CN114464007B

CN114464007B - Unmanned aerial vehicle-based smart city parking monitoring method and system and cloud platform

Info

Publication number: CN114464007B
Application number: CN202210375664.0A
Authority: CN
Inventors: 杨翰翔; 赖晓俊
Original assignee: Shenzhen Lianhe Intelligent Technology Co ltd
Current assignee: Shenzhen Lianhe Intelligent Technology Co ltd
Priority date: 2022-04-11
Filing date: 2022-04-11
Publication date: 2022-07-05
Anticipated expiration: 2042-04-11
Also published as: CN114464007A

Abstract

The invention provides a smart city parking monitoring method, a smart city parking monitoring system and a cloud platform based on an unmanned aerial vehicle, which are characterized in that by receiving a parking navigation monitoring request sent by a user through a vehicle-mounted electronic map, obtaining a target parking range according to the parking target position information included in the parking navigation monitoring request, obtaining a target unmanned aerial vehicle for monitoring parking of the target parking range by a farmer, then sending a parking monitoring navigation instruction to the target unmanned aerial vehicle, receiving an aerial photography monitoring image which is fed back by the unmanned aerial vehicle according to the parking monitoring navigation instruction and aims at the target parking range, and finally obtaining at least one target parking space according to the aerial photography monitoring image of the target parking range, and parking monitoring and navigation are carried out on the user through the vehicle-mounted electronic map according to the position information of at least one target parking space and the current position information of the user. The intelligent city parking monitoring system can realize parking monitoring and intelligent navigation of the intelligent city by combining the unmanned aerial vehicle with the vehicle-mounted electronic map.

Description

Unmanned aerial vehicle-based smart city parking monitoring method and system and cloud platform

Technical Field

The invention relates to the technical field of smart city monitoring and unmanned aerial vehicles, in particular to a smart city parking monitoring method and system based on an unmanned aerial vehicle and a cloud platform.

Background

At present, with the continuous rising of the automobile holding capacity of each large city, the urban traffic problem gradually becomes an increasingly important civil problem, and for example, the problems of traffic jam, parking space shortage and the like are all more concerned by people. In order to facilitate traveling and planning a traveling route, more and more electronic maps are adopted for real-time traveling navigation by users during traveling. In addition, when a user goes to a destination which is not familiar well, a problem which is relatively concerned by many users is a parking problem, and most of the existing electronic maps can only provide parking space data around the destination in a general manner, but cannot realize a specific parking space real-time monitoring and navigation function.

Further, Unmanned Aerial Vehicles (UAVs) are also known as drones. With the rapid development of unmanned flight technology, consumer unmanned aerial vehicles are widely applied in various industries and used for replacing people to execute corresponding work. Along with the continuous acceleration of wisdom city process, unmanned aerial vehicle is also extensively promoted in the application in wisdom city field. For example, unmanned aerial vehicle is used for various fields such as wisdom urban traffic control, wisdom urban environment monitoring and commander, automatic food delivery, wisdom urban commodity circulation, very big having made things convenient for people daily work and life, makes the city become more and more "intellectuality" simultaneously.

On the premise of the above, the application of the unmanned aerial vehicle to parking monitoring and navigation in the smart city will also become a major direction for the future smart city application, and therefore how to combine the unmanned aerial vehicle to achieve smart parking monitoring and navigation in the smart city is an important technical problem to be solved in the field.

Disclosure of Invention

In order to solve the above problem, in a first aspect, an embodiment of the present invention provides a smart city parking monitoring method based on an unmanned aerial vehicle, which is applied to a cloud platform of a smart city parking monitoring system, where the smart city parking monitoring system further includes the unmanned aerial vehicle in communication connection with the cloud platform, and the cloud platform is further used in communication connection with a user terminal to provide a vehicle-mounted electronic map service for a user, and the method includes:

receiving a parking navigation monitoring request sent by a user through a vehicle-mounted electronic map, wherein the parking navigation monitoring request comprises parking target position information;

acquiring a target parking range according to the parking target position information included in the parking navigation monitoring request and acquiring a target unmanned aerial vehicle for parking monitoring of the target parking range;

sending a parking monitoring navigation instruction to the target unmanned aerial vehicle, and receiving an aerial monitoring image which is fed back by the unmanned aerial vehicle according to the parking monitoring navigation instruction and aims at the target parking range;

and acquiring at least one target parking space according to the aerial monitoring image of the target parking range, and performing parking monitoring and navigation on the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user.

In a possible implementation manner of the first aspect, the obtaining at least one target parking space according to the aerial monitoring image of the target parking range includes:

performing image analysis on the aerial photography monitoring image to acquire significance identification information of a selected position in a non-occupied area of the target parking range, wherein the significance identification information comprises a plurality of identification information used for indicating parking space characteristics of the target parking range;

acquiring available parking spaces which are matched with the significance identification information and are positioned in the target parking range from a parking space information database obtained in advance according to the significance identification information of the selected position in the non-occupied area of the target parking range;

and acquiring at least one parking space from the available parking spaces in the target parking range as the target parking space.

