Method, device and server for determining utilization of interior space of vehicle cabin

Abstract

Embodiments of the present application provide a method and device for determining the space utilization rate in a vehicle cabin and a server, and relate to the technical field of detection. The method comprises: obtaining initial point cloud data sets of the interior space of a preset vehicle cabin collected by a laser radar at a preset position of the opening of the preset vehicle cabin; segmenting the interior space according to a preset minimum measurement size to obtain the number of unit cubic spaces of the interior space; wherein the unit cubic space is a unit cubic space corresponding to the preset minimum measurement size; converting the initial point cloud data sets according to the preset minimum measurement size to obtain converted point cloud data sets; performing outlier detection on the converted point cloud data sets to obtain and filter out abnormal points to obtain an effective point cloud point data set; and determining the utilization rate of the interior space of the preset vehicle cabin according to the number of the effective point cloud point data set and the number of the unit cubic spaces. Thus, the present application can be used to calculate the space utilization rate of objects in a vehicle cabin.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and more specifically, to a method, apparatus, and server for determining the utilization rate of space inside a train carriage. Background Technology

[0002] With the rapid development of the logistics industry, customers have many requirements for the compliance of freight vehicle loading and the statistics of non-standard object loading. This has led to the development of a LiDAR sensor that emits light covering the entire truck bed to sense information values ​​of various spatial directions within the truck bed, construct a point cloud dataset within the truck bed, and calculate the volume of the object space formed by the point cloud dataset and the truck bed through spatial analysis of the point cloud dataset, thereby obtaining the space utilization rate of the objects within the truck bed.

[0003] Currently, commonly used point cloud dataset processing techniques mainly include Python's Open3D library, or converting point cloud datasets into images and performing calculations based on image processing frameworks (OpenCV).

[0004] Since the point cloud dataset is a three-dimensional point surface formed by the contours of objects inside the carriage obtained by LiDAR scanning the space in front from a fixed position and emitting light, rather than a completely closed object contour surface, the above processing techniques are all based on the visualization, analysis and spatial calculation of the completely closed object contour point cloud dataset. This makes it impossible for these existing technologies to be directly used to process non-completely closed object contour point cloud datasets and to calculate the space utilization rate of objects inside the carriage. Summary of the Invention

[0005] The present invention aims to provide, for example, a method, apparatus and server for determining the space utilization rate inside a carriage, which can be used to process point cloud datasets of non-completely enclosed object contours, and then calculate the volume of the object space formed by the point cloud dataset and the carriage, thereby obtaining the space utilization rate of the object inside the carriage.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0007] In a first aspect, embodiments of this application provide a method for determining the utilization rate of interior space in a vehicle compartment, the method comprising:

[0008] Obtain an initial point cloud dataset of the interior space of the preset carriage, collected by a lidar at a preset position at the opening of the preset carriage; the lidar's field of view is directed toward the interior space;

[0009] The internal space is divided according to a preset minimum measurement size to obtain the number of unit three-dimensional spaces of the internal space; wherein, the unit three-dimensional space is the unit three-dimensional space corresponding to the preset minimum measurement size;

[0010] The initial point cloud dataset is transformed according to the preset minimum measurement size to obtain the transformed point cloud dataset;

[0011] Outlier detection is performed on the transformed point cloud dataset to obtain and filter out outliers, resulting in a valid point cloud dataset.

[0012] The utilization rate of the interior space of the preset carriage is determined based on the number of valid point cloud datasets and the number of unit three-dimensional spaces.

[0013] Optionally, the step of transforming the initial point cloud dataset according to a preset minimum measurement size to obtain a transformed point cloud dataset includes:

[0014] The initial point cloud dataset is transformed according to the preset minimum measurement size and the length unit corresponding to the preset minimum measurement size to obtain the transformed point cloud dataset.

[0015] Optionally, the step of dividing the internal space according to the preset minimum measurement size to obtain the number of cubes in the internal space includes:

[0016] Based on the preset minimum measurement size and the effective size of the internal space, the internal space is divided to obtain the number of unit three-dimensional spaces.

[0017] Optionally, before determining the utilization rate of the interior space of the preset carriage based on the number of valid point cloud point datasets and the number of cubes, the method further includes:

[0018] Based on the effective point cloud dataset, the internal space is saturated to obtain the saturation judgment result;

[0019] Based on the saturation judgment result, the effective point cloud dataset is filled in the first direction to obtain the first filled point cloud dataset; wherein, the first direction is the width direction of the preset carriage;

[0020] In the second direction, the first point cloud dataset is filled to obtain a second point cloud dataset; wherein, the second direction is the length direction of the preset carriage;

[0021] The second point cloud dataset is filled in the third direction to obtain the third point cloud dataset; wherein, the third direction is the height direction of the preset carriage;

[0022] Determining the utilization rate of the interior space of the preset carriage based on the number of valid point cloud point datasets and the number of cubes includes:

[0023] The utilization rate of the interior space of the preset carriage is determined based on the number of point cloud data in the third point cloud dataset and the number of cubes.

[0024] Optionally, the step of performing a saturation judgment on the internal space based on the effective point cloud point dataset to obtain a saturation judgment result includes:

[0025] Calculate the coordinates of the center position based on the effective point cloud dataset;

[0026] Based on the coordinates of the center position and a preset origin, the distances of the center position in three preset directions are determined; the three preset directions include the first direction, the second direction, and the third direction.

