Floor division method and device, equipment and storage medium

Abstract

The invention relates to the technical field of vehicle mapping, and discloses a floor division method and device, equipment, a medium and a product, and the method comprises the steps: obtaining a driving track of a target vehicle and scene information corresponding to the driving track; according to scene information corresponding to the driving track, determining a target track in an indoor range in the driving track; the target track comprises a plurality of track points; dividing a plurality of potential floors according to the heights corresponding to the track points; the height difference between two adjacent potential floors is greater than or equal to a first height threshold value; and according to the height relation between a plurality of potential floors and the ground, segmenting a target track in an indoor range. According to the scheme, automatic indoor parking floor division is achieved, the situation that the height difference between the adjacent potential floors needs to meet the first height threshold value is considered in the division process, and the accuracy of indoor parking lot floor division is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle mapping, and in particular to a floor division method, device, equipment and storage medium. Background Art

[0002] In offline point-to-point memory route mapping, the mapping scenario between parking lot A and parking lot B is involved. Parking lots usually have multiple floors (both above and below ground), and in the process of building a parking lot map, the floors of the parking lot need to be divided.

[0003] The stratification of parking lots usually requires obtaining the Z coordinate of the height indicated in the parking lot map to perform stratification, and dividing different floors according to different heights; if there is no parking lot map, the floors of the parking lot can only be divided manually, which is inefficient and inaccurate and extremely costly.

[0004] Therefore, there is an urgent need for a technical solution that can accurately divide parking lots into floors. Summary of the invention

[0005] In view of this, the present application provides a floor division method, device, equipment, medium and product, which improves the accuracy of indoor parking lot floor division. The technical solution is as follows.

[0006] In a first aspect, a floor division method is provided, the method comprising:

[0007] Acquire the driving trajectory of the target vehicle and scene information corresponding to the driving trajectory;

[0008] According to the scene information corresponding to the driving trajectory, a target trajectory in an indoor range is determined in the driving trajectory; the target trajectory includes a plurality of trajectory points;

[0009] Divide a plurality of potential floors according to the heights respectively corresponding to the plurality of trajectory points; the height difference between two adjacent potential floors is greater than or equal to a first height threshold;

[0010] The target trajectory in the indoor range is segmented according to the height relationship between several potential floors and the ground.

[0011] In a possible implementation, the step of dividing a plurality of potential floors according to the heights corresponding to the plurality of trajectory points includes:

[0012] If there is at least one flat section in the target trajectory, the height distribution of each track point in the at least one flat section is counted; the flat section track includes continuous track points located in the same flat section;

[0013] Acquire the height of the peak point in the height distribution as the first candidate floor;

[0014] If the height difference between two adjacent first candidate floors is less than the second height threshold, retain the candidate floor with a larger peak value of the peak point between the two adjacent first candidate floors;

[0015] If the height differences between two adjacent first candidate floors are both greater than or equal to the second height threshold, each of the first candidate floors is determined as a potential floor corresponding to the flat ground section.

[0016] In a possible implementation, the step of dividing a plurality of potential floors according to the heights corresponding to the plurality of trajectory points includes:

[0017] If there is a continuous slope section in the target trajectory, and the angle of the continuous slope section is less than the angle threshold, the continuous slope section is divided according to the specified length, and each division point is used as the second candidate floor;

[0018] A second candidate floor whose height difference with any potential floor corresponding to the flat ground section is greater than a third height threshold is determined as a potential floor; the third height threshold is greater than or equal to the first height threshold.

[0019] In a possible implementation, the step of dividing a plurality of potential floors according to the heights corresponding to the plurality of trajectory points includes:

[0020] If there are continuous slopes in the target trajectory, and the angle of the continuous slopes is greater than or equal to the angle threshold, the continuous slopes are segmented according to the specified angle, and each segmentation point is used as the third candidate floor;

[0021] A third candidate floor whose height difference with any potential floor corresponding to the flat ground section is greater than a fourth height threshold is determined as a potential floor; the fourth height threshold is greater than or equal to the first height threshold.

[0022] In a possible implementation, the step of dividing a plurality of potential floors according to the heights corresponding to the plurality of trajectory points includes:

[0023] Acquire a target trajectory point; the target trajectory point is at least one of an entry trajectory point and an exit trajectory point; the entry trajectory point is the first slope point of the target trajectory within the indoor range; the exit trajectory point is the last slope point of the target trajectory within the indoor range;

[0024] If the height difference between the target trajectory point and any of the potential floors corresponding to the flat ground section is greater than a fifth height threshold, the height corresponding to the target trajectory point is determined as a potential floor.

[0025] In a possible implementation, before dividing the potential floors according to the heights respectively corresponding to the plurality of trajectory points, the method further includes:

[0026] Acquire a first trajectory point before the entry trajectory point and a second trajectory point after the exit trajectory point in the driving trajectory;

[0027] If there is no corresponding positioning signal for either the first trajectory point or the second trajectory point, the floor corresponding to the target trajectory is determined to be the first floor above ground.

