CN113724525B - Automatic passenger-replacing patrol type parking method and system based on big data platform and storage device - Google Patents
Automatic passenger-replacing patrol type parking method and system based on big data platform and storage device Download PDFInfo
- Publication number
- CN113724525B CN113724525B CN202110632140.0A CN202110632140A CN113724525B CN 113724525 B CN113724525 B CN 113724525B CN 202110632140 A CN202110632140 A CN 202110632140A CN 113724525 B CN113724525 B CN 113724525B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking
- parking space
- map
- preset track
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
- G08G1/143—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces inside the vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
- G08G1/096775—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station
Abstract
The invention relates to the technical field of vehicles, in particular to an automatic passenger-replacing patrol type parking method, system and storage device based on a large data platform. The automatic passenger-replacing patrol parking method based on the big data platform comprises the following steps: acquiring a current parking lot map and preset track data through a cloud platform; controlling the automobile to run according to the current parking lot map and a preset track; during the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park. In the process of the method, various complex sensors are not required to be arranged in the parking lot to acquire various data, the automatic passenger-replacing patrol type parking of the vehicle can be realized only by the data communication between the vehicle and the cloud platform and the vehicle camera arranged on the vehicle, the parking lot is not required to be modified, and the method can be widely and conveniently popularized and applied.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to an automatic passenger-replacing patrol type parking method, system and storage device based on a large data platform.
Background
At present, people park in a residential area or a shopping mall, a parking space is not fixed, the current parking space is full, and the problem that people feel very distressing when the parking space is searched is solved. The existing passenger-replacing parking system is based on technologies such as an internet of vehicles and a high-precision map, sensors and networks need to be arranged in a parking lot to realize information management, and obtained information is transmitted to an automobile.
However, there are still many parking lots without sensors for cost saving, so that it is an urgent technical problem to realize automatic passenger-assistant parking in these parking lots without sensors.
Disclosure of Invention
Therefore, an automatic passenger-replacing patrol type parking method based on a big data platform needs to be provided for solving the technical problem that automatic passenger-replacing parking cannot be realized in the existing parking lot which is not provided with a sensor. The specific technical scheme is as follows:
an automatic passenger-replacing patrol parking method based on a big data platform comprises the following steps:
acquiring a current parking lot map and preset track data through a cloud platform;
controlling the automobile to run according to the current parking lot map and a preset track;
during the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park.
Further, the "judge the parking space through the vehicle camera" specifically includes the following steps:
identifying a parking space identification object, and judging the type of the current parking space according to an identification result, wherein the identification object comprises but is not limited to: the parking stall type comprises a marking lamp, a color parking stall line and a two-dimensional code mark, wherein the parking stall type comprises but is not limited to: private parking space, public parking space, private parking space.
Further, the "judge the parking space through the vehicle camera" specifically includes the following steps:
scanning and recording the license plate number of a vehicle parked on a passing parking space by the vehicle;
after "judge whether the parking stall accords with the parking condition", still include the step:
after the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track until the available parking space is found for automatic parking;
or
After the vehicle is controlled to run on the current parking lot in the preset track, if no vacant position exists, the vehicle is controlled to continue to run according to the preset track within the preset time, when the available parking space is not found after the preset time is exceeded, the result is fed back to the vehicle owner, the operation instruction sent by the vehicle owner is received, and the operation instruction is executed;
or
After the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track, license plates of other running vehicles are captured in the running process, and if the license plate of the running vehicle is found to be consistent with the license plate on the parking space recorded before, the running track of the vehicle is changed, and the vehicle runs to the position where the vehicle corresponding to the license plate parks before;
or
If the vehicle is parked in the wrong empty parking space, whether the information of being notified to leave is received or not is judged, if yes, the vehicle is automatically parked out and drives according to the preset track again.
Further, before the current parking lot map and the preset track data are acquired through the cloud platform, the method further comprises the following steps:
the cloud platform acquires current parking lot related information uploaded by different vehicles, wherein the current parking lot related information comprises but is not limited to: map information, track information and parking space information drawn in the driving process of the vehicle;
and the cloud platform analyzes and processes the relevant information of the current parking lot uploaded by different vehicles to obtain a complete map and a preset track of the current parking lot.
Further, the vehicle is provided with a laser radar and/or a camera sensor;
the vehicle is provided with software and hardware of an intelligent driving system;
and the vehicle is positioned and mapped through an inertial navigation module or an SLAM.
In order to solve the technical problem, the storage device is further provided, and the specific technical scheme is as follows:
a storage device having stored therein a set of instructions for performing:
acquiring a current parking lot map and preset track data through a cloud platform;
controlling the automobile to run according to the current parking lot map and a preset track;
in the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park.
Further, the set of instructions is further for performing: "judge the parking stall through the vehicle camera", still include the step specifically:
identifying a parking space identification object, and judging the type of the current parking space according to an identification result, wherein the identification object comprises but is not limited to: the parking stall type comprises a marking lamp, a color parking stall line and a two-dimensional code mark, wherein the parking stall type comprises but is not limited to: private parking space, public parking space, special parking space.