[0027] Based on the distance of the center position in the three preset directions and the maximum length in the three preset directions, calculate the proportion of the distance in the three preset directions;

[0028] If at least two of the distance percentages in the three preset directions are less than a preset threshold, then the saturation judgment result is determined to be the first judgment result, which is used to indicate that the internal space is saturated.

[0029] If at least two of the distance percentages in the three preset directions are greater than or equal to the preset threshold, then the saturation judgment result is determined as the second judgment result, which is used to indicate that the internal space is not saturated.

[0030] Optionally, the step of filling the effective point cloud dataset in the first direction according to the saturation judgment result to obtain the filled first point cloud dataset includes:

[0031] If the saturation judgment result indicates that the internal space is saturated, then in the first direction, the effective point cloud dataset is filled in the direction away from the lidar to obtain the first point cloud dataset;

[0032] If the saturation judgment result indicates that the internal space is not saturated, then the effective point cloud dataset is filled by the two-sided oscillation insertion method in the first direction to obtain the first point cloud dataset.

[0033] Optionally, the step of filling the first point cloud dataset in the second direction to obtain a second point cloud dataset includes:

[0034] The first point cloud dataset is filled in the second direction towards the front of the vehicle where the preset carriage is located to obtain the second point cloud dataset.

[0035] Optionally, the step of filling the second point cloud dataset in a third direction to obtain a third point cloud dataset includes:

[0036] The second point cloud dataset is filled in the direction of the floor of the vehicle where the preset carriage is located, upwards from the third point, to obtain the third point cloud dataset.

[0037] Secondly, embodiments of this application provide a device for determining the utilization rate of interior space in a vehicle compartment, the device comprising:

[0038] The acquisition module is used to acquire the initial point cloud dataset of the interior space of the preset carriage, collected by a lidar at a preset position at the opening of the preset carriage; the lidar's field of view is directed towards the interior space.

[0039] The segmentation module is used to segment the internal space according to a preset minimum measurement size to obtain the number of unit three-dimensional spaces of the internal space; wherein, the unit three-dimensional space is the unit three-dimensional space corresponding to the preset minimum measurement size;

[0040] The conversion module is used to convert the initial point cloud dataset according to the preset minimum measurement size to obtain the converted point cloud dataset.

[0041] The filtering module is used to detect outliers in the converted point cloud dataset, obtain and filter out abnormal points, and obtain a valid point cloud dataset.

[0042] The determination module is used to determine the utilization rate of the interior space of the preset carriage based on the number of valid point cloud point datasets and the number of unit three-dimensional spaces.

[0043] Thirdly, embodiments of this application provide a server, including a processor and a memory, wherein the processor is configured to execute a van loading rate determination program stored in the memory to implement any of the vehicle space utilization methods in the first aspect.

[0044] Compared with the prior art, this application has the following beneficial effects:

[0045] The embodiments of the present invention provide a method, apparatus, and server for determining the utilization rate of interior space in a carriage. The method involves acquiring an initial point cloud dataset of the interior space of a preset carriage from a LiDAR sensor at a preset location at the opening of the carriage. The interior space is then segmented according to a preset minimum measurement size to obtain the number of unit three-dimensional spaces within the interior space. Next, the initial point cloud dataset is transformed according to the preset minimum measurement size to obtain a transformed point cloud dataset. Outlier detection is performed on the transformed point cloud dataset to obtain and filter out abnormal points, resulting in a valid point cloud dataset. Finally, the utilization rate of the interior space of the preset carriage is determined based on the number of valid point cloud datasets and the number of unit three-dimensional spaces. Therefore, this application can obtain the number of valid point cloud datasets and the number of unit solid spaces based on the initial point cloud dataset, thereby determining the utilization rate of the interior space of a preset carriage. This method for determining the utilization rate of carriage interior space is based on the initial point cloud dataset of a non-completely closed object contour, which improves the accuracy of determining the utilization rate of carriage interior space. Furthermore, since the size of the interior space inside a carriage varies in real-world scenarios, the interior space inside the carriage is divided according to a preset minimum measurement size to obtain the number of unit solid spaces. This allows the interior space inside the carriage to be standardized using the preset minimum measurement size, which facilitates subsequent data calculation and improves the efficiency of the method for determining the utilization rate of carriage interior space. At the same time, using the method for determining the utilization rate of carriage interior space of this application can also reduce development costs. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A schematic diagram of a point cloud dataset acquisition device provided in an embodiment of this application;

[0048] Figure 2 A schematic diagram of the installation location of a point cloud dataset acquisition device provided in an embodiment of this application;

[0049] Figure 3 A flowchart illustrating the method for determining the utilization rate of interior space provided in this application embodiment. Figure 1 ;

[0050] Figure 4 A flowchart illustrating the method for determining the utilization rate of interior space provided in this application embodiment. Figure 2 ;

[0051] Figure 5 A flowchart illustrating the method for determining the utilization rate of interior space provided in this application embodiment. Figure 3 ;

[0052] Figure 6 A flowchart illustrating the method for determining the utilization rate of interior space provided in this application embodiment. Figure 4 ;

[0053] Figure 7 A schematic diagram of a device for determining the utilization rate of interior space in a vehicle compartment, provided in an embodiment of this application;

[0054] Figure 8 This is a schematic diagram of the server structure provided in an embodiment of this application. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0057] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0058] In the description of this invention, it should be noted that if terms such as "upper," "lower," "inner," or "outer" are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of this invention is usually placed, they are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0059] Furthermore, the terms "first" and "second" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0060] It should be noted that, where there is no conflict, the features in the embodiments of the present invention can be combined with each other.