In a possible implementation manner of the first aspect, the obtaining at least one parking space from the available parking spaces located in the target parking range as the target parking space includes:

respectively acquiring parking space position information of each available parking space from the parking space information database and acquiring current position information of the user;

calculating the driving distance between the user and each available parking space according to the parking space position information of each available parking space and the current position information of the user;

the available parking spaces are arranged in an ascending order according to the calculated driving distances corresponding to the available parking spaces respectively, two or more available parking spaces arranged in front are selected as target parking spaces according to an arrangement result, and the target parking spaces are added into a target parking bit sequence in sequence;

the monitoring and navigating the parking of the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user comprises the following steps:

a. sequentially selecting one target parking space as a current navigation parking space according to the arrangement sequence of the target parking spaces in the target parking bit sequence;

b. planning a navigation path from the current position of the user to the current navigation parking space through the vehicle-mounted electronic map according to the position information of the current navigation parking space;

c. before the user drives to the current navigation parking space, controlling the target unmanned aerial vehicle to monitor the current navigation parking space in real time and acquiring an aerial photography monitoring image including the current navigation parking space fed back by the target unmanned aerial vehicle;

d. and c, judging whether the current navigation parking space is occupied or not according to the aerial monitoring image, when the current navigation parking space is occupied, selecting another target parking space from the target parking space sequence as the current navigation parking space, and returning to the step b until the user drives to the position corresponding to the current navigation parking space.

Based on a possible implementation manner of the first aspect, the obtaining, from a space information database obtained in advance, an available space that matches the saliency identification information and is located in the target parking range, according to the saliency identification information of the selected position in the non-occupied area of the target parking range includes:

clustering the acquired significance identification information of the selected position in the non-occupied area of the target parking range to obtain clustered significance identification information which respectively belong to different information clusters;

determining a significance description component corresponding to the significance identification information of each information cluster according to the significance identification information of each information cluster, and generating a significance description component matrix corresponding to a non-occupied area of the target parking range according to the significance description component corresponding to the significance identification information of each information cluster, wherein each information cluster corresponds to one significance description component matrix;

and matching the significance description component matrixes corresponding to the non-occupied areas of the target parking range with the significance description component matrixes corresponding to the different parking spaces respectively according to the significance description component matrixes corresponding to the non-occupied areas of the target parking range and the significance description component matrixes corresponding to the different parking spaces which are labeled in advance and recorded in a parking space information database, and acquiring the available parking spaces in the target parking range from the different parking spaces according to the matching result.

In a possible implementation manner of the first aspect, the method further includes:

the acquired parking space associated information of the available parking spaces in the target parking range is sent to the unmanned aerial vehicle corresponding to the target parking range, so that the unmanned aerial vehicle corresponding to the target parking range acquires the available parking spaces in the target parking range according to the parking space associated information, and real-time aerial photography monitoring is carried out on each available parking space;

the acquired parking space correlation information of the available parking spaces in the target parking range comprises acquired parking space navigation position information corresponding to the available parking spaces in the target parking range, so that the unmanned aerial vehicle can carry out real-time aerial photography monitoring on the corresponding available parking spaces according to the parking space navigation position information.

In a possible implementation manner of the first aspect, after the obtaining the saliency identification information of the selected position in the non-occupied area of the target parking range, the method further includes:

according to the information description corresponding to the significance identification information of the selected position in the non-occupied area of the target parking range, performing digital feature conversion on the significance identification information of the selected position in the non-occupied area of the target parking range to obtain the significance identification information of the selected position in the non-occupied area of the target parking range after the digital feature conversion;

the clustering the acquired significance identification information of the selected position in the non-occupied area of the target parking range to obtain the clustered significance identification information comprises the following steps:

clustering the significance identification information of the selected position in the non-occupied area of the target parking range after the digital characteristic conversion to obtain the clustered significance identification information;

the method further comprises the following steps:

judging whether the information description corresponding to the significance identification information of the selected position in the non-occupied area of the target parking range meets a preset description rule or not;

and if the information description corresponding to the significance identification information of the selected position in the non-occupied area of the target parking range does not meet the preset description rule, optimizing the information description corresponding to the significance identification information of the selected position in the non-occupied area of the target parking range according to the preset optimization rule to obtain the optimized information description corresponding to the significance identification information of the selected position in the non-occupied area of the target parking range.

Based on a possible implementation manner of the first aspect, the clustering the obtained significant identification information at the selected position in the non-occupied area of the target parking range to obtain clustered significant identification information includes:

clustering the acquired significance identification information of the selected position in the non-occupied area of the target parking range by taking each selected parking space area in the non-occupied area of the target parking range as a clustering basis of information clustering, taking the significance identification information belonging to the same selected parking space area as a cluster to obtain clustered significance identification information, and further obtaining clustered significance identification information corresponding to each selected parking space area;

wherein, the matching the significance description component matrix corresponding to the non-occupied area of the target parking range with the significance description component matrices corresponding to the different parking spaces respectively according to the significance description component matrix corresponding to the non-occupied area of the target parking range and the significance description component matrices corresponding to the different parking spaces labeled in advance and recorded in the parking space information database comprises:

according to the significance description component matrix corresponding to the non-occupied area of the target parking range and significance description component matrices corresponding to a plurality of different parking spaces which are labeled in advance and recorded in a parking space information database, determining the matching degrees between the significance description component matrix corresponding to the non-occupied area of the target parking range and the significance description component matrices corresponding to the plurality of different parking spaces which are labeled in advance and recorded in the parking space information database respectively through a preset matching degree calculation mode, and obtaining a matching result according to the calculated matching degrees.