[0028] In a possible implementation, the scene information corresponding to the driving trajectory includes at least one of the position information corresponding to each trajectory point, the park range of the area where the trajectory point is located, and the parking space information of the area where the trajectory point is located;

[0029] The step of determining a target trajectory in an indoor range in the driving trajectory according to the scene information corresponding to the driving trajectory includes:

[0030] The scene information corresponding to each track point in the driving track is processed by a scene recognition model to obtain a recognition result corresponding to each track point;

[0031] The trajectory points within the indoor range as the recognition results are determined as the target trajectory.

[0032] In a second aspect, a floor division device is provided, the device comprising:

[0033] An acquisition module, used to acquire the driving trajectory of the target vehicle and scene information corresponding to the driving trajectory;

[0034] A determination module, configured to determine a target trajectory in an indoor range in the driving trajectory according to scene information corresponding to the driving trajectory; the target trajectory includes a plurality of trajectory points;

[0035] A division module, used to divide a plurality of potential floors according to the heights respectively corresponding to the plurality of trajectory points; the height difference between two adjacent potential floors is greater than or equal to a first height threshold;

[0036] The segmentation module is used to segment the target trajectory in the indoor range according to the height relationship between several potential floors and the ground.

[0037] In a possible implementation, the partitioning module is further configured to:

[0038] If there is at least one flat section in the target trajectory, the height distribution of each track point in the at least one flat section is counted; the flat section track includes continuous track points located in the same flat section;

[0039] Acquire the height of the peak point in the height distribution as the first candidate floor;

[0040] If the height difference between two adjacent first candidate floors is less than the second height threshold, retain the candidate floor with a larger peak value of the peak point between the two adjacent first candidate floors;

[0041] If the height differences between two adjacent first candidate floors are both greater than or equal to the second height threshold, each of the first candidate floors is determined as a potential floor corresponding to the flat ground section.

[0042] In a possible implementation, the division module is further configured to: if there is a continuous slope segment in the target trajectory and the angle of the continuous slope segment is less than the angle threshold, divide the continuous slope segment according to a specified length and use each division point as the second candidate floor;

[0043] A second candidate floor whose height difference with any potential floor corresponding to the flat ground section is greater than a third height threshold is determined as a potential floor; the third height threshold is greater than or equal to the first height threshold.

[0044] In a possible implementation, the division module is further configured to: if there is a continuous slope segment in the target trajectory, and the angle of the continuous slope segment is greater than or equal to the angle threshold, divide the continuous slope segment according to a specified angle, and use each division point as the third candidate floor;

[0045] A third candidate floor whose height difference with any potential floor corresponding to the flat ground section is greater than a fourth height threshold is determined as a potential floor; the fourth height threshold is greater than or equal to the first height threshold.

[0046] In a possible implementation, the division module is further used to: obtain a target trajectory point; the target trajectory point is at least one of an entry trajectory point and an exit trajectory point; the entry trajectory point is the first slope point of the target trajectory in the indoor range; the exit trajectory point is the last slope point of the target trajectory in the indoor range;

[0047] If the height difference between the target trajectory point and any of the potential floors corresponding to the flat ground section is greater than a fifth height threshold, the height corresponding to the target trajectory point is determined as a potential floor.

[0048] In a possible implementation, the partitioning module is further configured to:

[0049] Acquire a first trajectory point before the entry trajectory point and a second trajectory point after the exit trajectory point in the driving trajectory;

[0050] If there is no corresponding positioning signal for either the first trajectory point or the second trajectory point, the floor corresponding to the target trajectory is determined to be the first floor above ground.

[0051] In a possible implementation, the scene information corresponding to the driving trajectory includes at least one of the position information corresponding to each trajectory point, the park range of the area where the trajectory point is located, and the parking space information of the area where the trajectory point is located;

[0052] The determining module is further used for:

[0053] The scene information corresponding to each track point in the driving track is processed by a scene recognition model to obtain a recognition result corresponding to each track point;

[0054] The trajectory points within the indoor range as the recognition results are determined as the target trajectory.

[0055] In a third aspect, a computer device is provided, which includes a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the above-mentioned floor division method by executing the computer instructions.

[0056] In a fourth aspect, a computer-readable storage medium is provided, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the above-mentioned floor division method.

[0057] In a fifth aspect, a computer program product or a computer program is provided, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the above-mentioned floor division method.

[0058] The technical solution provided by this application may have the following beneficial effects:

[0059] When it is necessary to divide the floors in the memory route, the driving trajectory of the target vehicle in the memory route and the scene information corresponding to the driving trajectory can be obtained first. At this time, the computer device can determine the target trajectory within the indoor range according to the scene information corresponding to the driving trajectory; and for the multiple track points included in the target track, the computer can obtain the heights of the multiple track points, and divide several potential floors according to the heights of the multiple track points, and ensure that the height difference between two adjacent potential floors is greater than or equal to the first height threshold. At this time, according to the height relationship between the several potential floors and the ground, the target track within the indoor range can be divided into various floors. The above scheme first identifies the indoor range according to the scene information in the driving trajectory, and then divides the floors according to the height of the track points within the indoor range, thereby realizing automatic indoor parking floor division, and also considering that the height difference between adjacent potential floors must meet the first height threshold during the division process, thereby improving the accuracy of indoor parking floor division. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A schematic diagram of vehicle driving involved in an embodiment of the present application is shown.

