average person speaks normally at 40-60 decibels.
  • an abnormal sound is considered to occur.
  • the distance of at least two portraits in the results of the surrounding road environment analysis is less than the second distance threshold, such as less than 1.2 m, and the sound associated with the crowd exceeds 60 decibels, it may be judged that a traffic abnormality occurs, that is, a fighting event occurs.
  • the normal brightness is dynamically adjusted according to the environment in which the vehicle is located. For example, when the environment in which the vehicle is located is daytime, the normal brightness is 100-1000 when there is no cloud on sunny days. Nit, the normal brightness of cloudy days is 50-500 nits; when the environment of the vehicle is night, the normal brightness of street lighting is 20-200 nits, the normal brightness of no street lighting is 0.01-0.3 nits. . Therefore, when the brightness of the environmental data exceeds the normal brightness range, it indicates that there is a traffic abnormality, such as a fire.
  • the abnormal data may be further analyzed according to a preset algorithm such as an artificial intelligence algorithm or a weighted average algorithm to obtain an abnormal analysis result.
  • the abnormal analysis results include traffic anomaly type, traffic anomaly level, responsible party, and loss value.
  • the traffic abnormality is a road vehicle traffic accident.
  • the deep learning algorithm in the artificial intelligence algorithm is used to analyze whether the vehicle traffic accident at this time is a slight, general, serious or significant level according to the relationship between the intensity of the abnormal sound and the abnormal level.
  • the collected vehicle damage image data is obtained by weighting calculation to obtain an abnormal value, and then the vehicle traffic accident level at this time is determined according to the range of the abnormal value.
  • the responsible party can be calculated according to the collected vehicle license plate information and the speed, acceleration and vehicle travel direction of the vehicle within the preset time before the abnormality occurs.
  • the loss value is calculated based on the vehicle brand model, the vehicle license plate, the damage of the vehicle component, and the resulting traffic congestion condition in the collected vehicle damage image data.
  • artificial intelligence algorithms or weighted average algorithms can be used in the calculation of the responsible party and the loss value.
  • the artificial intelligence algorithm can be used to calculate and analyze the number of people in the portrait data, the degree of injury, the weapons used in the fight, etc., to determine whether the level of the fight is general, serious or significant. The value of the loss is calculated based on the degree of injury and the resulting traffic congestion.
  • the artificial intelligence algorithm can be used to analyze the source position of the brightness, the brightness difference value of the brightness and the surrounding environment to determine the fire level, and the loss value caused by the fire is calculated according to the range of the brightness coverage and the traffic congestion situation.
  • performing the corresponding measures according to the abnormal analysis result specifically includes: determining a corresponding traffic abnormality management center according to the traffic abnormality type; and transmitting the abnormality analysis result and the location to the corresponding traffic abnormality management center, so that the traffic abnormality management The center took measures to solve the traffic anomaly problem.
  • the corresponding traffic anomaly management center is a road traffic management service center.
  • the abnormality level, loss value, responsible party and traffic abnormality of the vehicle traffic accident are obtained.
  • the location is sent to the road traffic management service center, so that the road traffic management service center can notify the traffic police to deal with it in time; when the traffic is abnormal, the corresponding traffic anomaly management center is determined to be a public safety management service center.
  • the abnormal level, the degree of injury, and the location of the fight are sent to the Public Safety Management Service Center so that the Public Safety Management Service Center can notify the nearest public security police to deal with it in a timely manner; when the traffic is abnormally fire, determine the corresponding traffic abnormality management center as fire protection.
  • the safety management service center sends the fire level, the fire range and the location of the fire to the fire safety management service center, so that the fire safety management service center can notify the nearest fire police to handle it in time.
  • the in-vehicle device acquires the location information of the vehicle, acquires the traffic environment data of the vehicle according to the location information, analyzes and calculates the traffic environment data, and obtains the traffic environment data analysis result; according to the traffic environment data.
  • the analysis results determine whether there is a traffic anomaly; if so, the abnormal data is analyzed according to a preset algorithm to obtain an abnormal analysis result, and corresponding measures are performed according to the abnormal analysis result.
  • FIG. 2 is a schematic structural diagram of an in-vehicle device according to an embodiment of the present invention. As shown in FIG. 2, the in-vehicle device includes:
  • the acquiring unit 201 is configured to acquire location information of the vehicle.
  • the obtaining unit 201 may acquire the vehicle location information through the base station positioning technology of the mobile communication network, and may also acquire the location information of the vehicle through a satellite navigation system (such as GPS, Beidou, etc.).
  • a satellite navigation system such as GPS, Beidou, etc.
  • the obtaining unit 201 is further configured to acquire traffic environment data of the vehicle according to the location information.
  • the obtaining unit 201 is further configured to acquire traffic environment data of the vehicle according to the location information.
  • the traffic environment data of the vehicle includes: vehicle information of the vehicle, surrounding vehicle information and surrounding road environment information within a preset distance from the vehicle.
  • the acquiring unit 201 can acquire the traffic environment data of the vehicle, such as the vehicle information of the vehicle itself, and the periphery within the preset distance from the vehicle, by using various built-in sensors (camera sensor, acceleration sensor, gravity sensor, photosensitive sensor, etc.). Vehicle information and surrounding road environment information.
  • the preset distance can be 100m, 500m, or other distances. There is no limit here. The preset distance can be set according to the preferences of the vehicle user, or it can be fixed at the factory.
  • the analysis and calculation unit 202 is configured to analyze and calculate the traffic environment data, and obtain a traffic environment data analysis result.
  • the traffic environment data can be classified into vehicle data and surrounding road environment data.
  • the analysis calculation unit 202 After analyzing the calculation of the traffic environment data, the analysis calculation unit 202 obtains the traffic environment data analysis result and obtains the vehicle data analysis result and the surrounding road environment analysis result according to the classification.
  • the analysis and calculation unit 202 analyzes and calculates the traffic environment data, and specifically includes: calculating, according to the vehicle information and the surrounding vehicle information, a distance between the vehicle and the surrounding vehicle, and obtaining traffic vehicle data according to the ambient sound.
  • the analysis result is obtained by extracting the portrait data, the sound data, and the ambient brightness data according to the image data in the surrounding road environment information, and performing analysis and calculation to obtain the surrounding road environment analysis result.
  • the image data therein analyze the distance between the vehicle and the vehicle according to the image recognition algorithm or the artificial intelligence analysis algorithm, extract the portrait data and analyze the number of the calculation crowd, The type of the crowd, extracting the ambient brightness and calculating the brightness data; extracting the sound related to the vehicle, obtaining the decibel range of the sound, extracting the sound related to the crowd, and obtaining the decibel range of the sound and the type of the sound.
  • the distance between the vehicle and the vehicle and the sound decibel value related to the vehicle are taken as the traffic vehicle data analysis result;
  • the result of the portrait analysis (the number of people, the type of the crowd), the sound decibel range of the crowd, the sound type, and the ambient brightness data are taken as the periphery.
  • Road environment analysis results are taken as the distance between the vehicle and the vehicle and the sound decibel value related to the vehicle.
  • the determining unit 203 is configured to determine, according to the traffic environment data analysis result, whether a traffic abnormality occurs.
  • the determining unit 203 determines that a traffic abnormality occurs.
  • the first distance threshold may be a safety distance threshold, such as 0.5 m, or other values.
  • the abnormal sound may be abnormal noise generated by a vehicle collision or the like.
  • the decibel value can be used to judge whether there is abnormal sound. For example, the noise of heavy vehicles such as trucks and buses is 89-92. Decibels, while light vehicles such as cars and jeeps have a noise of about 82-85 decibels. When the sound decibel value associated with the vehicle exceeds the above range, an abnormal sound is considered to occur.
  • the distance of at least two vehicles in the result of the traffic vehicle data analysis is less than the safety distance threshold of 0.5 m, and the sound generated by the two vehicles exceeds 92 decibels, it can be judged that a traffic abnormality occurs, that is, a road vehicle traffic accident occurs.
  • the determining unit 203 determines that a traffic abnormality occurs.
  • the second distance threshold may be fixedly set in advance. For example, if the second distance threshold is set to 1.2 m (the safety distance between people is 1.2 m), the second distance threshold may be dynamically adjusted according to the intimacy of the crowd. For example, set to 0.45m and so on.
  • the abnormal sound can be the noise generated by the crowd quarrel.