Further, the set of instructions is further for performing:
"judge the parking stall through the vehicle camera", still include the step specifically:
scanning and recording the license plate number of a vehicle parked on a passing parking space by the vehicle;
after "judge whether the parking stall accords with parking condition", still include the step:
after the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track until an available parking space is found for automatic parking;
or
After the vehicle is controlled to run on the preset track in the current parking lot, if no vacant space exists, the vehicle is controlled to continue to run according to the preset track within preset time, when the available parking space is not found after the preset time is exceeded, a result is fed back to a vehicle owner, an operation instruction sent by the vehicle owner is received, and the operation instruction is executed;
or
After the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track, license plates of other running vehicles are captured in the running process, and if the license plate of the running vehicle is found to be consistent with the license plate on the parking space recorded before, the running track of the vehicle is changed, and the vehicle runs to the position where the vehicle corresponding to the license plate parks before;
or
If the parking is carried out in the wrong empty parking space, whether the information notified to leave is received or not is judged, if yes, the parking is carried out automatically, and the vehicle drives according to the preset track again.
Further, the storage device comprises a vehicle; the vehicle is provided with a laser radar and/or a camera sensor;
the vehicle is provided with software and hardware of an intelligent driving system;
and the vehicle is positioned and mapped through an inertial navigation module or an SLAM.
In order to solve the technical problems, the automatic passenger-replacing patrol type parking system based on the big data platform is further provided, and the specific technical scheme is as follows:
an automatic passenger-replacing patrol parking system based on a big data platform comprises: a cloud platform and a vehicle;
the vehicle is used for: acquiring a current parking lot map and preset track data through a cloud platform;
controlling the automobile to run according to the current parking lot map and a preset track;
in the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park;
the cloud platform is further configured to: obtaining relevant information of a current parking lot uploaded by different vehicles, wherein the relevant information of the current parking lot comprises but is not limited to: map information, track information and parking space information drawn in the driving process of the vehicle; and analyzing and processing the relevant information of the current parking lot uploaded by the different vehicles to obtain a complete map and a preset track of the current parking lot.
The invention has the beneficial effects that: an automatic passenger-replacing patrol parking method based on a big data platform comprises the following steps: acquiring a current parking lot map and preset track data through a cloud platform; controlling the automobile to run according to the current parking lot map and a preset track; during the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park. In the process of the method, various complex sensors are not required to be arranged in the parking lot to acquire various data, the automatic passenger-replacing patrol type parking of the vehicle can be realized only by the data communication between the vehicle and the cloud platform and the vehicle camera arranged on the vehicle, the parking lot is not required to be modified, and the method can be widely and conveniently popularized and applied.
Drawings
FIG. 1 is a flow chart of a method for automatic passenger-replacement patrol parking based on a big data platform according to an embodiment;
FIG. 2 is a schematic diagram of a SLAM framework according to an embodiment;
FIG. 3a is a schematic diagram of a map and a driving track recorded by an automobile A according to an embodiment;
FIG. 3B is a schematic diagram of a map and a driving track recorded by the automobile B according to an embodiment;
fig. 3c is a schematic diagram of an overlapping area between a map and a driving track recorded by the automobile a and a map and a driving track recorded by the automobile B according to the embodiment;
FIG. 3d is a diagram of a completed map according to an embodiment;
FIG. 3e is a diagram illustrating the preset trajectory according to an embodiment;
FIG. 4 is a block diagram of a memory device according to an embodiment;
fig. 5 is a schematic block diagram of an automatic passenger-replacement patrol parking system based on a big data platform according to an embodiment.
Description of reference numerals:
400. the storage device is provided with a memory for storing data,
500. an automatic passenger-replacing patrol parking system based on a big data platform,
501. the cloud platform is used for carrying out cloud service,
502. a vehicle.
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Referring to fig. 1 to 3e, in the present embodiment, an automatic passenger-replacement patrol parking method based on a big data platform may be applied to a storage device, in the present embodiment, the storage device may be a vehicle, and the vehicle is provided with a laser radar and/or a camera sensor; the vehicle is provided with software and hardware of an intelligent driving system; and the vehicle is positioned and mapped through an inertial navigation module or an SLAM.
The following description is respectively developed for the inertial navigation module (including the IMU) for positioning and mapping, and the camera and the lidar for positioning and mapping through SLAM:
an inertial navigation module: the inertial navigation module is mainly used for areas where satellite signals are shielded, such as underground parking lots and overpasses, the vehicle cannot be positioned at the time, and the inertial navigation module does not know where the vehicle is located and mainly acquires information such as the horizontal height, the acceleration direction and the attitude of the vehicle through the IMU. And finishing the positioning of the automobile. The main components comprise 1, a gyroscope 2 and an accelerometer, wherein the accelerometer detects acceleration signals of an object on three independent axes of a carrier coordinate system, the gyroscope detects angular velocity signals of the carrier relative to a navigation coordinate system, and after the signals are processed, the posture of the object can be calculated.
The basic working principle of inertial navigation is that based on Newton's law of mechanics, the acceleration of the carrier in inertial reference system is measured, the time is integrated, and the integrated acceleration is transformed into navigation coordinate system, so that the information of speed, yaw angle and position in the navigation coordinate system can be obtained.
Referring to fig. 2, SLAM positioning and mapping will be described:
SLAM (simultaneous Localization and Mapping), also known as CML (current Mapping and Localization), performs instantaneous Localization and Mapping, or Concurrent Mapping and Localization.
