CN111845728B - Driving assistance data acquisition method and system - Google Patents
Driving assistance data acquisition method and system Download PDFInfo
- Publication number
- CN111845728B CN111845728B CN202010573971.0A CN202010573971A CN111845728B CN 111845728 B CN111845728 B CN 111845728B CN 202010573971 A CN202010573971 A CN 202010573971A CN 111845728 B CN111845728 B CN 111845728B
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- data acquisition
- acquisition
- sample
- 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 65
- 238000003860 storage Methods 0.000 claims abstract description 17
- 238000004806 packaging method and process Methods 0.000 claims abstract description 7
- 230000004044 response Effects 0.000 claims abstract description 7
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 claims abstract 9
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 claims abstract 9
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 claims abstract 9
- 238000004891 communication Methods 0.000 claims description 27
- 238000013480 data collection Methods 0.000 claims description 26
- 238000004519 manufacturing process Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000000087 stabilizing effect Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 14
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 6
- 238000012216 screening Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a driving assistance data acquisition method and a system, wherein the method comprises the following steps: acquiring system statistical data through an ADAS system, and sending the system statistical data to a multimedia system; acquiring vehicle positioning data; packaging the system statistical data and the vehicle positioning data as acquisition decision data and sending the acquisition decision data to a cloud server; after receiving a data acquisition instruction transmitted by a cloud server, transmitting the data acquisition instruction to data acquisition equipment; acquiring target data based on the data acquisition frequency in response to the data acquisition instruction; and packaging and sending the target data to a cloud server for storage through a multimedia system. According to the invention, through crowdsourcing mode data acquisition, the hardware cost is reduced, and the problem of insufficient data coverage is solved. The cloud end adopts a decision algorithm, the data acquisition frequency of each ADAS terminal is flexibly adjusted, and invalid and repeated sample acquisition is reduced.
Description
Technical Field
The invention relates to the field of driving assistance, in particular to a driving assistance data acquisition method and system.
Background
In the past decade, the advanced driving assistance system of the intelligent vehicle has achieved significant achievement in improving driving safety, such as development of a front collision early warning system and an automatic emergency braking system. In the development process of the advanced driving assistance system, data acquisition is an essential link. For a Level2 Level driving assistance system, it is generally necessary to acquire 30 to 100 kilometers of image data, millimeter wave radar data, and the like for training a perception model, an identification model, an early warning model, and the like. As driving assistance systems evolve to higher levels, and when the model is mainly a data-driven model based on deep learning, the amount of data required for model training optimization increases exponentially.
In the data acquisition mode at the present stage, currently acquired data is generally not distinguished or deleted, and specifically, a manufacturer of the driving assistance system acquires data on a fixed route by using a special data acquisition vehicle. The problems caused by the method are that firstly, the driving scene covered by the fixed route is limited, and the full coverage is difficult to achieve; and secondly, the data of the special data acquisition vehicle cannot be used as effective driver behavior data for analysis. If the route is enlarged to cover more scenes, the collection amount of data is greatly increased, and most of the data is useless data and occupies a large amount of space of a storage device. In order to filter out useless data, a large amount of labor is also needed, and the cost is high. In addition, due to factors such as the number and the location of special data acquisition vehicles, the data availability ratio is not high, and optimization of later-stage algorithms is not facilitated.
Therefore, a new data acquisition method is needed to cover more driving scenes and road sections while considering the cost, and to achieve higher availability of the acquired data.
Disclosure of Invention
In order to solve the technical problem, the invention discloses a driving assistance data acquisition method and a driving assistance data acquisition system. The specific technical scheme is as follows.
In a first aspect, the present invention discloses a driving assistance data collecting method applied to a vehicle, the method comprising:
acquiring system statistical data through an ADAS system of a vehicle, and sending the system statistical data to a multimedia system of the vehicle;
acquiring vehicle positioning data through a positioning module of the multimedia system;
the multimedia system packages the system statistical data and the vehicle positioning data as acquisition decision data and sends the acquisition decision data to a cloud server, so that the cloud server judges whether data acquisition is needed or not according to the acquisition decision data;
after the multimedia system receives a data acquisition instruction transmitted by the cloud server, the data acquisition instruction is sent to at least one data acquisition device, and the data acquisition instruction comprises data acquisition frequency;
acquiring at least one type of target data based on the data acquisition frequency in response to the data acquisition instruction;
and packaging the at least one type of target data through the multimedia system and sending the target data to the cloud server for storage so as to develop and optimize a target ADAS.
Preferably, the at least one data acquisition device comprises a camera, a millimeter wave radar and a sensor, and the camera internally supports a data acquisition function and a communication function to realize data acquisition and communication with the multimedia system.
Further, acquiring system statistical data through the ADAS system, and sending the system statistical data to the multimedia system includes:
acquiring vehicle environment data through the millimeter wave radar, and sending the vehicle environment data to the camera through a CAN bus;
the method comprises the steps of obtaining image data and driver behavior data through the camera, and sending the image data, the driver behavior data and the vehicle environment data to the multimedia system through the camera.