  • the decibel value can be used to determine whether there is an abnormal sound.
  • an abnormal sound is considered to occur.
  • the distance of at least two portraits in the results of the surrounding road environment analysis is less than the second distance threshold, such as less than 1.2 m, and the sound associated with the crowd exceeds 60 decibels, it may be judged that a traffic abnormality occurs, that is, a fighting event occurs.
  • the determining unit 203 determines that a traffic abnormality occurs.
  • the normal brightness is dynamically adjusted according to the environment in which the vehicle is located. For example, when the environment in which the vehicle is located is daytime, the normal brightness is 100-1000 when there is no cloud on sunny days. Nit, the normal brightness of cloudy days is 50-500 nits; when the environment of the vehicle is night, the normal brightness of street lighting is 20-200 nits, the normal brightness of no street lighting is 0.01-0.3 nits. . Therefore, when the brightness of the environmental data exceeds the normal brightness range, it indicates that there is a traffic abnormality, such as a fire.
  • the executing unit 204 is configured to: if the determination result of the determining unit 203 is yes, analyze the abnormal data according to the preset algorithm to obtain an abnormal analysis result, and perform corresponding measures according to the abnormal analysis result.
  • the analysis calculation unit 202 may further analyze the abnormal data according to a preset algorithm such as an artificial intelligence algorithm or a weighted average algorithm to obtain an abnormal analysis result.
  • the abnormal analysis results include traffic anomaly type, traffic anomaly level, responsible party, and loss value.
  • the traffic abnormality is a road vehicle traffic accident.
  • the deep learning algorithm in the artificial intelligence algorithm is used to analyze whether the vehicle traffic accident at this time is a slight, general, serious or significant level according to the relationship between the intensity of the abnormal sound and the abnormal level.
  • the collected vehicle damage image data is obtained by weighting calculation to obtain an abnormal value, and then the vehicle traffic accident level at this time is determined according to the range of the abnormal value.
  • the analysis and calculation unit 202 can calculate the responsible party according to the collected vehicle license plate information and the speed, acceleration and vehicle travel direction of the vehicle within a preset time before the abnormality occurs.
  • the loss value is calculated based on the vehicle brand model, the vehicle license plate, the damage of the vehicle component, and the resulting traffic congestion condition in the collected vehicle damage image data.
  • artificial intelligence algorithms or weighted average algorithms can be used in the calculation of the responsible party and the loss value.
  • the artificial intelligence algorithm can be used to calculate and analyze the number of people in the portrait data, the degree of injury, the weapons used in the fight, etc., to determine whether the level of the fight is general, serious or significant. The value of the loss is calculated based on the degree of injury and the resulting traffic congestion.
  • the artificial intelligence algorithm can be used to analyze the source position of the brightness, the brightness difference value of the brightness and the surrounding environment to determine the fire level, and the loss value caused by the fire is calculated according to the range of the brightness coverage and the traffic congestion situation.
  • the execution unit 204 may perform corresponding measures according to the abnormal analysis result. Specifically, executing the corresponding measure according to the abnormality analysis result includes: determining a corresponding traffic abnormality management center according to the traffic abnormality type; and transmitting the abnormality analysis result and the location to the corresponding traffic abnormality management center, so as to The Traffic Anomaly Management Center takes measures to solve the traffic anomaly problem.
  • the corresponding traffic anomaly management center is a road traffic management service center.
  • the abnormality level, loss value, responsible party and traffic abnormality of the vehicle traffic accident are obtained.
  • the location is sent to the road traffic management service center, so that the road traffic management service center can notify the traffic police to deal with it in time; when the traffic is abnormal, the corresponding traffic anomaly management center is determined to be a public safety management service center.
  • the abnormal level, the degree of injury, and the location of the fight are sent to the Public Safety Management Service Center so that the Public Safety Management Service Center can notify the nearest public security police to deal with it in a timely manner; when the traffic is abnormally fire, determine the corresponding traffic abnormality management center as fire protection.
  • the safety management service center sends the fire level, the fire range and the location of the fire to the fire safety management service center, so that the fire safety management service center can notify the nearest fire police to handle it in time.
  • the in-vehicle device acquires the location information of the vehicle, acquires the traffic environment data of the vehicle according to the location information, analyzes and calculates the traffic environment data, and obtains the traffic environment data analysis result; according to the traffic environment data.
  • the analysis results determine whether there is a traffic anomaly; if so, the abnormal data is analyzed according to a preset algorithm to obtain an abnormal analysis result, and corresponding measures are performed according to the abnormal analysis result.
  • FIG. 3 is a schematic structural diagram of another vehicle-mounted device according to an embodiment of the present invention.
  • the in-vehicle device includes a processor 301, a memory 302, and a bus 303.
  • the processor 301 and the memory 302 can be coupled by a bus or other means.
  • FIG. 3 is connected by a bus 303 as an example.
  • the processor 301 can be digital signal processing (English: Digital Signal) Processing, DSP) chip.
  • the processor 301 can include: a management/communication module (administration) Module/communication module, AM/CM) (center for voice exchange and information exchange), module for completing call processing, signaling processing, radio resource management, radio link management, and circuit maintenance functions, code rate Transform and sub-multiplex module (transcoder Submultiplexer, TCSM) (for completing the multiplexing demultiplexing and code conversion functions) and other modules.
  • a management/communication module administration
  • AM/CM center for voice exchange and information exchange
  • module for completing call processing
  • signaling processing radio resource management
  • radio link management radio link management
  • circuit maintenance functions code rate Transform and sub-multiplex module (transcoder Submultiplexer, TCSM) (for completing the multiplexing demultiplexing and code conversion functions) and other modules.
  • code rate Transform and sub-multiplex module for completing the multiplexing demultiplexing and code conversion functions
  • the memory 302 is used to store the program code of the road traffic data processing.
  • the memory 302 can be a read-only memory (English: Read-Only Memory, ROM) or a random access memory (English: Random Access Memory, RAM). , can be used to store program code for road traffic data processing.
  • Bus 303 can be an industry standard architecture (English: Industry Standard Architecture, ISA) bus, external device interconnection (English: Peripheral Component Interconnect, PCI) bus, extended standard architecture (English: Extended Industry Standard Architecture (EISA) bus, integrated circuit bus (English: Inter Integrated Circuit, IIC).
  • ISA Industry Standard Architecture
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • IIC Inter Integrated Circuit
  • the processor 301 is further configured to invoke the executable application code stored in the memory 302, and perform the following operations:
  • the abnormal data is analyzed according to the preset algorithm to obtain the abnormal analysis result, and the corresponding measures are performed according to the abnormal analysis result.
  • the traffic environment data includes: vehicle information of the vehicle, surrounding vehicle information and surrounding road environment information within a preset distance from the vehicle; and the traffic environment data analysis result includes traffic vehicle data analysis result and Analysis of surrounding road environment;
  • the processor 301 performs the analysis to calculate the traffic environment data, and the specific manner is:
  • the portrait data, the sound data, and the ambient brightness data are extracted based on the image data in the surrounding road environment information, and analyzed and calculated to obtain a surrounding road environment analysis result.
  • the processor 301 performs, according to the analysis result of the traffic environment data, whether a traffic abnormality occurs, and the specific manner is:
  • the abnormal analysis result includes a traffic abnormality type, a traffic abnormality level, a responsible party, and a loss value.
  • the processor 301 performs the corresponding measures according to the abnormal analysis result, where the specific manner is:
  • the in-vehicle device acquires the location information of the vehicle, acquires the traffic environment data of the vehicle according to the location information, analyzes and calculates the traffic environment data, and obtains the traffic environment data analysis result; according to the traffic environment data.
  • the analysis results determine whether there is a traffic anomaly; if so, the abnormal data is analyzed according to a preset algorithm to obtain an abnormal analysis result, and corresponding measures are performed according to the abnormal analysis result.
  • the embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium can store a program, and the program includes some or all of the steps of the method for processing road traffic data described in the foregoing method embodiments.
  • the disclosed apparatus may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present invention may contribute to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a memory.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM, Random Access). Memory, removable hard disk, disk or optical disk, etc., which can store program code.