Sensor data: the method is mainly used for collecting various types of original data in the actual environment. Including laser scan data, video image data, point cloud data, etc.
And (3) visual odometer: the method is mainly used for estimating the relative position of the moving target at different time instants. Including application of algorithms such as feature matching, direct registration, etc.
A rear end: the method is mainly used for optimizing the accumulated error brought by the visual odometer. Including filter, graph optimization, etc. algorithm applications.
Establishing a graph: the method is used for three-dimensional map construction.
Loop detection: the method is mainly used for eliminating the spatial accumulated error.
The work flow is roughly as follows: after the sensor reads data, the visual odometer estimates relative motion (Ego-motion) at two moments, the back end processes accumulated errors of the estimation result of the visual odometer, a map is built according to motion tracks obtained by the front end and the back end, loop detection considers images of the same scene at different moments, and space constraint is provided to eliminate the accumulated errors.
Sensors currently used in SLAMs are largely classified into two types, one being a Lidar (Lidar) based and a Visual VSLAM (Visual SLAM).
The laser SLAM system calculates the change of the relative movement distance and the posture of the laser radar through matching and comparing two point clouds at different moments, and the robot is positioned.
Visual SLA: the eye is the main source of external information for humans. The visual SLAM has similar characteristics, can acquire massive redundant texture information from the environment, and has super-strong scene identification capability. The advantage of visual SLAM is the rich texture information it utilizes. For example, two billboards with the same size but different contents cannot be distinguished by the laser SLAM algorithm based on point cloud, but the two billboards can be easily distinguished by vision. This brings incomparable great advantages in repositioning and scene classification. Meanwhile, visual information can be easily used for tracking and predicting dynamic objects in a scene, such as pedestrians, vehicles and the like, and is very important for application in complex dynamic scenes.
After the two positioning and drawing modes are explained, the following explanation is specifically made for an automatic passenger-replacement patrol type parking method based on a big data platform:
step S101: and acquiring a current parking lot map and preset track data through the cloud platform.
Step S102: and controlling the automobile to run according to the current parking lot map and the preset track.
Step S103: during the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park.
It should be noted that one core technical point of the present application lies in a cloud platform sharing mechanism, that is: data sharing of cloud platform maps is based on a principle: the user of the data is also the data provider, i.e. the owner of the vehicle must agree to share the data, to use the data, and to contribute to the data. In a parking lot where a cloud platform and the vehicle are not provided with a map, when the vehicle owner uses the system, map data need to be established. After the system is started, the vehicle owner starts to search for the parking space, in the process, the laser radar or the camera starts to scan, and the vehicle owner positions and establishes a map according to the features and the IMU.
Therefore, before the current parking lot map and the preset track data are acquired through the cloud platform, the method further comprises the following steps:
the cloud platform acquires current parking lot related information uploaded by different vehicles, wherein the current parking lot related information comprises but is not limited to: map information, track information and parking space information drawn in the driving process of the vehicle;
and the cloud platform analyzes and processes the relevant information of the current parking lot uploaded by different vehicles to obtain a complete map and a preset track of the current parking lot. Such as: after parking, the current map information, track information, parking space information and the like are uploaded. The map data of the parking lot may be incomplete, and along with continuous uploading of vehicle owner data, the cloud platform can fuse the data according to the collected map information and track information of the same parking lot, and according to track coincidence, feature point positioning reconstructs a map, a map area is perfected, and more complete data are formed.
As shown in fig. 3a, the vehicle a is recorded with a map and a driving track, and the vehicle is directly turned to the right after entering the entrance to find a parking space. As shown in fig. 3B, the vehicle B is directly driven to the left to find a parking space behind the entrance of the map and the driving track recorded by the vehicle B. The data of the two vehicles can realize map fusion according to the track and the positioning, and the map expansion is completed to form a map of a larger area. The principle of map fusion: the basis of map fusion is based on SLAM mapping of unified standards, the same coordinate system is adopted, map data collected by different automobiles are different, and maps of the automobiles have overlapped areas. On the basis of the overlapped area, the same area can be obtained through feature comparison, such as texture analysis of the image, a unified coordinate system is converted into a coordinate system according to the positioning information, and the extension of the map is realized by taking the union of the two parts. For example, the map created by the above cars a and B, the overlapped part of which is shown in fig. 3c, can be expanded by the positioning information and the vehicle track based on the overlapped part. The method is equivalent to a household sweeping robot which sweeps the map for many times, the whole house map scanning is completed, and the whole house track planning is realized. We do this using different vehicles but using the same standard.
With the expansion of the map and the increase of the tracks, the map tends to be more and more perfect, for example, fig. 3d is a perfect map, a preset track can be formed according to the track summary and the route planning algorithm, the track line surrounding a closed loop is completed, the vehicle can walk in the area, whether a parking space is available is checked, and the parking is completed. As shown by the arrowed lines in fig. 3e, a closed loop trajectory is shown.