Further, the multimedia system packages the system statistical data and the vehicle positioning data as acquisition decision data and sends the acquisition decision data to a cloud server, and the method further comprises the following steps:
acquiring vehicle running state data through a chassis sensor, sending the vehicle running state data to the multimedia system, and adding the vehicle running state data to the collected decision data;
and generating a data acquisition request signal, and adding the data acquisition request signal to the acquisition decision data.
Further, the vehicle is a mass production vehicle, and the method further comprises:
adopt crowdsourcing mode, arbitrary vehicle in the volume production vehicle communicates with high in the clouds server as data acquisition vehicle terminal to obtain the data acquisition instruction that arbitrary vehicle in the volume production vehicle corresponds.
Further, the method further comprises:
when the automatic braking system or the electronic body stabilizing system of the vehicle performs emergency safety operation, the vehicle actively acquires at least one type of current target data and sends the at least one type of target data to the cloud server.
In a second aspect, the invention also discloses a driving assistance data acquisition method, which is applied to a cloud server, and the method comprises the following steps:
acquiring acquisition decision data sent by a vehicle;
judging whether data acquisition is needed or not based on the road section and the scene according to the acquisition decision data;
when data acquisition is needed, generating a data acquisition instruction, wherein the data acquisition instruction comprises data acquisition frequency;
sending the data acquisition instructions to a multimedia system of the vehicle to cause the multimedia system to communicate the data acquisition instructions to at least one data acquisition device of the vehicle;
receiving at least one type of target data acquired by the vehicle in response to the acquisition instruction;
and storing the at least one type of target data to perform development optimization of the target ADAS system.
Further, the collected decision data includes ADAS system statistical data, vehicle positioning data and vehicle driving state data.
Further, the determining whether data acquisition is required based on the road section and the scene according to the acquisition decision data includes:
establishing a database with road sections and/or scenes as labels;
abstracting the vehicle positioning data in the collected decision data into a target road section in a preset format;
retrieving sample data of the target road section in the database, and acquiring the number of the sample data;
and when the sample quantity of the sample data does not reach a preset threshold value, judging that data acquisition is required and generating a data acquisition instruction.
Further, when data acquisition is needed, generating a data acquisition instruction, where the data acquisition instruction includes a data acquisition frequency, and the data acquisition instruction includes:
acquiring the current time and the vehicle speed of the vehicle according to the acquired decision data, and calculating the average traffic flow and the collision time of the front vehicle;
processing the current time, the vehicle speed, the average traffic flow and the front vehicle collision time to obtain a target code;
screening the database to obtain a sample code of at least one sample data of which the Euclidean distance is smaller than a preset threshold value in the sample data of the target road section;
judging scene similarity based on the target code and the sample code of the at least one sample data;
and calculating the data acquisition frequency according to the sample number of the sample data and/or the scene similarity.
Further, the determining whether data acquisition is required further includes:
analyzing the collection decision data, and generating a data collection instruction when finding that an ADAS system of the vehicle detects a dangerous condition;
and/or generating a data acquisition instruction when detecting that the behavior of the driver is abnormal according to the behavior data of the driver in the acquired decision data.
In a third aspect, the present invention also discloses a driving assistance data acquisition system, which includes:
the cloud server is provided with a database and a decision module, the database is used for storing and retrieving sample data, and the decision module is used for judging whether data acquisition is needed or not and calculating data acquisition frequency;
a vehicle comprising an ADAS system, a multimedia system, and a sensor, wherein:
the ADAS system is provided with a camera and a radar and is used for collecting statistic data of the ADAS system;
the multimedia system is provided with a communication module and a positioning module and is used for acquiring vehicle positioning data and realizing communication between the vehicle and the cloud server;
the sensor is used for collecting vehicle running state data of the vehicle.
By adopting the technical scheme, the driving assistance data acquisition method and the driving assistance data acquisition system have the following beneficial effects: the invention adopts a crowdsourcing mode, each mass production vehicle is a data acquisition vehicle terminal, and a special data acquisition vehicle does not need to be manufactured, so that the labor cost of a data acquirer can be reduced, and more driving scenes, driving road sections, time and places, behavior operations of drivers and the like in the real world can be covered; in addition, the data are acquired by using the ADAS system installed on the mass production vehicle, so that the vehicle does not need to be modified or hardware equipment is not added, and the cost is reduced; moreover, the cloud server carries out acquisition decision, controls the triggering condition of data acquisition, flexibly adjusts the data acquisition frequency of each vehicle, and reduces invalid and repeated data sample acquisition, so that the acquired data is more diverse and diversified, and the utilization rate of the data is higher; finally, labels of scenes and road sections are defined for the data, the workload of manual labeling analysis is reduced, meanwhile, semi-automatic labeling enables the data to have more consistency and stability, and the efficiency of data acquisition and processing is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a driving assistance data acquisition method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another driving assistance data collection method provided by an embodiment of the invention;
fig. 3 is an exemplary diagram for indexing according to road segments according to an embodiment of the present invention;
fig. 4 is an exemplary diagram of another driving assistance data collection method provided by the embodiment of the invention;
fig. 5 is a driving assistance data collection system according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic may be included in at least one implementation of the invention. In describing the present invention, it is to be understood that the terms "first," "second," "third," and "fourth," etc. in the description and claims of the present invention and the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, 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 steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
First, key terms and abbreviations involved in the embodiments of the present disclosure are defined.
