CN114491736B

CN114491736B - Floor dividing method and device, electronic equipment and storage medium

Info

Publication number: CN114491736B
Application number: CN202111646617.7A
Authority: CN
Inventors: 何素; 王梓里; 冯洁
Original assignee: Guangzhou Xiaopeng Autopilot Technology Co Ltd
Current assignee: Guangzhou Xiaopeng Motors Technology Co Ltd
Priority date: 2021-12-30
Filing date: 2021-12-30
Publication date: 2023-03-31
Anticipated expiration: 2041-12-30
Also published as: CN114491736A

Abstract

The embodiment of the application provides a floor dividing method and device, electronic equipment and a storage medium, and relates to the technical field of automatic driving. The method mainly comprises the steps of acquiring track points of a single track, wherein the track points are acquired according to a preset sequence; determining a plurality of variable slope points to be selected according to the track points; determining a plurality of target flat layers and target variable slope points corresponding to each target flat layer according to the variable slope points to be selected; the floor serial numbers of the target levels are respectively determined based on the target slope changing points corresponding to the target levels, floor division can be automatically completed according to the driving track, and high cost of manual floor division is saved. Compared with the condition that the efficiency and accuracy of floor division are low due to the fact that the parking lot is complex, the method can greatly improve the efficiency and accuracy of floor division. In addition, floor division is automatically and quickly completed, and the time for manually dividing floors is greatly shortened, so that the map building time of the whole parking lot map is greatly saved, and the user experience is improved.

Description

Floor dividing method and device, electronic equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of automatic driving, in particular to a floor dividing method and device, electronic equipment and a storage medium.

Background

A parking lot generally has a plurality of floors (including above-ground and below-ground), and the floors of the parking lot need to be divided in the process of building a map of the parking lot. At present, the floors of the parking lot are divided mainly according to manpower, so that the efficiency and the accuracy are low, and the cost is extremely high.

Disclosure of Invention

The embodiment of the application provides a floor dividing method and device, electronic equipment and a storage medium, so as to solve the problems.

In a first aspect, an embodiment of the present application provides a floor division method. The method mainly comprises the following steps: acquiring track points of the single track, which are acquired according to a preset sequence; determining a plurality of variable slope points to be selected according to the track points; determining a plurality of target flat layers and a target variable slope point corresponding to each target flat layer according to the variable slope points to be selected; and respectively determining the floor serial numbers of the target flat floors based on the target slope changing points corresponding to the target flat floors.

In a second aspect, an embodiment of the present application provides a floor dividing device. The device mainly comprises a track point acquisition module, a variable slope point determination module to be selected, a target variable slope point determination module and a floor sequence number determination module. The track point acquisition module is used for acquiring track points of a single track, which are acquired according to a preset sequence. And the variable slope point determination module to be selected is used for determining a plurality of variable slope points to be selected according to the track points. The target variable slope point determining module is used for determining a plurality of target flat layers and target variable slope points corresponding to each target flat layer according to the variable slope points to be selected. And the floor sequence number determining module is used for respectively determining the floor sequence numbers of a plurality of target flat floors based on the target slope changing points corresponding to each target flat floor.

In a third aspect, an embodiment of the present application provides an electronic device. The electronic device generally includes memory, one or more processors, and one or more applications. Wherein the one or more applications are stored in the memory and configured to, when invoked by the one or more processors, cause the one or more processors to perform the floor-dividing method provided by embodiments of the present application.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The computer readable storage medium has stored therein program code configured to, when invoked by a processor, cause the processor to perform the floor-dividing method provided by embodiments of the present application.

The embodiment of the application provides a floor dividing method and device, electronic equipment and a storage medium. The method mainly comprises the steps of acquiring track points of a single track, wherein the track points are acquired according to a preset sequence; determining a plurality of variable slope points to be selected according to the track points; determining a plurality of target flat layers and a target variable slope point corresponding to each target flat layer according to the variable slope points to be selected; the floor serial numbers of the target levels are respectively determined based on the target slope changing points corresponding to the target levels, floor division can be automatically completed according to the driving track, and high cost of manual floor division is saved. Compared with the situation that the efficiency and the accuracy rate of manual floor division are low due to the complex parking lot situation, the method can greatly improve the efficiency and the accuracy rate of floor division. In addition, through automatic, accomplishing the floor fast and dividing, can greatly shorten the time of artifical division floor to save the picture time of building of whole parking area map by a wide margin, and then improve user experience.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic view of an application scenario of a floor division method according to an embodiment of the present application.

Fig. 2 is a flowchart illustrating a floor dividing method according to an embodiment of the present application.

Fig. 3 is a flowchart illustrating a floor dividing method according to another embodiment of the present application.

Fig. 4 is a flowchart illustrating a step S270 included in a floor dividing method according to another embodiment of the present application.

Fig. 5 is a schematic flowchart of a step S280 included in a floor dividing method according to another embodiment of the present application.

FIG. 6 is a schematic diagram of an exemplary target leveling and target ramping point provided in another embodiment of the present application.

Fig. 7 is a flowchart illustrating a step S290 included in a floor dividing method according to another embodiment of the present application.

Fig. 8 is a block diagram of a floor partitioning device according to an embodiment of the present application.

Fig. 9 is a block diagram of an electronic device according to an embodiment of the present application.

Fig. 10 is a block diagram of a computer-readable storage medium according to an embodiment of the present disclosure.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

Parking lots usually include multiple floors above and/or below ground, where the ground floor is usually a flat floor on which vehicles enter the garage, the garages above the ground floor are usually referred to as above-ground garages, and the garages below the ground floor are usually referred to as underground garages. The floors between adjacent levels are called the walkways.

In the process of building a full-field map of a parking lot, floor division is a relatively advanced and indispensable step. At present, the floors of the parking lot are mainly divided manually. Due to the fact that various inaccurate factors exist in vehicle track data and the conditions of parking lots are very complex, the parking lots are difficult to check on the spot, the cost of purely manually producing parking lot maps is extremely high, and the efficiency and accuracy of building the parking lot maps are low.