After the collection of the map and track data of the parking lot is finished, a vehicle owner uses the parking lot covered by the data, an intelligent driving system vehicle is configured to obtain a current parking lot map and preset track data through a cloud platform, and the vehicle is controlled to run according to the current parking lot map and the preset track;
wherein "judge the parking stall through the vehicle camera", still include the step specifically:
identifying a parking space identification object, and judging the type of the current parking space according to an identification result, wherein the identification object comprises but is not limited to: the parking stall type comprises a marking lamp, a color parking stall line and a two-dimensional code mark, wherein the parking stall type comprises but is not limited to: private parking space, public parking space, private parking space.
If the parking space meeting the parking condition is identified, namely the public parking space can be parked, and no vehicle or obstacle is in the parking space, the automobile can be automatically parked.
Further, the "judge the parking space through the vehicle camera" specifically includes the following steps:
scanning and recording license plate numbers of vehicles parked on passing parking spaces through the vehicles;
after "judge whether the parking stall accords with parking condition", still include the step:
and after the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track until an available parking space is found for automatic parking.
Or
And after the vehicle is controlled to run on the preset track in the current parking lot, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track within the preset time, and when the available parking space is not found after the preset time is exceeded, a result is fed back to the vehicle owner, an operation instruction sent by the vehicle owner is received, and the operation instruction is executed. After the vehicle owner receives the relevant information that the available parking space is not found, the vehicle owner can operate through the mobile phone APP to select whether to continue patrol.
Or
After the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track, license plates of other running vehicles are captured in the running process, and if the license plate of the running vehicle is found to be consistent with the license plate on the parking space recorded before, the running track of the vehicle is changed, and the vehicle runs to the position where the vehicle corresponding to the license plate parks before; if the position is free, the parking is finished, otherwise, the patrol according to the track is continued.
Or
If the parking is carried out in the wrong empty parking space, whether the information notified to leave is received or not is judged, if yes, the parking is carried out automatically, and the vehicle drives according to the preset track again. If the parking place is wrongly parked in the special parking place or the private parking place, the contact way of the parking place owner can be obtained through the two-dimensional code identification, the owner can be consulted whether to temporarily park or not through sending information, if so, the parking is temporarily stopped, and when the information which is notified to leave is received, the automatic parking out and the patrol parking are realized through the APP.
An automatic passenger-replacing patrol parking method based on a big data platform comprises the following steps: acquiring a current parking lot map and preset track data through a cloud platform; controlling the automobile to run according to the current parking lot map and a preset track; during the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park. In the process of the method, various complex sensors are not required to be arranged in the parking lot to acquire various data, the automatic passenger-replacing patrol type parking of the vehicle can be realized only by the data communication between the vehicle and the cloud platform and the vehicle camera arranged on the vehicle, the parking lot is not required to be modified, and the method can be widely and conveniently popularized and applied.
Further, the map in the above method is based on big data, and as the data volume increases, larger area coverage and precision improvement will be brought. In addition, the path planning is derived from a large amount of owner data, and is closer to the actual driving condition and more reasonable.
The whole process does not need manual parking, and the automatic patrol parking is completed by the car owner instead of the full parking space, so that the time is saved. Support most parking areas, the parking area only need increase simple discernment like two-dimensional code or landmark discernment etc. can, need not to invest in a large amount of funds and reform transform the parking area, do not need the cover of high accuracy map, through data sharing, accomplish map and orbit sharing.
Referring to fig. 2 to 4, in the present embodiment, an embodiment of a memory device 400 is as follows:
a storage device 400 having stored therein a set of instructions for performing:
acquiring a current parking lot map and preset track data through a cloud platform;
controlling the automobile to run according to the current parking lot map and a preset track;
during the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park.
The method comprises the following steps of obtaining a current parking lot map and preset track data through a cloud platform, wherein the current parking lot map and the preset track data can be as follows:
the cloud platform acquires current parking lot related information uploaded by different vehicles, wherein the current parking lot related information comprises but is not limited to: map information, track information and parking space information drawn in the driving process of the vehicle;
and the cloud platform analyzes and processes the relevant information of the current parking lot uploaded by different vehicles to obtain a complete map and a preset track of the current parking lot. Such as: after the vehicle is parked, the map information, the track information, the parking space information and the like are uploaded. The map data of the parking lot may be incomplete, and along with continuous uploading of vehicle owner data, the cloud platform can fuse the data according to the collected map information and track information of the same parking lot, and according to track coincidence, feature point positioning reconstructs a map, a map area is perfected, and more complete data are formed.
As shown in fig. 3a, the vehicle a is recorded with a map and a driving track, and the vehicle is directly turned to the right after entering the entrance to find a parking space. As shown in fig. 3B, the vehicle B is directly driven to the left to find a parking space behind the entrance of the map and the driving track recorded by the vehicle B. The data of the two vehicles can realize map fusion according to the track and the positioning, so that map expansion is completed, and a map of a larger area is formed. The principle of map fusion: the basis of map fusion is based on SLAM mapping of a unified standard, the same coordinate system is adopted, map data collected by different automobiles are different, and maps of the automobiles have overlapped areas. On the basis of the overlapped area, the same area can be obtained through feature comparison, such as texture analysis of the image, a unified coordinate system is converted into a coordinate system according to the positioning information, and the extension of the map is realized by taking the union of the two parts. For example, the map created by the above cars a and B, the overlapped part of which is shown in fig. 3c, can be expanded by the positioning information and the vehicle track based on the overlapped part. The method is equivalent to a household sweeping robot which sweeps the map for many times, the whole house map scanning is completed, and the whole house track planning is realized. We do this using different vehicles but using the same standard.
