CN115731714B - Road environment sensing method and device - Google Patents
Road environment sensing method and device Download PDFInfo
- Publication number
- CN115731714B CN115731714B CN202211533275.2A CN202211533275A CN115731714B CN 115731714 B CN115731714 B CN 115731714B CN 202211533275 A CN202211533275 A CN 202211533275A CN 115731714 B CN115731714 B CN 115731714B
- Authority
- CN
- China
- Prior art keywords
- road environment
- road
- weak learning
- abnormal
- current intersection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000002159 abnormal effect Effects 0.000 claims abstract description 123
- 238000012549 training Methods 0.000 claims description 43
- 238000004891 communication Methods 0.000 claims description 29
- 230000008447 perception Effects 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 12
- 241001465754 Metazoa Species 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000010276 construction Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 9
- 238000007405 data analysis Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000010354 integration Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/12—Detection or prevention of fraud
- H04W12/121—Wireless intrusion detection systems [WIDS]; Wireless intrusion prevention systems [WIPS]
- H04W12/122—Counter-measures against attacks; Protection against rogue devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a road environment sensing method and device, which can be used for rapidly identifying road safety conditions. The application relates to the technical field of information, which comprises the following steps: after acquiring road environment data from a V2X message gateway (or other equipment), the device inputs the road environment data into a strong classification learner composed of a plurality of weak classification learners to identify abnormal road conditions, so as to obtain a plurality of abnormal road condition identification results, namely V2X safety events; and finally, issuing the road environment sensing result to the current intersection and other intersections. The road environment sensing device can automatically perform data synchronization with other systems. By applying the technical scheme of the application, the road environment sensing capability can be provided for the road without the road side equipment.
Description
Technical Field
The application relates to the technical field of information, in particular to a road environment sensing method and device.
Background
The road environment perception decision is the basic capability of an automatic driving cloud control basic platform, and provides basic support for a V2X communication network.
Currently, perceived decisions of road environments are typically implemented at the road side. However, this method requires additional equipment to be deployed on the road side, has high construction cost and long construction period, and cannot provide road environment sensing capability for roads without additional equipment to be deployed, meanwhile, the computing capability of the road side equipment is generally limited, the reliability of the road environment sensing result cannot be ensured, and the road environment sensing result of the current intersection cannot be forwarded to other intersections, so that the road environment sensing result is unfavorable for other intersections to learn the overall road condition.
Disclosure of Invention
The invention provides a road environment sensing method and a road environment sensing device, which mainly characterized in that the road environment sensing device is independently deployed at a cloud end, so that the road environment sensing capability can be provided for a road without road side equipment, meanwhile, the reliability of a road environment sensing result can be ensured, and the road environment sensing result can be issued to different intersections.
According to a first aspect of an embodiment of the present invention, there is provided a vehicle roaming data processing method applied to a road environment sensing device independently deployed at a cloud, where the road environment sensing device is configured with a standardized interface, including:
when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device, acquiring an Internet protocol address of the target equipment;
if the Internet protocol address is in a preset trust list, receiving road environment data of the current intersection;
inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtaining abnormal road condition identification results respectively corresponding to the plurality of weak learning classifiers, wherein the plurality of weak learning classifiers respectively represent the mapping relation between the road environment data and the abnormal road condition identification results;
Determining a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, wherein the road environment sensing result comprises a V2X safety event;
issuing the road environment sensing result to the current intersection and other intersections;
and if the Internet protocol address is not in the preset trust list and the preset attack list, judging whether to accept the road environment data according to the dangerous coefficient and the historical access frequency corresponding to the target equipment.
According to a second aspect of an embodiment of the present invention, there is provided a road environment sensing device configured with a standardized interface, including:
the acquisition unit is used for acquiring an Internet protocol address of the target equipment when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device;
an accepting unit, configured to accept road environment data of the current intersection if the internet protocol address is in a preset trust list;
the recognition unit is used for inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to recognize abnormal road conditions, so as to obtain abnormal road condition recognition results respectively corresponding to the plurality of weak learning classifiers, wherein the plurality of weak learning classifiers respectively represent the mapping relation between the road environment data and the abnormal road condition recognition results;
The determining unit is used for determining a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, wherein the road environment sensing result comprises a V2X safety event;
the issuing unit is used for issuing the road environment sensing result to the current intersection and other intersections;
and the judging unit is used for judging whether the road environment data is accepted or not according to the dangerous coefficient and the historical access frequency corresponding to the target equipment if the Internet protocol address is not in the preset trust list and the preset attack list.
According to a third aspect of embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device, acquiring an Internet protocol address of the target equipment;
if the Internet protocol address is in a preset trust list, receiving road environment data of the current intersection;
inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtaining abnormal road condition identification results respectively corresponding to the plurality of weak learning classifiers, wherein the plurality of weak learning classifiers respectively represent the mapping relation between the road environment data and the abnormal road condition identification results;
Determining a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, wherein the road environment sensing result comprises a V2X safety event;
issuing the road environment sensing result to the current intersection and other intersections;
and if the Internet protocol address is not in the preset trust list and the preset attack list, judging whether to accept the road environment data according to the dangerous coefficient and the historical access frequency corresponding to the target equipment.
According to a fourth aspect of embodiments of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device, acquiring an Internet protocol address of the target equipment;
if the Internet protocol address is in a preset trust list, receiving road environment data of the current intersection;
inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtaining abnormal road condition identification results respectively corresponding to the plurality of weak learning classifiers, wherein the plurality of weak learning classifiers respectively represent the mapping relation between the road environment data and the abnormal road condition identification results;
Determining a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, wherein the road environment sensing result comprises a V2X safety event;
issuing the road environment sensing result to the current intersection and other intersections;
and if the Internet protocol address is not in the preset trust list and the preset attack list, judging whether to accept the road environment data according to the dangerous coefficient and the historical access frequency corresponding to the target equipment.
The innovation points of the embodiment of the invention include:
1. the road environment sensing device is independently deployed at the cloud, and the large-scale and standardized deployment and operation of the automatic driving cloud control basic platform are supported.
2. The method for obtaining the road environment data by using the standardized interface provided externally and providing the road safety perception capability for the road side and the vehicle end through AI analysis and big data analysis is one of the innovation points of the embodiment of the invention.