[0062] Figure 2 The figure is a flow chart of a method for dividing floors according to an exemplary embodiment.

[0063] Figure 3 The figure is a flow chart of a method for dividing floors according to an exemplary embodiment.

[0064] Figure 4 A schematic diagram of a driving trajectory of a target vehicle involved in an embodiment of the present application is shown.

[0065] Figure 5 A flow chart of indoor parking lot floor division according to an embodiment of the present application is shown.

[0066] Figure 6 It is a structural schematic diagram of a floor division device provided in an embodiment of the present application.

[0067] Figure 7 It is a structural schematic diagram of a computer device provided by an optional embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0069] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between two items, or an association relationship between the two items, or a relationship between indication and being indicated, configuration and being configured, and the like.

[0070] Figure 1 FIG. 1 is a schematic diagram showing the architecture of a vehicle control system involved in an embodiment of the present application. Figure 1 As shown, the vehicle control system includes a target vehicle 110 and a cloud server 120 .

[0071] The target vehicle 110 is provided with a plurality of sensors, such as a position sensor, a posture sensor, an image sensor, etc. During the driving process of the target vehicle 110, the position sensor of the target vehicle 110 will obtain the real-time position of the target vehicle 110 at a specified frequency, thereby forming a driving track consisting of a plurality of track points during the driving process of the target vehicle 110.

[0072] Optionally, when the target vehicle 110 is traveling, the image sensor in the target vehicle 110 will also collect the surrounding environment information in real time, and bind it to each track point in the driving track according to the timestamp.

[0073] Furthermore, during the driving process of the target vehicle 110, the posture sensor (such as a gyroscope) will also obtain the driving posture of the target vehicle 110 in real time. For example, the target vehicle 110 can determine whether each trajectory point is a trajectory point on a flat section or a trajectory point on a slope through the posture detected by the posture sensor.

[0074] Furthermore, the target vehicle 110 is also provided with a vehicle-mounted controller, which may be a computer device with high computing power. The vehicle-mounted controller may receive and process data from various sensors to implement various functions including identifying the driving trajectory of the target vehicle 110 indoors and dividing the indoor trajectory into floors.

[0075] Furthermore, the target vehicle 110 also includes a data transmission device, which can transmit the data of each sensor on the target vehicle 110 to the cloud server 120 via a wireless network. After the cloud server 120 receives the sensor data, it can realize various functions including identifying the driving trajectory of the target vehicle 110 indoors and dividing the indoor trajectory into floors.

[0076] Optionally, the above-mentioned cloud server can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms and other technical computing services.

[0077] Optionally, the system may further include a management device, which is used to manage the system (such as managing the connection status between each module and the server, etc.), and the management device is connected to the server via a communication network. Optionally, the communication network is a wired network or a wireless network.

[0078] Optionally, the above-mentioned wireless network uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any other network, including but not limited to any combination of local area network, metropolitan area network, wide area network, mobile, limited or wireless network, private network or virtual private network. In some embodiments, the technology and / or format including hypertext markup language, extensible markup language, etc. are used to represent the data exchanged through the network. In addition, conventional encryption technologies such as secure socket layer, transport layer security, virtual private network, Internet protocol security, etc. can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technology can also be used to replace or supplement the above-mentioned data communication technology.

[0079] Figure 2 1 is a flow chart of a method for floor division according to an exemplary embodiment. The method is executed by a computer device, which can be set in a target vehicle or a cloud server. Figure 2 As shown, the floor division method may include the following steps:

[0080] Step 201, obtaining a driving trajectory of a target vehicle and scene information corresponding to the driving trajectory.

[0081] In the process of mapping the point-to-point memory route, the target vehicle travels from point A to point B, where either point A or point B may be an indoor parking lot, and the indoor parking lot may have multiple floors. Therefore, in the process of mapping the memory route, it is necessary to consider the three-dimensional information after the target vehicle enters the multi-story parking building, so as to avoid the incorrect fusion of elements caused by the projection of the three-dimensional space information in the two-dimensional space. In order to achieve the above goal, it is necessary to accurately filter out the part of the target vehicle's driving trajectory that is in the multi-story parking building, and divide the various track points in this part of the trajectory according to different floors.

[0082] Therefore, in the embodiment of the present application, it is first necessary to obtain the driving trajectory of the target vehicle and obtain the scene information corresponding to the driving trajectory.

[0083] Optionally, the scene information corresponding to the driving trajectory is information collected by sensors in the target vehicle when the target vehicle generates the driving trajectory (that is, drives to each trajectory point therein).

[0084] For example, the scene information may include positioning information when the target vehicle travels to each track point, and the scene information may also include regional image information collected by the image sensor when the target vehicle travels to each track point.

[0085] Step 202: determining a target trajectory within an indoor range in the driving trajectory according to scene information corresponding to the driving trajectory.