The embodiment of the application provides a floor dividing method and device, electronic equipment and a storage medium, so as to solve the problems. Next, a brief description is given of an application scenario of the floor division method provided in the embodiment of the present application.

Referring to fig. 1, fig. 1 is a schematic view of an application scenario of a floor division method according to an embodiment of the present disclosure. The parking lot map production system 10 includes a vehicle 11 and a processing device 12. The vehicle 11 is connected to a processing device 12, and data exchange is possible between them. The vehicle 11 may be a gasoline vehicle, an electric vehicle, or the like, wherein the electric vehicle may be a pure electric vehicle, a hybrid vehicle, a fuel cell vehicle, or the like, and is not particularly limited herein. The processing device 12 may be a server, which may be a conventional server or a cloud server, and may also be other electronic devices with computing capability, and is not limited in particular herein. In some embodiments, the vehicle 11 may include the processing device 12, i.e., the processing device 12 may be disposed at the vehicle 11.

In some embodiments, the vehicle 11 may acquire the driving track of the vehicle 11 in real time through a camera; the trajectory of the vehicle 11 may also be acquired once at intervals of a preset time period (e.g., 0.3 seconds); the trajectory of the vehicle 11 may also be acquired once at a preset distance (e.g., 3 meters), which is not particularly limited herein. The vehicle 11 generates a map data file from the acquired trajectory, and reports the generated map data file to the processing device 12. The processing device 12 may automatically divide the floors of the parking lot according to the map data files reported by the vehicle 11 and generate a parking lot map based on the floor division results. In some embodiments, the parking lot map production system 10 may further include a mapping device (not shown), which may be a server. The processing device 12 may send the floor division results to a mapping device, which builds a parking lot map from the floor division results.

Next, a description will be given of a floor division method provided in an embodiment of the present application. It should be noted that, in the following description, the "previous" or "previous" in the embodiment of the present application refers to a track point or a gradient point to be selected in the previous acquisition order, and the "next" or "next" refers to a track point or a gradient point to be selected in the next acquisition order.

Referring to fig. 2, fig. 2 is a schematic flow chart illustrating a floor dividing method according to an embodiment of the present application. The floor dividing method can be applied to the parking lot map production system 10 as shown in fig. 1, and in particular, can be applied to the processing device 12. The floor division method includes the following steps S110 to S140.

And step S110, acquiring track points of the single track, which are acquired according to a preset sequence.

The single track refers to a single driving track of one vehicle. The track points collected according to the preset sequence may be track points collected sequentially according to the traveling direction of the vehicle.

In some embodiments, the vehicle may employ the camera to sequentially acquire track points of a travel track of the vehicle according to a travel direction of the vehicle, generate a map data file based on the acquired track points, and upload the map data file to the processing device. The map data file at least comprises track points of a driving track of the vehicle in the parking lot. The processing equipment acquires a map data file reported by the vehicle.

And step S120, determining a plurality of variable slope points to be selected according to the track points.

Wherein the grade change point may be a connection point connecting two floors.

In some embodiments, a track point is determined to be a candidate slope point if the track point satisfies the following condition: the forward type of the track point is a preset type and the backward type is not a preset type, or the forward type of the track point is not a preset type and the backward type is a preset type. The forward type can be used for representing the inclination degree of the track before the track point, and the backward type can be used for representing the inclination degree of the track after the track point. The preset type may be determined according to an actual algorithm design, and is not particularly limited herein. After the track point is determined as the variable slope point to be selected, the variable slope point to be selected can be added into the variable slope point list to be selected, so that the variable slope point to be selected can be processed uniformly in the following.

And step S130, determining a plurality of target flat layers and a target variable slope point corresponding to each target flat layer according to the plurality of variable slope points to be selected.

Wherein, each target flat layer can correspond to two target slope changing points.

In some embodiments, the variable slope points to be selected in the variable slope point list to be selected may be preprocessed to obtain a plurality of leveling layers and the variable slope points to be selected corresponding to each leveling layer; and combining the multiple flat layers to obtain a target flat layer.

In some embodiments, implementation of the pre-processing operation may include: and if the forward type and the backward type of the two variable points to be selected in the group of variable points to be selected are the same and the height difference of the two variable points to be selected is smaller than a first height difference threshold value, deleting one of the two variable points to be selected from the variable point list to be selected. And further, screening the remaining variable slope points to be selected to obtain a plurality of levels and the variable slope points to be selected corresponding to each level, wherein each level corresponds to two adjacent variable slope points to be selected, and the backward type of the former variable slope point to be selected is the preset type and the forward type of the latter variable slope point to be selected is the preset type in the two adjacent variable slope points to be selected corresponding to the same level. Particularly, if the backward type of the last variable slope point to be selected is the preset type, the last track point is added as the variable slope point to be selected.

In some embodiments, the implementation of merging multiple flat layers may include: calculating the height difference between the two adjacent flat layers, and searching the two adjacent flat layers with the minimum height difference; if the height difference of the two flat layers is not larger than a second height difference threshold value, combining the two flat layers; and if the height difference of the two leveling layers is larger than the second height difference threshold value, stopping the merging operation to obtain a plurality of target leveling layers and target gradient changing points corresponding to each target leveling layer. Wherein the second height difference threshold is greater than the first height difference threshold.

Step S140, respectively determining the floor serial numbers of a plurality of target flat floors based on the target slope changing points corresponding to the target flat floors.

In some embodiments, the depth of the target leveling may be calculated based on the target change points corresponding to the same target leveling, and the floor number of the target leveling may be determined according to the depth of the target leveling. In particular, the floor numbers of the aisle levels between adjacent target floors can also be determined from the floor numbers of the target floors.