[0061] To address the problem that existing technologies cannot be directly used to process point cloud datasets of non-complete and closed object contours, and to calculate the space utilization rate of objects within a carriage, this application provides a method, apparatus, and server for determining the space utilization rate within a carriage. The following detailed descriptions of the method, apparatus, and server for determining the space utilization rate within a carriage provided in this application are provided in conjunction with the accompanying drawings.

[0062] The process of acquiring the initial point cloud dataset provided in the embodiments of this application will be illustrated below with reference to the accompanying drawings. Figure 1 This is a schematic diagram of a point cloud dataset acquisition device provided in an embodiment of this application. Figure 1 As shown, the point cloud dataset acquisition device 100 includes: a power supply module 110, a lidar 120, a communication module 130, and a server 140.

[0063] The point cloud dataset acquisition device 100 is positioned at a preset location at the opening of a preset carriage. This preset location can be selected based on actual conditions; for example, it could be the upper right corner of the rear of the vehicle. Figure 2 As shown, Figure 2 This is a schematic diagram of the installation location of a point cloud dataset acquisition device provided in an embodiment of this application.

[0064] It should be noted that the opening of the carriage must be located above the rear of the vehicle to allow the point cloud dataset acquisition device 100 to monitor the loading status of the objects 150 inside the carriage. This allows for the calculation of the loading status of the objects 150 and the volume of the space within the carriage, thus determining the space utilization rate of the objects inside the carriage. The objects 150 may include all pre-defined items that can be loaded and / or transported within the vehicle carriage.

[0065] The preset carriage can be selected according to the actual situation. For example, the preset carriage can be selected as the carriage of a freight car.

[0066] The lidar 120 is connected to the power supply module 110 so that the power supply module 200 can provide electrical signals to the lidar 120. The lidar 120 is used to scan objects in the interior space of the preset carriage so that the point cloud dataset acquisition device 100 can obtain the scanning results of the loading status of objects in the interior space of the preset carriage through the lidar 120. The scanning results of the loading status of objects are sent to the server 140 through the communication module 130 so that the loading status of objects 150 and the volume of the object space formed by the carriage can be calculated based on the scanning results of the loading status of objects, thereby obtaining the space utilization rate of objects in the carriage.

[0067] The power supply module 110 can be provided by an onboard power supply or by a preset backup power supply from the point cloud dataset acquisition device 100. It should also be noted that the power supply module 110 provided in this embodiment primarily uses an onboard power supply; however, when the onboard power supply experiences a current shortage, the preset backup power supply can serve as the primary power source.

[0068] Server 140 is a server system with at least four processors and 8GB of memory, used for intensive computing and data caching.

[0069] The method for determining the utilization rate of the interior space of the vehicle according to the present application will be described in detail below with reference to the accompanying drawings and through multiple embodiments. Figure 3 A flowchart illustrating the method for determining the utilization rate of interior space provided in this application embodiment. Figure 1 The execution entity of this method is server 140. For example... Figure 3 As shown, the method may include:

[0070] S210. Obtain the initial point cloud dataset of the interior space of the preset carriage collected by the lidar at the preset position of the opening of the preset carriage; the lidar's field of view is directed towards the interior space.

[0071] Specifically, refer to the above Figure 1 The lidar 120 in the point cloud dataset acquisition device 110 acquires the scanning results of objects in the interior space of a preset carriage, and then sends the scanning results to the server 140 via the communication module 130, so that the server 140 can obtain the initial point cloud dataset of the interior space of the preset carriage. The lidar 120's field of view faces the interior space so that it can scan the light emitted from the preset carriage to obtain the scanning results of objects in the interior space of the preset carriage.

[0072] S220. Based on the preset minimum measurement size, the internal space is divided to obtain the number of unit three-dimensional spaces of the internal space.

[0073] Wherein, the unit solid space is the unit solid space corresponding to the preset minimum measurement size d.

[0074] Specifically, the space inside the preset carriage is divided according to a preset minimum measurement size d, resulting in N units of carriage interior space. This preset minimum measurement size d can be selected based on actual conditions; for example, it can be set to 50. This divides the carriage interior space into units of 50 as the minimum measurement size, thus standardizing the data of the preset carriage interior space using the minimum measurement size (d = 50).

[0075] S230. Based on the preset minimum measurement size, the initial point cloud dataset is transformed to obtain the transformed point cloud dataset.

[0076] Specifically, the initial point cloud dataset A is transformed according to the preset minimum measurement size d to obtain the transformed point cloud dataset S, which facilitates the calculation of the initial point cloud dataset A and thus improves the efficiency of the method for determining the space utilization rate inside the carriage.

[0077] S240. Perform outlier detection on the converted point cloud dataset, obtain and filter out outliers to obtain a valid point cloud dataset.

[0078] Specifically, outlier detection is performed on the transformed point cloud dataset S using a preset algorithm. The preset algorithm can be selected according to the actual situation. For example, the preset algorithm can be the GLOSH (Global and Local Outlier Scoresusing Hierarchies) algorithm, which is a global and local outlier scoring method based on hierarchical results.

[0079] The GLOSH algorithm is used to identify data points with abnormal behavior in the point cloud dataset S, both overall and locally, to detect outliers in the point cloud dataset S. Outliers (i.e., abnormal points) in the point cloud dataset S are then filtered out, resulting in a valid point cloud dataset S1.

[0080] S250. Based on the number of valid point cloud datasets and the number of unit three-dimensional spaces, determine the utilization rate of the interior space of the preset carriage.