ADAS: an Advanced driving assistance System is characterized in that various sensors (including millimeter wave radar, laser radar, single/binocular camera and satellite navigation) installed on a vehicle are utilized to sense the surrounding environment at any time in the driving process of the vehicle, collect data, identify, detect and track static and dynamic objects, and calculate and analyze the System by combining with map data of a navigator, so that drivers can perceive possible dangers in advance, and the comfort and safety of vehicle driving are effectively improved.
AEB: an automatic Braking system is an automobile active safety technology and mainly comprises 3 modules, namely a control module (ECU), a distance measuring module and a Braking module. The core of the distance measurement module comprises a microwave radar, a face recognition technology, a video system and the like, and the distance measurement module can provide safe, accurate and real-time images and road condition information of a front road.
ESP: electronic Stability Program, a vehicle body Electronic Stability system, is a generic term for a system or a Program for effectively preventing an automobile from being out of control when the automobile reaches its dynamic limit while aiming to improve the handling performance of the automobile. The electronic stabilization program can improve the safety and the controllability of the vehicle.
Head Unit: the car audio body, the stereo set host computer can regard as on-vehicle hypersystem's control module, in novel vehicle, can also integrate communication function and locate function.
Example one
Fig. 1 is a schematic flow chart of a driving assistance data acquisition method according to an embodiment of the present invention, which is applied to a vehicle. The present specification provides the method steps as described in the examples or flow diagrams, but may include more or fewer steps based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 1, the driving assistance data collection method may include:
s110: and acquiring system statistical data through an ADAS system of the vehicle, and sending the system statistical data to a multimedia system of the vehicle.
Specifically, the ADAS (Advanced Driving Assistance System) System may include, but is not limited to, a monocular vision camera, a binocular vision camera, a millimeter wave radar, a laser radar, an ultrasonic radar, and an in-vehicle sensor.
Preferably, an ethernet interface is arranged inside a camera of the ADAS system to realize in-vehicle communication with the multimedia system. Meanwhile, the camera of the ADAS system supports a detection function and a data acquisition function, and not only can acquire image data, but also can transmit data acquired by other sensors of the ADAS system.
Specifically, vehicle environment data are obtained through the millimeter wave radar, and are sent to a camera of the ADAS system, wherein the millimeter wave radar is connected with the camera through a CAN bus; the method comprises the steps of obtaining image data and/or driver behavior data through the camera, and sending the image data, the driver behavior data and the vehicle environment data to the multimedia system through an Ethernet interface of the camera.
S120: and acquiring vehicle positioning data through a positioning module of the multimedia system.
Preferably, the multimedia system may be a car audio host, including but not limited to the following modules:
the remote communication module is preferably a 4G or 5G communication module and is used for realizing remote communication with the cloud server;
the short-range communication module is preferably used for realizing in-vehicle communication and workshop communication with the ADAS and/or other sensors supporting the data acquisition function by running preset communication software;
the positioning module preferably adopts a global positioning system to realize a vehicle positioning function and obtains vehicle positioning data including vehicle longitude and latitude coordinates and time data information.
S130: and the multimedia system packages the system statistical data and the vehicle positioning data as acquisition decision data and sends the acquisition decision data to a cloud server, so that the cloud server judges whether data acquisition is needed according to the acquisition decision data.
In some possible implementations, step S210 provided in this embodiment of the present invention may further include:
acquiring vehicle driving state data including, but not limited to, vehicle speed, acceleration, and yaw angle via chassis sensors;
and after receiving the data sent by the camera and the chassis sensor, the multimedia system generates a data acquisition request signal, packs and compresses the system statistical data, the vehicle positioning data, the vehicle running state data and the data acquisition request signal, and generates acquisition decision data.
S140: after the multimedia system receives a data acquisition instruction downloaded by the cloud server, the data acquisition instruction is sent to at least one data acquisition device, and the data acquisition instruction comprises data acquisition frequency.
Specifically, the driving assistance data acquisition method provided by the embodiment of the present invention further includes:
the vehicle is the volume production vehicle, adopts crowdsourcing mode, arbitrary vehicle in the volume production vehicle communicates with high in the clouds server as data acquisition vehicle terminal to acquire the data acquisition instruction that arbitrary vehicle in the volume production vehicle corresponds.
