CN113190015A - Terrain recognition method and device, computer equipment and storage medium - Google Patents
Terrain recognition method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113190015A CN113190015A CN202110551249.1A CN202110551249A CN113190015A CN 113190015 A CN113190015 A CN 113190015A CN 202110551249 A CN202110551249 A CN 202110551249A CN 113190015 A CN113190015 A CN 113190015A
- Authority
- CN
- China
- Prior art keywords
- terrain
- identification
- target road
- vehicle
- road section
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 5
- 238000012876 topography Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
Abstract
The invention discloses a terrain recognition method, a terrain recognition device, computer equipment and a storage medium. The method comprises the following steps: acquiring identification reported data obtained by a first vehicle carrying out terrain identification on a target road section; determining a terrain recognition result of the target road section according to the recognition report data; and if the position information of the second vehicle is detected to meet the terrain recognition sharing triggering condition, sending the terrain recognition result to the second vehicle. By using the technical scheme of the invention, the accuracy of terrain identification can be improved, and the timeliness of vehicle terrain identification is ensured.
Description
Technical Field
The embodiment of the invention relates to automatic driving and vehicle control technologies, in particular to a terrain recognition method, a terrain recognition device, computer equipment and a storage medium.
Background
With the development of intelligent automobile technology and electronic control technology, vehicles which are only suitable for driving characteristics of a single road condition cannot meet the requirements of people. In order to enable the vehicle various system performances to be more comprehensively adapted to various complex terrains, terrain identification should be performed firstly in response to the change of terrain characteristics.
In the prior art, terrain recognition is performed, and a vehicle is taken as an independent individual to recognize the current terrain. In the terrain recognition mode based on a single vehicle, the accuracy of the terrain recognition result is not high due to the fact that the external information received by the vehicle is limited. Meanwhile, certain terrains (such as snowfields) can be identified only when the vehicle enters the road section, so that the single-vehicle terrain identification has delay and the improvement of the response performance of the vehicle to the terrain characteristic change is influenced.
Disclosure of Invention
The embodiment of the invention provides a terrain identification method, a terrain identification device, computer equipment and a storage medium, which are used for improving the accuracy of terrain identification and ensuring the timeliness of vehicle terrain identification.
In a first aspect, an embodiment of the present invention provides a terrain identification method, where the method includes:
acquiring identification reported data obtained by a first vehicle carrying out terrain identification on a target road section;
determining a terrain recognition result of the target road section according to the recognition report data;
and if the position information of the second vehicle is detected to meet the terrain recognition sharing triggering condition, sending the terrain recognition result to the second vehicle.
In a second aspect, an embodiment of the present invention further provides a terrain recognition apparatus, including:
the identification reported data acquisition module is used for acquiring identification reported data obtained by the first vehicle carrying out terrain identification on the target road section;
the terrain recognition result determining module is used for determining the terrain recognition result of the target road section according to the recognition report data;
and the terrain recognition result sharing module is used for sending the terrain recognition result to the second vehicle if the position information of the second vehicle is detected to meet the terrain recognition sharing triggering condition.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the terrain identification method according to any one of the embodiments of the present invention.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions for performing a terrain identification method as described in any of the embodiments of the present invention when executed by a computer processor.
According to the embodiment of the invention, the terrain recognition result of the target road section is determined through the recognition report data obtained by the first vehicle carrying out the terrain recognition on the target road section, and the terrain recognition result of the target road section is sent to the second vehicle when the position information of the second vehicle meets the terrain recognition sharing triggering condition. The problem of among the prior art because the terrain recognition mode accuracy rate of single vehicle is low to terrain recognition has the delay nature, thereby is unfavorable for the vehicle to make timely response to the topography feature change is solved, has realized improving the accuracy of terrain recognition, has guaranteed the promptness of vehicle terrain recognition.
Drawings
FIG. 1 is a flow chart of a terrain recognition method in one embodiment of the present invention;
FIG. 2a is a flow chart of a terrain recognition method according to a second embodiment of the present invention;
FIG. 2b is a schematic diagram of a terrain recognition system according to a first embodiment of the present invention;
fig. 3 is a schematic structural diagram of a terrain recognition apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device in the fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a terrain recognition method according to an embodiment of the present invention, where the present embodiment is applicable to a situation where a terrain recognition result is presented for a vehicle traveling to a target road segment, and the method may be executed by a terrain recognition device, which may be implemented by software and/or hardware and is generally integrated in a cloud server.
As shown in fig. 1, the technical solution of the embodiment of the present invention specifically includes the following steps:
and S110, acquiring identification reported data obtained by the first vehicle carrying out terrain identification on the target road section.
The first vehicle is a vehicle which is driven or is about to be driven to a target road section, the first vehicle needs to be provided with a terrain identification system to carry out terrain identification on the target road section, and needs to be provided with a transmission system to transmit identification reported data to the cloud server. The identification reported data is an identification result obtained by the first vehicle performing terrain identification on the target road section, and may include a terrain tag and a tag probability, where the terrain tag is used to represent the terrain of the target road section, and the tag probability is used to represent that the actual terrain of the target road section is the actual probability of the terrain represented by the terrain tag. The terrain may be a road, snow, sand, gravel, etc., and the present embodiment does not limit this.