With the expansion of the map and the increase of the tracks, the map tends to be more and more perfect, for example, fig. 3d is a perfect map, a preset track can be formed according to the track summary and the route planning algorithm, the track line surrounding a closed loop is completed, the vehicle can walk in the area, whether a parking space is available is checked, and the parking is completed. As shown by the arrowed line in fig. 3e, a closed loop trajectory is shown.
After the collection of the map and track data of the parking lot is finished, a vehicle owner uses the parking lot covered by the data, an intelligent driving system vehicle is configured to obtain a current parking lot map and preset track data through a cloud platform, and the vehicle is controlled to run according to the current parking lot map and the preset track;
further, the set of instructions is further operable to perform: "judge the parking stall through the vehicle camera", still include the step specifically:
identifying a parking space identification object, and judging the type of the current parking space according to an identification result, wherein the identification object comprises but is not limited to: the parking stall type comprises a marking lamp, a color parking stall line and a two-dimensional code mark, wherein the parking stall type comprises but is not limited to: private parking space, public parking space, special parking space.
If the parking space meeting the parking condition is identified, namely the public parking space can be parked, and no vehicle or obstacle is in the parking space, the automobile can be automatically parked.
Further, the set of instructions is further for performing:
"judge the parking stall through the vehicle camera", still include the step specifically:
scanning and recording license plate numbers of vehicles parked on passing parking spaces through the vehicles;
after "judge whether the parking stall accords with parking condition", still include the step:
after the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track until an available parking space is found for automatic parking;
or
After the vehicle is controlled to run on the current parking lot in the preset track, if no vacant position exists, the vehicle is controlled to continue to run according to the preset track within the preset time, when the available parking space is not found after the preset time is exceeded, the result is fed back to the vehicle owner, the operation instruction sent by the vehicle owner is received, and the operation instruction is executed;
or
After the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track, license plates of other running vehicles are captured in the running process, and if the license plate of the running vehicle is found to be consistent with the license plate on the parking space recorded before, the running track of the vehicle is changed, and the vehicle runs to the position where the vehicle corresponding to the license plate parks before;
or if the vehicle is parked in the wrong empty parking space, judging whether the information of being notified to leave is received, if so, automatically parking out and driving according to the preset track again.
Further, the storage device comprises a vehicle; the vehicle is provided with a laser radar and/or a camera sensor;
the vehicle is provided with software and hardware of an intelligent driving system;
and the vehicle is positioned and mapped through an inertial navigation module or an SLAM.
A memory device 400 having stored therein a set of instructions for performing: acquiring a current parking lot map and preset track data through a cloud platform; controlling the automobile to run according to the current parking lot map and a preset track; during the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park. In the execution process of the instruction set, various complex sensors are not required to be arranged in a parking lot to acquire various data, the vehicle only needs to be in data communication with a cloud platform, the vehicle is provided with a vehicle camera, automatic passenger-replacing patrol parking of the vehicle can be achieved, the parking lot does not need to be modified, and the method can be popularized and applied more widely and more conveniently.
Referring to fig. 3a to 3e, and fig. 5, an embodiment of an automatic passenger-replacement patrol parking system 500 based on a big data platform is as follows:
an automatic passenger-replacement patrol parking system 500 based on a big data platform, comprising: cloud platform 501 and vehicle 502;
the vehicle 502 is configured to: acquiring a current parking lot map and preset track data through the cloud platform 501;
controlling the automobile to run according to the current parking lot map and a preset track;
in the driving process, the parking space is judged through the vehicle 502 camera, whether the parking space meets the parking condition is judged, and if the parking space meets the parking condition, the vehicle 502 is controlled to automatically park;
the cloud platform 501 is further configured to: before acquiring a current parking lot map and preset track data through the cloud platform 501, the cloud platform 501 acquires current parking lot related information uploaded by different vehicles 502, and the acquisition of the current parking lot map and the preset track data through the cloud platform 501 includes but is not limited to: map information, track information, parking space information drawn during the driving of the vehicle 502 itself; the cloud platform 501 analyzes and processes the relevant information of the current parking lot uploaded by the different vehicles 502 to obtain a complete map and a preset track of the current parking lot. Such as: after the vehicle is parked, the map information, the track information, the parking space information and the like are uploaded. The map data of the parking lot may be incomplete, and along with continuous uploading of vehicle owner data, the cloud platform 501 can fuse the data according to the collected map information and track information of the same parking lot, and according to track coincidence, feature point positioning reconstructs a map, a map area is perfected, and more complete data are formed.