[0081] In a possible implementation, the utilization rate V of the interior space of the preset carriage is determined by the following formula (1) based on the number of valid cloud point data len(S1) in the valid point cloud data set S1 and the number of unit three-dimensional spaces N.

[0082] V = len(S1) / N (1)

[0083] An embodiment of the present invention provides a method for determining the utilization rate of interior space in a carriage. This method involves acquiring an initial point cloud dataset of the interior space of a preset carriage from a LiDAR sensor at a preset location at the opening of the carriage. The interior space is then segmented according to a preset minimum measurement size to obtain the number of unit three-dimensional spaces within the interior space. Next, the initial point cloud dataset is transformed according to the preset minimum measurement size to obtain a transformed point cloud dataset. Outlier detection is performed on the transformed point cloud dataset to obtain and filter out abnormal points, resulting in a valid point cloud dataset. Finally, the utilization rate of the interior space of the preset carriage is determined based on the number of valid point cloud datasets and the number of unit three-dimensional spaces. Therefore, this application can obtain the number of valid point cloud datasets and the number of unit solid spaces based on the initial point cloud dataset, thereby determining the utilization rate of the interior space of a preset carriage. This method for determining the utilization rate of carriage interior space is based on the initial point cloud dataset of a non-completely closed object contour, which improves the accuracy of determining the utilization rate of carriage interior space. Furthermore, since the size of the interior space inside a carriage varies in real-world scenarios, the interior space inside the carriage is divided according to a preset minimum measurement size to obtain the number of unit solid spaces. This allows the interior space inside the carriage to be standardized using the preset minimum measurement size, which facilitates subsequent data calculation and improves the efficiency of the method for determining the utilization rate of carriage interior space. At the same time, using the method for determining the utilization rate of carriage interior space of this application can also reduce development costs.

[0084] As an optional implementation, step S230 above, which involves transforming the initial point cloud dataset according to a preset minimum measurement size to obtain a transformed point cloud dataset, may include:

[0085] The initial point cloud dataset is transformed based on the preset minimum measurement size and the length unit corresponding to the preset minimum measurement size to obtain the transformed point cloud dataset.

[0086] The unit of length corresponding to the preset minimum measurement dimension d can be selected according to the actual situation. For example, the unit of length can be millimeters (mm).

[0087] In possible implementations, since the length unit corresponding to the measurement size of the space inside a general carriage is meter (m), the initial point cloud dataset A can be converted according to the preset minimum measurement size d (mm), and the converted point cloud dataset S can be obtained by using the following formula (2).

[0088] S= A*1000 / d (2)

[0089] As an optional implementation, step S220 above, which involves dividing the internal space according to a preset minimum measurement size to obtain the number of cubes in the internal space, may include:

[0090] Based on the preset minimum measurement size and the effective size of the internal space, the internal space is divided to obtain the number of unit three-dimensional spaces.

[0091] Taking the interior space of the preset carriage as a cuboid as an example, the effective maximum length of the interior space of the preset carriage is L_max meters; the effective maximum width is W_max meters; and the effective maximum height is H_max meters.

[0092] In possible implementations, the internal space inside the car can be divided according to the preset minimum measurement size d (mm) and the effective maximum length of the internal space as L_max meters; the effective maximum width as W_max meters; and the effective maximum height as H_max meters. The number of unit three-dimensional spaces N can be obtained by using the following formula (3).

[0093] N=L_max*1000 / d ×W_max*1000 / d ×L_max*1000 / d (3)

[0094] As an optional implementation method, Figure 4 A flowchart illustrating the method for determining the utilization rate of interior space provided in this application embodiment. Figure 2 .like Figure 4 As shown above, before determining the utilization rate of the interior space of the preset carriage based on the number of valid point cloud point datasets and the number of cubes, the method may further include:

[0095] S310. Based on the effective point cloud dataset, perform a saturation judgment on the internal space and obtain the saturation judgment result.

[0096] Specifically, a saturation judgment is performed on the effective point cloud dataset S1 of the interior space of the carriage to obtain the saturation judgment result, so as to quickly determine the space utilization rate of the current carriage and then determine the loading rate of the current carriage.

[0097] S320. Based on the saturation judgment result, fill the effective point cloud dataset in the first direction to obtain the first filled point cloud dataset.

[0098] Wherein, the first direction Y is the width direction of the preset carriage, that is, the width direction of the preset carriage is the corresponding width of the rear of the preset vehicle.

[0099] Specifically, based on the saturation judgment result, the effective point cloud dataset S1 is filled with points in the first direction X to obtain the filled first point cloud dataset S2, so that the accuracy of the obtained first point cloud dataset S2 in the first direction X is higher, which facilitates the rapid calculation of the internal space utilization rate of the current carriage corresponding to each frame of point cloud data.

[0100] S330. In the second direction, the first point cloud dataset is filled to obtain the second point cloud dataset.

[0101] Wherein, the second direction X is the length direction of the preset carriage, that is, the length direction of the preset carriage is the direction of extension from the rear to the front of the preset vehicle.

[0102] Specifically, based on the saturation judgment result, the first point cloud dataset S2 is filled with points in the second direction X to obtain the second point cloud dataset S3, so that the accuracy of the second point cloud dataset S3 in the second direction X is higher, which facilitates the rapid calculation of the internal space utilization rate of the current carriage corresponding to each frame of point cloud data.

[0103] S340. Fill the second point cloud dataset in the third direction to obtain the third point cloud dataset.