Landscapes

  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

本方案公开了一种道路交通数据的处理方法及车载设备，所述道路交通数据的处理方法包括：根据位置信息获取所述车辆的交通环境数据；分析计算所述交通环境数据，得到交通环境数据分析结果；根据所述交通环境数据分析结果判断是否出现交通异常；若是则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。采用本方案实施例实现了道路交通异常的快速上报和及时处理，对于缓解交通异常造成的拥堵带来了极大的便利，提升了交通异常的处理效率，也保证了管理中心救援的及时性。

Description

一种道路交通数据的处理方法及车载设备 技术领域
本发明涉及数据信息技术领域，尤其涉及一种道路交通数据的处理方法及车载设备。
 背景技术
随着人类城市化程度越来越高，汽车的需求量也越来越大，几乎所有大中城市都面临着交通堵塞的巨大压力。在正常行驶的时候，道路的交通承载能力与的汽车的容量达到一个临界，稍微有任何风吹草动都将会严重影响交通顺畅，而交通异常往往成为压死骆驼的最后一根稻草，一旦发生任何交通异常，造成汽车堵塞的积累效应，将造成严重拥堵。
现有技术中，一般通过驾驶员判断周边环境，发生异常之后，拨打管理中心及时报警，并等待管理中心做出响应；或者通过事故周边路过人员发现异常报警处理或者通过遍历政府部署的定点摄像头进行人工搜索。现有技术的处理方式一方面效率较低，另一方面报告给管理中心数据不够准确，无法帮助管理中心针对性的准备救援措施，导致救援时间缓慢，进一步加大了交通异常带来的损失。
 技术问题
本发明实施例提供一种道路交通数据的处理方法和设备，有利于解决现有技术中交通事故报警处理方式效率较低、数据不够准确、救援时间缓慢的问题，有利于提升交通异常的处理效率。
 技术解决方案
第一方面，本发明实施例提供一种道路交通数据的处理方法，所述方法应用于具有行车记录功能的车载设备，所述车载设备安装在车辆上，所述方法包括：获取所述车辆的位置信息；根据位置信息获取所述车辆的交通环境数据；分析计算所述交通环境数据，得到交通环境数据分析结果；根据所述交通环境数据分析结果判断是否出现交通异常；若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。
结合本发明实施例第一方面，在本发明实施例第一方面的第一种可能的实现方式中，所述交通环境数据包括：所述车辆的车辆信息，与所述车辆预设距离内的周边车辆信息和周边道路环境信息；所述交通环境数据分析结果包括交通车辆数据分析结果和周边道路环境分析结果；所述分析计算所述交通环境数据，具体包括：根据所述车辆信息和所述周边车辆信息分析计算所述车辆及周边车辆之间的距离，并结合环境声音得到交通车辆数据分析结果；根据所述周边道路环境信息中的图像数据提取人像数据、声音数据以及环境亮度数据并进行分析计算，得到周边道路环境分析结果。
结合本发明实施例第一方面的第一种可能的实现方式，在本发明实施例第一方面的第二种可能的实现方式中，所述根据所述交通环境数据分析结果判断是否出现交通异常，具体包括：当所述交通车辆数据分析结果中有至少两辆车的距离小于第一距离阈值时并伴随有异常声响时，判断出现交通异常；或者，当所述周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于第二距离阈值且伴随异常声音时，判断出现交通异常；或者，当所述周边道路环境分析结果中环境亮度数据超过正常亮度值时，判断出现交通异常。
结合本发明实施例第一方面、第一方面的第一种可能的实现方式、第一方面的第二种可能的实现方式，在本发明实施例第一方面的第三种可能的实现方式中，所述异常分析结果包括交通异常类型、交通异常级别、责任方、损失价值。
结合本发明实施例第一方面的第三种可能的实现方式，在本发明实施例第一方面的第四种可能的实现方式中，所述根据异常分析结果执行相应的措施，具体包括：根据交通异常类型确定对应的交通异常管理中心；将所述异常分析结果和位置发送至对应的交通异常管理中心，以便所述交通异常管理中心采取措施解决所述交通异常问题。
本发明第二方面提供了一种车载设备，所述车载设备包括：存储有可执行程序代码的存储器；与所述存储器耦合的处理器；所述处理器调用所述存储器中存储的所述可执行程序代码，执行以下步骤：获取车辆的位置信息；根据位置信息获取所述车辆的交通环境数据；分析计算所述交通环境数据，得到交通环境数据分析结果；根据所述交通环境数据分析结果判断是否出现交通异常；若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。
结合本发明实施例第二方面，在本发明实施例第二方面的第一种可能的实施方式中，所述交通环境数据包括：所述车辆的车辆信息，与所述车辆预设距离内的周边车辆信息和周边道路环境信息；所述交通环境数据分析结果包括交通车辆数据分析结果和周边道路环境分析结果；所述处理器执行所述分析计算所述交通环境数据，具体方式为：根据所述车辆信息和所述周边车辆信息分析计算所述车辆及周边车辆之间的距离，并结合环境声音得到交通车辆数据分析结果；根据所述周边道路环境信息中的图像数据提取人像数据、声音数据以及环境亮度数据并进行分析计算，得到周边道路环境分析结果。
结合本发明实施例第二方面的第一种可能的实施方式，在本发明实施例第二方面的第二种可能的实施方式中，所述处理器执行所述所述根据所述交通环境数据分析结果判断是否出现交通异常，具体方式为：当所述交通车辆数据分析结果中有至少两辆车的距离小于第一距离阈值时并伴随有异常声响时，判断出现交通异常；或者，当所述周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于第二距离阈值且伴随异常声音时，判断出现交通异常；或者，当所述周边道路环境分析结果中环境亮度数据超过正常亮度值时，判断出现交通异常。
结合本发明实施例第二方面、第二方面的第一种可能的实现方式、第二方面的第二种可能的实现方式，在本发明实施例第二方面的第三种可能的实现方式中，所述异常分析结果包括交通异常类型、交通异常级别、责任方、损失价值。
结合本发明实施例第二方面的第三种可能的实现方式，在本发明实施例第二方面的第四种可能的实现方式中，所述处理器执行所述根据异常分析结果执行相应的措施，具体方式为：根据交通异常类型确定对应的交通异常管理中心；将所述异常分析结果和位置发送至对应的交通异常管理中心，以便所述交通异常管理中心采取措施解决所述交通异常问题。
 有益效果
可以看出，在本发明的实施例中，获取所述车辆的位置信息；根据位置信息获取所述车辆的交通环境数据；分析计算所述交通环境数据，得到交通环境数据分析结果；根据所述交通环境数据分析结果判断是否出现交通异常；若是则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。采用上述方法，实现了道路交通异常的快速上报和及时处理，对于缓解交通异常造成的拥堵带来了极大的便利，提升了交通异常的处理效率，也保证了管理中心救援的及时性。
本发明的这些方面或其他方面在以下实施例的描述中会更加简明易懂。
 附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例提供的一种道路交通数据处理方法的流程示意图；