[0086] The target trajectory includes multiple trajectory points.

[0087] For example, taking the scene information including positioning information or regional image information as an example, by comparing the positioning information of the target vehicle at each trajectory point with the map information, it is possible to determine whether the target vehicle is likely to be in an indoor range; by identifying the regional image information collected by the image sensor, it is possible to directly determine whether the target vehicle is in an indoor range.

[0088] Step 203: divide a plurality of potential floors according to the heights respectively corresponding to the plurality of trajectory points; the height difference between two adjacent potential floors is greater than or equal to a first height threshold.

[0089] Optionally, since there are inertial navigation devices such as gyroscopes inside the target vehicle, the target vehicle can determine the height value corresponding to each trajectory point when recording each trajectory point. Therefore, when the target trajectory of the target vehicle in the indoor range is identified, the height of each trajectory point in the target trajectory can be determined, and each trajectory point can be divided into several potential floors according to the height, and the height difference between two adjacent potential floors is greater than or equal to the first height threshold.

[0090] Optionally, the first height threshold is 2.5 m, which is the lowest height of an indoor parking lot floor.

[0091] Optionally, if the target trajectory of the target vehicle passes through multiple floors of an indoor parking lot, the driving trajectory of the target vehicle will pass through flat sections and slope sections in the indoor parking lot, and at least one flat section will have more trajectory points than the slope section; and the height values ​​of the trajectory points in the same flat section should be basically the same.

[0092] Therefore, in the embodiment of the present application, the height of each trajectory point can be counted first, that is, the flat area that may exist in the indoor parking lot can be selected as the potential floor; and then, based on the condition that the height difference between two adjacent potential floors is greater than or equal to the first height threshold, the height of the trajectory point is gradually screened to obtain each potential floor.

[0093] Step 204 , segmenting the target trajectory in the indoor range based on the height relationship between several potential floors and the ground.

[0094] After screening out several potential floors, the target trajectory within the indoor range can be divided into various floors according to the height relationship between the potential floors and the ground. For example, when the height of the potential floor is higher than the ground, it can be divided into the second floor above ground, the third floor above ground, etc.; if the height of the potential floor is lower than the ground, it can be divided into the first underground floor, the second underground floor, etc.

[0095] At this time, the three-dimensional information is taken into account for multiple track points in the target trajectory within the indoor range, so that the multiple track points in the target estimation within the indoor range are divided into their corresponding potential floors, so that the target vehicle can accurately map the parking lot with multiple floors according to the memorized route.

[0096] In summary, when it is necessary to divide the floors in the memory route, the driving trajectory of the target vehicle in the memory route and the scene information corresponding to the driving trajectory can be obtained first. At this time, the computer device can determine the target trajectory within the indoor range according to the scene information corresponding to the driving trajectory; and for the multiple track points included in the target track, the computer can obtain the heights of the multiple track points, and divide several potential floors according to the heights of the multiple track points, and ensure that the height difference between two adjacent potential floors is greater than or equal to the first height threshold. At this time, according to the height relationship between the several potential floors and the ground, the target track within the indoor range can be divided into various floors. The above scheme first identifies the indoor range according to the scene information in the driving trajectory, and then divides the floors according to the height of the track points within the indoor range, thereby realizing automatic indoor parking floor division, and in the division process, it also takes into account that the height difference between adjacent potential floors must meet the first height threshold, thereby improving the accuracy of indoor parking floor division.

[0097] Figure 3 1 is a flow chart of a method for floor division according to an exemplary embodiment. The method is executed by a computer device, which can be set in a target vehicle or a cloud server. Figure 3 As shown, the floor division method may include the following steps:

[0098] Step 301, obtaining the driving trajectory of the target vehicle and scene information corresponding to the driving trajectory.

[0099] Optionally, in an embodiment of the present application, the scene information corresponding to the driving trajectory includes park range, scene identification information, parking space information, and GPS signal value.

[0100] Please refer to Figure 4 , which shows a schematic diagram of a driving trajectory of a target vehicle involved in an embodiment of the present application. Figure 4 As shown, the target trajectory is composed of various trajectory points that the target vehicle passes through during the process of driving from target area A to target area B. For example, target area A is a park range, and target area B is another park range, and the GPS signal value constitutes each trajectory point in the target vehicle's driving trajectory. The scene recognition information is obtained by identifying the surroundings through the image sensor during the target vehicle's driving process, for example, whether it is on the main road, whether it is on the road, and whether it is in the park, etc., and the parking space information can be whether there are parking spaces around the target vehicle during the driving process, and the location of the parking space, etc. The parking space information can also be obtained by recognizing the surrounding images collected by the image sensor.

[0101] Step 302: Process the scene information corresponding to each track point in the driving track through a scene recognition model to obtain a recognition result corresponding to each track point.

[0102] After the driving trajectory is acquired, the computer device can process the scene information corresponding to each track point in the driving trajectory through the scene recognition model, and directly identify the recognition result corresponding to the track point.