[0104] Wherein, the third direction Z is the height direction of the preset carriage, that is, the height direction of the preset carriage is the vertical direction from the point cloud dataset acquisition device on the preset vehicle to the ground.

[0105] Specifically, based on the saturation judgment result, the second point cloud dataset S3 is filled with points in the third direction Z to obtain the third point cloud dataset S4, so that the accuracy of the obtained third point cloud dataset S4 in the third direction Z is higher, which facilitates the rapid calculation of the internal space utilization rate of the current carriage corresponding to each frame of point cloud data.

[0106] In each preset direction, the effective point cloud dataset S1 is continuously filled to obtain the third point cloud dataset S4. Based on the number of effective point cloud datasets and the number of cubes, the utilization rate of the interior space of the preset carriage can be determined, which may include:

[0107] S350. Based on the number of point cloud data in the third point cloud dataset and the number of cubes, determine the utilization rate of the interior space of the preset carriage.

[0108] Specifically, based on the third point cloud dataset S4 obtained after filling each preset direction of the effective point cloud dataset S1, the number of point cloud data in the third point cloud dataset S4, len(S4), is calculated, and according to the calculation formula (3) of the above embodiment, the number of unit solid space N4 corresponding to the third point cloud dataset S4 is calculated. Based on the number of point cloud data, len(S4), and the number of unit solid space N4, the utilization rate V of the preset carriage's internal space is determined by formula (1), that is, V = len(S4) / N4.

[0109] This invention provides a method for determining the utilization rate of space inside a train carriage. Based on an effective point cloud dataset, the internal space is saturated to obtain a saturation judgment result. Then, based on the saturation judgment result, the effective point cloud dataset is filled in a first direction to obtain a filled first point cloud dataset. Next, the first point cloud dataset is filled in a second direction to obtain a second point cloud dataset. Finally, the second point cloud dataset is filled in a third direction to obtain a third point cloud dataset. Finally, the utilization rate of the interior space of a preset carriage is determined based on the number of point cloud data and the number of cubes in the third point cloud dataset. Therefore, this application, by filling the point cloud data in each preset direction of the effective point cloud dataset, achieves higher accuracy in the final third point cloud dataset, thereby enabling rapid calculation of the current carriage's interior space utilization rate corresponding to each frame of point cloud data.

[0110] As an optional implementation, this application also provides a possible way for cross-platform application development software to obtain parameters. Figure 5 A flowchart illustrating the method for determining the utilization rate of interior space provided in this application embodiment. Figure 3 .like Figure 5 As shown above, based on the effective point cloud point dataset, the internal space is saturated, and the saturation judgment result can include:

[0111] S410. Calculate the coordinates of the center position based on the valid point cloud dataset.

[0112] Specifically, the number of valid point cloud data points in the valid point cloud dataset S1 is counted as len(S1). The center position of the valid point cloud dataset S1 is then len(S1) / 2. The coordinates of the valid point cloud data point corresponding to the len(S1) / 2th valid point cloud data point in the valid point cloud dataset S1 are the coordinates (xˉ,yˉ,zˉ) of the center position of the valid point cloud dataset S1.

[0113] S420. Based on the coordinates of the center position and the preset coordinate origin, determine the distance of the center position in the preset three directions.

[0114] The three preset directions include the first direction Y, the second direction X, and the third direction Z; the preset coordinate origin can be selected according to the actual situation, for example, the preset coordinate origin can be (0, 0, 0).

[0115] In a possible implementation, the distance D of the center position in the three preset directions can be determined by the following formula (4) based on the coordinates (xˉ, yˉ, zˉ) of the center position and the preset coordinate origin (e.g., (0, 0, 0)).

[0116]

[0117] Where DY is the center position distance in the first direction; DX is the center position distance in the second direction; and DZ is the center position distance in the third direction.

[0118] S430. Calculate the distance ratio in the three preset directions based on the distance of the center position in the three preset directions and the maximum length in the three preset directions.

[0119] In a possible implementation, the distance ratio t in the three preset directions can be calculated using the following formula (5) based on the distances DY, DX and DZ of the center position in the three preset directions, as well as the maximum lengths Yp, Xp and Zp in the three preset directions.

[0120]

[0121] Where ty is the distance percentage in the first direction; tx is the distance percentage in the second direction; and tz is the distance percentage in the third direction.

[0122] S440. If at least two of the three preset distance percentages are less than a preset threshold, the saturation judgment result is determined as the first judgment result, which is used to indicate that the internal space is saturated.

[0123] The preset threshold can be selected according to the actual situation; for example, the preset threshold can be 20%.

[0124] Specifically, if at least two of the three preset distance percentages are less than a preset threshold (e.g., 20%), then the saturation judgment result is determined as the first judgment result, that is, the objects in the interior space of the carriage have reached a saturation state, and no more objects can be loaded into the carriage.

[0125] S450. If at least two of the three preset distance percentages are greater than or equal to a preset threshold, the saturation judgment result is determined as the second judgment result, which is used to indicate that the internal space is not saturated.

[0126] Specifically, if at least two of the three preset distance percentages are greater than or equal to a preset threshold (e.g., 20%), the saturation judgment result is determined as the second judgment result, meaning that the objects in the interior space of the carriage have not reached a saturated state, and the carriage can then be loaded with more objects.