It can be understood that the mass production vehicle is used as a vehicle terminal for data acquisition, so that more time, places, scenes and the like in the real world can be covered, and richer data can be acquired. In addition, a special data acquisition vehicle does not need to be manufactured, and a mass production vehicle does not need to be modified, so that from the perspective of a system manufacturing developer, the mass production vehicle and an ADAS system installed in the vehicle are used for data acquisition, and the hardware cost can be greatly reduced.
S150: in response to the data acquisition instruction, acquiring at least one type of target data based on the data acquisition frequency.
Preferably, the data acquisition instruction and the data acquisition frequency are obtained by analyzing and calculating the acquisition decision data by a cloud server, and are related to the road section and the scene where the vehicle is currently located. The generation of the data acquisition instruction mainly comprises the following conditions: firstly, the data sample size of the current road section or scene does not reach a preset value; secondly, the combination of the time, the place, the speed and the like of the current vehicle is a new driving scene; thirdly, detecting that the vehicle is in a dangerous condition according to the collected decision data; fourthly, detecting that the vehicle is not in a dangerous condition but the driver has emergent braking and emergent steering behaviors according to the collected decision data; fifthly, other customizable situations needing data collection.
It can be understood that the decision-making judgment of data acquisition is carried out by the cloud server, so that the high coverage of data can be ensured, a large amount of repeated data caused by directly carrying out data acquisition by a vehicle end is avoided, the data redundancy is reduced, and the utility of the data is improved.
Preferably, the data acquisition frequency is calculated and adjusted based on scene similarity and sample data similarity. It can be understood that the data acquisition drop-down can be effectively improved by flexibly adjusting the data acquisition frequency, and the invalid data amount is reduced.
S160: and packaging the at least one type of target data through the multimedia system and sending the target data to the cloud server for storage so as to develop and optimize a target ADAS.
Preferably, when the automatic braking system or the electronic body stabilizing system of the vehicle performs emergency safety operation, the vehicle actively acquires at least one type of current target data without waiting for the decision of the cloud server, and sends the at least one type of target data to the cloud server.
Example two
Fig. 2 is a schematic flow chart of a driving assistance data acquisition method according to an embodiment of the present invention, and is applied to a cloud server. The present specification provides the method steps as described in the examples or flow diagrams, but may include more or fewer steps based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 2, the driving assistance data collection method may include:
s210: and acquiring the collected decision data sent by the vehicle.
Preferably, the collected decision data includes, but is not limited to, ADAS system statistics, vehicle positioning data, and vehicle driving status data, wherein the ADAS system statistics include, but is not limited to, image data, vehicle environment data, and driver behavior data.
Preferably, the collection decision data is sent to a cloud server by a multimedia system of the vehicle.
S220: and judging whether data acquisition is needed or not based on the road section and the scene according to the acquisition decision data.
In some possible implementations, the step S220 provided by the embodiment of the present invention may include the following steps:
s221: and establishing a database with road sections and/or scenes as labels.
The method has the advantages that the sample data stored in the database is used for development and optimization of the target ADAS, the labels of road sections and scenes are added to the sample data, the cloud server can make data acquisition decisions, the coverage of the road sections of the data scenes is improved, meanwhile, the collection of a large amount of repeated data is reduced, and the data acquisition efficiency is improved.
S222: and abstracting the vehicle positioning data in the collected decision data into a target road section in a preset format.
In some possible embodiments, the collection decision Data is organized in units of road segments according to the vehicle positioning Data in the collection decision Data, and specifically, the road in the vehicle positioning Data is abstracted into elements such as simple points and lines according to a map format of a Geographic Data File (GDF), and a line segment between two points is a road segment.
S223: and retrieving the sample data of the target road section in the database, and acquiring the number of the sample data.
In some feasible embodiments, the collection decision data is organized in units of road segments, sample data in the database also has road segment labels, the database is indexed according to elements of the road segments, sample data in the database, which belongs to the same road segment as the collection decision data, is obtained, and the number of the sample data is calculated, so as to determine whether data collection is needed and calculate the data collection frequency. To briefly explain fig. 3 as an example, the elements a and B are located in the same link, and neither element point a nor element point C, D, E belong to the same link.
It is understood that the purpose of the road segment indexing is to find sample data having a certain similarity with the collected decision data, which is a preferred screening manner, in some other possible embodiments, other screening conditions such as weather elements, driver behavior elements, and the like, or different screening conditions in combination may be set to screen out sample data having a certain similarity with the collected decision data in advance, which is not limited in this embodiment of the present invention
S224: and when the sample quantity of the sample data does not reach a preset threshold value, judging that data acquisition is required and generating a data acquisition instruction.
In some other possible embodiments, the generation of the data acquisition instruction is not limited to that the number of samples of the sample data does not reach the preset threshold, and may further include the following cases: firstly, the combination of the time, the place, the speed and the like of the current vehicle is a new driving scene; secondly, detecting that the vehicle is in a dangerous condition according to the collected decision data; thirdly, detecting that the vehicle is not in a dangerous condition but the driver has emergent braking and emergent steering behaviors according to the collected decision data; and fourthly, other customizable situations needing to collect data are realized, and the invention is not particularly limited in this respect.