Based on a possible implementation manner of the first aspect, the matching, according to the saliency description component matrix corresponding to the non-occupied area of the target parking range and the saliency description component matrix corresponding to a plurality of different parking spaces labeled in advance and recorded in the parking space information database, the saliency description component matrix corresponding to the non-occupied area of the target parking range with the saliency description component matrices corresponding to the plurality of different parking spaces respectively, and acquiring, according to a matching result, an available parking space located in the target parking range from the plurality of different parking spaces includes:

acquiring current position information of a user according to the parking navigation monitoring request;

acquiring a plurality of parking spaces with preset parking occupation marks from the parking space information database as candidate parking spaces according to the current position information and the parking target position information;

sequencing the candidate parking spaces according to the distance between the parking space position information corresponding to each candidate parking space and the current position information of the user to obtain a candidate parking space sequence;

sequentially traversing each candidate parking space from the first candidate parking space of the candidate parking bit sequence according to the arrangement sequence of each candidate parking space in the candidate parking bit sequence;

for the candidate parking space traversed each time, matching the significance description component matrix corresponding to the candidate parking space with each significance description component matrix corresponding to the non-occupied area of the target parking range respectively, and taking the candidate parking space matched with the significance description component matrix corresponding to any one non-occupied area as the available parking space;

judging whether the number of the currently determined available parking spaces reaches a preset number, finishing the traversing operation of the candidate parking spaces when the number of the currently determined available parking spaces reaches the preset number, and continuously traversing the next candidate parking space if the number of the currently determined available parking spaces does not reach the preset number;

obtaining historical parking monitoring navigation data for performing parking monitoring navigation for different users within a preset historical time period, wherein the historical parking monitoring navigation data comprises statistical information of a current navigation parking space used by a navigation path planned by each user in each different parking monitoring navigation process corresponding to the target parking range, and the statistical information comprises the number of the used navigation parking spaces in each parking monitoring navigation process;

taking the maximum number of used navigation parking spaces in each planned navigation path as the preset number; or, the average number of used navigation parking spaces in each planned navigation path is taken as the preset number.

On the basis of the above, the preset parking occupancy flag may be a flag indicating that the corresponding parking space is not occupied by other vehicles, and may be preset flag information, for example, a flag indicating that the corresponding parking space is not occupied by other vehicles may be represented by 0, and a flag indicating that the corresponding parking space is occupied by 1. On this basis, the present embodiment may further include the following.

And after the user drives to the position of the target parking space, controlling the unmanned aerial vehicle to carry out aerial photography monitoring on the target position, judging whether the target parking space is occupied or not according to an aerial photography monitoring image fed back by the unmanned aerial vehicle, updating parking occupation identification corresponding to the target parking space in the parking space information database when the target parking space is occupied, for example, updating other identification different from the preset parking occupation identification, and correspondingly storing vehicle information occupying the target parking space.

In addition, the cloud platform can control the unmanned aerial vehicle to monitor the vehicles within the target parking range, and when the target vehicle is monitored to leave the corresponding parking space, the vehicle information of the target vehicle recorded in the parking space information database is deleted, and meanwhile, the parking occupation identification of the target parking space, which is stored correspondingly to the target vehicle, is updated to the preset parking occupation identification.

In a second aspect, an embodiment of the present invention further provides a smart city parking monitoring system based on an unmanned aerial vehicle, where the smart city parking monitoring system includes a cloud platform and a plurality of unmanned aerial vehicles in communication with the cloud platform, and the cloud platform includes:

the system comprises a request module, a parking navigation monitoring module and a parking navigation monitoring module, wherein the request module is used for receiving a parking navigation monitoring request sent by a user through a vehicle-mounted electronic map, and the parking navigation monitoring request comprises parking target position information;

the acquisition module is used for acquiring a target parking range according to the parking target position information included in the parking navigation monitoring request and acquiring a target unmanned aerial vehicle for parking monitoring of the target parking range;

the monitoring module is used for sending a parking monitoring navigation instruction to the target unmanned aerial vehicle and receiving an aerial monitoring image which is fed back by the unmanned aerial vehicle according to the parking monitoring navigation instruction and aims at the target parking range;

and the navigation module is used for acquiring at least one target parking space according to the aerial monitoring image of the target parking range, and carrying out parking monitoring and navigation on the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user.

In a third aspect, an embodiment of the present invention further provides a cloud platform, where the cloud platform is respectively in communication connection with a plurality of unmanned aerial vehicles for respectively performing aerial photography monitoring on target monitoring occasions, and the cloud platform includes a processor and a machine-readable storage medium, where the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions, or codes, and the processor is used to execute the programs, instructions, or codes in the machine-readable storage medium, so as to implement the foregoing method.

In summary, the smart city parking monitoring method, system and cloud platform based on the unmanned aerial vehicle provided by the embodiment of the invention receive the parking navigation monitoring request sent by the user through the vehicle-mounted electronic map, obtaining a target parking range according to the parking target position information included in the parking navigation monitoring request, obtaining a target unmanned aerial vehicle for parking monitoring of the target parking range by a farmer, then sending a parking monitoring navigation instruction to the target unmanned aerial vehicle, receiving an aerial photographing monitoring image which is fed back by the unmanned aerial vehicle according to the parking monitoring navigation instruction and aims at the target parking range, and finally obtaining at least one target parking space according to the aerial photographing monitoring image of the target parking range, and performing parking monitoring and navigation on the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user. So, can realize the parking control and the intelligent navigation in wisdom city with the mode that unmanned aerial vehicle and on-vehicle electronic map combined together, can realize accurate parking stall control and accurate parking navigation to specific parking stall, very big convenience of customers's use promotes user's use impression and promotes wisdom ization level and degree in wisdom city simultaneously.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic flow chart of a smart city parking monitoring method based on an unmanned aerial vehicle according to an embodiment of the present invention.

Fig. 2 is a schematic application environment diagram of a smart city parking monitoring system based on an unmanned aerial vehicle according to an embodiment of the present invention.

Fig. 3 is a flowchart illustrating sub-steps included in step S400 in fig. 1.

Fig. 4 is a schematic structural diagram of a cloud platform for implementing the smart city parking monitoring method based on the unmanned aerial vehicle according to the embodiment of the present invention.

Fig. 5 is a functional block diagram of the parking monitoring navigation device in fig. 4.