[0127] This invention provides a method for determining the space utilization rate inside a train carriage. Based on an effective point cloud dataset, the coordinates of the center position are calculated. Then, based on the center position coordinates and a preset origin, the distances of the center position in three preset directions are determined. Based on the distances of the center position in the three preset directions and the maximum length in each of the three preset directions, the distance percentages in those directions are calculated. If at least two of the distance percentages in the three preset directions are less than a preset threshold, a saturation judgment result is determined as a first judgment result, indicating that the internal space is saturated. If at least two of the distance percentages in the three preset directions are greater than or equal to the preset threshold, a saturation judgment result is determined as a second judgment result, indicating that the internal space is not saturated. Therefore, this application determines the saturation of the train carriage's internal space based on the fact that at least two of the distance percentages in the three preset directions are less than a preset threshold, enabling rapid determination of the current space utilization rate of the train carriage and thus the current loading rate of the train carriage.

[0128] As an optional implementation method, Figure 6 A flowchart illustrating the method for determining the utilization rate of interior space provided in this application embodiment. Figure 4 .like Figure 6 As shown above, based on the saturation judgment result, the effective point cloud dataset is filled in the first direction to obtain the filled first point cloud dataset, which may include:

[0129] S510, Saturation Judgment: The saturation judgment result indicates whether the internal space is saturated.

[0130] If yes, proceed to step S520; otherwise, proceed to step S530.

[0131] Specifically, based on the above calculation of the distance percentage t in the three preset directions, it is determined whether the distance percentage in at least two of the three preset directions is less than a preset threshold (e.g., 20%).

[0132] S520. If the saturation judgment result indicates that the internal space is saturated, then in the first direction, the effective point cloud dataset is filled in the direction away from the lidar to obtain the first point cloud dataset.

[0133] If the saturation judgment result indicates that the internal space is saturated, that is, at least two of the three preset distance ratios are less than the preset threshold (e.g., 20%), then in the first direction Y, towards the direction away from the lidar, that is, the other side of the lidar's installation direction, such as the left side of the lidar, the effective point cloud dataset S1 is filled. During the filling process, when encountering existing point cloud data or the preset carriage boundary, the filling of the effective point cloud dataset S1 is stopped, and all supplementary point cloud data is added to the effective point cloud dataset S1 to obtain the first point cloud dataset S2.

[0134] S520. If the saturation judgment result indicates that the internal space is not saturated, then the two-sided oscillation insertion method is used in the first direction to fill the effective point cloud dataset to obtain the first point cloud dataset.

[0135] If the saturation judgment result indicates that the internal space is not saturated, that is, at least two of the three preset distance ratios are greater than or equal to the preset threshold (e.g., 20%), then in the first direction Y, the effective point cloud dataset S1 is filled using the two-sided oscillation insertion method. During the filling process, when an existing point cloud data or the preset carriage boundary is encountered, the filling of the effective point cloud dataset S1 is stopped, and all supplementary point cloud data is added to the effective point cloud dataset S1 to obtain the first point cloud dataset S2.

[0136] Among them, the two-sided oscillating insertion method is a strategy to solve the problem of requiring certain elements to be non-adjacent. It involves first arranging the other elements, and then inserting the specified non-adjacent elements into the gaps or ends of the already arranged elements, thus solving the problem. For example, filling the space between valid point cloud data B1 and valid point cloud data B4 with adjacent valid point cloud data B2 and B3, where valid point cloud data B2 and B3 are points that do not exist in the valid point cloud dataset S1, are filled using the two-sided oscillating insertion method.

[0137] It should be noted that the oscillation scale on both sides in the two-sided oscillation insertion method can be selected according to the actual situation, and there is no restriction here. For example, the oscillation scale on both sides can be selected as 2.

[0138] This invention provides a method for determining the utilization rate of space inside a train carriage. A saturation judgment result indicates whether the internal space is saturated. If the saturation judgment result indicates that the internal space is saturated, then in a first direction, the effective point cloud dataset is filled in the direction away from the lidar to obtain a first point cloud dataset. If the saturation judgment result indicates that the internal space is not saturated, then in the first direction, a two-sided oscillating insertion method is used to fill the effective point cloud dataset to obtain the first point cloud dataset. Therefore, this application first fills the effective point cloud dataset in the first direction to obtain the first point cloud dataset, thus pre-filling the saturation of the effective point cloud dataset in the carriage's internal space, resulting in higher accuracy of the final first point cloud dataset. This enables rapid calculation of the current carriage's internal space utilization rate corresponding to each frame of point cloud data.

[0139] As an optional implementation, as shown above, filling the first point cloud dataset in the second direction to obtain the second point cloud dataset may include:

[0140] The first point cloud dataset is filled in the second direction towards the front of the vehicle where the preset carriage is located to obtain the second point cloud dataset.

[0141] Specifically, in the second direction X, i.e. towards the front of the vehicle where the preset carriage is located, the first point cloud dataset S2 obtained in the above embodiment is filled with point cloud data to obtain the second point cloud dataset S3, so that the accuracy of the second point cloud dataset S3 in the second direction X is higher, which facilitates the rapid calculation of the internal space utilization rate of the current carriage corresponding to each frame of point cloud data.

[0142] As an optional implementation, as shown above, filling the second point cloud dataset in a third-party direction to obtain a third point cloud dataset may include:

[0143] The second point cloud dataset is filled in the direction of the floor of the vehicle where the preset carriage is located, in the direction of the third point upward, to obtain the third point cloud dataset.