S230: when data acquisition is needed, a data acquisition instruction is generated, and the data acquisition instruction comprises data acquisition frequency.
It can be understood that the data acquisition command and the data acquisition frequency thereof can be obtained according to a sample screening condition and a calculation formula set by a user, and are not limited to the determination method and the calculation method provided below in the embodiment of the present invention.
Preferably, step S230 provided in the embodiment of the present invention may include the following steps:
s231: and acquiring the current time and the vehicle speed of the vehicle according to the acquired decision data, and calculating the average traffic flow and the collision time of the front vehicle.
It is understood that the average traffic flow indicates the average number of front targets in a past period, and the front vehicle collision time is calculated by monitoring front vehicles at any time by a front collision early warning system through a radar, and determining the distance, direction and relative speed between the front vehicles and the front vehicles.
S232: and performing information processing on the current time, the vehicle speed, the average traffic flow and the front vehicle collision time to obtain a target code.
Preferably, the information processing may adopt a processing mode as shown in table 1:
TABLE 1 data processing Table
S233: and screening the sample code of at least one sample data of which the Euclidean distance is smaller than a preset threshold value in the sample data of the target road section from the database.
Preferably, firstly, a threshold value of the Euclidean distance is determined, secondly, sample data is screened out according to the threshold value, and sample codes of the sample data are obtained according to the same data processing method.
S234: and judging scene similarity based on the target code and the sample code of the at least one sample data.
Preferably, calculating the average euclidean distance with the target code according to the sample codes of the sample data can be used for judging the similarity of the scene.
S235: and calculating the data acquisition frequency according to the sample number of the sample data and/or the scene similarity.
Preferably, the data acquisition frequency is determined according to parameters such as the number of samples of the sample data, the average euclidean distance, and the threshold of the euclidean distance according to a preset function formula.
S240: sending the data acquisition instructions to a multimedia system of the vehicle to cause the multimedia system to communicate the data acquisition instructions to at least one data acquisition device of the vehicle.
In some possible embodiments, the determining whether the data acquisition instruction needs to be generated may further include:
analyzing the collection decision data, and generating a data collection instruction when finding that an ADAS system of the vehicle detects a dangerous condition;
and/or generating a data acquisition instruction when detecting that the behavior of the driver is abnormal according to the behavior data of the driver in the acquired decision data.
S250: receiving at least one type of target data collected by the vehicle in response to the collection instruction.
S260: and storing the at least one type of target data to perform development optimization of the target ADAS system.
Preferably, the at least one type of object data is stored according to the labels of the road sections and/or scenes, and the database is updated for later judgment and calculation.
EXAMPLE III
Fig. 4(1) - (2) are exemplary diagrams of another driving assistance data collection method according to an embodiment of the present invention, which relates to a vehicle and a cloud server, where fig. 4(2) is a simplified method. The present specification provides the method steps as described in the examples or flow diagrams, but may include more or fewer steps based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 4(1), the driving assistance data collection method may include:
s310: the camera of the vehicle ADAS system collects data such as images, vehicle signals and millimeter wave radars and sends the data to a Head Unit of a host of the multimedia system.
S320: and the Head Unit sends the time, the position, the vehicle information, the ADAS statistical data and the acquisition request signal to a cloud server through network communication.
S330: and the cloud server performs decision judgment, positions the position information to the road section, and adjusts the sample acquisition interval according to the number of existing samples and scene similarity of the same road section.
Preferably, as shown in fig. 4(2), the following function is designed to calculate the sample collection interval:
f(d)＝(d0d) a/m, wherein D, D0And a is a preset adjustable parameter, and m is the number of collected samples of the same road section with the Euclidean distance to the target code smaller than D.
It can be understood that, when the vehicle appears on a new road segment for the first time, the data sample size of the road segment in the database is 0, and the sample data of the new road segment at this time is collected, that is, a data record is added to the database. And at the next time point, when the vehicle arrives at the road section, retrieving all data samples of the road section in the database, comparing the Euclidean distance with the target code of the vehicle at the current time point, and if the Euclidean distance is smaller than D, acquiring the current data. After a period of time, the data samples of the road section in the database are more and more, that is, the larger m is, the smaller the value of f (d) is, the smaller the number of samples that need to be collected on the road section is, and the purpose of automatic adjustment is achieved.
S340: and sending the acquisition interval of the data to the Head Unit.
S350: and the HeadUnit sends the acquisition interval to an ADAS system.
S360: and when the timer of the ADAS system finishes timing or triggers such as burst AEB, ESP and the like, acquiring data, and packaging the acquired data and sending the packaged data to the Head Unit.
S370: the Head Unit packages the acquired data and data such as vehicle body signals, time, positions and the like, sends the data to the cloud server, and the cloud server stores the data after receiving the data and updates the database.