When the first vehicle performs terrain recognition on the target road section through the terrain recognition system, optionally, a vehicle driving information recognition mode can be adopted for terrain recognition, the terrain recognition system of the first vehicle acquires driving information such as speed and acceleration of the first vehicle, extracts movement characteristics of the driving information, and acquires road surface characteristics corresponding to the extracted movement characteristics according to the relation between the preset movement characteristics and the road surface characteristics, so that the terrain of the target road section is determined. Optionally, a camera sensing recognition mode may also be adopted, an image of a target road section in front of the vehicle is acquired through a vehicle-mounted camera, the image is subjected to pixel and/or region segmentation, and road surface feature matching is performed on the segmented image, so that the terrain of the target road section is determined. Optionally, an ultrasonic radar recognition mode can be adopted, the road sound waves reflected by the vehicle-mounted ultrasonic radar are processed, the road surface features of the road sound waves are matched, and the terrain of the target road section is determined. Optionally, the point cloud data of the target road section can be acquired through the vehicle-mounted laser radar in a laser radar identification mode, point cluster classification is performed, road surface feature vector analysis is performed on the classified point cloud data, and the terrain of the target road section is identified. The embodiment does not limit the method and the specific principle of the terrain recognition of the target road section by the vehicle.
The identification reported data may be obtained by performing terrain identification on the target road section before the first vehicle travels to the target road section, and for example, the identification reported data may be obtained by using a camera sensing identification mode, an ultrasonic radar identification mode and a laser radar identification mode before the first vehicle travels to the target road section. The identification report data may be obtained by performing terrain identification on the target road segment after the first vehicle has traveled the target road segment, and for example, the identification report data may be obtained only after the first vehicle has traveled the target road segment in a vehicle travel information identification manner.
And S120, determining a terrain recognition result of the target road section according to the recognition reported data.
And after the cloud server obtains the identification reported data reported by the first vehicle, determining a terrain identification result of the target road section. After the first vehicle reports the identification reported data to the cloud server, the cloud server determines a terrain identification result of the target terrain according to the identification reported data. The advantage that sets up like this lies in, on the one hand each vehicle all reports the discernment data of reporting to the high in the clouds server, confirms the topography identification result of target highway section by the high in the clouds server, compares in the topography identification result that each vehicle confirmed alone, and the accuracy is higher. On the other hand, the cloud server can send the terrain recognition result of the target terrain to other vehicles about to travel to the target road section, so that the other vehicles can know the terrain of the target road section in advance, and the timeliness of the vehicle system for responding to the terrain is improved.
And S130, if the position information of the second vehicle is detected to meet the terrain recognition sharing triggering condition, sending the terrain recognition result to the second vehicle.
The second vehicle is a vehicle about to travel to the target road section, and when the terrain recognition sharing triggering condition is met, the terrain recognition result determined by the cloud server needs to be sent to the second vehicle. The terrain recognition sharing triggering condition is met, the second vehicle can be about to travel to the target road section, the second vehicle can also send a terrain query request of the target road section to the cloud server, and the embodiment does not limit the terrain query request.
In the embodiment of the invention, the cloud server sends the terrain recognition result to the second vehicle about to travel to the target road section, so that the second vehicle can predict the terrain of the target road section in advance, and other related systems of the second vehicle, such as an engine, a transmission or a suspension, are adjusted in advance, so that the second vehicle can effectively and quickly react to the terrain change.
According to the technical scheme, the terrain recognition result of the target road section is determined through recognition report data obtained by the first vehicle performing terrain recognition on the target road section, and the terrain recognition result of the target road section is sent to the second vehicle when the position information of the second vehicle meets the terrain recognition sharing triggering condition. The problem of among the prior art because the terrain recognition mode accuracy rate of single vehicle is low to terrain recognition has the delay nature, thereby is unfavorable for the vehicle to make timely response to the topography feature change is solved, has realized improving the accuracy of terrain recognition, has guaranteed the promptness of vehicle terrain recognition.
Example two
Fig. 2a is a flowchart of a terrain recognition method according to a second embodiment of the present invention, where the second embodiment of the present invention further embodies a process of determining a terrain recognition result of a target road segment according to recognition report data and a process of determining whether location information of a second vehicle meets a terrain recognition sharing trigger condition, and adds a step of updating the terrain recognition result of the target road segment according to the recognition report data of the second vehicle.
Correspondingly, as shown in fig. 2a, the technical solution of the embodiment of the present invention specifically includes the following steps:
s210, acquiring identification reported data obtained by the first vehicle carrying out terrain identification on the target road section.