图2为本发明实施例提供的一种车载设备结构示意图；
图3为本发明实施例提供的另一种车载设备结构示意图。
 本发明的实施方式
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本发明保护的范围。
以下分别进行详细说明。
本发明的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本发明的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
本发明实施例应用于具有行车记录功能的车载设备，车载设备可以是车载终端，车载记录仪、OBD盒子等，也可以是其他具有计算功能和行车记录功能的车载设备。上述举例仅用于说明本发明实施例可能的执行主体，不应被认为对本发明实施例的限定。
下面结合附图对本申请的实施例进行描述。
请参见图1，图1为本发明实施例提供的一种道路交通数据处理方法的流程示意图。如图1所示，该方法包括：
S101、获取车辆的位置信息。
车载设备可以通过移动通信网络的基站定位技术获取车辆位置信息，也可以通过卫星导航系统（如GPS、北斗等）获取车辆的位置信息。
S102、根据位置信息获取所述车辆的交通环境数据。
获取到车辆的位置信息后，车载设备即可以根据位置信息获取车辆的交通环境数据。车辆的交通环境数据包括：所述车辆的车辆信息，与所述车辆预设距离内的周边车辆信息和周边道路环境信息。
具体的，车载设备可以利用内置的各种传感器（摄像头传感器、加速度传感器、重力传感器、光敏传感器等）获取车辆的交通环境数据如车辆自身的车辆信息、与所述车辆预设距离内的周边车辆信息和周边道路环境信息。预设距离可以是100m，500m，也可以是其他距离。此处不做限定。预设距离可以根据车辆用户的喜好自行设定，也可以是车载设备在出厂时固定设置。
S103、分析计算所述交通环境数据，得到交通环境数据分析结果。
进一步的，可以将交通环境数据分类为车辆数据和周边道路环境数据。分析计算交通环境数据后，得到交通环境数据分析结果按照分类得到车辆数据分析结果和周边道路环境分析结果。
具体的，分析计算所述交通环境数据，具体包括：根据所述车辆信息和所述周边车辆信息分析计算所述车辆及周边车辆之间的距离，并结合环境声音得到交通车辆数据分析结果；根据所述周边道路环境信息中的图像数据提取人像数据、声音数据以及环境亮度数据并进行分析计算，得到周边道路环境分析结果。
在具体的计算分析过程中，根据获取到的交通环境数据，提取其中的图像数据，按照图像识别算法或者人工智能分析算法分析车辆与车辆之间的距离，提取人像数据并分析计算人群的数量、人群的类型，提取环境亮度并计算得到亮度数据；提取与车辆有关的声音，获取该声音的分贝范围，提取与人群相关的声音，得到声音的分贝范围及声音的类型。然后将车辆与车辆之间的距离及车辆有关的声音分贝值作为交通车辆数据分析结果；将人像分析结果（人群数量、人群类型）、人群相关的声音分贝范围及声音类型、环境亮度数据作为周边道路环境分析结果。
S104、根据所述交通环境数据分析结果判断是否出现交通异常。
具体的，当所述交通车辆数据分析结果中有至少两辆车的距离小于第一距离阈值时并伴随有异常声响时，判断出现交通异常。其中，第一距离阈值可以是安全距离阈值，比如0.5m，也可以是其他数值。异常声响可以是车辆碰撞等产生的异常噪音。在具体的分析过程中，可以通过分贝值来判断是否有异常声响。例如，载重汽车、公共汽车等重型车辆的噪声在89-92 分贝，而轿车、吉普车等轻型车辆噪声约有82-85分贝。当车辆有关的声音分贝值超过上述范围，则认为出现异常声响。当交通车辆数据分析的结果中出现至少两辆车的距离小于安全距离阈值如0.5m，且这两辆车产生的声音超过92分贝，则可以判断出现交通异常，即发生了道路车辆交通事故。
具体的，当所述周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于第二距离阈值且伴随异常声音时，判断出现交通异常。其中，第二距离阈值可以预先固定设置，如将第二距离阈值设置为1.2m（人与人之间的安全距离在1.2m），也可以根据人群的动作亲密程度动态调整第二距离阈值，比如设置为0.45m等。异常声音可以是人群吵架产生的喧闹声。在具体的分析过程中，可以通过分贝值来判断是否有异常声音。一般人正常说话的声音在40-60分贝。当周边道路环境分析结果中与人群有关的声音超过60分贝时，则认为出现异常声音。当周边道路环境分析的结果中出现至少两个人像的距离小于第二距离阈值如小于1.2m，与人群有关的声音超过60分贝，则可以判断出现交通异常，即发生了斗殴事件。
具体的，当所述周边道路环境分析结果中环境亮度数据超过正常亮度值时，判断出现交通异常。其中，正常亮度是根据车辆所处的环境动态调整的。例如当车辆所处的环境为白天，晴天无云的情况下正常亮度为100-1000 尼特，阴天的正常亮度为50-500尼特；当车辆所处的环境为夜晚时，有路灯照明的正常亮度在20-200尼特，无路灯照明的正常亮度在0.01-0.3尼特。因此当环境数据亮度超过正常亮度范围，则表明当前出现交通异常，比如发生火灾。
S105、若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。
当存在交通异常时，可以按照预设的算法如人工智能算法或者加权平均算法进一步分析异常数据得到异常分析结果。异常分析结果包括交通异常类型、交通异常级别、责任方、损失价值等。
具体的，当车辆之间的距离小于安全距离阈值且伴随有异常声响时，则交通异常为道路车辆交通事故。利用人工智能算法中的深度学习算法根据异常声响的强度和异常级别的关系分析此时的车辆交通事故是轻微、一般、严重还是重大级别。或者结合声响、采集的车辆损毁图像数据通过加权计算的方式得到一个异常值，然后根据异常值所在的范围判断此时的车辆交通事故级别。同时可以根据采集到的车辆牌照信息和异常发生前预设时间内的车辆的速度、加速度、车辆行驶方向分析计算责任方。根据采集到的车辆损毁图像数据中的车辆品牌型号、车辆牌照、车辆部件损坏情况以及造成的交通拥堵状况分析计算损失价值。同样的，在责任方和损失价值的计算过程中也可以采用人工智能算法或者加权平均算法。
具体的，当周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于人与人之间的安全距离阈值，且伴随有超出正常分贝的声音出现，则交通异常为斗殴事件。此时可以利用人工智能算法计算分析人像数据中的人群数量、人员受伤程度、斗殴使用的武器等得出斗殴级别为一般、严重还是重大。根据人员的受伤程度和造成的交通拥堵状况分析计算损失价值。
具体的，当周边道路环境分析结果中环境亮度数据超过正常亮度值时，则交通异常为火灾。此时可以利用人工智能算法分析亮度的来源位置、亮度与周围环境的亮度差异值判断火灾的级别，根据该亮度覆盖的范围以及造成的交通拥堵情况分析计算火灾造成的损失价值。
进一步的，在得到异常分析结果后，可以根据异常分析结果执行相应的措施。具体而言，根据异常分析结果执行相应的措施具体包括：根据交通异常类型确定对应的交通异常管理中心；将所述异常分析结果和位置发送至对应的交通异常管理中心，以便所述交通异常管理中心采取措施解决所述交通异常问题。