An embodiment of the present invention further provides a driving assistance data acquisition system, as shown in fig. 5, the system includes:
the cloud server 510 is provided with a database for storing and retrieving sample data and a decision module for determining whether data acquisition is required and calculating data acquisition frequency.
A vehicle comprising an ADAS system 530, a multimedia system 540, and a sensor 550, wherein:
the ADAS system 530 is provided with a camera 531 and a radar 532 for collecting statistical data of the ADAS system.
It can be understood that the ADAS system is a driving assistance system installed on a mass-production vehicle and put into use, and the acquisition of more scene data can be realized without modifying the vehicle or adding software and hardware devices, thereby reducing the cost and improving the richness of the data.
Preferably, the ADAS system may further include other types of sensors or positioning modules, the ADAS system implements communication with the multimedia system through a network interface of the camera 531, and the camera 531 and the radar 532 are connected through a CAN bus.
The multimedia system 540 is provided with a communication module 541 and a positioning module 542, and is configured to collect vehicle positioning data and implement communication between the vehicle and the cloud server.
Specifically, the multimedia system may be a Head Unit of a car audio host.
Preferably, the communication module 541 may be divided into a long-range communication module and a short-range communication module, where the long-range communication module is preferably a 4G or 5G communication module, and implements long-range communication with the cloud server 510; the short-range communication module preferably runs preset communication software to realize in-vehicle communication with a vehicle-mounted ADAS system and other sensors supporting the data acquisition function; the communication module 541 also enables inter-vehicle communication with other vehicles around the vehicle to obtain more types of data.
The sensor 550 is configured to collect vehicle driving state data of the vehicle.
Preferably, the sensors 550 are chassis sensors, by which vehicle driving state data including, but not limited to, vehicle speed, acceleration, and yaw angle are acquired.
The driving assistance data acquisition system and the driving assistance data acquisition method according to the embodiments of the present invention are based on the same inventive concept, and please refer to the method embodiments for details, which are not described herein again.
An embodiment of the present invention further provides a computer device, where the computer device includes: the driving assistance data acquisition system comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded by the processor and executed to realize the driving assistance data acquisition method according to the embodiment of the invention.
The memory may be used to store software programs and modules, and the processor may execute various functional applications by executing the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.
The method embodiments provided by the embodiments of the present invention may be executed in a computer terminal, a server, or a similar computing device, that is, the computer device may include a computer terminal, a server, or a similar computing device. The internal structure of the computer device may include, but is not limited to: a processor, a network interface, and a memory. The processor, the network interface and the memory in the computer device may be connected by a bus or other means. The processor (or CPU) is a computing core and a control core of the computer device. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI, mobile communication interface, etc.). Memory (Memory) is a Memory device in a computer device used to store programs and data. It is understood that the memory herein may be a high-speed RAM storage device, or may be a non-volatile storage device (non-volatile memory), such as at least one magnetic disk storage device; optionally, at least one memory device located remotely from the processor. The memory provides storage space that stores an operating system of the electronic device, which may include, but is not limited to: a Windows system (an operating system), a Linux system (an operating system), an Android system, an IOS system, etc., which are not limited in the present invention; also, one or more instructions, which may be one or more computer programs (including program code), are stored in the memory space and are adapted to be loaded and executed by the processor. In an embodiment of this specification, the processor loads and executes one or more instructions stored in the memory to implement the driving assistance data collection method provided in the above-described method embodiment.
The embodiment of the present invention further provides a computer storage medium, where at least one instruction or at least one program is stored in the computer storage medium, and the at least one instruction or the at least one program is loaded by the processor and executes the driving assistance data acquisition method according to the embodiment of the present invention.
Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus, system and server embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A driving assistance data collection method applied to a vehicle, characterized by comprising:
acquiring system statistical data through an ADAS system of a vehicle, and sending the system statistical data to a multimedia system of the vehicle;
acquiring vehicle positioning data through a positioning module of the multimedia system;
the multimedia system packages the system statistical data and the vehicle positioning data as acquisition decision data and sends the acquisition decision data to a cloud server, so that the cloud server determines sample data of a target road section corresponding to the vehicle positioning data in a database and judges whether data acquisition is needed or not according to the number of the sample data;
after the multimedia system receives a data acquisition instruction transmitted by the cloud server, the data acquisition instruction is sent to at least one data acquisition device, and the data acquisition instruction comprises data acquisition frequency; the determination of the data acquisition frequency comprises: acquiring the current time and the vehicle speed of the vehicle according to the acquired decision data, and calculating the average traffic flow and the collision time of the front vehicle; processing the current time, the vehicle speed, the average traffic flow and the front vehicle collision time to obtain a target code; determining a sample code of at least one sample data of which the Euclidean distance is smaller than a preset threshold value in the sample data of the target road section; judging scene similarity based on the target code and the sample code of the at least one sample data; calculating according to the scene similarity to obtain the data acquisition frequency;
acquiring at least one type of target data based on the data acquisition frequency in response to the data acquisition instruction;
and packaging the at least one type of target data through the multimedia system and sending the target data to the cloud server for storage so as to develop and optimize a target ADAS.