Detailed Description

Referring to fig. 1, fig. 1 is a schematic flow chart of a smart city parking monitoring method based on an unmanned aerial vehicle according to an embodiment of the present invention. In the embodiment of the present invention, as shown in fig. 2, the method may be implemented by a smart city parking monitoring system 100 based on an unmanned aerial vehicle. In this embodiment, the smart city parking monitoring system 100 based on unmanned aerial vehicles may include a cloud platform 11 and a plurality of unmanned aerial vehicles 12 communicatively connected to the cloud platform 11. In this embodiment, cloud platform 11 is used for managing and dispatching each unmanned aerial vehicle 12, each unmanned aerial vehicle 12 is in the realization is respectively carried out the monitoring of taking photo by plane to the target monitoring occasion under cloud platform 11's dispatch control or mutually support, for example carry out the control of taking photo by plane in the parking stall to the wisdom parking area of the difference that sets up in the wisdom city for the wisdom control in cooperation cloud platform realization parking stall is used for carrying out intelligent parking navigation to the user. In this embodiment, the cloud platform 11 may be a service platform that is set up according to a smart city and is used for performing remote communication with a plurality of unmanned aerial vehicles 12 in a set monitoring area to perform remote control and scheduling on the unmanned aerial vehicles 12, and may provide an electronic map service for a user at the same time. The cloud platform 11 may be, but is not limited to, a server, a computer monitoring area, a cloud service center, a machine room control center, a cloud platform, and other monitoring areas that are established and provided by an electronic map service provider and have communication control capability and big data analysis capability. The people flow monitoring terminal 13 may be a computer device disposed in a corresponding monitoring area for communicating with the unmanned aerial vehicle 12 and controlling the unmanned aerial vehicle 12.

In the following, the smart city parking monitoring method based on the unmanned aerial vehicle of the above method is described in detail with reference to the accompanying drawings, in this embodiment, the method includes the following steps S100-S400, which are exemplarily described as follows.

Step S100, receiving a parking navigation monitoring request sent by a user through a vehicle-mounted electronic map, wherein the parking navigation monitoring request comprises parking destination position information and current position information of the user.

In this embodiment, the vehicle-mounted electronic map may be any type of electronic map currently in a vehicle of a user, for example, the vehicle-mounted electronic map may be an electronic map installed on a vehicle, or an electronic map installed on a mobile device (such as a mobile phone, a tablet computer, and the like) carried by the user. The user can start the vehicle-mounted electronic map at any time in the driving process and input a destination required to be reached for map navigation. In the process of navigation, parking navigation can be performed through operation option selection on the vehicle-mounted electronic map, after the parking space navigation is selected, the vehicle-mounted electronic map can automatically generate the parking navigation monitoring request and feed back the parking navigation monitoring request to a background (namely a cloud platform) of the vehicle-mounted electronic map in real time, and when the parking navigation monitoring request is generated, current position information of a user and a destination set by the user during navigation can be automatically captured through the vehicle-mounted electronic map to serve as parking destination position information, or a position required to be parked and input by the user at present can be obtained to serve as the parking destination information.

Without loss of generality, the parking monitoring and navigation service supported by the cloud platform may be limited to a part of specific areas of the smart city, and when the parking destination position set by the user is not in the corresponding specific area, the user may be directly prompted that the parking monitoring and navigation service is not supported by the current position, which may be specifically determined according to actual implementation conditions.

Step S200, a target parking range is obtained according to the parking target position information included in the parking navigation monitoring request, and a target unmanned aerial vehicle for parking monitoring of the target parking range is obtained.

In this embodiment, a corresponding target parking range may be obtained according to the parking destination position information, for example, a specific city area including the parking destination position information is used as the target parking range. Correspondingly, in order to enable the corresponding target parking range to support parking monitoring navigation service, one or more unmanned aerial vehicles can be arranged in the corresponding target parking range to be used for parking monitoring of the target parking range and assisting the cloud platform in parking space navigation. Based on this, when receiving the parking navigation monitoring request, the cloud platform obtains the target unmanned aerial vehicle corresponding to the corresponding target parking range.

And step S300, sending a parking monitoring navigation instruction to the target unmanned aerial vehicle, and receiving an aerial photography monitoring image which is fed back by the unmanned aerial vehicle according to the parking monitoring navigation instruction and aims at the target parking range.

In this embodiment, when obtaining corresponding target parking scope, the cloud platform can send to corresponding target unmanned aerial vehicle parking control navigation instruction, unmanned aerial vehicle is receiving when parking control navigation instruction, can carry out the aerial photograph control and feed back corresponding aerial photograph monitoring image in real time for the cloud platform in corresponding target parking scope, wherein, the aerial photograph monitoring image of feedback can be that unmanned aerial vehicle aims at with different aerial photograph gesture, aerial photograph angle, aerial photograph direction each region in the target parking scope carries out the aerial photograph and obtains continuous or discrete aerial photograph monitoring image frame.

And S400, acquiring at least one target parking space according to the aerial monitoring image of the target parking range, and performing parking monitoring and navigation on the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user.

In summary, in the embodiment of the present invention, a parking navigation monitoring request sent by a user through a vehicle-mounted electronic map is received, a target parking range is obtained according to position information of a parking target included in the parking navigation monitoring request, a target unmanned aerial vehicle for monitoring parking of a farmer in the target parking range is obtained, a parking monitoring navigation instruction is sent to the target unmanned aerial vehicle, an aerial photograph monitoring image fed back by the unmanned aerial vehicle according to the parking monitoring navigation instruction and directed to the target parking range is received, finally, at least one target parking space is obtained according to the aerial photograph monitoring image of the target parking range, and parking monitoring and navigation are performed on the user through the vehicle-mounted electronic map according to position information of the at least one target parking space and current position information of the user. So, can realize the parking control and the intelligent navigation in wisdom city with the mode that unmanned aerial vehicle and on-vehicle electronic map combined together, can realize accurate parking stall control and accurate parking navigation to specific parking stall, very big convenience of customers's use promotes user's use impression and promotes wisdom ization level and degree in wisdom city simultaneously.

Specific implementations of the above steps are exemplarily described below.

First, in step S400, as shown in fig. 3, a possible implementation manner of obtaining at least one target parking space according to the aerial surveillance image of the target parking range may include the following steps S4001 to S4003, which are described in detail as follows.

Step S4001, performing image analysis on the aerial photography monitoring image, and acquiring significance identification information of a selected position in a non-occupied area of the target parking range, wherein the significance identification information includes a plurality of identification information used for indicating parking space characteristics of the target parking range.

In this embodiment, the selected position may be, but is not limited to, a position close to a roadside, a position located in a rectangular frame, and the like, which may be used to calibrate the relevant position information of the parking space, and may be determined according to the actual situation. The non-occupied area may be a relevant area not including the object (e.g., vehicle) identified by the object identification (e.g., vehicle contour identification) method two.

Step S4002, according to the significance identification information of the selected position in the non-occupied area of the target parking range, obtaining an available parking space which is matched with the significance identification information and is located in the target parking range from a parking space information database obtained in advance.

Step S4003, obtaining at least one parking space from the available parking spaces located in the target parking range as the target parking space.

Step S4002 can be realized by the steps of S4021 to S4023 described below, and is exemplarily described as follows.

Step S4021, clustering the acquired significance identification information of the selected position in the non-occupied area of the target parking range to obtain the clustered significance identification information respectively belonging to different information clusters.

For example, in one possible implementation, the significant identification information may be parking space direction information, parking space size information, parking space number identification information, special parking space identification, female parking space identification, and the like of a parking space, which may be determined according to the requirements of intelligent parking monitoring and navigation. In addition, one information cluster may be the saliency flag information corresponding to one parking space, for example, the saliency flag information included in one rectangular frame is taken as one cluster, and then the available parking space may be determined according to the saliency flag information corresponding to each information cluster for performing parking monitoring and navigation services.

In detail, in step S4021, this embodiment may use each selected parking space region in the non-occupied region of the target parking range as a clustering basis for information clustering, cluster the obtained significant identification information at the selected position in the non-occupied region of the target parking range, use the significant identification information belonging to the same selected parking space region as a cluster, obtain clustered significant identification information, and further obtain clustered significant identification information corresponding to each selected parking space region. Therefore, the significance identification information respectively corresponding to each selected parking space region can be obtained, and the information matching of the relevant information (such as the significance description component matrix) of each corresponding parking space region and the significance description component matrix which is labeled in advance and is recorded in the parking space information database and corresponds to a plurality of different parking spaces is facilitated.

Further, in a possible real-time manner, after obtaining the saliency identification information of the selected position in the non-occupied area of the target parking range, the implementation may perform digital feature conversion on the saliency identification information of the selected position in the non-occupied area of the target parking range according to the information description corresponding to the saliency identification information of the selected position in the non-occupied area of the target parking range, so as to obtain the saliency identification information of the selected position in the non-occupied area of the target parking range after the digital feature conversion.

For example, the information description corresponding to the saliency identification information may be text description information or character description information corresponding to each saliency identification information. The digital conversion method may be, for example, mapping the corresponding information description into the corresponding digital features according to a set digital mapping rule, and finally converting the corresponding saliency identification information into the corresponding digital features, so that the later information comparison and matching are faster. For example, the parking space size (including the length and width attribute) of the parking space corresponding to the non-occupied area, the parking space specific information (such as female specific information), and the like may be mapped into corresponding digital features according to the set digital mapping rule, and then the corresponding digital features are arranged and combined according to the set information arrangement rule to obtain the significance identification information of the selected position in the non-occupied area of the target parking range after the digital features are converted. Then, clustering the obtained significance identification information of the selected position in the non-occupied area of the target parking range to obtain clustered significance identification information, which can be clustering the significance identification information of the selected position in the non-occupied area of the target parking range after digital feature conversion to obtain clustered significance identification information.

Further, on the basis of the above content, in this embodiment, it may also be determined whether the information description corresponding to the saliency identification information of the selected position in the non-occupied area of the target parking range meets a preset description rule; and if the information description corresponding to the significance identification information of the selected position in the non-occupied area of the target parking range does not meet the preset description rule, optimizing the information description corresponding to the significance identification information of the selected position in the non-occupied area of the target parking range according to the preset optimization rule to obtain the optimized information description corresponding to the significance identification information of the selected position in the non-occupied area of the target parking range.

For example, the saliency identification information of the corresponding parking spaces in some non-occupied areas may have information missing or the like, so that when information matching comparison is performed on the saliency description component matrixes corresponding to a plurality of different parking spaces in the parking space information database, information matching is abnormal due to abnormality such as information missing. Accordingly, the corresponding optimization rule may include supplement for missing description information (e.g., supplement with preset blank information), standardized conversion or unification of information presentation formats of the description information, and the like.

Step S4022, determining a significance description component corresponding to the significance identification information of each information cluster according to the significance identification information of each information cluster, and generating a significance description component matrix corresponding to the unoccupied area of the target parking range according to the determined significance description component corresponding to the significance identification information of each information cluster.

For example, in this embodiment, for example, the restrictive description components corresponding to the saliency flag information respectively corresponding to different information clusters may be sequentially added to the set feature vector matrix according to the set information aggregation rule, so as to obtain the saliency description component matrix. For example, information aggregation may be performed according to a matrix data format of a saliency description component matrix corresponding to a plurality of different parking spaces labeled and recorded in advance in a parking space information database, so as to facilitate subsequent feature matching and comparison operations.