3. By setting a preset trust list, a preset attack list, symmetric encryption and the like, ensuring the safe access of the system is one of the innovation points of the embodiment of the invention.
Compared with the road environment perception decision mode of the road side in the prior art, the road environment perception method and device provided by the invention can acquire the Internet protocol address of the target device when the target device calls the standardized interface to send the road environment data of the current intersection to the road environment perception device, if the Internet protocol address is in a preset trust list, the road environment data of the current intersection is accepted, the road environment data is input into a strong learning classifier formed by a plurality of weak learning classifiers to carry out abnormal road condition recognition, and the abnormal road condition recognition results corresponding to the weak learning classifiers are obtained, wherein the weak learning classifiers respectively represent the mapping relation between the road environment data and the abnormal road condition recognition results, meanwhile, the road environment perception result of the current intersection is determined according to the abnormal road condition recognition results corresponding to the weak learning classifiers, and finally, the road environment perception result is issued to the current intersection and other intersections. Therefore, the road environment sensing device is independently deployed at the cloud, road safety sensing capability can be provided for the road side, so that additional deployment equipment at the road side can be avoided, construction cost is reduced, the road environment sensing device which is independently deployed can ensure reliability of road environment sensing results through carrying out big data and AI analysis, and can forward the road environment sensing results to different intersections.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a schematic flow chart of a road environment sensing method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of another road environment sensing method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a road environment sensing device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of another road environment sensing device according to an embodiment of the present application;
Fig. 5 shows a schematic entity structure of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The road environment perception decision-making mode is realized at the road side, equipment is required to be additionally arranged at the road side, the construction cost is high, the construction period is long, the road environment perception capability cannot be provided for the road without the additional arrangement equipment, meanwhile, the calculation capability of the road side equipment is generally limited, the reliability of the road environment perception result cannot be ensured, the road environment perception result of the current road junction cannot be forwarded to other road junctions, and therefore the whole road condition is not easy to be known for other road junctions.
In order to solve the above-mentioned problems, an embodiment of the present invention provides a road environment sensing method applied to a road environment sensing device independently deployed at a cloud, where the road environment sensing device is configured with a standardized interface, as shown in fig. 1, and the method includes:
and step 101, when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device, acquiring the Internet protocol address of the target equipment.
The road environment sensing device is independently deployed on an edge cloud of the automatic driving cloud control basic platform, the target equipment is any equipment for sending road environment data to the road environment sensing device which is independently deployed, such as road side equipment, a message gateway, a vehicle and the like, and the road environment data comprises: BSM messages (Basic Safety Message ), RSI messages (Road Side Information, roadside information), SPAT messages (Signal phase and timing message, traffic light phase and timing messages), MAP messages (MAP messages), radar data, camera data, etc., the BSM messages specifically include speed, steering, braking, double flashing, location, etc., and are used in V2V scenes, i.e., lane change early warning, blind zone early warning, intersection collision early warning, etc.; the RSI message is used for reporting and issuing events, road side RSU integration, platform issuing and is mostly used for V2I scenes, namely road construction, speed limit signs, overspeed early warning, bus lane early warning and the like; the SPAT message is used for guiding the vehicle speed, pushing green waves, and the like, and the road side RSU integrates the annunciator, or the annunciator is transmitted to the platform in a UU mode; the MAP message is used for describing an intersection and a lane, and has a corresponding relationship with traffic lights of the intersection; the camera data specifically includes video image frames of the intersection.
The embodiment of the invention is mainly suitable for a scene of providing road safety sensing capability for a road side and a vehicle end by utilizing the independently deployed road environment sensing device. The execution subject of the embodiment of the invention is a road environment sensing device which is independently deployed at a cloud.
The road environment sensing device which is independently deployed in the embodiment of the invention is provided with the standardized software and hardware interface, provides a standardized data interface for the outside, and can be used for data integration with other systems. The standardized interfaces related to the road environment sensing devices independently deployed in the embodiments of the present invention are described in detail below.
In a specific application scenario, when the standardized interface is a user authentication interface, the method includes: receiving a user authentication request sent by a user through the user authentication interface, wherein the user authentication request carries a first user identifier and a first password; and generating an authentication token corresponding to the user according to the first user identifier and the first password, and feeding back the authentication token to the user. The first user identifier may specifically be a user name. The core code that invokes the user authentication interface is as follows:
the parameters related to the codes have the following meanings:
| Sequence number | Parameters (parameters) | Meaning of field | Type(s) | Whether or not to fill |
| 1 | User_name | User name | string | Is that |
| 2 | User_pwd | User password | string | Is that |
For the embodiment of the invention, in order to ensure the communication safety between the independently deployed road environment sensing device and other product equipment, the road environment sensing device generates a corresponding token according to the user name and the password configured by the other product equipment and feeds the token back to the other product equipment, and the other product equipment can communicate with the road environment sensing device according to the token, so that the communication safety between the product equipment can be ensured.
In a specific application scenario, when the standardized interface is a message gateway communication configuration interface, the method further includes: receiving a communication configuration request sent by the message gateway through calling the communication configuration interface, wherein the communication configuration request carries a second user identifier and a second password; based on the second user identification and the second password, carrying out communication configuration with the message gateway; and when the communication configuration with the message gateway is successful, feeding back a communication configuration success message to the message gateway. The second user identifier may specifically be a user name. The core code for invoking the message gateway communication configuration interface is as follows:
The meaning of the parameters carried by the communication configuration request in the code is as follows:
| sequence number | Parameters (parameters) | Meaning of field | Type(s) | Field description | Whether or not to fill |
| 1 | Broker | MQ server | string | tcp://ip:port | Is that |
| 2 | User_name | User name | string | MQ broker user | Is that |
| 3 | User_pwd | Password code | decimal | Use of MQBrokerHousehold | Is that |
The parameter related to the return value in the code has the following meaning:
| sequence number | Parameters (parameters) | Meaning of field | Type(s) | Whether or not to fill |
| 1 | Code | State code | string | Is that |
| 2 | Msg | Message | string | Whether or not |
Therefore, the MQ message gateway can be configured through the message gateway communication configuration interface, so that the road environment perception device can acquire the message from the MQ message gateway or send the message to the MQ message gateway.