In the floor dividing method provided by the embodiment of the application, the steps S110-S140 are mainly executed, the floor division can be automatically completed according to the driving track, and the high cost of manually dividing the floor is saved. Compared with the situation that the efficiency and the accuracy rate of manual floor division are low due to the complex parking lot situation, the floor division method provided by the embodiment of the application can greatly improve the efficiency and the accuracy rate of floor division. In addition, floor division is automatically and quickly completed, and the time for manually dividing floors can be greatly shortened, so that the map building time of the whole parking lot map is greatly saved, and the user experience is improved.

Referring to fig. 3, fig. 3 is a schematic flow chart of a floor dividing method according to another embodiment of the present application. The floor dividing method may be applied to the parking lot map production system 10 as shown in fig. 1, and in particular, may be applied to the processing device 12. The floor division method includes the following steps S210 to S290.

And step S210, acquiring track points of the single track, track names of the single track and entry points of the single track, wherein the track points, the track names and the entry points are acquired according to a preset sequence.

The track point, track name, and entry point of the single track are included in the map data file collected and reported by the vehicle, and for the specific implementation of collecting and reporting the map data file by the vehicle, please refer to the description of step S110, which is not described herein again.

In some embodiments, the processing device obtains a map data file reported by the vehicle end, and analyzes track points, track names and entry points of a single track from the map data file. Wherein, the track point and the entry point can be represented by coordinates of a three-dimensional space, such as (x, y, z).

And step S220, if the track name indicates that the single track is the warehousing track, arranging track points of the single track in a reverse order, and executing subsequent operation based on the track points after the reverse order arrangement.

In some embodiments, whether the track of a single track is a warehousing track or not can be judged according to the track name; if the track name indicates that the single track is a warehousing track (for example, the track name contains IN or the track name does not contain OUT), arranging track points of the single track IN a reverse order, and executing subsequent steps based on the track points arranged IN the reverse order; if the track name indicates that the single track is an ex-warehouse track (for example, the track name includes OUT), the subsequent operation can be directly executed according to the acquired track point. In the embodiment, by performing the reverse order operation on all track points of the warehousing track, the same set of algorithm (which is used for automatically dividing floors according to the track of a single vehicle) can be adopted to calculate the two tracks in the warehousing direction and the ex-warehouse direction without designing two sets of algorithms to respectively calculate the two tracks in the ex-warehouse direction and the warehousing direction, so that the algorithm can be simplified, and the development time can be saved.

And step S230, determining the track point closest to the entry point from the track points as a target track point.

Here, the entry point is a Global Positioning System (GPS) signal vanishing point. The entry point is a trace point on the ground floor that may indicate that the vehicle has entered the garage from the ground floor.

In some embodiments, the distance between each trajectory point and the entry point (e.g., the euclidean distance between each trajectory point and the entry point) may be calculated, and the trajectory point having the shortest distance may be determined as the target trajectory point (e.g., point E).

Step S240, calculating a first average height of a first preset number of track points before the target track point and a second average height of a first preset number of track points after the target track point.

The first preset number may be set according to actual requirements for precision, and is not specifically limited herein. The higher the requirement for accuracy is, the larger the first preset number is, but in order to save calculation time and computational power of the processing apparatus, the first preset number may be set to 200 in general.

In some embodiments, an implementation of calculating the first average height of the first preset number of track points before the target track point and the second average height of the first preset number of track points after the target track point may be: searching 200 track points before a target track point (point E), and calculating the average height of the 200 track points to obtain a first average height; and searching for 200 track points behind the target track point (point E), and calculating the average height of the 200 track points to obtain a second average height.

And S250, if the first average height is larger than the second average height, determining that the garage is an underground garage.

The first average height is greater than the second average height, which indicates that the direction of the vehicle entering the garage from the ground floor is approximately inclined downwards, so that the garage can be determined to be an underground garage.

And step S260, if the first average height is not larger than the second average height, determining that the garage is an overground garage.

The first average height is not greater than the second average height, which indicates that the direction of the vehicle entering the garage from the ground floor is approximately upward inclined, so that the garage can be determined to be an above-ground garage.

And step S270, determining a plurality of variable slope points to be selected according to the track points.

It should be noted that, as described above, if the track name indicates that the single track is the track to be put in storage, the track points of the single track are arranged in a reverse order, and a plurality of variable slope points to be selected are determined according to the track points arranged in the reverse order, that is, all subsequent operations are performed based on the track points arranged in the reverse order; and if the track name indicates that the single track is the ex-warehouse track, directly determining a plurality of variable slope points to be selected according to the track points of the single track, namely, directly executing all subsequent operations based on the acquired track points.

In some embodiments, please refer to fig. 4, fig. 4 is a flowchart illustrating a step S270 included in a floor dividing method according to another embodiment of the present application. Step S270 includes the following steps S271 to S272.

Step S271, calculate the forward type and backward type of each trace point.

In some embodiments, the implementation of step S271 may be: respectively calculating the forward angle and the backward angle of each track point; calculating the forward type of each track point according to the forward angle of each track point; and calculating the backward type of each track point according to the backward angle of each track point.

In some embodiments, an implementation of calculating the forward and backward angles for each trace point may be as follows: calculating the angles of each track point and a second preset number (for example, 5) of track points before the track point, wherein the median of the obtained multiple angles is the forward angle of the track point; and calculating the angles of each track point and a second preset number of track points behind the track point, and taking the median of the obtained multiple angles as the backward angle of the track point. The second preset number is smaller than the first preset number, and may be set according to actual requirements, which is not specifically limited herein. It should be noted that the units of the forward angle and the backward angle may be angles or radians, and are not limited specifically herein.

In some embodiments, calculating the forward type for each track point based on its forward angle may be calculated according to table 1. For example, if the forward angle of the track point falls into the first interval, the forward type of the track point is type 0; if the forward angle of the track point falls into a second interval, the forward type of the track point is type 1; and if the forward angle of the track point falls into a third interval, the forward type of the track point is type 2. Wherein the angle threshold may be 1 degree or 0.017 radians.