[0103] Optionally, the scene recognition model can be trained based on sample scene information and sample annotations. That is, the computer device can use the scene information of the target vehicle at a certain track point as a sample, and use whether the track point is indoors as an annotation to train the artificial intelligence model, thereby obtaining the scene recognition model. The trained scene recognition model can accurately predict whether the track point is indoors based on the scene information corresponding to the track point.

[0104] Step 303: determine the trajectory points within the indoor range as the target trajectory.

[0105] After the computer device identifies each trajectory point in the indoor range, it can filter out the target trajectory in the indoor range from the driving trajectory.

[0106] Optionally, since the scene information collected by the target vehicle may be biased and the prediction results obtained by the artificial intelligence model may also have certain errors, in order to avoid the target trajectory within the indoor range being inconsistent with the actual situation, the target trajectory within the indoor range may be corrected using slope point information.

[0107] Specifically, the computer may determine whether the trajectory point is an uphill point, a downhill point, or a trajectory point on a flat area according to the posture (eg, pitch angle) corresponding to the trajectory point.

[0108] Specifically, at least one of the starting point and the end point of the target trajectory is obtained; if the indoor space where the target trajectory is located is an underground parking lot, the highest slope point in the driving trajectory within a specified range of at least one of the starting point and the end point is taken as the first target point, and the target trajectory is extended to the first target point according to the driving trajectory;

[0109] If the indoor area where the target trajectory is located is a ground parking lot, the lowest slope point in the driving trajectory within a specified range of at least one of the starting point and the end point is taken as the second target point, and the target trajectory is extended to the second target point along the driving trajectory.

[0110] Since the target trajectory is an indoor trajectory, that is, when the target vehicle generates the target trajectory, the target vehicle has entered an indoor parking lot. In actual scenarios, indoor parking lots include underground parking lots and ground parking lots (such as parking buildings).

[0111] The target vehicle needs to enter the underground parking lot through a downhill passage, and when the target vehicle exits the underground parking lot, it needs to drive to the ground through an uphill passage. That is, for the underground parking lot, the trajectory points at its entrance and exit should be the highest points among the trajectory points generated after the target vehicle enters the underground parking lot. Therefore, in the embodiment of the present application, the target trajectory can be extended to the highest slope point in the driving trajectory within a certain range to correct the target trajectory.

[0112] Similarly, the target vehicle needs to enter the ground parking lot through the uphill passage, and when the target vehicle exits the ground parking lot, it needs to drive to the ground through the downhill passage. That is, for the ground parking lot, the trajectory points at its entrance and exit should be the lowest points among the trajectory points generated after the target vehicle drives into the underground parking lot. Therefore, in the embodiment of the present application, the target trajectory can be extended to the highest slope point in the driving trajectory within a certain range to correct the target trajectory.

[0113] Step 304: divide a number of potential floors according to the heights corresponding to the plurality of trajectory points; the height difference between two adjacent potential floors is greater than or equal to a first height threshold.

[0114] In an embodiment of the present application, multiple trajectory points in the target trajectory can be divided into three categories, namely, trajectory points in a flat section, trajectory points in a continuous slope section, and entry / exit trajectory points.

[0115] In the embodiment of the present application, firstly, the potential floors indoors can be acquired based on the trajectory points on the flat ground.

[0116] At this time, in a possible implementation, if there is at least one flat ground section in the target trajectory, the height distribution of each trajectory point in the at least one flat ground section is counted; the flat ground section trajectory includes continuous trajectory points located in the same flat ground section; the height of the peak point in the height distribution is obtained as the first candidate floor;

[0117] If the height difference between two adjacent first candidate floors is less than the second height threshold, the candidate floor with a larger peak value between the two adjacent first candidate floors is retained;

[0118] If the height differences between two adjacent first candidate floors are both greater than or equal to the second height threshold, each of the first candidate floors is determined as a potential floor corresponding to the flat section.

[0119] The computer device can obtain each trajectory point on the flat ground and establish a height distribution according to the height value of each trajectory point. At this time, the peak of the height distribution represents that there are a large number of trajectory points of the target vehicle at the peak height, that is, the target vehicle has traveled a distance at the peak height. Therefore, the peak height is likely to be the height value of a certain floor of the indoor parking lot. Therefore, the height of the peak point can be first obtained as the first candidate floor.

[0120] According to the above process, there may be multiple peak points in the height distribution, and multiple first candidate floors can be screened out at this time. However, in an actual parking lot, the height between two adjacent floors must meet the building requirements. Therefore, when the computer equipment screens potential floors, it is also necessary to consider that the height difference between the potential floors must be greater than or equal to the second height threshold (the second height threshold can be greater than or equal to the above-mentioned first height threshold, for example 2.5m).

[0121] Specifically, when the height difference between two adjacent first candidate floors is less than the second height threshold, the candidate floor with a larger peak value between the two adjacent first candidate floors is retained, that is, the candidate floor with a greater possibility of being a potential floor is retained.

[0122] In the embodiment of the present application, after the potential floors corresponding to the flat ground section are obtained, the potential floors corresponding to the continuous slope section can also be obtained. The continuous slope section includes a plurality of continuous slope points.