[0144] Specifically, in the third direction Z, that is, towards the floor of the vehicle where the preset carriage is located, the second point cloud dataset S3 is filled with points to obtain the third point cloud dataset S4, so that the accuracy of the third point cloud dataset S4 in the third direction Z is higher, which facilitates the rapid calculation of the internal space utilization rate of the current carriage corresponding to each frame of point cloud data.

[0145] Based on the same inventive concept, this application also provides a vehicle interior space utilization rate determination device corresponding to the method for determining vehicle interior space utilization rate. Since the principle of the device in this application is similar to the above-mentioned vehicle interior space utilization rate determination method in this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0146] Figure 7 This is a schematic diagram of a device for determining the utilization rate of interior space in a vehicle, provided as an embodiment of this application. Figure 7 As shown, the carriage interior space utilization determination device 60 includes:

[0147] The acquisition module 61 is used to acquire the initial point cloud dataset of the interior space of the preset carriage collected by the lidar at a preset position at the opening of the preset carriage; the lidar's field of view is directed towards the interior space.

[0148] The segmentation module 62 is used to segment the internal space according to the preset minimum measurement size to obtain the number of unit solid spaces in the internal space; wherein, the unit solid space is the unit solid space corresponding to the preset minimum measurement size;

[0149] The conversion module 63 is used to convert the initial point cloud dataset according to the preset minimum measurement size to obtain the converted point cloud dataset;

[0150] The filtering module 64 is used to detect outliers in the converted point cloud dataset, obtain and filter out abnormal points, and obtain a valid point cloud dataset.

[0151] The determination module 65 is used to determine the utilization rate of the interior space of the preset carriage based on the number of valid point cloud point datasets and the number of unit three-dimensional spaces.

[0152] As an optional implementation, the conversion module 63 is specifically used for:

[0153] The initial point cloud dataset is transformed based on the preset minimum measurement size and the length range corresponding to the preset minimum measurement size to obtain the transformed point cloud dataset.

[0154] As an optional implementation, the segmentation module 62 is specifically used for:

[0155] Based on the preset minimum measurement size and the effective size of the internal space, the internal space is divided to obtain the number of unit three-dimensional spaces.

[0156] As an optional implementation, the determining module 65 is further configured to:

[0157] Based on the effective point cloud dataset, the internal space is saturated, and the saturation judgment result is obtained.

[0158] Based on the saturation judgment result, the effective point cloud dataset is filled in the first direction to obtain the first filled point cloud dataset; where the first direction is the width direction of the preset carriage.

[0159] In the second direction, the first point cloud dataset is filled to obtain the second point cloud dataset; the second direction is the length direction of the preset carriage.

[0160] The third point cloud dataset is obtained by filling the second point cloud dataset in the third direction; where the third direction is the height direction of the preset carriage.

[0161] Based on the number of valid point cloud datasets and the number of cubes, the utilization rate of the interior space of the preset carriage is determined, including:

[0162] Based on the number of point cloud data points and the number of cubes in the third point cloud dataset, the utilization rate of the interior space of the preset carriage is determined.

[0163] As an optional implementation, the determining module 65 is specifically used for:

[0164] Calculate the coordinates of the center position based on the valid point cloud dataset;

[0165] Based on the coordinates of the center position and the preset origin, determine the distances of the center position in three preset directions; the three preset directions include the first direction, the second direction, and the third direction; based on the distances of the center position in the three preset directions and the maximum length in the three preset directions, calculate the proportion of the distances in the three preset directions.

[0166] If the distance percentages in at least two of the three preset directions are less than the preset threshold, then the saturation judgment result is determined as the first judgment result, which is used to indicate that the internal space is saturated.

[0167] If at least two of the three preset distance percentages are greater than or equal to a preset threshold, then the saturation judgment result is determined as the second judgment result, which is used to indicate that the internal space is not saturated.

[0168] As an optional implementation, the determining module 65 is specifically used for:

[0169] If the saturation judgment result indicates that the internal space is saturated, then in the second direction, the effective point cloud dataset is filled in the direction away from the lidar to obtain the first point cloud dataset.

[0170] If the saturation judgment result indicates that the internal space is not saturated, then the two-sided oscillation insertion method is used in the second direction to fill the effective point cloud dataset to obtain the first point cloud dataset.

[0171] As an optional implementation, the determining module 65 is specifically used for:

[0172] The first point cloud dataset is filled in the second direction towards the front of the vehicle where the preset carriage is located to obtain the second point cloud dataset.

[0173] As an optional implementation, the determining module 65 is specifically used for:

[0174] The second point cloud dataset is filled in the direction of the floor of the vehicle where the preset carriage is located, in the direction of the third point upward, to obtain the third point cloud dataset.

[0175] This application embodiment also provides a server 70, such as Figure 8 As shown, Figure 8 The server structure diagram provided in this application embodiment includes: a processor 71 and a memory 72, and optionally, a bus 63. The memory 72 stores machine-readable instructions executable by the processor 71. When the server 70 is running, the processor 71 and the memory 72 communicate via the bus 73. When the machine-readable instructions are executed by the processor 71, the steps of the method described in the foregoing method embodiment are executed.

[0176] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described method for determining the utilization rate of space inside a carriage.

[0177] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0178] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0179] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for determining the utilization rate of space inside a train carriage, characterized in that, The method includes: Obtain an initial point cloud dataset of the interior space of the preset carriage, collected by a lidar at a preset position at the opening of the preset carriage; the lidar's field of view is directed toward the interior space; The internal space is divided according to a preset minimum measurement size to obtain the number of unit three-dimensional spaces of the internal space; wherein, the unit three-dimensional space is the unit three-dimensional space corresponding to the preset minimum measurement size; The initial point cloud dataset is transformed according to the preset minimum measurement size to obtain the transformed point cloud dataset; Outlier detection is performed on the transformed point cloud dataset to obtain and filter out outliers, resulting in a valid point cloud dataset. Calculate the coordinates of the center position based on the effective point cloud dataset; Based on the coordinates of the center position and the preset coordinate origin, the distances of the center position in three preset directions are determined; the three preset directions include a first direction, a second direction, and a third direction; wherein, the first direction is the width direction of the preset carriage, the second direction is the length direction of the preset carriage, and the third direction is the height direction of the preset carriage. Based on the distance of the center position in the three preset directions and the maximum length in the three preset directions, calculate the proportion of the distance in the three preset directions; If at least two of the distance percentages in the three preset directions are less than a preset threshold, then the saturation judgment result is determined as the first judgment result, which is used to indicate that the internal space is saturated. If at least two of the distance percentages in the three preset directions are greater than or equal to the preset threshold, then the saturation judgment result is determined to be the second judgment result, which is used to indicate that the internal space is not saturated. If the saturation judgment result indicates that the internal space is saturated, then in the first direction, the effective point cloud dataset is filled in the direction away from the lidar to obtain the first point cloud dataset; If the saturation judgment result indicates that the internal space is not saturated, then the effective point cloud dataset is filled by the two-sided oscillation insertion method in the first direction to obtain the first point cloud dataset. In the second direction, the first point cloud dataset is filled to obtain the second point cloud dataset; The third party populates the second point cloud dataset upwards to obtain the third point cloud dataset; The utilization rate of the interior space of the preset carriage is determined based on the number of point cloud data in the third point cloud dataset and the number of unit three-dimensional spaces.

2. The method according to claim 1, characterized in that, The step of transforming the initial point cloud dataset according to a preset minimum measurement size to obtain a transformed point cloud dataset includes: The initial point cloud dataset is transformed according to the preset minimum measurement size and the length unit corresponding to the preset minimum measurement size to obtain the transformed point cloud dataset.

3. The method according to claim 1, characterized in that, The step of dividing the internal space according to the preset minimum measurement size to obtain the number of cubes in the internal space includes: Based on the preset minimum measurement size and the effective size of the internal space, the internal space is divided to obtain the number of unit three-dimensional spaces.

4. The method according to claim 1, characterized in that, In the second direction, the first point cloud dataset is filled to obtain a second point cloud dataset, including: The first point cloud dataset is filled in the second direction towards the front of the vehicle where the preset carriage is located to obtain the second point cloud dataset.

5. The method according to claim 1, characterized in that, The process of populating the second point cloud dataset in a third-party direction to obtain a third point cloud dataset includes: The second point cloud dataset is filled in the direction of the floor of the vehicle where the preset carriage is located, upwards from the third point, to obtain the third point cloud dataset.

6. A device for determining the utilization rate of interior space in a train carriage, characterized in that, The device includes: The acquisition module is used to acquire the initial point cloud dataset of the interior space of the preset carriage, collected by a lidar at a preset position at the opening of the preset carriage; the lidar's field of view is directed towards the interior space. The segmentation module is used to segment the internal space according to a preset minimum measurement size to obtain the number of unit three-dimensional spaces of the internal space; wherein, the unit three-dimensional space is the unit three-dimensional space corresponding to the preset minimum measurement size; The conversion module is used to convert the initial point cloud dataset according to the preset minimum measurement size to obtain the converted point cloud dataset. The filtering module is used to detect outliers in the converted point cloud dataset, obtain and filter out abnormal points, and obtain a valid point cloud dataset. The determination module is used to calculate the coordinates of the center position based on the effective point cloud dataset; determine the distance of the center position in three preset directions based on the coordinates of the center position and a preset origin; the three preset directions include a first direction, a second direction, and a third direction; wherein the first direction is the width direction of the preset carriage, the second direction is the length direction of the preset carriage, and the third direction is the height direction of the preset carriage; calculate the distance ratio of the three preset directions based on the distance of the center position in the three preset directions and the maximum length in the three preset directions; if the distance ratio of at least two of the three preset directions is less than a preset threshold, then the saturation judgment result is determined as the first judgment result, which is used to indicate that the internal space is saturated; if the distance ratio of at least two of the three preset directions is less than a preset threshold, then the saturation judgment result is determined as the first judgment result, which is used to indicate that the internal space is saturated; if the distance ratio of at least two of the three preset directions is less than a preset threshold, then the saturation judgment result is determined as the first judgment result. If the value is greater than or equal to the preset threshold, the saturation judgment result is determined as the second judgment result, which indicates that the internal space is not saturated. If the saturation judgment result indicates that the internal space is saturated, the effective point cloud dataset is filled in the first direction in the direction away from the lidar to obtain a first point cloud dataset. If the saturation judgment result indicates that the internal space is not saturated, the effective point cloud dataset is filled in the first direction using a two-sided oscillation insertion method to obtain the first point cloud dataset. The first point cloud dataset is filled in the second direction to obtain a second point cloud dataset. The second point cloud dataset is filled in the third direction to obtain a third point cloud dataset. The utilization rate of the internal space of the preset carriage is determined based on the number of point cloud data in the third point cloud dataset and the number of unit three-dimensional spaces.

7. A server, characterized in that, include: A processor and a memory, the processor being configured to execute a van loading rate determination program stored in the memory to implement the vehicle space utilization method of any one of claims 1 to 5.

Images