Step S4023, according to the significance description component matrix corresponding to the non-occupied area of the target parking range and the significance description component matrices corresponding to a plurality of different parking spaces labeled in advance and recorded in the parking space information database, matching the significance description component matrix corresponding to the non-occupied area of the target parking range with the significance description component matrices corresponding to the plurality of different parking spaces respectively, and according to the matching result, acquiring available parking spaces located in the target parking range from the plurality of different parking spaces.

Further, in this embodiment, the saliency description component matrix may be a set of a plurality of different description components, and each matrix element may correspond to one description component. In order to find out available parking spaces conveniently, the significance description component matrixes corresponding to the different parking spaces in the parking space information database and the significance description components corresponding to the significance identification information of the information cluster have the same data format or data presentation mode. The data description component may be a representation of a feature vector with digitized information, and is not particularly limited.

In a possible implementation manner, the cloud platform may determine, according to the saliency description component matrix corresponding to the non-occupied area of the target parking range and the saliency description component matrix corresponding to the plurality of different parking spaces labeled in advance and recorded in the parking space information database, matching degrees between the saliency description component matrix corresponding to the non-occupied area of the target parking range and the saliency description component matrices corresponding to the plurality of different parking spaces labeled in advance and recorded in the parking space information database, respectively, through a preset matching degree calculation manner, and obtain a matching result according to the calculated matching degree. For example, the preset matching degree calculation method may be a matching degree calculation method based on a pearson correlation coefficient, a cosine distance, an euclidean distance, or the like, to calculate the matching degree, thereby obtaining a corresponding matching result.

In this embodiment, when an available parking space in the target parking range is acquired, the cloud platform may further send the acquired parking space association information of the available parking space in the target parking range to the unmanned aerial vehicle corresponding to the target parking range, so that the unmanned aerial vehicle corresponding to the target parking range acquires the available parking space in the target parking range according to the parking space association information, and performs real-time aerial photography monitoring on each available parking space. The acquired parking space correlation information of the available parking spaces in the target parking range comprises acquired parking space navigation position information corresponding to the available parking spaces in the target parking range, so that the unmanned aerial vehicle can carry out real-time aerial photography monitoring on the corresponding available parking spaces according to the parking space navigation position information. The parking space navigation position information can be longitude and latitude information of a corresponding parking space, and the unmanned aerial vehicle can be positioned to the corresponding parking space according to a pre-constructed parking space positioning model so as to realize aerial photography monitoring on the parking space.

Further, in some possible cases, there may be a plurality of available parking spaces in the target parking range, and if the relevant information of each parking space is subjected to corresponding matching calculation, a plurality of computing resources of the cloud platform may be wasted, based on which, in the present embodiment, in the step S4023, according to the saliency description component matrix corresponding to the non-occupied area of the target parking range and the saliency description component matrices corresponding to a plurality of different parking spaces labeled and recorded in the parking space information database in advance, the saliency description component matrices corresponding to the non-occupied area of the target parking range are respectively matched with the saliency description component matrices corresponding to the plurality of different parking spaces, and according to a matching result, an available parking space located in the target parking range is obtained from the plurality of different parking spaces, specific implementations may include the following steps, which are exemplary described below.

(1) And acquiring the current position information of the user according to the parking navigation monitoring request.

(2) And acquiring a plurality of parking spaces with preset parking occupation marks from the parking space information database as candidate parking spaces according to the current position information and the parking target position information.

(3) And sequencing the candidate parking spaces according to the distance between the parking space position information corresponding to each candidate parking space and the current position information of the user to obtain a candidate parking space sequence.

(4) Sequentially traversing each candidate parking space from the first candidate parking space of the candidate parking bit sequence according to the arrangement sequence of each candidate parking space in the candidate parking bit sequence;

(5) for the candidate parking space traversed each time, matching the significance description component matrix corresponding to the candidate parking space with each significance description component matrix corresponding to the non-occupied area of the target parking range respectively, and taking the candidate parking space matched with the significance description component matrix corresponding to any one non-occupied area as the available parking space;

(6) and judging whether the number of the currently determined available parking spaces reaches a preset number, finishing the traversing operation of the candidate parking spaces when the number of the currently determined available parking spaces reaches the preset number, and continuously traversing the next candidate parking space if the number of the currently determined available parking spaces does not reach the preset number.

Therefore, based on the above content, only a part of traversal calculation needs to be performed on the available parking spaces, and when the determined number of the available parking spaces reaches the preset number, the traversal can be stopped, so that the calculation amount of the cloud platform is reduced. The preset number may be obtained from statistical information of the number of available parking spaces used historically in the parking path navigation planning process for different users in the same parking navigation. For example, in a possible real-time manner, the method of this embodiment further includes a step of determining the preset number, which is exemplarily described as follows:

In this embodiment, the preset time period may be set according to actual conditions, and may be a time period within a week or a month before the current time node, for example. Therefore, through acquiring historical parking monitoring navigation data in the historical time period, the number of available parking spaces required to be used when navigation paths are planned for different users in corresponding target parking ranges in the historical time period can be analyzed, on one hand, it can be guaranteed that the users can be guided to the available parking spaces possibly used for parking monitoring and navigation as far as possible, on the other hand, the calculation amount when the cloud platform analyzes the available parking spaces is limited and restricted through the preset number set by the historical data, the calculation amount of the cloud platform can be reduced, and the efficiency of monitoring and navigation is improved.

In this embodiment, for step S4003, in a possible real-time manner, parking space position information of each available parking space may be first obtained from the parking space information database, and current position information of the user may be obtained; then, calculating the driving distance between the user and each available parking space according to the parking space position information of each available parking space and the current position information of the user; and finally, selecting at least one available parking space as the target parking space according to the calculated driving distance corresponding to each available parking space. For example, the available parking spaces may be arranged in an ascending order according to the driving distance, and then a preset number of available parking spaces in the front of the ascending order are selected as the target parking spaces, or an available parking space with the smallest driving distance may be used as the target parking space.

Preferably, in a possible real-time manner, the selecting at least one available parking space as the target parking space according to the calculated driving distance corresponding to each available parking space may include: and arranging the available parking spaces in an ascending order according to the calculated driving distances corresponding to the available parking spaces, selecting two or more available parking spaces arranged in front as target parking spaces according to an arrangement result, and adding the target parking spaces into a target parking bit sequence in sequence.

Based on this, in step S400, the monitoring and navigating of parking for the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user may further include the following steps a to d, which are exemplarily described as follows.

a. And sequentially selecting one target parking space as the current navigation parking space according to the arrangement sequence of the target parking spaces in the target parking bit sequence.

b. And planning a navigation path from the current position of the user to the current navigation parking space through the vehicle-mounted electronic map according to the position information of the current navigation parking space.

c. And before the user drives the current navigation parking space, controlling the target unmanned aerial vehicle to monitor the current navigation parking space in real time and acquiring an aerial monitoring image including the current navigation parking space fed back by the target unmanned aerial vehicle.

d. And c, judging whether the current navigation parking space is occupied according to the aerial monitoring image, when the current navigation parking space is occupied, selecting another target parking space from the target parking space sequence as the current navigation parking space, and returning to the step b until the user drives to the position corresponding to the current navigation parking space.

For example, when the distance range between the user and the current navigation parking space is within the preset distance range, the user may be considered to have traveled to the position corresponding to the current navigation parking space.

So, through above-mentioned mode, before the user reachs specific parking position, accessible unmanned aerial vehicle is real-time to the current navigation parking stall of confirming and is monitored, when this current navigation parking stall is taken up by other users, still can be timely pass through other target parking stalls in the target parking bit sequence plan the navigation route of line for the user to guide the accurate position department of traveling to corresponding target parking stall of user. It will be appreciated that this applies to situations where the target parking space is located on a different adjacent road segment or at a different parking orientation.

As shown in fig. 4, an architectural schematic diagram of a cloud platform 11 provided in the embodiment of the present invention for implementing the foregoing method is provided. In this embodiment, the cloud platform 11 may include a parking monitoring navigation device 110, a machine-readable storage medium 120, and a processor 130.

In this embodiment, the machine-readable storage medium and the processor may be located in the cloud platform 11 and separately provided. The machine-readable storage medium 120 may also be independent of the cloud platform 11 and accessed by the processor 130. The parking monitoring navigation device 110 may include a plurality of functional modules stored in a machine-readable storage medium, such as software functional modules included in the parking monitoring navigation device 110. When the processor executes the software function module in the parking monitoring navigation device 110, the block chain big data processing method provided by the foregoing method embodiment is realized.

In this embodiment, the cloud platform 11 may include one or more processors. The processor may process information and/or data related to the service request to perform one or more of the functions described in this disclosure. In some embodiments, a processor may include one or more processing engines (e.g., a single-core processor or a multi-core processor). For example only, the processor may include one or more hardware processors such as one of a central processing unit CPU, an application specific integrated circuit ASIC, an application specific instruction set processor ASIP, a graphics processor GPU, a physical arithmetic processing unit PPU, a digital signal processor DSP, a field programmable gate array FPGA, a programmable logic device PLD, a controller, a microcontroller unit, a reduced instruction set computer RISC, a microprocessor, or the like, or any combination thereof.

A machine-readable storage medium may store data and/or instructions. In some embodiments, a machine-readable storage medium may store the obtained data or material. In some embodiments, a machine-readable storage medium may store data and/or instructions for execution or use by the cloud platform 11, which the cloud platform 11 may execute or use to implement the example methods described herein. In some embodiments, a machine-readable storage medium may include mass storage, removable storage, volatile read-write memory, read-only memory ROM, the like, or any combination of the foregoing. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memories may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read-write memory may include random access memory RAM. Exemplary random access memories may include dynamic RAM, double-rate synchronous dynamic RAM, static RAM, thyristor RAM, zero-capacitance RAM, and the like. Exemplary ROMs may include masked ROMs, programmable ROMs, erasable programmable ROMs, electrically erasable programmable ROMs, compact disk ROMs, digital versatile disk ROMs, and the like.

The parking monitoring navigation device 110 included in the cloud platform 11 may include one or more software functional modules. The software functional modules may be a program, instructions stored in the machine-readable storage medium, which when executed by a corresponding processor, are configured to implement the above-described method, e.g., when executed by a processor of a drone, or when executed by the cloud platform, are configured to implement the above-described method steps performed by the drone, or the cloud platform.

As shown in fig. 5, the parking monitoring navigation device 110 may include a request module 1101, an acquisition module 1102, a monitoring module 1103, and a navigation module 1104.

The request module 1101 is configured to receive a parking navigation monitoring request sent by a user through a vehicle-mounted electronic map, where the parking navigation monitoring request includes information of a parking destination.

The obtaining module 1102 is configured to obtain a target parking range according to the parking target position information included in the parking navigation monitoring request, and obtain a target unmanned aerial vehicle for performing parking monitoring on the target parking range.

And the monitoring module 1103 is configured to send a parking monitoring navigation instruction to the target unmanned aerial vehicle, and receive an aerial monitoring image of the unmanned aerial vehicle for the target parking range, which is fed back by the parking monitoring navigation instruction.