[0123] In actual parking lots, it is common for continuous slopes to span multiple floors. For example, a continuous slope can lead directly from the third underground floor to the ground. In the process of vehicle mapping, the continuous slope also needs to be divided according to potential floors to reflect the characteristics of the continuous slope in three-dimensional space.

[0124] In a possible implementation, if there is a continuous slope section in the target trajectory, and the angle of the continuous slope section is less than the angle threshold, the continuous slope section can be identified as a straight slope section. In this case, the continuous slope section can be divided according to the specified length, and each division point is used as the second candidate floor;

[0125] A second candidate floor whose height difference with any potential floor corresponding to the flat section is greater than a third height threshold is determined as a potential floor; the third height threshold is greater than or equal to the first height threshold (eg, 2.5 m).

[0126] In a possible implementation, if there is a continuous slope section in the target trajectory, and the angle of the continuous slope section is greater than or equal to the angle threshold, then the continuous slope section can be identified as a spiral slope section, and the continuous slope section is divided according to the specified angle, and each division point is used as the third candidate floor;

[0127] A third candidate floor whose height difference with any potential floor corresponding to the flat section is greater than a fourth height threshold is determined as a potential floor; the fourth height threshold is greater than or equal to the first height threshold (eg, 2.5 m).

[0128] In a possible implementation, at least one of an entry trajectory point and an exit trajectory point is obtained; the entry trajectory point is the first slope point of the target trajectory in the indoor range; the exit trajectory point is the last slope point of the target trajectory in the indoor range;

[0129] If the height difference between the entry trajectory point and at least one of the exit trajectory points and any one of the potential floors corresponding to the flat ground section is greater than a fifth height threshold, the height corresponding to the entry trajectory point and at least one of the exit trajectory points is determined as a potential floor.

[0130] That is, in the embodiment of the present application, if the entrance trajectory point or the exit trajectory point exists, it can also be used as the height of a potential floor. If the height difference with any potential floor on the flat ground is too small, it will not be used as a potential floor.

[0131] Furthermore, before executing the above-mentioned potential floor judgment process, it is first necessary to judge whether the entry trajectory point and the exit trajectory point are valid. Specifically, the first trajectory point before the entry trajectory point and the second trajectory point after the exit trajectory point are judged; if there is no corresponding positioning signal for the first trajectory point and the second trajectory point, the above-mentioned potential floor division will not be performed, and the floor corresponding to the target trajectory will be directly determined as the first floor above ground.

[0132] Step 305 , segmenting the target trajectory in the indoor range based on the height relationship between several potential floors and the ground.

[0133] Specifically, the potential floors can be sorted by height. If the entry trajectory point exists, the potential floor closest to the entry trajectory point is selected as the ground floor. Otherwise, the potential floor closest to the exit trajectory point is selected as the ground floor. The floor with a height greater than the ground floor is the ground floor, the underground floor, and so on; the floor with a height less than the ground floor is the underground floor, the underground floor, and so on. All floors are created, and the trajectory between the entry trajectory point and the exit trajectory point is divided by floor, that is, the trajectory is divided according to the floor height.

[0134] Please refer to Figure 5 , which shows a flow chart of indoor parking lot floor division involved in the embodiment of the present application. Figure 5 As shown in the figure, this solution needs to obtain the park range, scene recognition information, parking space information, GPS signal value and other information based on scene recognition, and then vote on whether the current location is indoors. Then the trajectory points are smoothed to obtain the fused indoor range.

[0135] For each track point in the driving track, the position of the track point is determined to be uphill, downhill or flat according to the pitch angle of the track point, and smoothed, and then the slope point information is extracted;

[0136] Since the original information used for scene recognition has errors, the fused indoor range has deviations and does not match the actual indoor range. Therefore, the slope information can be used to correct the indoor range in the embodiment of the present application. The underground parking lot extends the starting point and end point of the indoor range to the highest slope point within the specified range (for example, a range of 100 meters). Similarly, the ground parking lot extends the starting point and end point of the indoor range to the lowest slope point within a range of 100 meters.

[0137] For each modified basement, the basement entrance and exit need to be extracted: the basement entrance is the first slope point in the indoor range, and the track point before the entrance point has a valid GPS signal, otherwise it is an invalid entry point; the basement exit is the last slope point in the indoor range, and the track point after the exit point has a small GPS, otherwise it is an invalid exit point. If no valid entry point or exit point exists, the floor division will not be performed, and all floors of the basement are on the ground floor, and the process ends;

[0138] The trajectory is segmented, continuous upslope or continuous downslope or continuous flat section is the same section, the continuous flat section is called a flat layer, the continuous upslope or continuous downslope is an aisle layer, and then the potential process is selected according to the trajectory points of the continuous flat section and the aisle layer respectively. The process can refer to the execution process shown in step 304, which will not be repeated here.

[0139] After obtaining each potential process, the potential floor heights can be sorted according to the corresponding heights of each potential floor. If the entry point exists, the potential floor closest to the entry point height is selected as the ground floor. Otherwise, the potential floor closest to the exit point height is selected as the ground floor. The floor with a height greater than the ground floor is the ground floor, the third underground floor, and so on; the floor with a height less than the ground floor is the underground floor, the second underground floor, and so on, and all floors are created.