TABLE 1

Angular interval	Type (B)
		A first interval: angle of rotation<-0.5 angular threshold	0
A second interval: -0.5 angular threshold<Angle of rotation<0.5 angular threshold	1
		The third interval: angle of rotation>0.5 angular threshold	2

Similarly, calculating the backward type for each track point based on its backward angle can also be calculated from table 1. For example, if the backward angle of the track point falls into the first interval, the backward type of the track point is type 0; the backward angle of the track point falls into a second interval, and the backward type of the track point is type 1; and if the backward angle of the track point falls into a third interval, the backward type of the track point is type 2.

And step S272, determining the variable slope points to be selected according to the forward type and the backward type of each track point, and adding the variable slope points to be selected into a variable slope point list to be selected, wherein one of the forward type and the backward type of the variable slope points to be selected is a preset type, and the other one is not the preset type.

Wherein the preset type may be type 1 in table 1. The candidate variable slope point list may be pre-established and stored in the processing device or the cloud, or may be newly added in the operation process and temporarily exist in the processing device or the cloud, which is not specifically limited herein.

In some embodiments, if the forward type of a track point is type 1 and the backward type is not type 1, or the forward type of the track point is not type 1 and the backward type is type 1, determining that the track point is a variable slope point to be selected, and adding the variable slope point to be selected to a variable slope point list to be selected.

Step S280, determining a plurality of target flat layers and a target variable slope point corresponding to each target flat layer according to the plurality of variable slope points to be selected.

In some embodiments, please refer to fig. 5, fig. 5 is a flowchart illustrating a step S280 included in a floor dividing method according to another embodiment of the present application. Step S280 includes the following steps S281 to S282.

And step S281, processing the variable slope points to be selected in the variable slope point list to be selected based on the forward type and the backward type of the variable slope points to be selected, and obtaining a plurality of flat layers corresponding to the processed variable slope points to be selected.

In some embodiments, the implementation of step S281 may be: dividing two adjacent variable slope points to be selected in the variable slope point list to be selected into a group; if the forward type and the backward type of two variable points to be selected in the group of variable points to be selected are the same and the height difference is smaller than a first height difference threshold value, deleting one of the two variable points to be selected from the variable point list to be selected; and determining a plurality of leveling layers and leveling layer pairs corresponding to each leveling layer from the remaining variable slope points to be selected in the variable slope point list to be selected, wherein the backward type of the previous variable slope point to be selected in the leveling layer pairs is a preset type, and the forward type of the next variable slope point to be selected is a preset type. Wherein the first height difference threshold may be one-half of the height between two adjacent flat layers, for example, the height between two adjacent flat layers is usually 3.5 meters, and the first height difference threshold is 1.75 meters. Particularly, if the type of the last variable slope point to be selected is a preset type (type 1), the last track point is taken as the variable slope point to be selected and added into the variable slope point list to be selected.

In some embodiments, the determining a plurality of levels and the level pair corresponding to each level from the remaining variable slope points to be selected in the variable slope point list to be selected may be as follows: sequentially searching a first variable slope point to be selected with a backward type of 1 in a variable slope point list to be selected according to the sequence from front to back, and taking the first variable slope point to be selected as the previous variable slope point of the first leveling pair; sequentially searching a to-be-selected variable slope point with a first forward type as a preset type backwards, and taking the to-be-selected variable slope point as a to-be-selected variable slope point behind a first leveling pair, wherein the two to-be-selected variable slope points are a leveling pair; and in the same way, determining a plurality of flat layers and the corresponding flat layer pair of each flat layer from the remaining variable slope points to be selected in the variable slope point list to be selected. The number of flat layers (pairs of flat layers) is 1+ n, i.e. the total number of slope points to be selected is 2+ n, where n represents the number of layers and is an integer. For example, the parking lot includes 3 floors, and there are 1+ 3=4 flat floors and 2+ 3=8 slope points to be selected.

Step S282, processing the multiple leveling layers according to the height difference between two adjacent leveling layers to obtain multiple target leveling layers and a target gradient changing point corresponding to each target leveling layer.

In some embodiments, the implementation of step S282 may be: calculating the height difference of adjacent flat layer pairs; determining the adjacent flat layer pair with the minimum height difference; if the determined height difference of the adjacent flat layer pair with the minimum height difference is not larger than a second height difference threshold value, combining the adjacent flat layer pair with the minimum height difference to obtain a new flat layer and a variable slope point to be selected corresponding to the new flat layer; and if the determined height difference of the adjacent flat layer pair with the minimum height difference is larger than a second height difference threshold value, stopping the combination operation of the plurality of flat layers to obtain a plurality of target flat layers and a target slope changing point corresponding to each target flat layer. Wherein the second height difference threshold is greater than the first height difference threshold. The second height difference threshold may be 1.2 times the first height difference threshold, e.g., 1.75 meters for the first height difference threshold and 2.1 meters for the second height difference threshold.

In some embodiments, an implementation of calculating the height difference of adjacent flat pairs may be: and respectively calculating the height difference between every two of the four variable slope points to be selected corresponding to the adjacent flat layer pairs to obtain six height differences, and taking the maximum height difference in the six height differences as the height difference of the adjacent flat layer pairs.

In particular, after the above merging operation on multiple flat floors is completed, the floor division method provided in the embodiment of the present application may further include the following refinement processing on the ground floor: determining a first forward variable slope point to be selected with a preset type (type 1) before an entry point as a next variable slope point of a ground layer; determining a first track point of the single track as a previous slope point of the ground layer; deleting all to-be-selected variable slope points between the previous variable slope point and the next variable slope point of the ground layer; and if the height difference between the next variable slope point of the ground layer and the next variable slope point of the next flat layer of the ground layer is smaller than the second height difference threshold value, deleting the next flat layer of the ground layer. Through the refinement processing of the ground layer, the ground layer can be prevented from being wrongly divided into two flat layers due to the fact that the ground layer possibly has a certain inclination in an actual application scene, and therefore the accuracy of dividing the ground layer is improved.

In particular, the floor division method provided by the embodiment of the present application may further include: and intercepting the floors with the opposite trend of going upstairs and downstairs. For example, if the garage is determined to be an underground garage and the track name of the single track represents that the track is a track for leaving the garage, the floor with the trend opposite to the ascending trend of the vehicle is cut off; and if the garage is determined to be the ground garage and the track name of the single track represents that the track is the track for leaving the garage, the floor opposite to the descending trend of the vehicle is cut off.

For example, when the garage is determined to be an underground garage and the track name of the single track represents that the track is a track for leaving the garage, in the process of leaving the garage, when a vehicle runs to the second floor, the situation that the user forgets something and returns to the third floor may exist, so that the second floor and the third floor may be repeatedly calculated for many times, and the result of floor division has an error, therefore, the floor corresponding to the track for returning the user to the third floor from the second floor can be cut off, and the error of the result of floor division caused by repeatedly dividing the floor is avoided, so that the accuracy of floor division is improved.

Namely, the floors with the opposite trend to the upward and downward trends are cut off, so that the consistent trend of the vehicles going downward or upward can be ensured, errors in floor dividing results caused by actual operation of users are avoided, and the accuracy of floor dividing is improved.

Particularly, after the steps, if the track name of a single track represents that the track is a warehousing track, the track points of the whole track need to be inverted again, so that the two tracks for warehousing and ex-warehousing can be calculated by adopting the same program, the algorithm is simplified, and the development time is saved.

By executing the steps, a plurality of target flat layers and a target gradient change point [ S ] corresponding to each target flat layer can be obtained ₀ ,S ₁ ,S ₂ ,…,S _n ]Wherein n is an integer. As shown in FIG. 6, (S) ₀ ,S ₁ ) Is a ground layer; (S) ₂ ,S ₃ )，(S ₄ ,S ₅ )，……，(S _n-3 ,S _n-2 )，(S _n-1 ,S _n ) Is flat layer, (S) ₁ ,S ₂ )，(S ₃ ,S ₄ )，……，(S _n-2 ,S _n-1 ) Is a via layer. Note that the total number of target gradient change points is an even number.

And step S290, respectively determining the floor serial numbers of a plurality of target flat floors based on the target slope changing points corresponding to the target flat floors.

In some embodiments, please refer to fig. 7, fig. 7 is a flowchart illustrating a step S290 included in a floor dividing method according to another embodiment of the present application. Step S290 includes the following steps S291 to S293.

And S291, acquiring the depth of the track point of the single track and historical flat dividing data, wherein the historical flat dividing data comprises a historical flat serial number and a historical flat depth.

The depth of the track point of the single track can be included in the map data file, and the depth of the track point can be the distance between the track point and the reference point of the ground layer, wherein the reference point of the ground layer can be preset according to actual requirements. The flat bed depth may be the distance between the flat bed and the ground bed.

In some embodiments, the processing device may obtain the depth of the track point of the single track from the map data file, and obtain the historical flat layer division data from the database or the cloud. For example, the history flat layer division data may be [ FL0: H0, FL1: H1, FL2: H2, \ 8230 ], FLn: hn ], where n is an integer, FLn denotes the number of the nth flat layer, and Hn denotes the depth of the nth flat layer.

And step S292, determining the next grade change point of the ground layer as a reference point.

In some embodiments, the ramp point S may be varied from the above target ₀ ,S ₁ ,S ₂ ,…,S _n ]Determining the next slope change point (S) of the ground layer ₁ ) Is a reference point.

In other embodiments, the next grade change point of the ground layer can be determined as a reference point from a plurality of target grade change points obtained through manual division.

And step S293, respectively determining the floor serial numbers of a plurality of target floors according to the historical floor dividing data and the depths of the reference points based on the target slope changing points corresponding to each target floor.

In some embodiments, the implementation of step S293 may be: calculating the depth of each target flat layer based on the depth of the reference point and the target variable slope points, for example, determining the median of the depths of all track points between two target variable slope points corresponding to each target flat layer, and subtracting the depth of the reference point from the median to obtain the depth of each target flat layer (Hc, hc is the depth of the c-th target flat layer, and c is the serial number of the c-th target flat layer); and respectively determining the floor serial numbers of a plurality of target floors (FLc, FLc is the floor serial number of the c-th target floor) according to the depth of the target floor and the historical floor dividing data.

In some embodiments, the floor numbers of a plurality of target floors are determined based on the depth of the target floor and the historical floor plan, respectively, and a piecewise function as shown in table 2 may be employed to determine the floor number of each target floor. H0 represents the depth of the ground layer, ha represents the depth of the a-th flat layer, hb represents the depth of the b-th flat layer, and Hn represents the depth of the n-th flat layer, wherein a, b, and n are integers and can be preset according to actual requirements, and no specific limitation is imposed thereon. Round () "is a rounding function. As shown in table 2, if Hc < H0, c =0+ math. Round ((Hc-H0)/3.5); c = n + Math.round ((Hc-Hn)/3.5) if Hc > Hn; (Hb) if Ha < Hc, c = a + math.round ((Hc-Ha)/((Hb-Ha)/(b-a))); correspondingly, the floor number of the c-th target landing is FLc.

TABLE 2

Hc<H0	c＝0+Math.round((Hc-H0)/3.5)
		Hc>Hn	c＝n+Math.round((Hc-Hn)/3.5)
Ha<Hc<Hb	c＝a+Math.round((Hc-Ha)/((Hb-Ha)/(b-a)))

In other embodiments, if the historical leveling dividing data is not obtained, that is, the historical leveling dividing data does not exist, the corresponding floor number may be determined directly according to the depth of the target leveling. Round (Hc/3.5), for example, c = math, and accordingly, the floor number of the c-th target floor is FLc.

In particular, after determining the floor number of the target level, the floor number of the aisle level between adjacent target levels may be determined based on the floor number of the target level. For example, the floor numbers of the adjacent target floors of a certain aisle floor are FLm and FLn, where m and n are integers and m is smaller than n, and the floor number of the aisle floor is FLm _ FLn.

Particularly, after the floor serial numbers of the target flat floor and the aisle floor are determined, the determined floor serial numbers of the target flat floor and the aisle floor can be fused with historical flat floor dividing data in a weighted average mode, so that track data acquired by multiple cars are spliced together, and the accuracy of floor dividing is improved.

Particularly, after the floor division is automatically completed in steps S210 to S290, the floor division result can be manually checked and adjusted by using a visualization tool, so as to further improve the accuracy of the floor division.

In the floor dividing method provided by the embodiment of the application, the steps S210-S290 are mainly executed, the floor division can be automatically completed according to the driving track, and the high cost of manually dividing the floor is saved. Compared with the method that the efficiency and the accuracy of floor division are improved manually due to the complex parking lot condition, the method can greatly improve the efficiency and the accuracy of floor division. Through automatic, accomplish the floor fast and divide, can greatly shorten the time of artifical division floor to save the time of drawing of building of whole parking area map by a wide margin, and then improve user experience. By performing the reverse operation on the input tracks, the algorithm can be simplified and the development time can be saved. The accuracy of floor division can be further improved by judging whether the garage is an overground garage or an underground garage. By thinning the ground floor, the ground floor can be prevented from being wrongly divided into two layers due to certain inclination, so that the floor division accuracy is further improved.

Referring to fig. 8, fig. 8 is a block diagram of a floor dividing device according to an embodiment of the present disclosure. The floor dividing apparatus 300 can be applied to the parking lot map production system 10 shown in fig. 1, and in particular, can be applied to the processing device 12. The floor dividing device 300 comprises a track point acquisition module 310, a variable slope point to be selected determination module 320, a target variable slope point determination module 330 and a floor sequence number determination module 340. The track point obtaining module 310 is configured to obtain track points of a single track, which are collected according to a preset sequence. The candidate variable slope point determining module 320 is configured to determine a plurality of candidate variable slope points according to the track points. The target slope changing point determining module 330 is configured to determine a plurality of target leveling layers and a target slope changing point corresponding to each target leveling layer according to the plurality of slope changing points to be selected. The floor sequence number determining module 340 is configured to determine the floor sequence numbers of a plurality of target floors respectively based on the target slope changing point corresponding to each target floor.

In particular, the candidate variable slope point determining module 320 includes a type calculating submodule and a candidate variable slope point determining submodule. And the type calculation submodule is used for calculating the forward type and the backward type of each track point. And the variable slope point to be selected determining submodule is used for determining the variable slope point to be selected according to the forward type and the backward type of each track point, and adding the variable slope point to be selected into the variable slope point list to be selected, wherein one of the forward type and the backward type of the variable slope point to be selected is a preset type, and the other one is not the preset type.

In particular, the type calculation submodule includes an angle calculation unit, a forward type calculation unit, and a backward type calculation unit. The angle calculation unit is used for calculating the forward angle and the backward angle of each track point respectively. The forward type calculating unit is used for calculating the forward type of each track point according to the forward angle of each track point. And the backward type calculating unit is used for calculating the backward type of each track point according to the backward angle of each track point.

In particular, the target change point determination module 330 includes a flat layer segmentation sub-module and a flat layer processing sub-module. The leveling division submodule is used for processing the variable slope points to be selected in the variable slope point list to be selected based on the forward type and the backward type of the variable slope points to be selected to obtain a plurality of leveling layers corresponding to the processed variable slope points to be selected. And the leveling processing submodule is used for processing the plurality of leveling layers according to the height difference between two adjacent leveling layers to obtain a plurality of target leveling layers and a target slope changing point corresponding to each target leveling layer.

Specifically, the flat-layer division submodule includes a division unit, a deletion unit, and a flat-layer determination unit. The dividing unit is used for dividing two adjacent variable slope points to be selected in the variable slope point list to be selected into a group. The deleting unit is used for deleting one of the two variable slope points to be selected from the variable slope point list to be selected if the forward type and the backward type of the two variable slope points to be selected in the group of variable slope points to be selected are the same and the height difference is smaller than a first height difference threshold value. The leveling determining unit is used for determining a plurality of leveling and leveling pairs corresponding to each leveling from the remaining variable slope points to be selected in the variable slope point list to be selected, wherein the backward type of the previous variable slope point to be selected in the leveling pairs is a preset type, and the forward type of the next variable slope point to be selected in the leveling pairs is a preset type.

Specifically, the leveling processing submodule includes a height difference calculation unit, a leveling pair determination unit, a merging unit, and a stop unit. Wherein the height difference calculating unit is used for calculating the height difference of adjacent flat layer pairs. The flat layer pair determination unit is used for determining the adjacent flat layer pair with the minimum height difference. And the merging unit is used for merging the adjacent flat layer pairs with the minimum height difference to obtain a new flat layer and a variable slope point to be selected corresponding to the new flat layer if the determined height difference of the adjacent flat layer pairs with the minimum height difference is not greater than the second height difference threshold value. The stopping unit is used for stopping the merging operation of the multiple flat layers if the height difference of the determined adjacent flat layer pair with the smallest height difference is larger than a second height difference threshold value, so that multiple target flat layers and target slope changing points corresponding to the target flat layers are obtained, wherein the second height difference threshold value is larger than the first height difference threshold value.

Specifically, the floor dividing apparatus 300 further includes an entry point acquiring module, a determining module, a change point deleting module, and a leveling deleting module. The entrance point acquisition module is used for acquiring an entrance point of a single track, and determining that a track point with a first forward type before the entrance point as the preset type is a rear variable slope point of a ground layer, wherein the ground layer is a flat layer for a vehicle to drive into the garage. The determining module is used for determining that the first track point of the single track is the previous slope change point of the ground layer. The variable slope point deleting module is used for deleting all variable slope points to be selected between the previous variable slope point and the next variable slope point of the ground layer. And the flat layer deleting module is used for deleting the next flat layer of the ground layer if the height difference between the next slope-changing point of the ground layer and the next slope-changing point of the next flat layer of the ground layer is less than a preset height difference threshold value.