In a specific application scene, the road environment sensing device can also acquire BSM information, RSI information, SPAT information, radar data, camera data and the like through a standardized interface, and then provide road environment sensing capability for a road side or a vehicle end through big data analysis or AI analysis. Specifically, the V2X security event that occurs can be identified through big data analysis or AI analysis, and typical V2X security event events specifically include abnormal road conditions, abnormal vehicle conditions, bad weather, traffic lights, warning signs, automatic driving pre-warning, and the like. The abnormal road conditions comprise traffic accidents, road congestion, pedestrian recognition, bicycle recognition, animal recognition and the like, the traffic lights comprise red light reminding and green light reminding, the abnormal vehicle conditions comprise vehicle overspeed, vehicle slow running, vehicle stopping, vehicle reverse running, large truck recognition and the like, the bad weather comprises rain, hail, wind, fog, snow, haze, sand storm and the like, the warning sign comprises sharp turning, continuous downhill, falling of attention, crosswind, tunnel, danger attention, road construction, front vehicle queuing, traffic prohibition, road speed limitation, toll station forenotice without ETC lanes, toll station forenotice with ETC lanes, service area forenotice and the like, and the automatic driving warning comprises forward collision warning, intersection collision warning, left turning assistance, blind area forewarning or lane changing forewarning, reverse overtaking forewarning, emergency braking, abnormal vehicle reminding, vehicle out-of-control warning, road danger condition prompt, speed limiting forewarning, potential traffic participant collision forewarning, green wave guiding, in-vehicle sign, front congestion warning and emergency vehicle warning. It should be noted that the V2X security event according to the embodiment of the present invention is not limited to the above-listed event, and may also include other events.
The V2X security event occurring at the current intersection can be determined by carrying out big data analysis or AI analysis on the BSM message, the RSI message, the SPAT message, the radar data and the camera data, and then the road environment perception result of the current intersection can be determined. For big data analysis, a flink stream process can be adopted to realize, for example, vehicle reverse running, speed limiting and the like; for AI analysis, the recognition of the V2X security event can be realized based on a strong learner and a weak learner, for example, the ABC Boost (Adaptive Base Class Boost) model is adopted to recognize abnormal road conditions such as pedestrian recognition, bicycle recognition or animal recognition, and the specific process of recognizing abnormal road conditions by adopting the ABC Boost model is described in detail in the following steps.
It should be noted that, the standardized interfaces related to the road environment sensing device in the embodiment of the present invention are not limited to the above-mentioned interfaces, and may include other types of standardized interfaces.
Meanwhile, the road environment sensing device which is independently deployed in the embodiment of the invention can also automatically perform data synchronization with other systems, wherein the other systems can be specifically message gateways.
In order to realize safe access of the system, a preset trust list and a preset attack list of the road environment sensing device are arranged in the embodiment of the invention, the preset trust list stores the internet protocol addresses which are allowed to be accessed, and the preset attack list stores the internet protocol addresses which are forbidden to be accessed. In order to avoid malicious attacks on the road environment sensing device by the access equipment, when the target equipment calls the standardized interface to send road environment data to the road environment sensing device which is independently deployed, the internet protocol address of the target equipment needs to be acquired, the internet protocol address of the target equipment is compared with the internet protocol addresses in the preset trust list and the preset attack list, and whether the road environment data is accepted is judged according to the comparison result.
Step 102, if the internet protocol address is in a preset trust list, receiving the road environment data of the current intersection.
For the embodiment of the invention, if the internet protocol address of the target device is in the preset trust list, the target device is indicated not to cause malicious attack on the road environment sensing device, so that the road environment sensing device can accept the road environment data sent by the target device.
And 103, inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtaining abnormal road condition identification results respectively corresponding to the plurality of weak learning classifiers.
The strong learning classifier can be specifically an ABC Boost model, and the plurality of weak learning classifiers respectively represent a mapping relationship between the road environment data and an abnormal road condition recognition result, and in addition, the abnormal road condition recognition result comprises that the current intersection has an abnormal road condition and the current intersection does not have an abnormal road condition.
For the embodiment of the invention, after the road environment sensing device acquires the road environment data of the current intersection, the road environment sensing device can identify the V2X security event of the current intersection based on the road environment data, and particularly can input the road environment data into the ABC Boost model for identifying abnormal road conditions, and when the current intersection is identified to have pedestrians, bicycles or animals and other objects, the abnormal road conditions of the current intersection are determined; when the situation that no pedestrian, bicycle or animal and other objects exist at the current intersection is identified, determining that no abnormal road condition exists at the current intersection. The ABC Boost model is composed of a plurality of weak learning classifiers, and road environment data of the current intersection can be respectively input into the plurality of weak learning classifiers for abnormal road condition recognition during specific recognition, so that road abnormal recognition results respectively corresponding to the plurality of weak learning classifiers are obtained.
And 104, determining a road environment perception result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers.
For the embodiment of the invention, after the abnormal road condition recognition results respectively corresponding to the weak learning classifiers are obtained, the road abnormal recognition results respectively corresponding to the weak learning classifiers can be synthesized to obtain the final road abnormal recognition result, namely the road environment perception result of the current intersection, wherein the road environment perception result is the recognized V2X safety event, and the V2X safety event specifically comprises abnormal road conditions, abnormal vehicle conditions, bad weather, traffic lights, warning signs, automatic driving early warning and the like. The specific events included in the abnormal road condition, the abnormal vehicle condition, the bad weather, the traffic light, the warning sign and the automatic driving early warning are completely consistent with those described in the step 101, and are not repeated here.
And 105, issuing the road environment sensing result to the current intersection and other intersections.
For the embodiment of the invention, after the road environment sensing device analyzes and obtains the road environment sensing result of the current intersection, the road environment sensing result can be issued to the current intersection or other intersections, so that the road environment sensing capability can be provided for the road side.
Compared with the mode that the road environment sensing result cannot be forwarded in the prior art, the road environment sensing device in the embodiment of the invention can send the road environment sensing result to different intersections.