As shown in fig. 3a, the vehicle a is recorded with a map and a driving track, and the vehicle is directly turned to the right after entering the entrance to find a parking space. As shown in fig. 3B, the vehicle B is directly driven to the left to find a parking space behind the entrance of the map and the driving track recorded by the vehicle B. The data of the two vehicles can realize map fusion according to the track and the positioning, and the map expansion is completed to form a map of a larger area. The principle of map fusion: the basis of map fusion is based on SLAM mapping of unified standards, the same coordinate system is adopted, map data collected by different automobiles are different, and maps of the automobiles have overlapped areas. On the basis of the overlapped area, the same area can be obtained through feature comparison, such as texture analysis of the image, a unified coordinate system is converted from the coordinate system according to the positioning information, and the union of the two parts is taken, so that the expansion of the map is realized. Such as the map created by the top car a and car B, the overlapping parts of which are shown in fig. 3c, on the basis of which the non-overlapping parts can be expanded by the positioning information and the trajectory of the vehicle 502. The method is equivalent to a household sweeping robot which sweeps the map for many times, the whole house map scanning is completed, and the whole house track planning is realized. We do this using a different vehicle 502, but using the same standard.
With the expansion of the map and the increase of the tracks, the map tends to be more and more perfect, for example, as shown in fig. 3d, a preset track is formed according to the track summary and the route planning algorithm, so as to complete the track line around a closed loop, so that the vehicle 502 can walk in the area, check whether there is a free parking space, and complete parking. As shown by the arrowed lines in fig. 3e, a closed loop trajectory is shown.
After the collection of the map and track data of the parking lot is finished, a vehicle owner uses the parking lot covered by the data, the intelligent driving system vehicle 502 is configured to obtain the current parking lot map and the preset track data through the cloud platform 501, and the vehicle is controlled to run according to the current parking lot map and the preset track;
the vehicle 502 is also configured to: identifying a parking space identification object, and judging the type of the current parking space according to an identification result, wherein the identification object comprises but is not limited to: the parking stall type comprises a marking lamp, a color parking stall line and a two-dimensional code mark, wherein the parking stall type comprises but is not limited to: private parking space, public parking space, private parking space.
If the parking space meeting the parking condition is identified, namely the public parking space can be parked, and no vehicle 502 or obstacle is in the parking space, the automobile can be automatically parked.
Further, after the vehicle 502 runs in the current parking lot in the preset track, if no empty space exists, the vehicle continues to run in the preset track until an available parking space is found for automatic parking.
Or
After the vehicle 502 finishes driving the preset track in the current parking lot, if no vacancy exists, the vehicle 502 continues to drive according to the preset track within the preset time, and when the available parking space is not found after the preset time is exceeded, a result is fed back to a vehicle owner, an operation instruction sent by the vehicle owner is received, and the operation instruction is executed. After the vehicle owner receives the relevant information that the available parking space is not found, the vehicle owner can operate through the mobile phone APP to select whether to continue patrol.
Or
After the vehicle 502 runs the pre-track in the current parking lot, if no vacancy exists, the vehicle 502 continues to run according to the pre-track, license plates of other running vehicles 502 are captured in the running process, and if the license plate of the running vehicle 502 is found to be consistent with the license plate recorded in the previous parking space, the running track of the vehicle 502 is changed, and the vehicle is driven to the position, corresponding to the license plate, of the vehicle 502 parked in the previous parking space; if the position is free, the parking is finished, otherwise, the patrol is continued according to the track.
Or if the vehicle is parked in the wrong empty parking space, judging whether the information notified of leaving is received, if so, automatically parking out and driving according to the preset track again. If the parking place is wrongly parked in the special parking place or the private parking place, the contact way of the parking place owner can be obtained through the two-dimensional code identification, the owner can be consulted whether to temporarily park or not through sending information, if so, the parking is temporarily stopped, and when the information which is notified to leave is received, the automatic parking out and the patrol parking are realized through the APP.
An automatic passenger-replacement patrol parking system 500 based on a big data platform, comprising: cloud platform 501 and vehicle 502;
the vehicle 502 is configured to: acquiring a current parking lot map and preset track data through the cloud platform 501;
controlling the automobile to run according to the current parking lot map and a preset track;
during the driving process, the parking space is judged through the vehicle 502 camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle 502 is controlled to automatically park. In the system, various complex sensors are not required to be arranged in the parking lot to acquire various data, the vehicle 502 is only required to be in data communication with the cloud platform 501, the vehicle 502 is provided with the vehicle 502 camera, automatic passenger-replacing patrol parking of the vehicle 502 can be achieved, any transformation on the parking lot is not required, and the system can be popularized and applied more widely and more conveniently.
Further, the maps in the above system are based on big data, which will bring larger area coverage and accuracy improvement as the data volume increases. In addition, the path planning is derived from a large amount of owner data, and is closer to the actual driving condition and more reasonable.
The whole system does not need manual parking, and replaces the car owner to finish automatic patrol parking under the condition that the parking space is full, so that the time is saved. Support most parking areas, the parking area only need increase simple discernment like two-dimensional code or landmark identification thing can, need not to invest in a large amount of funds and reform transform the parking area, do not need the cover of high accuracy map, through data sharing, accomplish map and orbit sharing.
It should be noted that, although the above embodiments have been described herein, the invention is not limited thereto. Therefore, based on the innovative concepts of the present invention, the technical solutions of the present invention can be directly or indirectly applied to other related technical fields by making changes and modifications to the embodiments described herein, or by using equivalent structures or equivalent processes performed in the content of the present specification and the attached drawings, which are included in the scope of the present invention.