在具体的处理过程中，当交通异常为道路车辆交通事故时，则确定对应的交通异常管理中心为道路交通管理服务中心，此时将车辆交通事故的异常级别、损失价值、责任方以及交通异常的位置发送至道路交通管理服务中心，以使道路交通管理服务中心通知交警及时处理；当交通异常为斗殴事件时，确定对应的交通异常管理中心为公共安全管理服务中心，此时将斗殴事件的异常级别、人员受伤程度以及斗殴发生的位置发送至公共安全管理服务中心，以使公共安全管理服务中心通知最近的公安民警及时处理；当交通异常为火灾时，确定对应的交通异常管理中心为消防安全管理服务中心，此时将火灾的级别、火灾的范围以及火灾的位置发送至消防安全管理服务中心，以使消防安全管理服务中心通知最近的消防警察及时处理。
在本实施例中，车载设备通过获取所述车辆的位置信息；根据位置信息获取所述车辆的交通环境数据；分析计算所述交通环境数据，得到交通环境数据分析结果；根据所述交通环境数据分析结果判断是否出现交通异常；若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。从而实现了道路交通异常的快速上报和及时处理，对于缓解交通异常造成的拥堵带来了极大的便利，提升了交通异常的处理效率，也保证了管理中心救援的及时性。
请参见图2，图2为本发明实施例提供的一种车载设备结构示意图。如图2所示，该车载设备包括：
获取单元201，用于获取车辆的位置信息。
获取单元201可以通过移动通信网络的基站定位技术获取车辆位置信息，也可以通过卫星导航系统（如GPS、北斗等）获取车辆的位置信息。
获取单元201，还用于根据位置信息获取所述车辆的交通环境数据。
获取到车辆的位置信息后，获取单元201还用于根据位置信息获取车辆的交通环境数据。车辆的交通环境数据包括：所述车辆的车辆信息，与所述车辆预设距离内的周边车辆信息和周边道路环境信息。
具体的，获取单元201可以利用内置的各种传感器（摄像头传感器、加速度传感器、重力传感器、光敏传感器等）获取车辆的交通环境数据如车辆自身的车辆信息、与所述车辆预设距离内的周边车辆信息和周边道路环境信息。预设距离可以是100m，500m，也可以是其他距离。此处不做限定。预设距离可以根据车辆用户的喜好自行设定，也可以在出厂时固定设置。
分析计算单元202，用于分析计算所述交通环境数据，得到交通环境数据分析结果。
进一步的，可以将交通环境数据分类为车辆数据和周边道路环境数据。分析计算单元202分析计算交通环境数据后，得到交通环境数据分析结果按照分类得到车辆数据分析结果和周边道路环境分析结果。
具体的，分析计算单元202分析计算所述交通环境数据，具体包括：根据所述车辆信息和所述周边车辆信息分析计算所述车辆及周边车辆之间的距离，并结合环境声音得到交通车辆数据分析结果；根据所述周边道路环境信息中的图像数据提取人像数据、声音数据以及环境亮度数据并进行分析计算，得到周边道路环境分析结果。
在具体的计算分析过程中，根据获取到的交通环境数据，提取其中的图像数据，按照图像识别算法或者人工智能分析算法分析车辆与车辆之间的距离，提取人像数据并分析计算人群的数量、人群的类型，提取环境亮度并计算得到亮度数据；提取与车辆有关的声音，获取该声音的分贝范围，提取与人群相关的声音，得到声音的分贝范围及声音的类型。然后将车辆与车辆之间的距离及车辆有关的声音分贝值作为交通车辆数据分析结果；将人像分析结果（人群数量、人群类型）、人群相关的声音分贝范围及声音类型、环境亮度数据作为周边道路环境分析结果。
判断单元203，用于根据所述交通环境数据分析结果判断是否出现交通异常。
具体的，当所述交通车辆数据分析结果中有至少两辆车的距离小于第一距离阈值时并伴随有异常声响时，判断单元203判断出现交通异常。其中，第一距离阈值可以是安全距离阈值，比如0.5m，也可以是其他数值。异常声响可以是车辆碰撞等产生的异常噪音。在具体的分析过程中，可以通过分贝值来判断是否有异常声响。例如，载重汽车、公共汽车等重型车辆的噪声在89-92 分贝，而轿车、吉普车等轻型车辆噪声约有82-85分贝。当车辆有关的声音分贝值超过上述范围，则认为出现异常声响。当交通车辆数据分析的结果中出现至少两辆车的距离小于安全距离阈值如0.5m，且这两辆车产生的声音超过92分贝，则可以判断出现交通异常，即发生了道路车辆交通事故。
具体的，当所述周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于第二距离阈值且伴随异常声音时，判断单元203判断出现交通异常。其中，第二距离阈值可以预先固定设置，如将第二距离阈值设置为1.2m（人与人之间的安全距离在1.2m），也可以根据人群的动作亲密程度动态调整第二距离阈值，比如设置为0.45m等。异常声音可以是人群吵架产生的喧闹声。在具体的分析过程中，可以通过分贝值来判断是否有异常声音。一般人正常说话的声音在40-60分贝。当周边道路环境分析结果中与人群有关的声音超过60分贝时，则认为出现异常声音。当周边道路环境分析的结果中出现至少两个人像的距离小于第二距离阈值如小于1.2m，与人群有关的声音超过60分贝，则可以判断出现交通异常，即发生了斗殴事件。
具体的，当所述周边道路环境分析结果中环境亮度数据超过正常亮度值时，判断单元203判断出现交通异常。其中，正常亮度是根据车辆所处的环境动态调整的。例如当车辆所处的环境为白天，晴天无云的情况下正常亮度为100-1000 尼特，阴天的正常亮度为50-500尼特；当车辆所处的环境为夜晚时，有路灯照明的正常亮度在20-200尼特，无路灯照明的正常亮度在0.01-0.3尼特。因此当环境数据亮度超过正常亮度范围，则表明当前出现交通异常，比如发生火灾。
执行单元204，用于，若判断单元203的判断结果为是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。
当存在交通异常时，分析计算单元202可以按照预设的算法如人工智能算法或者加权平均算法进一步分析异常数据得到异常分析结果。异常分析结果包括交通异常类型、交通异常级别、责任方、损失价值等。
具体的，当车辆之间的距离小于安全距离阈值且伴随有异常声响时，则交通异常为道路车辆交通事故。利用人工智能算法中的深度学习算法根据异常声响的强度和异常级别的关系分析此时的车辆交通事故是轻微、一般、严重还是重大级别。或者结合声响、采集的车辆损毁图像数据通过加权计算的方式得到一个异常值，然后根据异常值所在的范围判断此时的车辆交通事故级别。同时分析计算单元202可以根据采集到的车辆牌照信息和异常发生前预设时间内的车辆的速度、加速度、车辆行驶方向分析计算责任方。根据采集到的车辆损毁图像数据中的车辆品牌型号、车辆牌照、车辆部件损坏情况以及造成的交通拥堵状况分析计算损失价值。同样的，在责任方和损失价值的计算过程中也可以采用人工智能算法或者加权平均算法。
具体的，当周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于人与人之间的安全距离阈值，且伴随有超出正常分贝的声音出现，则交通异常为斗殴事件。此时可以利用人工智能算法计算分析人像数据中的人群数量、人员受伤程度、斗殴使用的武器等得出斗殴级别为一般、严重还是重大。根据人员的受伤程度和造成的交通拥堵状况分析计算损失价值。