And step 106, if the internet protocol address is not in the preset trust list and the preset attack list, judging whether to accept the road environment data according to the risk coefficient and the historical access frequency corresponding to the target equipment.
The risk coefficient of the target equipment is related to the type of the called standardized interface, and the higher the safety level of the called standardized interface is, the higher the corresponding risk coefficient is; the lower the security level of the standardized interface called in opposite, the lower the corresponding risk factor.
For the embodiment of the invention, when the internet protocol address is neither in the preset trust list nor in the preset attack list, whether the access equipment (target equipment) has a malicious attack or not needs to be further evaluated according to the risk coefficient and the historical access frequency corresponding to the access equipment (target equipment), if so, the road environment data is refused to be accepted, and the internet protocol address of the access equipment (target equipment) is added into the preset attack list.
According to the road environment sensing method provided by the embodiment of the invention, the road environment sensing device is independently deployed at the cloud end, so that road safety sensing capability can be provided for the road side, additional deployment equipment at the road side can be avoided, construction cost is reduced, the road environment sensing device which is independently deployed can ensure reliability of a road environment sensing result through carrying out big data and AI analysis, and can forward the road environment sensing result to different intersections, meanwhile, the road environment sensing device is independently deployed at the cloud end, and the road environment sensing capability is provided for the road side and the vehicle end, so that large-scale, standardized deployment and operation of an automatic driving cloud control basic platform can be supported.
Further, as a refinement and extension to the above embodiment, the embodiment of the present invention provides another road environment sensing method, as shown in fig. 2, where the method includes:
step 201, when the target device invokes the standardized interface to send the road environment data of the current intersection to the road environment sensing device, acquiring the internet protocol address of the target device.
For the embodiment of the invention, in order to ensure the safe access of the system, when the target device sends the road environment data to the road environment sensing device, the internet protocol address of the target device needs to be acquired, and whether the road environment data sent by the target device is accepted or not is judged according to the internet protocol address, the preset trust list and the preset attack list.
Step 202, if the internet protocol address is in a preset trust list, receiving the road environment data of the current intersection.
For the embodiment of the invention, if the internet protocol address of the target equipment is in the preset trust list, the target equipment is indicated not to cause malicious attack on the road environment sensing device, so that the road environment data sent by the target equipment can be accepted.
And 203, inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtaining abnormal road condition identification results respectively corresponding to the plurality of weak learning classifiers.
The strong learning classifier can be specifically an ABC Boost model, and the ABC Boost model includes a plurality of weak learning classifiers, where the plurality of weak learning classifiers respectively characterize a mapping relationship between the road environment data and the abnormal road condition recognition result.
In the embodiment of the invention, the nature of abnormal road condition recognition is recognition of a target object, the target object can be a foreign object such as a pedestrian, a bicycle or an animal, and when the target object exists at the current intersection, the abnormal road condition exists at the current intersection is determined; and when the target object exists at the current intersection, determining that the abnormal road condition does not exist at the current intersection. Based on this, 203 specifically includes: inputting the road environment data into the strong learning classifier formed by a plurality of weak learning classifiers to identify a target object; aiming at any one weak learning classifier in the plurality of weak learning classifiers, if the any one weak learning classifier identifies that a target object exists at the current intersection, determining that an abnormal road condition identification result corresponding to the any one weak learning classifier is that the abnormal road condition exists at the current intersection; if the any classifier does not recognize that the target object exists at the current intersection, determining that the abnormal road condition recognition result corresponding to the any weak learning classifier is that the abnormal road condition does not exist at the current intersection.
Specifically, any one of the weak learning classifiers of the present embodiment may perform two classification, and the classification result includes the absence of a target object (pedestrian, bicycle, animal, etc.) and the presence of a target object (pedestrian, bicycle, animal, etc.). When the specific recognition is carried out, road environment data can be respectively input into a plurality of weak learning classifiers for target object recognition, each weak learning classifier can output a first probability value that no target object exists at the current intersection and a second probability value that the target object exists at the current intersection, when the first probability value is larger than the second probability value, the weak learning classifier is determined to not recognize that the target object exists at the current intersection, namely, the abnormal road condition recognition result corresponding to the weak learning classifier is determined to be that no abnormal road condition exists at the current intersection; when the first probability value is smaller than or equal to the second probability value, determining that the weak learning classifier recognizes that the target object exists at the current intersection, namely determining that the abnormal road condition recognition result corresponding to the weak learning classifier is that the abnormal road condition exists at the current intersection. Therefore, the abnormal road condition recognition results corresponding to the weak learning classifiers can be obtained according to the mode.
And 204, determining a road environment perception result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers.
The road environment sensing result comprises a V2X safety event, the road environment sensing result is an identified V2X safety event, and the V2X safety event specifically comprises abnormal road conditions, abnormal vehicle conditions, bad weather, traffic lights, warning signs, automatic driving early warning and the like. The specific events included in the abnormal road condition, the abnormal vehicle condition, the bad weather, the traffic light, the warning sign and the automatic driving early warning are completely consistent with those described in the step 101, and are not repeated here.
For the embodiment of the present invention, in order to determine the road environment sensing result of the current intersection, step 204 specifically includes: and according to the weight values respectively corresponding to the weak learning classifiers, synthesizing abnormal road condition recognition results respectively corresponding to the weak learning classifiers to obtain a road environment perception result of the current intersection.
For example, when the abnormal road condition recognition result of the weak learning classifier is that the abnormal road condition does not exist at the current intersection, the abnormal road condition is represented by-1; when the abnormal road condition recognition result of the weak learning classifier is that the road condition of the current intersection is abnormal, the abnormal road condition is represented by +1. Further, the abnormal road condition recognition results corresponding to the weak learning classifiers are multiplied by the corresponding weight values, so that a final abnormal road condition recognition result can be obtained, and if the final calculated value is 0.9, the final abnormal road condition recognition result is indicated as the target object existing at the current intersection due to the fact that the final abnormal road condition recognition result is close to 1, and the road condition is abnormal, so that the road environment perception result of the current intersection can be determined.