In particular, the floor number determination module 340 includes a data acquisition sub-module, a reference point determination sub-module, and a number determination sub-module. The data acquisition submodule is used for acquiring the depth of track points of a single track and historical flat dividing data, wherein the historical flat dividing data comprises a historical flat sequence number and historical flat depth. The reference point determining submodule is used for determining the next slope changing point of the ground layer as a reference point. And the sequence number determination submodule is used for respectively determining the floor sequence numbers of a plurality of target levels according to the historical level division data and the depths of the reference points on the basis of the target variable slope points corresponding to each target level.

In particular, the candidate gradient point determining module 320 includes a track name obtaining sub-module, a first determining sub-module, and a second determining sub-module. The track name acquisition submodule is used for acquiring track names corresponding to the single tracks. The first determining submodule is used for arranging track points of the single track in a reverse order if the track name represents the single track as a warehousing track, and determining a plurality of variable slope points to be selected according to the track points after the reverse order arrangement. And the second determining submodule is used for determining a plurality of variable slope points to be selected according to the track points of the single track if the single track is represented by the track name and is taken out of the warehouse.

In particular, the floor-dividing apparatus 300 further includes an altitude calculation module, an underground garage determination module, and an above-ground garage determination module. The entry point acquisition module is further used for determining a track point closest to the entry point from the track points as a target track point. The height calculating module is used for calculating a first average height of a preset number of track points before the target track point and a second average height of a preset number of track points after the target track point. The underground garage determining module is used for determining that the garage is the underground garage if the first average height is larger than the second average height. And the ground garage determining module is used for determining that the garage is a ground garage if the first average height is not greater than the second average height.

It can be clearly understood by those skilled in the art that the floor dividing device 300 provided in the embodiments of the present application can implement the floor dividing method provided in the embodiments of the present application. The specific working process of the above devices and modules may refer to the process corresponding to the floor dividing method in the embodiment of the present application, and is not described herein again.

In the embodiments provided in this application, the coupling, direct coupling or communication connection between the modules shown or discussed may be an indirect coupling or communication coupling through some interfaces, devices or modules, and may be in an electrical, mechanical or other form, which is not limited in this application.

In addition, each functional module in the embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated module can be realized in a form of hardware, and can also be realized in a form of a functional module of software.

Referring to fig. 9, fig. 9 is a block diagram of an electronic device according to an embodiment of the present disclosure. The electronic device 400 may be disposed in the vehicle 11 or the processing device 12, and is not limited thereto. Electronic device 400 may include one or more of the following components: a memory 410, one or more processors 420, and one or more applications, wherein the one or more applications may be stored in the memory 410 and configured to cause the one or more processors 420 to perform the above-described floor-dividing method provided by embodiments of the present application when invoked by the one or more processors 420.

Processor 420 may include one or more processing cores. The processor 420 interfaces with various components throughout the electronic device 400 using various interfaces and lines for executing or executing instructions, programs, code sets, or instruction sets stored in the memory 410, as well as invoking execution or execution of data stored in the memory 410, performing various functions of the electronic device 400 and processing the data. Alternatively, the processor 420 may be implemented in hardware using at least one of Digital Signal Processing (DSP), field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). Processor 420 may integrate one or a combination of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 420, but may be implemented by a communication chip.

The Memory 410 may include a Random Access Memory (RAM) or a Read-Only Memory (ROM). The memory 410 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 410 may include a program storage area and a data storage area. Wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, and the like. The storage data area may store data or the like created by the electronic device 400 in use.

Referring to fig. 10, fig. 10 is a block diagram of a computer readable storage medium according to an embodiment of the present disclosure. The computer readable storage medium 500 has program code 510 stored therein, and the program code 510 is configured to, when called by a processor, cause the processor to execute the above-mentioned floor dividing method provided in the embodiment of the present application.

The computer-readable storage medium 500 may be an electronic Memory such as a flash Memory, an Electrically-Erasable Programmable Read-Only-Memory (EEPROM), an Erasable Programmable Read-Only-Memory (EPROM), a hard disk, or a ROM. Alternatively, the Computer-Readable Storage Medium 500 includes a Non-volatile Computer-Readable Medium (Non-TCRSM). The computer readable storage medium 500 has storage space for program code 510 that may be compressed in a suitable form to perform any of the method steps described above. The program code 510 can be read from or written to one or more computer program products.

To sum up, the floor division method, the floor division device, the electronic device and the storage medium provided by the embodiment of the application mainly acquire track points of a single track, which are acquired according to a preset sequence; determining a plurality of variable slope points to be selected according to the track points; determining a plurality of target flat layers and target variable slope points corresponding to each target flat layer according to the variable slope points to be selected; the floor sequence numbers of the target flat floors are respectively determined based on the target variable slope points corresponding to the target flat floors, floor division can be automatically completed according to the driving tracks, and high cost of manual floor division is saved. Compared with the situation that the efficiency and the accuracy rate of manual floor division are low due to the complex parking lot situation, the method can greatly improve the efficiency and the accuracy rate of floor division. In addition, floor division is automatically and quickly completed, and the time for manual floor division can be greatly shortened, so that the map building time of the whole parking lot map is greatly saved, and the user experience is improved.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art will appreciate that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A method of floor division, comprising:

acquiring track points of a single track, which are acquired according to a preset sequence, wherein the single track is a single driving track of a vehicle;

determining a plurality of variable slope points to be selected according to the track points, wherein the variable slope points to be selected are track points of which one is a preset type and the other is not the preset type, the forward type represents the inclination degree of a track before the track points, and the backward type represents the inclination degree of a track after the track points;

determining a plurality of target flat layers and target variable slope points corresponding to each target flat layer according to the plurality of variable slope points to be selected;

and respectively determining the floor serial numbers of the target levels based on the target slope changing points corresponding to the target levels.

2. The method according to claim 1, wherein determining a plurality of candidate gradient points according to the trajectory points comprises:

calculating the forward type and the backward type of each track point;

and determining a variable slope point to be selected according to the forward type and the backward type of each track point, and adding the variable slope point to be selected into a variable slope point list to be selected.

3. The method of claim 2, wherein calculating the forward type and the backward type of each trace point comprises:

respectively calculating the forward angle and the backward angle of each track point;

calculating the forward type of each track point according to the forward angle of each track point;

and calculating the backward type of each track point according to the backward angle of each track point.

4. The method according to claim 2, wherein determining a plurality of target leveling layers and a target slope change point corresponding to each target leveling layer according to the plurality of slope change points to be selected comprises:

processing the variable slope points to be selected in the variable slope point list to be selected based on the forward type and the backward type of the variable slope points to be selected to obtain a plurality of flat layers corresponding to the processed variable slope points to be selected;

and processing the plurality of flat layers according to the height difference between two adjacent flat layers to obtain the plurality of target flat layers and a target slope changing point corresponding to each target flat layer.

5. The method according to claim 4, wherein the processing the variable slope points to be selected in the variable slope point list based on the forward type and the backward type of the variable slope points to be selected to obtain a plurality of levels corresponding to the processed variable slope points to be selected comprises:

dividing two adjacent variable slope points to be selected in the variable slope point list to be selected into a group;

if the forward type and the backward type of two variable slope points to be selected in the group of variable slope points to be selected are the same and the height difference of the two variable slope points to be selected is smaller than a first height difference threshold value, deleting one of the two variable slope points to be selected from the variable slope point list to be selected;

and determining a plurality of leveling layers and leveling layer pairs corresponding to each leveling layer from the remaining variable slope points to be selected in the variable slope point list to be selected, wherein the backward type of the previous variable slope point to be selected in the leveling layer pairs is the preset type, and the forward type of the next variable slope point to be selected is the preset type.

6. The method of claim 5, wherein processing the plurality of flat layers according to the height difference between two adjacent flat layers to obtain the plurality of target flat layers and the target gradient change point corresponding to each target flat layer comprises:

calculating the height difference of adjacent flat layer pairs;

determining the adjacent flat layer pair with the minimum height difference;

if the determined height difference of the adjacent flat layer pair with the minimum height difference is not larger than a second height difference threshold value, combining the adjacent flat layer pair with the minimum height difference to obtain a new flat layer and a variable slope point to be selected corresponding to the new flat layer, wherein the second height difference threshold value is larger than the first height difference threshold value;

and if the determined height difference of the adjacent flat layer pair with the minimum height difference is larger than the second height difference threshold value, stopping the combination operation of the plurality of flat layers to obtain the plurality of target flat layers and the target slope changing point corresponding to each target flat layer.

7. The method of claim 4, wherein after processing the plurality of flat layers according to the height difference between two adjacent flat layers to obtain the plurality of target flat layers and the target slope changing point corresponding to each target flat layer, the method further comprises:

obtaining an entry point of the single track, and determining that a first forward variable slope point to be selected with the type being the preset type before the entry point is a next variable slope point of a ground layer, wherein the ground layer is a flat layer when a vehicle enters a garage;

determining a first track point of the single track as a previous variable slope point of the ground layer;

deleting all variable slope points to be selected between the previous variable slope point and the next variable slope point of the ground layer;

and if the height difference between the next slope-changing point of the ground layer and the next slope-changing point of the next flat layer of the ground layer is smaller than a preset height difference threshold value, deleting the next flat layer of the ground layer.

8. The method of claim 7, wherein the determining the floor numbers of the plurality of target levels respectively based on the target change points corresponding to each target level comprises:

obtaining the depth of a track point of the single track and historical flat division data, wherein the historical flat division data comprises a historical flat sequence number and a historical flat depth;

determining the next slope changing point of the ground layer as a reference point;

and respectively determining the floor serial numbers of the target levels according to the historical level division data and the depths of the reference points on the basis of the target slope change points corresponding to the target levels.

9. The method according to claim 1, wherein the determining a plurality of slope change points to be selected according to the track points comprises:

acquiring a track name corresponding to the single track;

if the track name indicates that the single track is a warehousing track, track points of the single track are arranged in a reversed order, and the multiple variable slope points to be selected are determined according to the track points arranged in the reversed order;

and if the track name represents that the single track is the ex-warehouse track, determining the variable slope points to be selected according to the track points of the single track.

10. The method of claim 1, wherein after obtaining the track points of the single track collected in the preset order, the method further comprises:

obtaining an entry point of the single track, and determining a track point closest to the entry point from the track points as a target track point;

calculating a first average height of a preset number of track points before the target track point and a second average height of the preset number of track points after the target track point;

if the first average height is larger than the second average height, determining that the garage is an underground garage;

and if the first average height is not larger than the second average height, determining that the garage is an overground garage.

11. A floor-dividing apparatus, comprising:

the track point acquisition module is used for acquiring track points of a single track, which are acquired according to a preset sequence, wherein the single track is a single driving track of a vehicle;

the candidate variable slope point determining module is used for determining a plurality of candidate variable slope points according to the track points, wherein the candidate variable slope points are track points of which one is a preset type and the other is not the preset type, the forward type represents the inclination degree of a track before the track points, and the backward type represents the inclination degree of a track after the track points;

the target variable slope point determining module is used for determining a plurality of target flat layers and a target variable slope point corresponding to each target flat layer according to the plurality of variable slope points to be selected;

and the floor sequence number determining module is used for respectively determining the floor sequence numbers of the target flat floors based on the target slope changing points corresponding to the target flat floors.

12. An electronic device, comprising:

a memory;

one or more processors; and

one or more application programs, wherein the one or more application programs are stored in the memory and configured to, when invoked by the one or more processors, cause the one or more processors to perform the method of any of claims 1-10.

13. A computer-readable storage medium, having stored therein program code configured to, when invoked by a processor, cause the processor to perform the method of any of claims 1 to 10.