具体的，当周边道路环境分析结果中环境亮度数据超过正常亮度值时，则交通异常为火灾。此时可以利用人工智能算法分析亮度的来源位置、亮度与周围环境的亮度差异值判断火灾的级别，根据该亮度覆盖的范围以及造成的交通拥堵情况分析计算火灾造成的损失价值。
进一步的，在分析计算单元202得到异常分析结果后，执行单元204可以根据异常分析结果执行相应的措施。具体而言，执行单元204根据异常分析结果执行相应的措施具体包括：根据交通异常类型确定对应的交通异常管理中心；将所述异常分析结果和位置发送至对应的交通异常管理中心，以便所述交通异常管理中心采取措施解决所述交通异常问题。
在具体的处理过程中，当交通异常为道路车辆交通事故时，则确定对应的交通异常管理中心为道路交通管理服务中心，此时将车辆交通事故的异常级别、损失价值、责任方以及交通异常的位置发送至道路交通管理服务中心，以使道路交通管理服务中心通知交警及时处理；当交通异常为斗殴事件时，确定对应的交通异常管理中心为公共安全管理服务中心，此时将斗殴事件的异常级别、人员受伤程度以及斗殴发生的位置发送至公共安全管理服务中心，以使公共安全管理服务中心通知最近的公安民警及时处理；当交通异常为火灾时，确定对应的交通异常管理中心为消防安全管理服务中心，此时将火灾的级别、火灾的范围以及火灾的位置发送至消防安全管理服务中心，以使消防安全管理服务中心通知最近的消防警察及时处理。
在本实施例中，车载设备通过获取所述车辆的位置信息；根据位置信息获取所述车辆的交通环境数据；分析计算所述交通环境数据，得到交通环境数据分析结果；根据所述交通环境数据分析结果判断是否出现交通异常；若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。从而实现了道路交通异常的快速上报和及时处理，对于缓解交通异常造成的拥堵带来了极大的便利，提升了交通异常的处理效率，也保证了管理中心救援的及时性。
参见图3，图3为本发明实施例提供的另一种车载设备结构示意图。如图3所示，该车载设备包括处理器301、存储器302和总线303，其中处理器301、存储器302可以通过总线或其他方式耦合连接，图3以通过总线303连接为例。
其中，处理器301可以是数字信号处理（英文：Digital Signal Processing，DSP）芯片。具体实现中，处理器301可包括：管理/通信模块（administration module/communication module，AM/CM）（用于话路交换和信息交换的中心）、用于完成呼叫处理、信令处理、无线资源管理、无线链路的管理和电路维护功能的模块、码速率变换与子复用模块（transcoder submultiplexer，TCSM）（用于完成复用解复用及码变换功能）等模块。具体信息可参考移动通讯相关知识。
存储器302用于存储道路交通数据处理的程序代码，具体实现中，存储器302可以采用只读存储器（英文：Read-Only Memory，ROM）或随机存取存贮器（英文：Random Access Memory，RAM），可用于存储道路交通数据处理的程序代码。
总线303可以是工业标准体系结构（英文：Industry Standard Architecture，ISA）总线、外部设备互连（英文：Peripheral Component Interconnect，PCI）总线、扩展标准体系结构（英文：Extended Industry Standard Architecture，EISA）总线、集成电路总线（英文：Inter Integrated Circuit，IIC）等。
本发明实施例中，所述处理器301还用于调用存储器302中存储的可执行应用程序代码，执行以下操作：
获取车辆的位置信息；
根据位置信息获取所述车辆的交通环境数据；
分析计算所述交通环境数据，得到交通环境数据分析结果；
根据所述交通环境数据分析结果判断是否出现交通异常；
若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。
可选的，所述交通环境数据包括：所述车辆的车辆信息，与所述车辆预设距离内的周边车辆信息和周边道路环境信息；所述交通环境数据分析结果包括交通车辆数据分析结果和周边道路环境分析结果；
所述处理器301执行所述分析计算所述交通环境数据，具体方式为：
根据所述车辆信息和所述周边车辆信息分析计算所述车辆及周边车辆之间的距离，并结合环境声音得到交通车辆数据分析结果；
根据所述周边道路环境信息中的图像数据提取人像数据、声音数据以及环境亮度数据并进行分析计算，得到周边道路环境分析结果。
可选的，所述处理器301执行所述所述根据所述交通环境数据分析结果判断是否出现交通异常，具体方式为：
当所述交通车辆数据分析结果中有至少两辆车的距离小于第一距离阈值时并伴随有异常声响时，判断出现交通异常；
或者，
当所述周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于第二距离阈值且伴随异常声音时，判断出现交通异常；
或者，
当所述周边道路环境分析结果中环境亮度数据超过正常亮度值时，判断出现交通异常。
可选的，所述异常分析结果包括交通异常类型、交通异常级别、责任方、损失价值。
可选的，所述处理器301执行所述根据异常分析结果执行相应的措施，具体方式为：
根据交通异常类型确定对应的交通异常管理中心；
将所述异常分析结果和位置发送至对应的交通异常管理中心，以便所述交通异常管理中心采取措施解决所述交通异常问题。
根据交通异常类型确定对应的交通异常管理中心；
将所述异常分析结果和位置发送至对应的交通异常管理中心，以便所述交通异常管理中心采取措施解决所述交通异常问题。
在本实施例中，车载设备通过获取所述车辆的位置信息；根据位置信息获取所述车辆的交通环境数据；分析计算所述交通环境数据，得到交通环境数据分析结果；根据所述交通环境数据分析结果判断是否出现交通异常；若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。从而实现了道路交通异常的快速上报和及时处理，对于缓解交通异常造成的拥堵带来了极大的便利，提升了交通异常的处理效率，也保证了管理中心救援的及时性。
本发明实施例还提供一种计算机存储介质，其中，该计算机存储介质可存储有程序，该程序执行时包括上述方法实施例中记载的任何一种道路交通数据的处理方法的部分或全部步骤。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，因为依据本发明，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本发明所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备（可为个人计算机、服务器或者网络设备等）执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器（英文：Read-Only Memory ，简称：ROM）、随机存取器（英文：Random Access Memory，简称：RAM）、磁盘或光盘等。
以上对本发明实施例进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上上述，本说明书内容不应理解为对本发明的限制。