[0140] In the embodiment of the present application, only the trajectory between the entry point and the exit point is divided into floors. Specifically, the trajectory is divided according to the floor height, and the division point is at the intersection of the trajectory segment. The trajectory other than the entry point and the exit point is not divided into floors and is unified as the ground floor.

[0141] Then, in the process of vehicle mapping, the fused elements (such as parking spaces, etc.) can be matched with the corresponding trajectory point floor information, which is convenient for element visualization and element extraction and alignment in the positioning process.

[0142] In summary, when it is necessary to divide the floors in the memory route, the driving trajectory of the target vehicle in the memory route and the scene information corresponding to the driving trajectory can be obtained first. At this time, the computer device can determine the target trajectory within the indoor range according to the scene information corresponding to the driving trajectory; and for the multiple track points included in the target track, the computer can obtain the heights of the multiple track points, and divide several potential floors according to the heights of the multiple track points, and ensure that the height difference between two adjacent potential floors is greater than or equal to the first height threshold. At this time, according to the height relationship between the several potential floors and the ground, the target track within the indoor range can be divided into various floors. The above scheme first identifies the indoor range according to the scene information in the driving trajectory, and then divides the floors according to the height of the track points within the indoor range, thereby realizing automatic indoor parking floor division, and in the division process, it also takes into account that the height difference between adjacent potential floors must meet the first height threshold, thereby improving the accuracy of indoor parking floor division.

[0143] In the embodiments of the present application, a floor division device is also provided, which is used to implement the above embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0144] The embodiment of the present application provides a floor division device, Figure 6 : is a structural schematic diagram of a floor division device provided in an embodiment of the present application, the device comprising:

[0145] An acquisition module 601 is used to acquire a driving trajectory of a target vehicle and scene information corresponding to the driving trajectory;

[0146] A determination module 602 is used to determine a target trajectory in an indoor range in the driving trajectory according to scene information corresponding to the driving trajectory; the target trajectory includes a plurality of trajectory points;

[0147] A division module 603 is used to divide a plurality of potential floors according to the heights respectively corresponding to the plurality of trajectory points; the height difference between two adjacent potential floors is greater than or equal to a first height threshold;

[0148] The segmentation module 604 is used to segment the target trajectory in the indoor range according to the height relationship between several potential floors and the ground.

[0149] In a possible implementation, the division module 603 is further configured to:

[0150] If there is at least one flat section in the target trajectory, the height distribution of each track point in the at least one flat section is counted; the flat section track includes continuous track points located in the same flat section;

[0151] Acquire the height of the peak point in the height distribution as the first candidate floor;

[0152] If the height difference between two adjacent first candidate floors is less than the second height threshold, retain the candidate floor with a larger peak value of the peak point between the two adjacent first candidate floors;

[0153] If the height differences between two adjacent first candidate floors are both greater than or equal to the second height threshold, each of the first candidate floors is determined as a potential floor corresponding to the flat ground section.

[0154] In a possible implementation, the division module 603 is further configured to: if there is a continuous slope segment in the target trajectory, and the angle of the continuous slope segment is less than the angle threshold, divide the continuous slope segment according to a specified length, and use each division point as the second candidate floor;

[0155] A second candidate floor whose height difference with any potential floor corresponding to the flat ground section is greater than a third height threshold is determined as a potential floor; the third height threshold is greater than or equal to the first height threshold.

[0156] In a possible implementation, the division module 603 is further configured to: if there is a continuous slope segment in the target trajectory, and the angle of the continuous slope segment is greater than or equal to the angle threshold, divide the continuous slope segment according to a specified angle, and use each division point as the third candidate floor;

[0157] A third candidate floor whose height difference with any potential floor corresponding to the flat ground section is greater than a fourth height threshold is determined as a potential floor; the fourth height threshold is greater than or equal to the first height threshold.

[0158] In a possible implementation, the division module 603 is further used to: obtain a target trajectory point; the target trajectory point is at least one of an entry trajectory point and an exit trajectory point; the entry trajectory point is the first slope point of the target trajectory in the indoor range; the exit trajectory point is the last slope point of the target trajectory in the indoor range;

[0159] If the height difference between the target trajectory point and any of the potential floors corresponding to the flat ground section is greater than a fifth height threshold, the height corresponding to the target trajectory point is determined as a potential floor.

[0160] In a possible implementation, the division module 603 is further configured to:

[0161] Acquire a first trajectory point before the entry trajectory point and a second trajectory point after the exit trajectory point in the driving trajectory;

[0162] If there is no corresponding positioning signal for either the first trajectory point or the second trajectory point, the floor corresponding to the target trajectory is determined to be the first floor above ground.

[0163] In a possible implementation, the scene information corresponding to the driving trajectory includes at least one of the position information corresponding to each trajectory point, the park range of the area where the trajectory point is located, and the parking space information of the area where the trajectory point is located;

[0164] The determining module 602 is further configured to:

[0165] The scene information corresponding to each track point in the driving track is processed by a scene recognition model to obtain a recognition result corresponding to each track point;

[0166] The trajectory points within the indoor range as the recognition results are determined as the target trajectory.