And the navigation module 1104 is configured to acquire at least one target parking space according to the aerial monitoring image of the target parking range, and perform parking monitoring and navigation on the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user.

Wherein the navigation module is further specifically configured to:

It should be noted that the requesting module 1101, the obtaining module 1102, the monitoring module 1103 and the navigation module 1104 may be respectively configured to perform the corresponding steps of S100 to S400 provided in the method embodiment of the present invention. For details of these modules, reference may be made to detailed embodiments of corresponding method steps, which are not described herein again.

In summary, the smart city parking monitoring method, system and cloud platform based on the unmanned aerial vehicle provided by the embodiments of the present invention receive the parking navigation monitoring request sent by the user through the vehicle-mounted electronic map, obtaining a target parking range according to the parking target position information included in the parking navigation monitoring request, obtaining a target unmanned aerial vehicle for parking monitoring of the target parking range by a farmer, then sending a parking monitoring navigation instruction to the target unmanned aerial vehicle, receiving an aerial photographing monitoring image which is fed back by the unmanned aerial vehicle according to the parking monitoring navigation instruction and aims at the target parking range, and finally obtaining at least one target parking space according to the aerial photographing monitoring image of the target parking range, and performing parking monitoring and navigation on the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user. So, can realize the parking control and the intelligent navigation in wisdom city with the mode that unmanned aerial vehicle and on-vehicle electronic map combined together, can realize accurate parking stall control and accurate parking navigation to specific parking stall, very big convenience of customers's use promotes user's use impression and promotes wisdom ization level and degree in wisdom city simultaneously.

While the invention has been described with reference to a particular embodiment, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Furthermore, the detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention, but is merely representative of selected embodiments of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims. Moreover, all other embodiments that can be made available by a person skilled in the art without inventive step based on the embodiments of the present invention shall fall within the scope of protection of the present invention.

Claims

1. The utility model provides a smart city parking monitoring method based on unmanned aerial vehicle, is applied to smart city parking monitoring system's cloud platform, its characterized in that, smart city parking monitoring system still include with the unmanned aerial vehicle of cloud platform communication connection, the cloud platform still is used for providing on-vehicle electronic map service for the user with user terminal communication connection, the method includes:

acquiring at least one target parking space according to the aerial monitoring image of the target parking range, and performing parking monitoring and navigation on the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user;

the step of obtaining at least one target parking space according to the aerial monitoring image of the target parking range comprises the following steps:

acquiring at least one parking space from the available parking spaces in the target parking range as the target parking space;

the obtaining at least one parking space from the available parking spaces located in the target parking range as the target parking space includes:

d. judging whether the current navigation parking space is occupied or not according to the aerial photography monitoring image, when the current navigation parking space is occupied, selecting another target parking space from the target parking space sequence as the current navigation parking space, and returning to the step b until the user drives to the position corresponding to the current navigation parking space;

the acquiring, from a parking space information database obtained in advance, available parking spaces that are matched with the significance identification information and located in the target parking range, according to the significance identification information of the selected position in the non-occupied area of the target parking range, includes:

clustering the acquired significance identification information of the selected position in the non-occupied area of the target parking range to obtain clustered significance identification information respectively belonging to different information clusters;

2. The method of claim 1, further comprising:

3. The method of claim 1, wherein after obtaining the saliency identification information for the selected position in the non-occupied region of the target parking range, the method further comprises:

the method further comprises the following steps:

4. The method according to claim 1, wherein the clustering the acquired significant identification information at the selected position in the non-occupied area of the target parking range to obtain the clustered significant identification information respectively belonging to different information clusters comprises:

wherein, the matching, according to the significance description component matrix corresponding to the non-occupied area of the target parking range and the significance description component matrices corresponding to a plurality of different parking spaces labeled in advance and recorded in the parking space information database, the significance description component matrices corresponding to the non-occupied area of the target parking range with the significance description component matrices corresponding to the plurality of different parking spaces respectively includes:

5. The method according to any one of claims 1 to 4, wherein the matching, according to the saliency description component matrix corresponding to the non-occupied area of the target parking range and the saliency description component matrix corresponding to a plurality of different parking spaces labeled in advance and recorded in a parking space information database, the saliency description component matrix corresponding to the non-occupied area of the target parking range with the saliency description component matrix corresponding to the plurality of different parking spaces respectively, and acquiring an available parking space located in the target parking range from the plurality of different parking spaces according to a matching result includes:

wherein the preset number is obtained by:

6. The utility model provides a wisdom city monitoring system that parks based on unmanned aerial vehicle, a serial communication port, wisdom city monitoring system that parks include the cloud platform, with a plurality of unmanned aerial vehicles that the cloud platform communication links to each other, the cloud platform includes:

the system comprises a request module, a parking navigation monitoring module and a parking navigation monitoring module, wherein the request module is used for receiving a parking navigation monitoring request sent by a user through a vehicle-mounted electronic map, and the parking navigation monitoring request comprises parking destination position information;

the navigation module is used for acquiring at least one target parking space according to the aerial monitoring image of the target parking range, and performing parking monitoring and navigation on the user through the vehicle-mounted electronic map according to the position information of the at least one target parking space and the current position information of the user;

the acquiring of at least one target parking space according to the aerial monitoring image of the target parking range comprises:

7. A cloud platform, wherein the cloud platform is respectively in communication connection with a plurality of drones for respectively performing aerial monitoring on target monitoring occasions, and the cloud platform comprises a processor, a machine-readable storage medium, the machine-readable storage medium is connected with the processor, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, instructions or codes in the machine-readable storage medium to implement the method of any one of claims 1 to 5.