2. The driving assistance data collection method according to claim 1, wherein the at least one data collection device includes a camera, a millimeter wave radar, and a sensor, the camera internally supports a data collection function and a communication function, the obtaining of the system statistical data by the ADAS system and the sending of the system statistical data to the multimedia system includes:
acquiring vehicle environment data through the millimeter wave radar, and sending the vehicle environment data to the camera through a CAN bus;
the method comprises the steps of obtaining image data and driver behavior data through the camera, and sending the image data, the driver behavior data and the vehicle environment data to the multimedia system through the camera.
3. The method as claimed in claim 2, wherein the step of the multimedia system packaging the system statistics and the vehicle positioning data as the collection decision data to send to a cloud server further comprises:
acquiring vehicle running state data through a chassis sensor, sending the vehicle running state data to the multimedia system, and adding the vehicle running state data to the collected decision data;
and generating a data acquisition request signal, and adding the data acquisition request signal to the acquisition decision data.
4. The driving assistance data collection method according to claim 1, wherein the vehicle is a mass production vehicle, the method further comprising:
adopt crowdsourcing mode, arbitrary vehicle in the volume production vehicle communicates with high in the clouds server as data acquisition vehicle terminal to obtain the data acquisition instruction that arbitrary vehicle in the volume production vehicle corresponds.
5. The driving assistance data collection method according to claim 1, characterized by further comprising:
when the automatic braking system or the electronic body stabilizing system of the vehicle performs emergency safety operation, the vehicle actively acquires at least one type of current target data and sends the at least one type of target data to the cloud server.
6. A driving assistance data acquisition method is applied to a cloud server, and is characterized by comprising the following steps:
acquiring acquisition decision data sent by a vehicle;
determining sample data of a target road section corresponding to the vehicle positioning data in a database according to the vehicle positioning data in the acquisition decision data, and judging whether data acquisition is needed or not according to the number of the sample data;
when data acquisition is needed, generating a data acquisition instruction, wherein the data acquisition instruction comprises data acquisition frequency; the determination of the data acquisition frequency comprises: acquiring the current time and the vehicle speed of the vehicle according to the acquired decision data, and calculating the average traffic flow and the collision time of the front vehicle; processing the current time, the vehicle speed, the average traffic flow and the front vehicle collision time to obtain a target code; determining a sample code of at least one sample data of which the Euclidean distance is smaller than a preset threshold value in the sample data of the target road section; judging scene similarity based on the target code and the sample code of the at least one sample data; calculating according to the scene similarity to obtain the data acquisition frequency;
sending the data acquisition instructions to a multimedia system of the vehicle to cause the multimedia system to communicate the data acquisition instructions to at least one data acquisition device of the vehicle;
receiving at least one type of target data acquired by the vehicle in response to the acquisition instruction;
and storing the at least one type of target data to perform development optimization of the target ADAS system.
7. The method according to claim 6, wherein the decision data includes ADAS system statistical data, vehicle positioning data, and vehicle driving status data, and the determining, according to the vehicle positioning data in the decision data, sample data of a target road segment corresponding to the vehicle positioning data in a database, and determining, according to the number of the sample data, whether data collection is required comprises:
establishing a database with road sections and/or scenes as labels;
abstracting the vehicle positioning data in the collected decision data into a target road section in a preset format;
retrieving sample data of the target road section in the database, and acquiring the number of the sample data;
and when the sample quantity of the sample data does not reach a preset threshold value, judging that data acquisition is required and generating a data acquisition instruction.
8. The driving assistance data collection method according to claim 7, wherein the determining whether data collection is required further comprises:
analyzing the collection decision data, and generating a data collection instruction when finding that an ADAS system of the vehicle detects a dangerous condition;
and/or generating a data acquisition instruction when detecting that the behavior of the driver is abnormal according to the behavior data of the driver in the acquired decision data.