Claims (10)
1. An automatic passenger-replacing patrol parking method based on a big data platform is characterized by comprising the following steps:
acquiring a current parking lot map and preset track data through a cloud platform;
controlling the automobile to run according to the current parking lot map and a preset track;
in the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park;
judge the parking stall through the vehicle camera, specifically still include the step:
scanning and recording the license plate number of a vehicle parked on a passing parking space by the vehicle;
after judging whether the parking space accords with the parking condition, the method also comprises the following steps:
and after the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track, license plates of other running vehicles are captured in the running process, and when the license plate of the running vehicle is found to be consistent with the license plate on the parking space recorded before, the running track of the vehicle is changed, and the vehicle runs to the position where the vehicle corresponding to the license plate parks before.
2. The automatic passenger-replacing patrol parking method based on the big data platform as claimed in claim 1, wherein the parking space is judged by the vehicle camera, and the method specifically comprises the following steps:
identifying a parking space identification object, and judging the type of the current parking space according to an identification result, wherein the identification object comprises: marker light, colour car position line, two-dimensional code mark, the parking stall type includes: private parking space, public parking space, special parking space.
3. The automatic passenger-replacement patrol parking method based on the big data platform as claimed in claim 1,
after judging whether the parking space accords with the parking condition, the method further comprises the following steps:
after the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track until the available parking space is found for automatic parking;
or
After the vehicle is controlled to run on the current parking lot in the preset track, if no vacant position exists, the vehicle is controlled to continue to run according to the preset track within the preset time, when the available parking space is not found after the preset time is exceeded, the result is fed back to the vehicle owner, the operation instruction sent by the vehicle owner is received, and the operation instruction is executed;
or
If the parking is carried out in the wrong empty parking space, whether the information notified to leave is received or not is judged, if yes, the parking is carried out automatically, and the vehicle drives according to the preset track again.
4. The automatic passenger-replacement patrol parking method based on the big data platform as claimed in claim 1, wherein before the current parking lot map and the preset track data are obtained through the cloud platform, the method further comprises the following steps:
the cloud platform acquires the current parking lot related information uploaded by different vehicles, wherein the current parking lot related information comprises: map information, track information and parking space information drawn in the driving process of the vehicle;
and the cloud platform analyzes and processes the relevant information of the current parking lot uploaded by different vehicles to obtain a complete map and a preset track of the current parking lot.
5. The automatic passenger-replacing patrol parking method based on the big data platform is characterized in that the vehicle is provided with a laser radar and/or a camera sensor;
the vehicle is provided with software and hardware of an intelligent driving system;
and the vehicle is positioned and mapped through an inertial navigation module or an SLAM.
6. A storage device having a set of instructions stored therein, the set of instructions being operable to perform:
acquiring a current parking lot map and preset track data through a cloud platform;
controlling the automobile to run according to the current parking lot map and a preset track;
in the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park;
the parking space is judged through the vehicle camera, and the method specifically comprises the following steps:
scanning and recording the license plate number of a vehicle parked on a passing parking space by the vehicle;
after "judge whether the parking stall accords with parking condition", still include the step:
and after the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track, license plates of other running vehicles are captured in the running process, and when the license plate of the running vehicle is found to be consistent with the license plate on the parking space recorded before, the running track of the vehicle is changed, and the vehicle runs to the position where the vehicle corresponding to the license plate parks before.
7. The storage device of claim 6, wherein the set of instructions is further configured to perform: judge the parking stall through the vehicle camera, specifically still include the step:
identifying a parking space identification object, and judging the type of the current parking space according to an identification result, wherein the identification object comprises: marker light, colour car position line, two-dimensional code mark, the parking stall type includes: private parking space, public parking space, special parking space.
8. The storage device of claim 6, wherein the set of instructions is further configured to perform:
after "judge whether the parking stall accords with parking condition", still include the step:
after the vehicle is controlled to run on the current parking lot in the preset track, if no vacancy exists, the vehicle is controlled to continue to run according to the preset track until the available parking space is found for automatic parking;
or
After the vehicle is controlled to run on the current parking lot in the preset track, if no vacant position exists, the vehicle is controlled to continue to run according to the preset track within the preset time, when the available parking space is not found after the preset time is exceeded, the result is fed back to the vehicle owner, the operation instruction sent by the vehicle owner is received, and the operation instruction is executed;
or
If the parking is carried out in the wrong empty parking space, whether the information notified to leave is received or not is judged, if yes, the parking is carried out automatically, and the vehicle drives according to the preset track again.
9. A storage device according to any one of claims 6 to 8, wherein the storage device comprises a vehicle; the vehicle is provided with a laser radar and/or a camera sensor;
the vehicle is provided with software and hardware of an intelligent driving system;
and the vehicle is positioned and mapped through an inertial navigation module or an SLAM.