[0167] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0168] The floor division device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0169] The embodiment of the present invention further provides a computer device, wherein the computer device is arranged in a target vehicle, or the computer device is implemented as a cloud server corresponding to the target vehicle, and the computer device has the above Figure 6 The floor dividing device shown.

[0170] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphic information in a graphical user interface on an external input / output device (such as a display device coupled to an interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0171] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0172] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0173] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0174] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0175] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0176] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0177] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0178] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A floor division method, characterized in that: The method comprises: Acquire the driving trajectory of the target vehicle and scene information corresponding to the driving trajectory; According to the scene information corresponding to the driving trajectory, a target trajectory in an indoor range is determined in the driving trajectory; the target trajectory includes a plurality of trajectory points; Divide a plurality of potential floors according to the heights respectively corresponding to the plurality of trajectory points; the height difference between two adjacent potential floors is greater than or equal to a first height threshold; The target trajectory in the indoor range is segmented according to the height relationship between several potential floors and the ground.

2. The method according to claim 1, characterized in that The method of dividing a plurality of potential floors according to the heights corresponding to the plurality of trajectory points includes: If there is at least one flat section in the target trajectory, the height distribution of each track point in the at least one flat section is counted; the flat section track includes continuous track points located in the same flat section; Acquire the height of the peak point in the height distribution as the first candidate floor; If the height difference between two adjacent first candidate floors is less than the second height threshold, retain the candidate floor with a larger peak value of the peak point between the two adjacent first candidate floors; If the height differences between two adjacent first candidate floors are both greater than or equal to the second height threshold, each of the first candidate floors is determined as a potential floor corresponding to the flat ground section.

3. The method according to claim 2, characterized in that The method of dividing a plurality of potential floors according to the heights corresponding to the plurality of trajectory points includes: If there is a continuous slope section in the target trajectory, and the angle of the continuous slope section is less than the angle threshold, the continuous slope section is divided according to the specified length, and each division point is used as the second candidate floor; A second candidate floor whose height difference with any potential floor corresponding to the flat ground section is greater than a third height threshold is determined as a potential floor; the third height threshold is greater than or equal to the first height threshold.

4. The method according to claim 2, characterized in that: The method of dividing a plurality of potential floors according to the heights corresponding to the plurality of trajectory points includes: If there are continuous slopes in the target trajectory, and the angle of the continuous slopes is greater than or equal to the angle threshold, the continuous slopes are segmented according to the specified angle, and each segmentation point is used as the third candidate floor; A third candidate floor whose height difference with any potential floor corresponding to the flat ground section is greater than a fourth height threshold is determined as a potential floor; the fourth height threshold is greater than or equal to the first height threshold.

5. The method according to claim 2, characterized in that: The method of dividing a plurality of potential floors according to the heights corresponding to the plurality of trajectory points includes: Acquire a target trajectory point; the target trajectory point is at least one of an entry trajectory point and an exit trajectory point; the entry trajectory point is the first slope point of the target trajectory within the indoor range; the exit trajectory point is the last slope point of the target trajectory within the indoor range; If the height difference between the target trajectory point and any of the potential floors corresponding to the flat ground section is greater than a fifth height threshold, the height corresponding to the target trajectory point is determined as a potential floor.

6. The method according to claim 5, characterized in that Before dividing a plurality of potential floors according to the heights respectively corresponding to the plurality of trajectory points, the method further includes: Acquire a first trajectory point before the entry trajectory point and a second trajectory point after the exit trajectory point in the driving trajectory; If there is no corresponding positioning signal for either the first trajectory point or the second trajectory point, the floor corresponding to the target trajectory is determined to be the first floor above ground.

7. The method according to any one of claims 1 to 5, characterized in that: The scene information corresponding to the driving trajectory includes at least one of the location information corresponding to each trajectory point, the park range of the area where the trajectory point is located, and the parking space information of the area where the trajectory point is located; The step of determining a target trajectory in an indoor range in the driving trajectory according to the scene information corresponding to the driving trajectory includes: The scene information corresponding to each track point in the driving track is processed by a scene recognition model to obtain a recognition result corresponding to each track point; The trajectory points within the indoor range as the recognition results are determined as the target trajectory.

8. A floor division device, characterized in that: The device comprises: An acquisition module, used to acquire the driving trajectory of the target vehicle and scene information corresponding to the driving trajectory; A determination module, configured to determine a target trajectory in an indoor range in the driving trajectory according to scene information corresponding to the driving trajectory; the target trajectory includes a plurality of trajectory points; A division module, used to divide a plurality of potential floors according to the heights respectively corresponding to the plurality of trajectory points; the height difference between two adjacent potential floors is greater than or equal to a first height threshold; The segmentation module is used to segment the target trajectory in the indoor range according to the height relationship between several potential floors and the ground.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the floor division method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the floor division method according to any one of claims 1 to 7.

Images