Further, before the abnormal road condition is identified by using the strong learning classifier (ABCBoost model), training is required in advance, and the method includes, as an optional implementation manner, for the training process of the strong learning classifier: collecting road environment sample data, constructing a sample training set, and determining initial weight distribution corresponding to the sample training set; training a first weak learning classifier according to the sample training set and the initial weight distribution corresponding to the sample training set; calculating a classification error rate corresponding to the first weak learning classifier according to the abnormal road condition recognition result output by the first weak learning classifier and the actual road condition corresponding to the sample training set; calculating a weight value corresponding to the first weak learning classifier based on the classification error rate; updating the initial weight distribution based on the weight value of the first weak learning classifier to obtain the updated weight distribution of the sample training set; and continuing to train a second weak learning classifier according to the sample training set and the updated weight distribution, repeating the training process of the weak learning classifier until the preset training times are reached, and adding the trained multiple weak learning classifiers according to the corresponding weight values to obtain the strong learning classifier.
Specifically, a sample training set t= { (x) is first constructed 1 ,y 1 ),(x 2 ,y 2 ),…,(x m ,y m ) And determining the training times of the strong learning classifier to be K+1, wherein x m Is road environment data, y m Is-1 or 1. Then initializing weight distribution of initial sample training set, D (1) = (w) 11 ,w 12 ,…,w 1m )；w 1i =1/m; i=1, 2, …, m, followed by training the first weak learning classifier G using the initial weight distribution 1 (X) and calculates a classification error rate e corresponding to the first weak learning classifier 1 Further, based on the classification error rate e 1 Calculate a first weak learning classifier G 1 Weight value a of (X) 1 Finally based on the first weak learning classifier G 1 Weight value a of (X) 1 Updating the initial weight distribution D (1) to obtain the weight distribution of the updated sample training set, and repeating the process to continuously train the second weak learning classifier G 2 (X)。
G for kth training k (X) whose corresponding weight distribution is D (k) = (w) k1 ,w k2 ,…,w km ) Computing a weak learning classifier G k (X) the corresponding classification error rate e k The method comprises the following steps:
wherein w is ki Classifier G for weak learning k Weight distribution of (X), G k (x i ) Classifier G for weak learning k And (3) outputting an abnormal road condition identification result, wherein yi is an actual road condition.
Further, a weak learning classifier G is calculated k Weight value a of (X) k The specific formula is as follows:
further, the weight distribution of the sample training set is updated, and the specific formula is as follows:
Wherein w is k+1,i Z for updated weight distribution k Is a normalization factor. Further, the updated weight distribution w of the sample training set may be utilized k+1,i Training weak learning classifier G k+1 And (X) finally adding all the weak learning classifiers according to the weight values corresponding to all the trained weak learning classifiers to obtain strong learning classifiers as follows:
therefore, according to the formula, the strong learning classifier can be trained, and the recognition of abnormal road conditions can be realized by using the strong learning classifier.
And 205, issuing the road environment sensing result to the current intersection and other intersections.
For the embodiment of the invention, the road environment sensing result determined by the road environment sensing device can be issued not only to the current intersection but also to other intersections.
Step 206, if the internet protocol address is not in the preset trust list and the preset attack list, determining a risk coefficient corresponding to the target device according to the standardized interface type called by the target device.
For the embodiment of the invention, the security levels corresponding to different types of standardized interfaces are different, and when the security level of the standardized interface called by the target equipment is higher, the corresponding danger coefficient is higher; conversely, the lower the security level of the standardized interface called by the target device, the lower the corresponding risk coefficient.
Step 207, refusing to accept the road environment data when the risk coefficient reaches a preset risk coefficient or the history access frequency reaches a preset access frequency.
For example, the preset access frequency is 30 times/min, if the historical access frequency of the target device exceeds 30 times/min, it is determined that a malicious attack exists on the target device, the road environment data is refused to be accepted, and the internet protocol address of the target device is added into a preset attack list. For another example, the preset risk coefficient is 0.5, if the risk coefficient of the target device reaches 0.6, the road environment data is refused to be accepted, and the internet protocol address of the target device is added into the preset attack list. Therefore, through the arrangement of the preset trust list and the preset attack list, the safe access of the system can be ensured.
And step 208, accepting the road environment data when the risk coefficient does not reach the preset risk coefficient and the history access frequency does not reach the preset access frequency.
In order to further ensure the system security, the communication data in the embodiment of the invention can be encrypted in a symmetrical way. Based thereon, the method further comprises: and when other equipment calls the standardized interface to carry out data communication with the road environment sensing device, carrying out symmetric encryption on transmission data.
Specifically, for the data encryption process, firstly converting original data into byte streams, then encrypting the byte streams by adopting an RSA public key, and then performing base64 encoding to obtain final encrypted data; for the data decryption process, firstly, base64 decoding is carried out on the encrypted data, then, the decoded data is decrypted by utilizing an RSA private key to obtain byte streams, and finally, decrypted data, namely original data, is obtained.
Therefore, the embodiment of the invention can ensure the safe access of the system by means of preset trust lists, preset attack lists, multi-factor identity authentication (passwords, short message verification codes, true random codes), asymmetric encryption and the like.
According to the road environment sensing method provided by the embodiment of the invention, the road environment sensing device is independently deployed at the cloud end, so that road safety sensing capability can be provided for the road side, additional deployment equipment at the road side can be avoided, construction cost is reduced, the road environment sensing device which is independently deployed can ensure reliability of a road environment sensing result through carrying out big data and AI analysis, and can forward the road environment sensing result to different intersections, meanwhile, the road environment sensing device is independently deployed at the cloud end, and the road environment sensing capability is provided for the road side and the vehicle end, so that large-scale, standardized deployment and operation of an automatic driving cloud control basic platform can be supported.
Further, as a specific implementation of fig. 1, an embodiment of the present invention provides a road environment sensing device, as shown in fig. 3, where the device includes: an acquisition unit 31, an acceptance unit 32, an identification unit 33, a determination unit 34, a issuing unit 35, and a determination unit 36.
The obtaining unit 31 may be configured to obtain an internet protocol address of the target device when the target device invokes the standardized interface to send the road environment data of the current intersection to the road environment sensing device.
The receiving unit 32 may be configured to receive the road environment data of the current intersection if the internet protocol address is in a preset trust list.