In the embodiment of the present invention, the identification report data may further include a location of the target road segment, in addition to the terrain tag and the tag probability obtained by the first vehicle performing terrain identification on the target road segment.
S220, acquiring the position of the target road section, and acquiring the weather information and the traffic information of the target road section according to the position of the target road section.
The position of the target link may be represented by position information of a start point, an end point, or a middle point of the target link, which is not limited in this embodiment. Optionally, the first vehicle may obtain the location of the target road segment through a Global Positioning System (GPS).
The weather information may include information such as weather, temperature, or air humidity at the location of the target road segment, and the weather information may be obtained by the cloud server according to the weather information system. Specifically, after the cloud server determines the position of the target road section, a weather information query request is constructed according to the position of the target road section and sent to a weather information system, and weather information fed back by the weather information system is received.
The traffic information may include information of a location of the target link, the number of passing vehicles per unit time, an average speed, a maximum speed, etc. of passing vehicles per unit time. The cloud server can acquire traffic information through a traffic information system. Specifically, after the cloud server determines the position of the target road section, a traffic information query request is constructed according to the position of the target road section and sent to the traffic information system, the number of passing vehicles in unit time and the speed of each vehicle fed back by the traffic information system are received, the average speed of each vehicle is calculated, and the maximum speed of each vehicle is determined.
In the embodiment of the invention, the meteorological information and the traffic information of the target road section are determined according to the position of the target road section, and the rationality judgment can be further carried out on the identification reported data reported by the first vehicle through the meteorological information and the traffic information, so that the terrain identification result determined by the cloud server is more accurate.
And S230, judging the rationality of the identification reported data according to the meteorological information and the traffic information of the target road section.
In this embodiment, the weather information and the traffic information of the target road segment are taken as an example, the rationality of the identification reported data reported by the first vehicle is determined, and only the weather information or only the traffic information may be used, which is not limited in this embodiment.
Accordingly, S230 further includes:
and S231, judging whether the meteorological information is matched with the identification reported data, if so, executing S232, and otherwise, executing S234.
For example, when the terrain is snowy, the weather in the weather information is snowy and cloudy, and the temperature is below 10 ℃, the weather information and the identification reported data can be considered to be matched. When the terrain is snowy, the weather in the weather information is sunny, and the temperature is above 25 ℃, the weather information and the identification reported data can be considered to be not matched.
Specifically, the weather information and the terrain label in the identification report data can be input into the weather information matching model, and the matching result output by the weather information matching model is obtained. The meteorological information matching model can be obtained by training a preset machine learning model according to historical meteorological information and historical terrain labels after a plurality of labeled matching results. And weather information corresponding to different terrains can be preset, and if the weather information of the currently acquired target road section is matched with the weather information preset by the current terrain label, the weather information is matched with the identification reported data. The embodiment does not limit the specific implementation manner of determining whether the weather information is matched with the identification reported data.
Optionally, if the weather information matches the identification reported data, the matching degree between the weather information and the identification reported data may be further calculated, so as to determine the terrain identification result of the target road segment according to the matching degree in the following.
In the embodiment of the invention, the terrain label obtained by the terrain recognition of the target road section by the single vehicle has inaccurate condition, so the recognition report data needs to be reported to the cloud server, the cloud server can judge the rationality of the recognition report data through meteorological information, and the accuracy of the terrain recognition result of the target road section can be improved especially for the terrains which are greatly related to meteorological factors, such as snowfields, mud fields and the like.
And S232, judging whether the traffic information is matched with the identification reported data, if so, executing S233, otherwise, executing S234.
For example, when the terrain label of the target road segment is a terrain affecting the running speed of the vehicle, such as snow, mud, gravel and the like, if the average speed and the maximum speed of the vehicle passing through the traffic information in unit time are respectively less than or equal to the preset average speed threshold and the preset maximum speed threshold, the traffic information can be considered to be matched with the identification report data. Wherein the same or different average and maximum speed thresholds may be set for different terrain. When the terrain label of the target road section is a terrain such as a road and the like where vehicles can normally run, if the average speed and the maximum speed of the passing vehicles in unit time in the traffic information are respectively greater than or equal to the preset average speed value and the preset maximum speed value, the traffic information can be considered to be matched with the identification reported data.
Optionally, if the traffic information is matched with the identification reported data, the matching degree of the traffic information and the identification reported data may be further calculated, so as to determine the terrain identification result of the target road segment according to the matching degree in the following.
And S233, determining that the reported data is reasonable to identify.
And when the weather information and the traffic information are matched with the identification reported data, the identification reported data is determined to be reasonable. Otherwise, if one of the weather information and the traffic information is unreasonable, the reported data is considered to be unreasonable to identify.
And S234, determining that the reported data is unreasonable to identify.
And S240, determining a terrain recognition result of the target road section according to the rationality judgment result.
Accordingly, S240 may further include:
and S241, determining whether a historical terrain recognition result matched with the target road section exists, if so, executing S242, otherwise, executing S243.