Claims (10)

  1. 一种道路交通数据的处理方法，其特征在于，所述方法应用于具有行车记录功能的车载设备，所述车载设备安装在车辆上，所述方法包括：
    获取所述车辆的位置信息；
    根据位置信息获取所述车辆的交通环境数据；
    分析计算所述交通环境数据，得到交通环境数据分析结果；
    根据所述交通环境数据分析结果判断是否出现交通异常；
    若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。
  2. 根据权利要求1所述的方法，其特征在于，所述交通环境数据包括：所述车辆的车辆信息，与所述车辆预设距离内的周边车辆信息和周边道路环境信息；所述交通环境数据分析结果包括交通车辆数据分析结果和周边道路环境分析结果；
    所述分析计算所述交通环境数据，具体包括：
    根据所述车辆信息和所述周边车辆信息分析计算所述车辆及周边车辆之间的距离，并结合环境声音得到交通车辆数据分析结果；
    根据所述周边道路环境信息中的图像数据提取人像数据、声音数据以及环境亮度数据并进行分析计算，得到周边道路环境分析结果。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述交通环境数据分析结果判断是否出现交通异常，具体包括：
    当所述交通车辆数据分析结果中有至少两辆车的距离小于第一距离阈值时并伴随有异常声响时，判断出现交通异常；
    或者，
    当所述周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于第二距离阈值且伴随异常声音时，判断出现交通异常；
    或者，
    当所述周边道路环境分析结果中环境亮度数据超过正常亮度值时，判断出现交通异常。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述异常分析结果包括交通异常类型、交通异常级别、责任方、损失价值。
  5. 根据权利要求4所述的方法，其特征在于，所述根据异常分析结果执行相应的措施，具体包括：
    根据交通异常类型确定对应的交通异常管理中心；
    将所述异常分析结果和位置发送至对应的交通异常管理中心，以便所述交通异常管理中心采取措施解决所述交通异常问题。
  6. 一种车载设备，其特征在于，所述车载设备包括：
    存储有可执行程序代码的存储器；
    与所述存储器耦合的处理器；
    所述处理器调用所述存储器中存储的所述可执行程序代码，执行以下步骤：
    获取车辆的位置信息；
    根据位置信息获取所述车辆的交通环境数据；
    分析计算所述交通环境数据，得到交通环境数据分析结果；
    根据所述交通环境数据分析结果判断是否出现交通异常；
    若是，则按照预设算法分析异常数据得到异常分析结果，并根据异常分析结果执行相应的措施。
  7. 如权利要求6所述的车载设备，其特征在于，所述交通环境数据包括：所述车辆的车辆信息，与所述车辆预设距离内的周边车辆信息和周边道路环境信息；所述交通环境数据分析结果包括交通车辆数据分析结果和周边道路环境分析结果；
    所述处理器执行所述分析计算所述交通环境数据，具体方式为：
    根据所述车辆信息和所述周边车辆信息分析计算所述车辆及周边车辆之间的距离，并结合环境声音得到交通车辆数据分析结果；
    根据所述周边道路环境信息中的图像数据提取人像数据、声音数据以及环境亮度数据并进行分析计算，得到周边道路环境分析结果。
  8. 根据权利要求7所述的车载设备，其特征在于，所述处理器执行所述根据所述交通环境数据分析结果判断是否出现交通异常，具体方式为：
    当所述交通车辆数据分析结果中有至少两辆车的距离小于第一距离阈值时并伴随有异常声响时，判断出现交通异常；
    或者，
    当所述周边道路环境分析结果中有至少两个以上人像，人像之间的距离小于第二距离阈值且伴随异常声音时，判断出现交通异常；
    或者，
    当所述周边道路环境分析结果中环境亮度数据超过正常亮度值时，判断出现交通异常。
  9. 根据权利要求6-8任一项所述的车载设备，其特征在于，所述异常分析结果包括交通异常类型、交通异常级别、责任方、损失价值。
  10. 根据权利要求9所述的车载设备，其特征在于，所述处理器执行所述根据异常分析结果执行相应的措施，具体方式为：
    根据交通异常类型确定对应的交通异常管理中心；
    将所述异常分析结果和位置发送至对应的交通异常管理中心，以便所述交通异常管理中心采取措施解决所述交通异常问题。
PCT/CN2018/085875 2017-12-27 2018-05-07 一种道路交通数据的处理方法及车载设备 WO2019128027A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711439620.5 2017-12-27
CN201711439620.5A CN108269397A (zh) 2017-12-27 2017-12-27 一种道路交通数据的处理方法及车载设备

Publications (1)

Publication Number Publication Date
WO2019128027A1 true WO2019128027A1 (zh) 2019-07-04

Family

ID=62772676

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/085875 WO2019128027A1 (zh) 2017-12-27 2018-05-07 一种道路交通数据的处理方法及车载设备

Country Status (2)

Country Link
CN (1) CN108269397A (zh)
WO (1) WO2019128027A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111489545B (zh) * 2019-01-28 2023-03-31 阿里巴巴集团控股有限公司 道路监控方法、装置以及设备、存储介质
CN112116167A (zh) * 2020-09-28 2020-12-22 北京嘀嘀无限科技发展有限公司 数据处理方法、数据处理装置、存储介质和电子设备
CN114143941A (zh) * 2021-11-25 2022-03-04 安徽极光照明工程有限公司 一种基于智能控制的园林照路灯控制系统及方式

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN85204022U (zh) * 1985-09-29 1986-10-29 北京工业大学 火灾报警器
CN102098492A (zh) * 2009-12-11 2011-06-15 上海弘视通信技术有限公司 音视频联合分析的打架斗殴检测系统及其检测方法
CN104751629A (zh) * 2013-12-31 2015-07-01 中国移动通信集团公司 一种交通事件的检测方法和系统
CN105225408A (zh) * 2014-06-19 2016-01-06 宇龙计算机通信科技(深圳)有限公司 自动报警的方法及装置
CN105513361A (zh) * 2016-02-01 2016-04-20 广州君合智能装备技术有限公司 一种基于互联网的交通报警方法及系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105227654B (zh) * 2015-09-25 2018-10-26 宇龙计算机通信科技(深圳)有限公司 一种智能出险的方法、装置和系统
CN106021548A (zh) * 2016-05-27 2016-10-12 大连楼兰科技股份有限公司 基于分布式人工智能图像识别的远程定损方法及系统
CN106101628A (zh) * 2016-06-30 2016-11-09 深圳市元征科技股份有限公司 一种车辆事故处理的方法以及终端
CN106296118A (zh) * 2016-08-03 2017-01-04 深圳市永兴元科技有限公司 基于图像识别的车辆定损方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN85204022U (zh) * 1985-09-29 1986-10-29 北京工业大学 火灾报警器
CN102098492A (zh) * 2009-12-11 2011-06-15 上海弘视通信技术有限公司 音视频联合分析的打架斗殴检测系统及其检测方法
CN104751629A (zh) * 2013-12-31 2015-07-01 中国移动通信集团公司 一种交通事件的检测方法和系统
CN105225408A (zh) * 2014-06-19 2016-01-06 宇龙计算机通信科技(深圳)有限公司 自动报警的方法及装置
CN105513361A (zh) * 2016-02-01 2016-04-20 广州君合智能装备技术有限公司 一种基于互联网的交通报警方法及系统

Also Published As

Publication number Publication date
CN108269397A (zh) 2018-07-10

Similar Documents

Publication Publication Date Title
WO2017193933A1 (zh) 交通事故预警方法及交通事故预警装置
WO2019128028A1 (zh) 一种道路交通数据的记录方法及车载设备
JP2020513617A (ja) 運転行為の確定方法、装置、機器及び記憶媒体
US20180114445A1 (en) Method of providing sound tracking information, sound tracking apparatus for vehicles, and vehicle having the same
CN108226854B (zh) 提供后车的可视化信息的装置和方法
WO2019128027A1 (zh) 一种道路交通数据的处理方法及车载设备
CN109895767B (zh) 汽车的控制方法、装置及存储介质
US9733346B1 (en) Method for providing sound detection information, apparatus detecting sound around vehicle, and vehicle including the same
CN112744174B (zh) 车辆碰撞监测方法、装置、设备及计算机可读存储介质
De Godoy et al. Paws: A wearable acoustic system for pedestrian safety
CN111540191B (zh) 基于车联网的行车示警方法、系统、设备及存储介质
JP7436061B2 (ja) 運転支援装置、方法及びプログラム
CN111785057A (zh) 一种突发事件的提示方法、装置及车辆
CN111275848A (zh) 车辆事故报警方法、装置、存储介质和行车记录仪
CN205232353U (zh) 一种交互式车载智能终端系统
US20230351894A1 (en) Accident reporter
JP2021163463A (ja) 情報処理方法、情報処理装置、及びプログラム
CN111145554B (zh) 一种基于自动驾驶aeb的场景定位方法和装置
CN111147738A (zh) 警用车载全景慧眼系统、装置、电子设备及介质
CN116453375A (zh) 城市道路危险数据监控管理方法、装置、电子设备及介质
CN114677848B (zh) 感知预警系统、方法、装置及计算机程序产品
KR102067547B1 (ko) 이동통신단말 및 건물 cctv카메라 간의 통신연결 및 영상분석 기반의 주변차량 위험상황 감지 및 방법
CN116432911A (zh) 数据处理方法、装置及存储介质
JP2021163462A (ja) 情報処理方法、情報処理装置、及びプログラム
CN113283286A (zh) 一种驾驶员异常行为检测方法和装置

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: 18895964

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18895964

Country of ref document: EP

Kind code of ref document: A1