The identifying unit 33 may be configured to input the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtain abnormal road condition identification results corresponding to the plurality of weak learning classifiers, where the plurality of weak learning classifiers respectively represent a mapping relationship between the road environment data and the abnormal road condition identification results.
The determining unit 34 may be configured to determine a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, where the road environment sensing result includes a V2X security event.
The issuing unit 35 may be configured to issue the road environment sensing result to the current intersection and other intersections.
The determining unit 36 may be configured to determine whether to accept the road environment data according to the risk coefficient and the historical access frequency corresponding to the target device if the internet protocol address is not in the preset trust list and the preset attack list.
In a specific application scenario, the identifying unit 33, as shown in fig. 4, includes: an identification module 331 and a determination module 332.
The recognition module 331 may be configured to input the road environment data into the strong learning classifier composed of a plurality of weak learning classifiers to perform target object recognition.
The determining module 332 may be configured to determine, for any one of the weak learning classifiers, that an abnormal road condition exists at the current intersection if the any one of the weak learning classifiers identifies that the target object exists at the current intersection, where the abnormal road condition identification result corresponds to the any one of the weak learning classifiers.
The determining module 332 may be further configured to determine that the abnormal road condition recognition result corresponding to the any one weak learning classifier is that the abnormal road condition does not exist at the current intersection if the any one classifier does not recognize that the target object exists at the current intersection.
In a specific application scenario, the determining unit 34 may be specifically configured to synthesize the abnormal road condition recognition results corresponding to the weak learning classifiers according to the weight values corresponding to the weak learning classifiers, so as to obtain the road environment perception result of the current intersection.
In a specific application scenario, the apparatus further includes: training unit 37.
The training unit 37 may be configured to collect road environment sample data, construct a sample training set, and determine an initial weight distribution corresponding to the sample training set; training a first weak learning classifier according to the sample training set and the initial weight distribution corresponding to the sample training set; calculating a classification error rate corresponding to the first weak learning classifier according to the abnormal road condition recognition result output by the first weak learning classifier and the actual road condition corresponding to the sample training set; calculating a weight value corresponding to the first weak learning classifier based on the classification error rate; updating the initial weight distribution based on the weight value of the first weak learning classifier to obtain the updated weight distribution of the sample training set; and continuing to train the second weak learning classifier according to the sample training set and the updated weight distribution, repeating the training process of the weak learning classifier until the preset training times are reached, and adding the trained multiple weak learning classifiers according to the corresponding weight values to obtain the preset strong learning classifier.
In a specific application scenario, the determining unit 34 may be further configured to determine a risk coefficient corresponding to the target device according to a standardized interface type called by the target device.
In a specific application scenario, the determining unit 36 may be specifically configured to refuse to accept the road environment data when the risk coefficient reaches a preset risk coefficient or the historical access frequency reaches a preset access frequency; and when the dangerous coefficient does not reach the preset dangerous coefficient and the historical access frequency does not reach the preset access frequency, receiving the road environment data.
In a specific application scenario, the standardized interface includes a user authentication interface, and the apparatus further includes: a generating unit 38.
The generating unit 38 may be configured to receive a user authentication request sent by a user through the user authentication interface, where the user authentication request carries a first user identifier and a first password; and generating an authentication token corresponding to the user according to the first user identifier and the first password, and feeding back the authentication token to the user.
In a specific application scenario, the standardized interface includes a message gateway communication configuration interface, and the apparatus further includes: a configuration unit 39.
The configuration unit 39 may be configured to receive a communication configuration request sent by the message gateway by calling the communication configuration interface, where the communication configuration request carries a second user identifier and a second password; based on the second user identification and the second password, carrying out communication configuration with the message gateway; and when the communication configuration with the message gateway is successful, feeding back a communication configuration success message to the message gateway.
It should be noted that, other corresponding descriptions of each functional module related to the road environment sensing device provided by the embodiment of the present invention may refer to corresponding descriptions of the method shown in fig. 1, and are not repeated herein.
Based on the above method as shown in fig. 1, correspondingly, the embodiment of the present invention further provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the following steps: when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device, acquiring an Internet protocol address of the target equipment; if the Internet protocol address is in a preset trust list, receiving road environment data of the current intersection; inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtaining abnormal road condition identification results respectively corresponding to the plurality of weak learning classifiers, wherein the plurality of weak learning classifiers respectively represent the mapping relation between the road environment data and the abnormal road condition identification results; determining a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, wherein the road environment sensing result comprises a V2X safety event; issuing the road environment sensing result to the current intersection and other intersections; and if the Internet protocol address is not in the preset trust list and the preset attack list, judging whether to accept the road environment data according to the dangerous coefficient and the historical access frequency corresponding to the target equipment.
Based on the embodiment of the method shown in fig. 1 and the device shown in fig. 3, the embodiment of the invention further provides a physical structure diagram of an electronic device, as shown in fig. 5, where the electronic device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, the processor 41 performing the following steps when said program is executed: when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device, acquiring an Internet protocol address of the target equipment; if the Internet protocol address is in a preset trust list, receiving road environment data of the current intersection; inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtaining abnormal road condition identification results respectively corresponding to the plurality of weak learning classifiers, wherein the plurality of weak learning classifiers respectively represent the mapping relation between the road environment data and the abnormal road condition identification results; determining a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, wherein the road environment sensing result comprises a V2X safety event; issuing the road environment sensing result to the current intersection and other intersections; and if the Internet protocol address is not in the preset trust list and the preset attack list, judging whether to accept the road environment data according to the dangerous coefficient and the historical access frequency corresponding to the target equipment.
According to the embodiment of the invention, the road environment sensing device is independently deployed at the cloud end, so that road safety sensing capability can be provided for the road side, additional deployment equipment at the road side can be avoided, construction cost is reduced, the road environment sensing device which is independently deployed can ensure reliability of a road environment sensing result through carrying out big data and AI analysis, and the road environment sensing result can be forwarded to different intersections.
Those of ordinary skill in the art will appreciate that: the drawing is a schematic diagram of one embodiment and the modules or flows in the drawing are not necessarily required to practice the invention.