The historical terrain recognition result refers to a terrain recognition result which is stored in the cloud server and is confirmed in advance for the target road section. The historical terrain recognition result matched with the target road section exists, which indicates that historical recognition report data of the target road section is uploaded by other vehicles in advance, the historical recognition report data is reasonable, and the cloud server determines the historical terrain recognition result according to the historical recognition report data.
When the historical terrain recognition result exists, on one hand, before the first vehicle drives to the target road section, the cloud server sends the historical terrain recognition result to the first vehicle so that a relevant system of the first vehicle can respond to the historical terrain recognition result. On the other hand, if the identification reported data reported by the first vehicle is reasonable, the historical terrain identification result is updated according to the identification reported data reported by the first vehicle, so that the accuracy and instantaneity of the terrain identification of the target road section are improved.
And S242, updating the historical terrain recognition result according to the rationality judgment result.
And if the historical terrain recognition result exists, updating the historical terrain recognition result according to the rationality judgment result to obtain the terrain recognition result of the target road section.
Accordingly, S242 may further include:
and S2420, judging whether the terrain label is the same as the historical terrain label, if so, executing S2421, otherwise, executing S2422.
And if the terrain label is the same as the historical terrain label, namely the terrain obtained by the first vehicle through recognizing the target road section is the same as the terrain of the target road section stored by the cloud server, updating the historical label probability.
S2421, determining target label probability according to the rationality judgment result, the label probability and the historical label probability, and updating the historical terrain identification result according to the terrain label and the target label probability.
Optionally, if the rationality determination result is unreasonable, the historical tag probability may be reduced, and the value obtained by reducing the historical tag probability is used as the target tag probability. It may be stipulated in advance that the historical tag probability is reduced by a preset value when the rationality determination result is unreasonable. The value of the reduction of the historical tag probability can also be determined according to the rationality judgment result and the tag probability, and the embodiment does not limit the way of determining the value of the reduction of the historical tag probability. The reason for this is that there is variability in the terrain, and when the terrain label is the same as the historical terrain label but the terrain label is not reasonable, the terrain may have changed, and at this time, the historical label probability is reduced, and the influence of the terrain change on the target road section terrain recognition result can be considered in time.
Optionally, if the rationality judgment result is unreasonable, the identification report data can be directly discarded, the historical tag probability is kept unchanged, and the historical tag probability is used as the target tag probability. The reason for the arrangement is that the accuracy and stability of terrain recognition of the single vehicle are low, and the recognition reported data of the single vehicle is not reasonable, so that the single vehicle can be directly discarded, and the influence of the recognition error of the single vehicle on the terrain recognition result of the target road section can be reduced. The embodiment does not limit the processing mode of the target label probability when the reported data is unreasonable to identify.
And if the rationality judgment result is reasonable, increasing the historical label probability according to the matching degree and the label probability of the identified reported data, and taking the value of the increased historical label probability as the target label probability. Specifically, the historical tag probability may be directly increased by a preset specified value, or the increased value of the historical tag probability may be determined according to the matching degree and the tag probability of the identified reported data. For example, if the matching degree of the identification report data with the weather information and the traffic information is high, and the tag probability is also high, the historical tag probability may be raised by a high value.
And updating the historical label probability, and after the target label probability is obtained, the terrain label and the target label probability are the terrain recognition result of the target road section.
And S2422, updating the tag probability according to the rationality judgment result, and updating the historical terrain identification result according to the terrain tag and the updated tag probability.
When the terrain label obtained by the first vehicle identification is different from the historical terrain label, the terrain is changed, and the terrain identification result can be determined according to the terrain label and the updated label probability only by updating the label probability obtained by the first vehicle identification according to the rationality judgment result.
The label probability is updated according to the reasonableness judgment result, illustratively, when the reasonableness judgment result is reasonable, the label probability can be increased, the degree of increasing the label probability can be determined according to the matching degree, and the label probability can be increased by a preset probability value according to the stipulation. When the result of the rationality determination is not reasonable, the tag probability may be reduced, and it may be prescribed in advance that the tag probability is reduced by a preset probability value. The embodiment does not limit the specific manner of updating the tag probability according to the rationality determination result.
And S243, updating the label probability according to the rationality judgment result, and taking the terrain label and the updated label probability as a terrain identification result of the target road section.
And when the historical terrain recognition result does not exist, the first vehicle is a first vehicle passing through the target road section, the label probability obtained by the first vehicle recognition is updated according to the reasonability judgment result, and the terrain label obtained by the first vehicle recognition and the updated label probability are directly used as the terrain recognition result of the target road section.
Updating the tag probability according to the rationality determination result is described above, and this embodiment is not described herein again.
And S250, judging whether the distance from the second vehicle to the target road section is determined to be smaller than or equal to the preset distance according to the position information of the second vehicle, if so, executing S260, otherwise, returning to execute S250.
The cloud server acquires the position information of the second vehicle in real time, and when the distance from the second vehicle to the target road section is smaller than or equal to the preset distance according to the position information of the second vehicle, namely the second vehicle is about to reach the target road section, the terrain recognition result of the target road section is sent to the second vehicle. By the arrangement, the terrain recognition result of the target road section can be obtained before the second vehicle reaches the target road section, and the relevant system of the second vehicle responds to the terrain of the target road section in advance to make corresponding adjustment, so that the whole vehicle control performance of the second vehicle under different terrains can be improved.
And S260, sending the terrain recognition result to a second vehicle.
And S270, acquiring identification reported data obtained by the second vehicle carrying out terrain identification on the target road section.
The second vehicle is not only a main body for receiving the terrain recognition result of the target road section, but also a main body for carrying out terrain recognition on the target road section and reporting the recognition report data obtained by recognition to the cloud server, so that the cloud server updates the terrain recognition result according to the recognition report data reported by the second vehicle.
And S280, updating the terrain recognition result of the target road section according to the recognition reported data reported by the second vehicle.
In the embodiment of the invention, the second vehicle is a beneficiary party for sending the terrain recognition result by the cloud server and is a contributor party for recognizing and reporting data by a single vehicle.
Specific application scenario 1
Fig. 2b is a schematic structural diagram of a terrain recognition system in a first specific application scenario of the present invention, and as shown in fig. 2b, the terrain recognition system includes a cloud server, a host terrain recognition system, a host vehicle-side transmission system, a slave vehicle-side reception system, a slave vehicle terrain recognition system, a slave vehicle-side transmission system, a weather information system, a traffic information system, and a map information system. The working principle of the terrain recognition system is as follows:
after the terrain identification system of the main vehicle identifies the terrain of the target road section, the identification reported data is reported to the cloud server through the main vehicle end transmission system, the cloud server locates the target road section in the map information system, receives the weather information and the traffic information of the target road section sent by the weather information system and the traffic information system, and carries out rationality judgment on the identification reported data according to the weather information. And if the identification reported data are not reasonable, discarding the identification reported data, and acquiring the identification reported data sent by other vehicles again. And if the identification reported data is determined to be reasonable, updating the label probability, further determining whether the target road section has the corresponding historical terrain label and the historical label probability, and if not, establishing the terrain label and the label probability newly. And further, judging the rationality of the identified and reported data according to the traffic information, and updating the label probability again. And if the distance from the vehicle to the target road section is detected to be less than or equal to the preset distance, transmitting the terrain label and the updated label probability in a broadcasting mode, and responding to the terrain in time after receiving the terrain label from the vehicle-end receiving system. Meanwhile, the slave vehicle terrain recognition system also carries out terrain recognition on the target road section, and recognized and reported data are fed back to the cloud server through the slave vehicle end transmission system so that the cloud server can further update terrain labels and label probability.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a terrain recognition device in a third embodiment of the present invention, where the terrain recognition device is disposed in a cloud server, and includes: an identification reporting data acquisition module 310, a terrain identification result determination module 320 and a terrain identification result sharing module 330. Wherein:
an identification reported data acquisition module 310, configured to acquire identification reported data obtained by performing terrain identification on a target road segment by a first vehicle;
a terrain recognition result determining module 320, configured to determine a terrain recognition result of the target road segment according to the recognition report data;
and a terrain recognition result sharing module 330, configured to send the terrain recognition result to the second vehicle if it is detected that the location information of the second vehicle meets a terrain recognition sharing trigger condition.
According to the technical scheme, the terrain recognition result of the target road section is determined through recognition report data obtained by the first vehicle performing terrain recognition on the target road section, and the terrain recognition result of the target road section is sent to the second vehicle when the position information of the second vehicle meets the terrain recognition sharing triggering condition. The problem of among the prior art because the terrain recognition mode accuracy rate of single vehicle is low to terrain recognition has the delay nature, thereby is unfavorable for the vehicle to make timely response to the topography feature change is solved, has realized improving the accuracy of terrain recognition, has guaranteed the promptness of vehicle terrain recognition.
On the basis of the above embodiment, the terrain recognition result determining module 320 includes:
the information acquisition unit is used for acquiring the position of the target road section and acquiring meteorological information and/or traffic information of the target road section according to the position of the target road section;
the reasonability judgment unit is used for judging the reasonability of the identification reported data according to the meteorological information and/or traffic information of the target road section;
and the terrain recognition result determining unit is used for determining the terrain recognition result of the target road section according to the rationality judging result.
On the basis of the foregoing embodiment, the rationality determining unit is specifically configured to:
if the meteorological information is matched with the identification reported data and the traffic information is matched with the identification reported data, determining that the identification reported data is reasonable;
and judging the rationality of the identification reported data according to the meteorological information of the target road section, wherein the judgment comprises the following steps:
if the weather information is matched with the identification reported data, determining that the identification reported data is reasonable;
and judging the rationality of the identified and reported data according to the traffic information of the target road section, wherein the judgment comprises the following steps:
and if the traffic information is matched with the identification reported data, determining that the identification reported data is reasonable.
On the basis of the embodiment, the identification reported data comprises a terrain label and a label probability;
the terrain recognition result determining unit is specifically configured to:
if the historical terrain recognition result matched with the target road section does not exist, updating the label probability according to the reasonableness judgment result, and taking the terrain label and the updated label probability as the terrain recognition result of the target road section;
and if the historical terrain recognition result matched with the target road section exists, updating the historical terrain recognition result according to a reasonableness judgment result.
On the basis of the foregoing embodiment, the terrain recognition result determining unit is specifically configured to:
if the terrain label is the same as the historical terrain label, determining a target label probability according to a reasonableness judgment result, the label probability and the historical label probability, and updating the historical terrain identification result according to the terrain label and the target label probability;
otherwise, updating the label probability according to the reasonableness judgment result, and updating the historical terrain identification result according to the terrain label and the updated label probability.
On the basis of the above embodiment, the terrain recognition result sharing module 330 includes:
and the terrain identification sharing trigger condition judging unit is used for determining that the position information of the second vehicle meets the terrain identification sharing trigger condition if the distance from the second vehicle to the target road section is determined to be less than or equal to the preset distance according to the position information of the second vehicle.
On the basis of the above embodiment, the apparatus further includes:
the second vehicle data acquisition module is used for acquiring identification reported data obtained by the second vehicle carrying out terrain identification on the target road section;
and the terrain identification result updating module is used for updating the terrain identification result of the target road section according to the identification reported data reported by the second vehicle.
The terrain recognition device provided by the embodiment of the invention can execute the terrain recognition method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of a computer apparatus according to a fourth embodiment of the present invention, as shown in fig. 4, the computer apparatus includes a processor 70, a memory 71, an input device 72, and an output device 73; the number of processors 70 in the computer device may be one or more, and one processor 70 is taken as an example in fig. 4; the processor 70, the memory 71, the input device 72 and the output device 73 in the computer apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 4.
The memory 71 is used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as modules corresponding to the terrain identification method in the embodiment of the present invention (for example, the identification reporting data acquisition module 310, the terrain identification result determination module 320, and the terrain identification result sharing module 330 in the terrain identification device, the processor 70 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 71, so as to implement the above-mentioned terrain identification method.
Acquiring identification reported data obtained by a first vehicle carrying out terrain identification on a target road section;
determining a terrain recognition result of the target road section according to the recognition report data;
and if the position information of the second vehicle is detected to meet the terrain recognition sharing triggering condition, sending the terrain recognition result to the second vehicle.
The memory 71 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 71 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 non-volatile solid state storage device. In some examples, the memory 71 may further include memory located remotely from the processor 70, which may be connected to a computer device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 72 may be used to receive input numeric or character information and generate key signal inputs relating to user settings and function controls of the computer apparatus. The output device 73 may include a display device such as a display screen.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a terrain recognition method, the method including:
acquiring identification reported data obtained by a first vehicle carrying out terrain identification on a target road section;
determining a terrain recognition result of the target road section according to the recognition report data;
and if the position information of the second vehicle is detected to meet the terrain recognition sharing triggering condition, sending the terrain recognition result to the second vehicle.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the terrain recognition method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the terrain recognition apparatus, the included units and modules are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A terrain recognition method, performed by a cloud server, the method comprising:
acquiring identification reported data obtained by a first vehicle carrying out terrain identification on a target road section;
determining a terrain recognition result of the target road section according to the recognition report data;
and if the position information of the second vehicle is detected to meet the terrain recognition sharing triggering condition, sending the terrain recognition result to the second vehicle.
2. The method according to claim 1, wherein the determining a result of the terrain identification of the target road segment according to the identification report data comprises:
acquiring the position of a target road section, and acquiring meteorological information and/or traffic information of the target road section according to the position of the target road section;
judging the rationality of the identification reported data according to meteorological information and/or traffic information of a target road section;
and determining the terrain recognition result of the target road section according to the reasonableness judgment result.
3. The method according to claim 2, wherein the judging the rationality of the identification reported data according to the meteorological information and the traffic information of the target road section comprises the following steps:
if the meteorological information is matched with the identification reported data and the traffic information is matched with the identification reported data, determining that the identification reported data is reasonable;
otherwise, determining that the reported data is unreasonable to identify;
and judging the rationality of the identification reported data according to the meteorological information of the target road section, wherein the judgment comprises the following steps:
if the weather information is matched with the identification reported data, determining that the identification reported data is reasonable;
otherwise, determining that the reported data is unreasonable to identify;
and judging the rationality of the identified and reported data according to the traffic information of the target road section, wherein the judgment comprises the following steps:
if the traffic information is matched with the identification reported data, determining that the identification reported data is reasonable;
otherwise, determining that the reported data is unreasonable to identify.
4. The method of claim 2, wherein the identifying reported data comprises a terrain tag and a tag probability;
the determining the terrain recognition result of the target road section according to the rationality judgment result comprises the following steps:
if the historical terrain recognition result matched with the target road section does not exist, updating the label probability according to the reasonableness judgment result, and taking the terrain label and the updated label probability as the terrain recognition result of the target road section;
and if the historical terrain recognition result matched with the target road section exists, updating the historical terrain recognition result according to a reasonableness judgment result.
5. The method of claim 4, wherein updating the historical terrain identification results based on the rationality determination comprises:
if the terrain label is the same as the historical terrain label, determining a target label probability according to a reasonableness judgment result, the label probability and the historical label probability, and updating the historical terrain identification result according to the terrain label and the target label probability;
otherwise, updating the label probability according to the reasonableness judgment result, and updating the historical terrain identification result according to the terrain label and the updated label probability.
6. The method of claim 1, wherein detecting that the location information of the second vehicle satisfies the terrain recognition sharing trigger condition comprises:
and if the distance from the second vehicle to the target road section is determined to be less than or equal to the preset distance according to the position information of the second vehicle, determining that the position information of the second vehicle meets the terrain recognition sharing triggering condition.
7. The method according to any of claims 1-6, wherein after sending the terrain identification result to a second vehicle, further comprising:
acquiring identification reported data obtained by the second vehicle carrying out terrain identification on the target road section;
and updating the terrain recognition result of the target road section according to the recognition reported data reported by the second vehicle.
8. The terrain recognition device is characterized in that the terrain recognition device is arranged in a cloud server, and the terrain recognition device comprises:
the identification reported data acquisition module is used for acquiring identification reported data obtained by the first vehicle carrying out terrain identification on the target road section;
the terrain recognition result determining module is used for determining the terrain recognition result of the target road section according to the recognition report data;
and the terrain recognition result sharing module is used for sending the terrain recognition result to the second vehicle if the position information of the second vehicle is detected to meet the terrain recognition sharing triggering condition.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the terrain recognition method according to any of claims 1-7 when executing the program.
10. A storage medium containing computer-executable instructions for performing the terrain identification method of any of claims 1-7 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110551249.1A CN113190015A (en) | 2021-05-20 | 2021-05-20 | Terrain recognition method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110551249.1A CN113190015A (en) | 2021-05-20 | 2021-05-20 | Terrain recognition method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113190015A true CN113190015A (en) | 2021-07-30 |
Family
ID=76982733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110551249.1A Pending CN113190015A (en) | 2021-05-20 | 2021-05-20 | Terrain recognition method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113190015A (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101005375A (en) * | 2005-12-15 | 2007-07-25 | 卡特彼勒群伯控制技术有限公司 | System and method for sharing terrain data among multiple machines |
| CN104980343A (en) * | 2015-06-30 | 2015-10-14 | 北京奇虎科技有限公司 | Sharing method and system of road condition information, automobile data recorder, and cloud server |
| CN105741595A (en) * | 2016-04-27 | 2016-07-06 | 常州加美科技有限公司 | Unmanned vehicle navigation driving method based on cloud database |
| CN106448225A (en) * | 2016-08-25 | 2017-02-22 | 深圳市元征科技股份有限公司 | Road information sharing method and device |
| CN106969781A (en) * | 2017-03-29 | 2017-07-21 | 范志国 | A kind of road surface navigation system |
| CN107204095A (en) * | 2017-06-16 | 2017-09-26 | 方圆 | A kind of highway ice and snow road Car warning system |
| CN107679576A (en) * | 2017-10-11 | 2018-02-09 | 北京摩拜科技有限公司 | The fault monitoring method and device of vehicle |
| CN109643367A (en) * | 2016-07-21 | 2019-04-16 | 御眼视觉技术有限公司 | Crowdsourcing and the sparse map of distribution and lane measurement for autonomous vehicle navigation |
| CN109727334A (en) * | 2017-10-30 | 2019-05-07 | 长城汽车股份有限公司 | Recognition methods, device and the vehicle of landform locating for vehicle |
| CN110188687A (en) * | 2019-05-30 | 2019-08-30 | 爱驰汽车有限公司 | Landform recognition methods, system, equipment and the storage medium of automobile |
| CN110324368A (en) * | 2018-03-29 | 2019-10-11 | 上海博泰悦臻网络技术服务有限公司 | A kind of sharing method and its system of the predicting road conditions based on weather |