10. An automatic passenger-replacement patrol parking system based on a big data platform, which is based on the automatic passenger-replacement patrol parking method based on the big data platform of claim 1, and comprises: a cloud platform and a vehicle;
the vehicle is used for: acquiring a current parking lot map and preset track data through a cloud platform;
controlling the automobile to run according to the current parking lot map and a preset track;
in the driving process, the parking space is judged through the vehicle camera, whether the parking space meets the parking condition or not is judged, and if the parking space meets the parking condition, the vehicle is controlled to automatically park;
the cloud platform is further configured to: obtaining the relevant information of the current parking lot uploaded by different vehicles, wherein the relevant information of the current parking lot comprises: map information, track information and parking space information drawn in the driving process of the vehicle; and analyzing and processing the relevant information of the current parking lot uploaded by the different vehicles to obtain a complete map and a preset track of the current parking lot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110632140.0A CN113724525B (en) | 2021-06-07 | 2021-06-07 | Automatic passenger-replacing patrol type parking method and system based on big data platform and storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110632140.0A CN113724525B (en) | 2021-06-07 | 2021-06-07 | Automatic passenger-replacing patrol type parking method and system based on big data platform and storage device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113724525A CN113724525A (en) | 2021-11-30 |
| CN113724525B true CN113724525B (en) | 2023-01-20 |
Family
ID=78672897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110632140.0A Active CN113724525B (en) | 2021-06-07 | 2021-06-07 | Automatic passenger-replacing patrol type parking method and system based on big data platform and storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724525B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114937369B (en) * | 2022-04-06 | 2023-04-04 | 福思(杭州)智能科技有限公司 | Autonomous agent parking method, system, vehicle, parking lot end, device and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014145270A1 (en) * | 2013-03-15 | 2014-09-18 | Municipal Parking Services Inc. | Parking lot monitoring system |
| CN105303883A (en) * | 2015-11-25 | 2016-02-03 | 智慧互通科技有限公司 | Roadside parking management system and method thereof |
| CN112017467A (en) * | 2019-05-28 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013222071A1 (en) * | 2013-10-30 | 2015-04-30 | Robert Bosch Gmbh | Parking management system |
| DE102014211557A1 (en) * | 2014-06-17 | 2015-12-31 | Robert Bosch Gmbh | Valet parking procedure and system |
| JP6651001B2 (en) * | 2016-04-01 | 2020-02-19 | 三菱電機株式会社 | Automatic parking system, automatic parking control device and automatic parking control method |
| CN108482366A (en) * | 2018-03-23 | 2018-09-04 | 重庆长安汽车股份有限公司 | Valet parking system and method based on Vehicular automatic driving |
| CN111415523B (en) * | 2020-03-06 | 2021-04-09 | 北京智行者科技有限公司 | Autonomous passenger-riding-substituting parking method and system |
| CN111784857A (en) * | 2020-06-22 | 2020-10-16 | 浙江大华技术股份有限公司 | Parking space management method and device and computer storage medium |
| CN112802346B (en) * | 2020-12-28 | 2022-04-15 | 苏州易航远智智能科技有限公司 | Autonomous parking system and method based on cloud sharing and map fusion |
-
2021
- 2021-06-07 CN CN202110632140.0A patent/CN113724525B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014145270A1 (en) * | 2013-03-15 | 2014-09-18 | Municipal Parking Services Inc. | Parking lot monitoring system |
| CN105303883A (en) * | 2015-11-25 | 2016-02-03 | 智慧互通科技有限公司 | Roadside parking management system and method thereof |
| CN112017467A (en) * | 2019-05-28 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113724525A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112802346B (en) | Autonomous parking system and method based on cloud sharing and map fusion | |
| JP7147119B2 (en) | Device and method for autonomous self-localization | |
| CN111063202B (en) | Intelligent parking management method based on electronic map | |
| CN105946853B (en) | The system and method for long range automatic parking based on Multi-sensor Fusion | |
| CN105637321B (en) | The method and mobile unit of absolute position for acquiring mobile unit | |
| CN111976720B (en) | Autonomous passenger-replacing parking method, device, equipment and storage medium | |
| CN110497901A (en) | A kind of parking position automatic search method and system based on robot VSLAM technology | |
| EP3939863A1 (en) | Overhead-view image generation device, overhead-view image generation system, and automatic parking device | |
| CN103890606A (en) | Methods and systems for creating maps with radar-optical imaging fusion | |
| CN112216136A (en) | Parking space detection method and device, vehicle and storage medium | |
| CN112419776B (en) | Autonomous parking method and device, automobile and computing equipment | |
| Moras et al. | A lidar perception scheme for intelligent vehicle navigation | |
| CN110293965A (en) | Method of parking and control device, mobile unit and computer-readable medium | |
| CN112172793B (en) | Parking path planning method and device, vehicle and storage medium | |
| CN112492522B (en) | Control method for autonomous parking of vehicle | |
| CN112224198A (en) | Parking space parking method and device, vehicle and storage medium | |
| CN115503694B (en) | Autonomous learning-based memory parking path generation method and device and electronic equipment | |
| CN112406855A (en) | Automatic parking method and device, vehicle and storage medium | |
| CN110766962A (en) | Intelligent vehicle searching method, device and system based on unmanned aerial vehicle and server | |
| CN113724525B (en) | Automatic passenger-replacing patrol type parking method and system based on big data platform and storage device | |
| CN115042806B (en) | Method and device for displaying paths of passenger car parking and electronic equipment | |
| CN110794821B (en) | Vehicle-mounted control device, field end positioning device, vehicle control system and vehicle | |
| CN113345118B (en) | Parking charge management method, system and storage medium | |
| CN115424468A (en) | Parking stall detecting system based on many cameras fuse | |
| CN116762094A (en) | Data processing method and device |
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 |