Those of ordinary skill in the art will appreciate that: the modules in the apparatus of the embodiments may be distributed in the apparatus of the embodiments according to the description of the embodiments, or may be located in one or more apparatuses different from the present embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. The road environment sensing method is characterized by being applied to a road environment sensing device which is independently deployed at a cloud end, wherein the road environment sensing device is configured with a standardized interface and comprises the following steps:
when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device, acquiring an Internet protocol address of the target equipment;
if the Internet protocol address is in a preset trust list, receiving road environment data of the current intersection;
inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, and obtaining abnormal road condition identification results corresponding to the weak learning classifiers respectively, wherein the weak learning classifiers respectively represent mapping relations between the road environment data and the abnormal road condition identification results, the road environment data comprises basic safety information, road side information, traffic light phase and time sequence information, map information, radar data and camera data, and if any one of the weak learning classifiers identifies that a target object exists at the current intersection, the abnormal road condition identification result corresponding to the any one weak learning classifier is determined to be the abnormal road condition existing at the current intersection, and the target object comprises pedestrians, bicycles and animals;
Determining a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, wherein the road environment sensing result comprises a V2X safety event;
issuing the road environment sensing result to the current intersection and other intersections;
if the Internet protocol address is not in the preset trust list and the preset attack list, judging whether to accept the road environment data according to the dangerous coefficient and the historical access frequency corresponding to the target equipment;
before determining whether to accept the road environment data according to the risk coefficient and the historical access frequency corresponding to the target device, the method further comprises:
determining a risk coefficient corresponding to the target equipment according to the type of the standardized interface called by the target equipment, wherein the security levels corresponding to different types of standardized interfaces are different;
the determining whether to accept the road environment data according to the risk coefficient and the historical access frequency corresponding to the target device comprises the following steps:
when the risk coefficient reaches a preset risk coefficient or the history access frequency reaches a preset access frequency, refusing to accept the road environment data;
And when the dangerous coefficient does not reach the preset dangerous coefficient and the historical access frequency does not reach the preset access frequency, receiving the road environment data.
2. The method according to claim 1, wherein the inputting the road environment data into a strong learning classifier composed of a plurality of weak learning classifiers for abnormal road condition recognition, to obtain abnormal road condition recognition results respectively corresponding to the plurality of weak learning classifiers, includes:
inputting the road environment data into the strong learning classifier formed by a plurality of weak learning classifiers to identify a target object;
if the any classifier does not recognize that the target object exists at the current intersection, determining that the abnormal road condition recognition result corresponding to the any weak learning classifier is that the abnormal road condition does not exist at the current intersection.
3. The method of claim 1, wherein the determining the road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers comprises:
and according to the weight values respectively corresponding to the weak learning classifiers, synthesizing abnormal road condition recognition results respectively corresponding to the weak learning classifiers to obtain a road environment perception result of the current intersection.
4. The method according to claim 1, wherein before the inputting the road environment data into a strong learning classifier composed of a plurality of weak learning classifiers for abnormal road condition recognition, obtaining abnormal road condition recognition results respectively corresponding to the plurality of weak learning classifiers, the method further comprises:
collecting road environment sample data, constructing a sample training set, and determining initial weight distribution corresponding to the sample training set;
training a first weak learning classifier according to the sample training set and the initial weight distribution corresponding to the sample training set;
calculating a classification error rate corresponding to the first weak learning classifier according to the abnormal road condition recognition result output by the first weak learning classifier and the actual road condition corresponding to the sample training set;
calculating a weight value corresponding to the first weak learning classifier based on the classification error rate;
updating the initial weight distribution based on the weight value of the first weak learning classifier to obtain the updated weight distribution of the sample training set;
and continuing to train the second weak learning classifier according to the sample training set and the updated weight distribution, repeating the training process of the weak learning classifier until the preset training times are reached, and adding the trained multiple weak learning classifiers according to the corresponding weight values to obtain the strong learning classifier.
5. The method of any of claims 1-4, wherein the standardized interface comprises a user authentication interface, the method further comprising:
receiving a user authentication request sent by a user through the user authentication interface, wherein the user authentication request carries a first user identifier and a first password;
and generating an authentication token corresponding to the user according to the first user identifier and the first password, and feeding back the authentication token to the user.
6. The method of any of claims 1-4, wherein the standardized interface comprises a message gateway communication configuration interface, the method further comprising:
receiving a communication configuration request sent by the message gateway through calling the communication configuration interface, wherein the communication configuration request carries a second user identifier and a second password;
based on the second user identification and the second password, carrying out communication configuration with the message gateway;
and when the communication configuration with the message gateway is successful, feeding back a communication configuration success message to the message gateway.