| CN110834639A (en) * | 2019-10-24 | 2020-02-25 | 中国第一汽车股份有限公司 | Vehicle control method, device, equipment and storage medium |
| CN111209770A (en) * | 2018-11-21 | 2020-05-29 | 北京三星通信技术研究有限公司 | Lane line identification method and device |
| CN111367292A (en) * | 2020-03-20 | 2020-07-03 | 特路（北京）科技有限公司 | Intelligent road system for automatically driving automobile |
| CN111688692A (en) * | 2019-03-13 | 2020-09-22 | 本田技研工业株式会社 | Vehicle control device, vehicle control method, and storage medium |
| CN112163348A (en) * | 2020-10-24 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Method and device for detecting road abnormal road surface, simulation method, vehicle and medium |
-
2021
- 2021-05-20 CN CN202110551249.1A patent/CN113190015A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101005375A (en) * | 2005-12-15 | 2007-07-25 | 卡特彼勒群伯控制技术有限公司 | System and method for sharing terrain data among multiple machines |
| CN104980343A (en) * | 2015-06-30 | 2015-10-14 | 北京奇虎科技有限公司 | Sharing method and system of road condition information, automobile data recorder, and cloud server |
| CN105741595A (en) * | 2016-04-27 | 2016-07-06 | 常州加美科技有限公司 | Unmanned vehicle navigation driving method based on cloud database |
| CN109643367A (en) * | 2016-07-21 | 2019-04-16 | 御眼视觉技术有限公司 | Crowdsourcing and the sparse map of distribution and lane measurement for autonomous vehicle navigation |
| CN106448225A (en) * | 2016-08-25 | 2017-02-22 | 深圳市元征科技股份有限公司 | Road information sharing method and device |
| CN106969781A (en) * | 2017-03-29 | 2017-07-21 | 范志国 | A kind of road surface navigation system |
| CN107204095A (en) * | 2017-06-16 | 2017-09-26 | 方圆 | A kind of highway ice and snow road Car warning system |
| CN107679576A (en) * | 2017-10-11 | 2018-02-09 | 北京摩拜科技有限公司 | The fault monitoring method and device of vehicle |
| CN109727334A (en) * | 2017-10-30 | 2019-05-07 | 长城汽车股份有限公司 | Recognition methods, device and the vehicle of landform locating for vehicle |
| CN110324368A (en) * | 2018-03-29 | 2019-10-11 | 上海博泰悦臻网络技术服务有限公司 | A kind of sharing method and its system of the predicting road conditions based on weather |
| CN111209770A (en) * | 2018-11-21 | 2020-05-29 | 北京三星通信技术研究有限公司 | Lane line identification method and device |
| CN111688692A (en) * | 2019-03-13 | 2020-09-22 | 本田技研工业株式会社 | Vehicle control device, vehicle control method, and storage medium |
| CN110188687A (en) * | 2019-05-30 | 2019-08-30 | 爱驰汽车有限公司 | Landform recognition methods, system, equipment and the storage medium of automobile |
| CN110834639A (en) * | 2019-10-24 | 2020-02-25 | 中国第一汽车股份有限公司 | Vehicle control method, device, equipment and storage medium |
| CN111367292A (en) * | 2020-03-20 | 2020-07-03 | 特路（北京）科技有限公司 | Intelligent road system for automatically driving automobile |
| CN112163348A (en) * | 2020-10-24 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Method and device for detecting road abnormal road surface, simulation method, vehicle and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110146100B (en) | Trajectory prediction method, apparatus and storage medium | |
| CN108263382B (en) | Cooperative adaptive cruise control system based on driving pattern of target vehicle | |
| US10838423B2 (en) | Intelligent vehicle navigation systems, methods, and control logic for deriving road segment speed limits | |
| JP6424761B2 (en) | Driving support system and center | |
| US10204516B2 (en) | Automobile and computing system | |
| CN109767619B (en) | Intelligent networking pure electric vehicle running condition prediction method | |
| CN108764042B (en) | Abnormal road condition information identification method and device and terminal equipment | |
| WO2020116264A1 (en) | Vehicle travel assistance method, vehicle travel assistance device and autonomous driving system | |
| CN111932884A (en) | Traffic jam recognition method and device, vehicle and storage medium | |
| CN112926575A (en) | Traffic accident recognition method, device, electronic device and medium | |
| CN109094560A (en) | A kind of adaptive cruise method and device | |
| CN113076773A (en) | Target detection clustering method, system, computer device and readable storage medium | |
| US20200286371A1 (en) | Traffic system for predicting and providing traffic signal switching timing | |
| WO2023023336A1 (en) | Detected object path prediction for vision-based systems | |
| WO2022147785A1 (en) | Autonomous driving scenario identifying method and apparatus | |
| US20170092121A1 (en) | Method and System for Determining and Using Property Associations | |
| CN113190015A (en) | Terrain recognition method and device, computer equipment and storage medium | |
| JP3639196B2 (en) | Vehicle identification device | |
| CN111243316A (en) | Method for judging whether road speed limit value of navigation system needs to be updated in real time | |
| US20230079116A1 (en) | Adaptive communication for a vehicle in a communication network | |
| US20220111865A1 (en) | Driver scoring system and method using optimum path deviation | |
| CN115331480A (en) | Vehicle early warning method and device and computing equipment | |
| CN115320627A (en) | Vehicle driving method, device and system | |
| CN111409467B (en) | Automobile braking energy recovery method, terminal equipment, vehicle and server | |
| CN115512511A (en) | Early warning method, early warning device, mobile terminal and readable storage 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210730 |