9. A driving assistance data collection system, characterized in that the system comprises:
a cloud server for executing a driving assistance data collection method according to any one of claims 6 to 8;
vehicle comprising an ADAS system, a multimedia system and sensors for carrying out a driving assistance data collection method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010573971.0A CN111845728B (en) | 2020-06-22 | 2020-06-22 | Driving assistance data acquisition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010573971.0A CN111845728B (en) | 2020-06-22 | 2020-06-22 | Driving assistance data acquisition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111845728A CN111845728A (en) | 2020-10-30 |
| CN111845728B true CN111845728B (en) | 2021-09-21 |
Family
ID=72987124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010573971.0A Active CN111845728B (en) | 2020-06-22 | 2020-06-22 | Driving assistance data acquisition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111845728B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113611007B (en) * | 2021-08-05 | 2023-04-18 | 北京百姓车服网络科技有限公司 | Data processing method and data acquisition system |
| CN113743356A (en) * | 2021-09-15 | 2021-12-03 | 东软睿驰汽车技术（沈阳）有限公司 | Data acquisition method and device and electronic equipment |
| CN113612673A (en) * | 2021-09-30 | 2021-11-05 | 北汽福田汽车股份有限公司 | Automatic emergency braking data acquisition method and system and vehicle |
| CN114363475A (en) * | 2021-12-17 | 2022-04-15 | 福瑞泰克智能系统有限公司 | Video processing device and equipment, and video simulation system |
| CN115457677B (en) * | 2022-07-22 | 2024-05-14 | 江铃汽车股份有限公司 | Vehicle data acquisition method and system |
| CN116056002B (en) * | 2022-08-17 | 2023-09-22 | 荣耀终端有限公司 | Data acquisition method and electronic equipment |
| CN115604541B (en) * | 2022-09-21 | 2023-04-25 | 昆易电子科技(上海)有限公司 | Data acquisition processing method and system for vehicle, electronic equipment and storage medium |
| CN118560510A (en) * | 2023-02-28 | 2024-08-30 | 华为技术有限公司 | Data monitoring method and device |
| CN116129653B (en) * | 2023-04-17 | 2023-07-07 | 创意信息技术股份有限公司 | Bayonet vehicle detection method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1197822A2 (en) * | 2000-10-13 | 2002-04-17 | Hitachi, Ltd. | On-vehicle breakdown-warning report system |
| CN109857002A (en) * | 2019-01-15 | 2019-06-07 | 北京百度网讯科技有限公司 | Collecting method, device, equipment and computer readable storage medium |
| CN110264586A (en) * | 2019-05-28 | 2019-09-20 | 浙江零跑科技有限公司 | L3 grades of automated driving system driving path data acquisitions, analysis and method for uploading |
| CN110287276A (en) * | 2019-05-27 | 2019-09-27 | 百度在线网络技术（北京）有限公司 | High-precision map updating method, device and storage medium |
-
2020
- 2020-06-22 CN CN202010573971.0A patent/CN111845728B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1197822A2 (en) * | 2000-10-13 | 2002-04-17 | Hitachi, Ltd. | On-vehicle breakdown-warning report system |
| CN109857002A (en) * | 2019-01-15 | 2019-06-07 | 北京百度网讯科技有限公司 | Collecting method, device, equipment and computer readable storage medium |
| CN110287276A (en) * | 2019-05-27 | 2019-09-27 | 百度在线网络技术（北京）有限公司 | High-precision map updating method, device and storage medium |
| CN110264586A (en) * | 2019-05-28 | 2019-09-20 | 浙江零跑科技有限公司 | L3 grades of automated driving system driving path data acquisitions, analysis and method for uploading |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111845728A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111845728B (en) | Driving assistance data acquisition method and system | |
| CN109421738B (en) | Method and apparatus for monitoring autonomous vehicles | |
| CN110809790B (en) | Vehicle information storage method, vehicle travel control method, and vehicle information storage device | |
| CN106781485B (en) | Road congestion identification method, V2X vehicle-mounted terminal and Internet of vehicles system | |
| CN111324120A (en) | Cut-in and cut-out scene extraction method for automatic driving front vehicle | |
| US10916124B2 (en) | Method, device and system for wrong-way driver detection | |
| CN110371018B (en) | Improving vehicle behavior using information from other vehicle lights | |
| CN111547055B (en) | Method and device for controlling distance between vehicles, electronic equipment and storage medium | |
| US10629073B2 (en) | Method, device and system for wrong-way driver detection | |
| US20200133303A1 (en) | Map information system | |
| US20200234578A1 (en) | Prioritized vehicle messaging | |
| US10841761B2 (en) | Adaptive vehicle-to-infrastructure communications | |
| CN105564429A (en) | Running safety pre-warning method and device | |
| CN112287801A (en) | Vehicle-mounted data processing method and device, server and readable storage medium | |
| CN114419573A (en) | Dynamic occupancy grid estimation method and device | |
| CN111612938A (en) | Event recording equipment control method, device, equipment and storage medium | |
| US10769942B2 (en) | Method, device and system for wrong-way driver detection | |
| US10532750B2 (en) | Method, device and system for wrong-way driver detection | |
| CN115782911B (en) | Data processing method and related device for steering wheel hand-off event in driving scene | |
| CN116443046A (en) | Assistance system with a leader determination module for an automatic vehicle in a merge trajectory | |
| US10876843B2 (en) | Method, device and system for wrong-way driver detection | |
| US20210103050A1 (en) | Radar calibration system | |
| CN111731285A (en) | Vehicle anti-collision method and device based on V2X technology | |
| CN113256845B (en) | Data acquisition method, device, storage medium and system | |
| CN115641569B (en) | Driving scene processing method, device, equipment and medium |
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 |