7. A road environment awareness apparatus, wherein the road environment awareness apparatus is configured with a standardized interface, comprising:
The acquisition unit is used for acquiring an Internet protocol address of the target equipment when the target equipment calls the standardized interface to send the road environment data of the current intersection to the road environment sensing device;
an accepting unit, configured to accept road environment data of the current intersection if the internet protocol address is in a preset trust list;
the identification unit is used for inputting the road environment data into a strong learning classifier formed by a plurality of weak learning classifiers to identify abnormal road conditions, so as to obtain abnormal road condition identification results corresponding to the weak learning classifiers respectively, wherein the weak learning classifiers respectively represent the mapping relation between the road environment data and the abnormal road condition identification results, the road environment data comprises basic safety information, road side information, traffic light phase and time sequence information, map information, radar data and camera data, and if any one of the weak learning classifiers identifies that a target object exists at the current intersection, the abnormal road condition identification result corresponding to any one of the weak learning classifiers is determined to be the abnormal road condition existing at the current intersection, and the target object comprises pedestrians, bicycles and animals;
The determining unit is used for determining a road environment sensing result of the current intersection according to the abnormal road condition recognition results respectively corresponding to the weak learning classifiers, wherein the road environment sensing result comprises a V2X safety event;
the issuing unit is used for issuing the road environment sensing result to the current intersection and other intersections;
the judging unit is used for judging whether the road environment data is accepted or not according to the dangerous coefficient and the historical access frequency corresponding to the target equipment if the Internet protocol address is not in the preset trust list and the preset attack list;
the determining unit is further configured to determine a risk coefficient corresponding to the target device according to the type of the standardized interface called by the target device, where security levels corresponding to different types of standardized interfaces are different;
the judging unit is specifically configured to refuse to accept the road environment data when the risk coefficient reaches a preset risk coefficient or the historical access frequency reaches a preset access frequency; and when the dangerous coefficient does not reach the preset dangerous coefficient and the historical access frequency does not reach the preset access frequency, receiving the road environment data.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the method of any of claims 1 to 6.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2022110932308 | 2022-09-08 | ||
| CN202211093230.8A CN115472012A (en) | 2022-09-08 | 2022-09-08 | Road environment sensing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115731714A CN115731714A (en) | 2023-03-03 |
| CN115731714B true CN115731714B (en) | 2023-11-24 |
Family
ID=84368399
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211093230.8A Withdrawn CN115472012A (en) | 2022-09-08 | 2022-09-08 | Road environment sensing method and device |
| CN202211533275.2A Active CN115731714B (en) | 2022-09-08 | 2022-12-02 | Road environment sensing method and device |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211093230.8A Withdrawn CN115472012A (en) | 2022-09-08 | 2022-09-08 | Road environment sensing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN115472012A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388947A (en) * | 2018-02-06 | 2018-08-10 | 大唐高鸿信息通信研究院（义乌）有限公司 | Improvement machine learning method suitable for vehicle-mounted short haul connection net safe early warning |
| CN108388919A (en) * | 2018-02-28 | 2018-08-10 | 大唐高鸿信息通信研究院（义乌）有限公司 | The identification of vehicle-mounted short haul connection net security feature and method for early warning |
| CN108520626A (en) * | 2018-03-20 | 2018-09-11 | 深圳市金溢科技股份有限公司 | V2X car-mounted terminals, road side base station, road condition information acquisition method and system |
| CN109756548A (en) * | 2018-01-24 | 2019-05-14 | 启迪云控(北京)科技有限公司 | Intelligent network joins automobile cloud control basic platform data processing method, system and device |
| CN112614342A (en) * | 2020-12-10 | 2021-04-06 | 大唐高鸿数据网络技术股份有限公司 | Early warning method for road abnormal event, vehicle-mounted equipment and road side equipment |
| CN113409607A (en) * | 2021-03-30 | 2021-09-17 | 新奇点智能科技集团有限公司 | Road condition information pushing system, method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210097311A1 (en) * | 2019-09-27 | 2021-04-01 | Dish Network L.L.C. | Wireless vehicular systems and methods for detecting roadway conditions |
-
2022
- 2022-09-08 CN CN202211093230.8A patent/CN115472012A/en not_active Withdrawn
- 2022-12-02 CN CN202211533275.2A patent/CN115731714B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109756548A (en) * | 2018-01-24 | 2019-05-14 | 启迪云控(北京)科技有限公司 | Intelligent network joins automobile cloud control basic platform data processing method, system and device |
| CN108388947A (en) * | 2018-02-06 | 2018-08-10 | 大唐高鸿信息通信研究院（义乌）有限公司 | Improvement machine learning method suitable for vehicle-mounted short haul connection net safe early warning |
| CN108388919A (en) * | 2018-02-28 | 2018-08-10 | 大唐高鸿信息通信研究院（义乌）有限公司 | The identification of vehicle-mounted short haul connection net security feature and method for early warning |
| CN108520626A (en) * | 2018-03-20 | 2018-09-11 | 深圳市金溢科技股份有限公司 | V2X car-mounted terminals, road side base station, road condition information acquisition method and system |
| CN112614342A (en) * | 2020-12-10 | 2021-04-06 | 大唐高鸿数据网络技术股份有限公司 | Early warning method for road abnormal event, vehicle-mounted equipment and road side equipment |
| CN113409607A (en) * | 2021-03-30 | 2021-09-17 | 新奇点智能科技集团有限公司 | Road condition information pushing system, method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115731714A (en) | 2023-03-03 |
| CN115472012A (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210281986A1 (en) | Vehicle-to-Everything Abnormal Behavior Detection Method, Apparatus, and System | |
| US10932135B2 (en) | Context system for providing cyber security for connected vehicles | |
| US20180197025A1 (en) | Platform for acquiring driver behavior data | |
| Kolandaisamy et al. | A multivariant stream analysis approach to detect and mitigate DDoS attacks in vehicular ad hoc networks | |
| CN110366107A (en) | Vehicle communication method and the device for using this method | |
| US20220076565A1 (en) | Method, Device and Computer Program for a Vehicle | |
| US20230057394A1 (en) | Cooperative vehicle-infrastructure processing method and apparatus, electronic device, and storage medium | |
| CN111210620B (en) | Method, device and equipment for generating driver portrait and storage medium | |
| Huq et al. | Cyberattacks against intelligent transportation systems | |
| CN113415275A (en) | Vehicle message processing method and device, readable medium and electronic equipment | |
| Stübing | Multilayered security and privacy protection in Car-to-X networks: solutions from application down to physical layer | |
| Özkul et al. | Police‐less multi‐party traffic violation detection and reporting system with privacy preservation | |
| CN115731714B (en) | Road environment sensing method and device | |
| He et al. | Towards C-V2X Enabled Collaborative Autonomous Driving | |
| KR20190127303A (en) | Apparatus for providing notification information based on driving video and method for the same | |
| KR20170129531A (en) | Warning Apparatus for Road Speed Based on Image | |
| US20230059220A1 (en) | Method and device for validating vehicle-to-x messages in order to regulate the traffic flow | |
| Kshirsagar et al. | Review on intelligent traffic management system based on VANET | |
| Bubeníková et al. | Security solutions of intelligent transportation system's applications with using VANET networks | |
| CN114220079A (en) | Method and device for identifying surface water, computer equipment and storage medium | |
| Tang et al. | Cooperative connected smart road infrastructure and autonomous vehicles for safe driving | |
| Caballero-Gil et al. | Ubiquitous collision avoidance system for red light running | |
| KR20220038857A (en) | Autonomous driving situation recognition algorithm evaluation service device and method | |
| EP4277202A1 (en) | Threat detection for a processing system of a motor vehicle | |
| van der Ploeg et al. | SECREDAS: Safe and (Cyber-) Secure Cooperative and Automated Mobility |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |