A method, apparatus and medium for determining a scene change rate of a target object

Abstract

The present disclosure relates to the technical field of testing, and discloses a method, device and medium for determining a scene change rate of a target object, the method comprising: for any one grid in a grid map corresponding to the target object, determining an equivalent occupancy rate of the any one grid based on each element in a target weight matrix corresponding to the any one grid and a change value of an occupancy situation of a target grid group, the target grid group comprising a plurality of grids centered on the any one grid, each grid in the target grid group corresponding to each element in one-to-one correspondence, the target weight matrix being used to represent a contribution rate of a change in the occupancy situation of the target grid group, and determining the scene change rate of the target object based on each grid with a target occupancy rate and all grids corresponding to the target object in the grid map, thereby improving the accuracy of the scene change rate of the target object after considering the influence of the occupancy rate change of surrounding grids on a certain grid.

Description

Technical Field

[0001] This disclosure relates to the field of testing technology, and provides a method, apparatus and medium for determining the scene change rate of a target object. Background Technology

[0002] In scenarios such as warehousing and logistics, and smart factories, mobile robots typically locate and navigate using grid maps. A grid map is an electronic map that breaks down the spatial environment of a warehouse, factory, or similar facility into local units. During implementation, the state of each grid is described by whether it is occupied by obstacles (e.g., shelves). Typically, each grid corresponds to a numerical value indicating whether it is occupied by an obstacle. This provides a detailed description of the environment, enabling the robot to locate itself and plan its path.

[0003] To measure the change in occupancy of a location in an environment, one can determine it by the changes in the values ​​of each grid in a binary or grayscale image. However, considering that the shape of obstacles is difficult to perfectly match with the grid, the method of corresponding a grid with a value in a binary or grayscale image is difficult to accurately measure the change in the occupancy of a target object. Summary of the Invention

[0004] This disclosure provides a method, apparatus, and medium for determining the scene change rate of a target object, thereby improving the accuracy of the change in the occupancy rate of the target object.

[0005] The specific technical solution provided in this disclosure is as follows:

[0006] In a first aspect, embodiments of this disclosure provide a method for determining the scene change rate of a target object, comprising:

[0007] For any grid cell in the grid map, the equivalent occupancy rate of any grid cell is determined based on the change in the occupancy of the target grid group and the elements in the target weight matrix corresponding to the grid cell. The grid map is the map corresponding to the target object, the target grid group includes multiple grid cells centered on any grid cell, and each grid cell in the target grid group corresponds one-to-one with each element. The target weight matrix is ​​used to characterize the contribution rate of the change in the occupancy of the target grid group.

[0008] Based on the equivalent occupancy rate as the target occupancy rate for each grid and all grids corresponding to the target object in the grid map, determine the scene change rate of the target object.

[0009] Optionally, the change in occupancy of the target grid group can be determined in the following way:

[0010] Perform the following operations on any cell in the target raster group:

[0011] The first occupancy status of the grid is determined at a first preset time, wherein the first occupancy status is used to characterize the probability that the grid is occupied by an obstacle;

[0012] The second occupancy status of the grid is determined at the second preset time, wherein the second occupancy status is used to characterize the probability that the grid is occupied by an obstacle, and the duration between the second preset time and the first preset time is greater than the preset duration;

[0013] The absolute value of the difference between the first and second occupancy situations is determined as the change value of the grid's occupancy.

[0014] Optionally, the target raster group corresponding to any given raster can be determined in the following way:

[0015] Determine the order of the preset target weight matrix, wherein the type of the target weight matrix is ​​a mean filter matrix or a Gaussian operator matrix, and the order is N*N;

[0016] If any row or column of any grid cell is located at the edge of the grid map, then blank grid cells are added outside the edge of the grid map so that the number of rows or columns of the grid group centered on any grid cell and including at least one blank grid cell is the same as the order. The grid group centered on any grid cell and including at least one blank grid cell is determined as the target grid group corresponding to any grid cell, wherein the change value of the occupancy of blank grid cells is zero.

[0017] Otherwise, a surrounding grid is defined around any given grid so that the number of rows or columns of the grid group centered on any given grid and including the surrounding grids is the same as the order, and the grid group consisting of any given grid and the surrounding grids is defined as the target grid group corresponding to any given grid.

[0018] Optionally, if the map corresponding to the target object is a 3D map, then the order of the target weight matrix is ​​N*N*N.

[0019] Optionally, based on the changes in the occupancy of each element in the target weight matrix corresponding to any given raster and the occupancy status of the target raster group, the equivalent occupancy rate of any raster is determined, including:

[0020] The target weight matrix is ​​associated with each grid in the target grid group to obtain a set of association relationships between grids and elements. Among them, the element located at the center of the target weight matrix corresponds one-to-one with the change value of the occupancy of the grid located at the center of the target grid group, and the element located at the periphery of the target weight matrix corresponds one-to-one with the change value of the occupancy of the grid located at the edge of the target grid group.

[0021] Multiply the element in any association with the change in the occupancy of the grid in any association to obtain the association product value corresponding to any association.

[0022] The equivalent occupancy rate of any grid cell is determined by summing the product values ​​of each association in the association set.

[0023] Optionally, based on the equivalent occupancy rate of each grid cell representing the target occupancy rate and all grid cells corresponding to the target object in the grid map, the scene change rate of the target object is determined, including:

[0024] Determine the grid area corresponding to each grid with an equivalent occupancy rate as the target occupancy rate, and add up the grid areas to obtain the grid occupancy area;

[0025] Determine the total area of ​​all grid cells corresponding to the target object in the grid map;

[0026] The ratio of the area occupied by the grid to the total area of ​​the grid is determined as the scene change rate of the target object.

[0027] Optionally, if the target object is not rectangular, the corresponding grid map is determined as follows:

[0028] If the raster map is not rectangular, add raster cells to the edges of the raster map until the raster map is rectangular.

[0029] Secondly, embodiments of this disclosure also provide an apparatus for determining the scene change rate of a target object, comprising:

[0030] The first determining unit is used to determine the equivalent occupancy rate of any grid cell in the grid map based on the change values ​​of each element in the target weight matrix corresponding to the grid cell and the occupancy of the target grid group. The grid map is the map corresponding to the target object, the target grid group includes multiple grid cells centered on the grid cell, and each grid cell in the target grid group corresponds one-to-one with each element. The target weight matrix is ​​used to characterize the contribution rate of the change in the occupancy of the target grid group.

[0031] The second determining unit is used to determine the scene change rate of the target object based on each grid and all grids corresponding to the target object in the grid map, with the equivalent occupancy rate as the target occupancy rate.

[0032] Thirdly, a smart terminal includes:

[0033] Memory, used to store executable instructions;

[0034] A processor for reading and executing executable instructions stored in memory to implement the method as described in any of the first aspects.

[0035] Fourthly, a computer-readable storage medium, when instructions in the storage medium are executed by a processor, enables the processor to perform the method described in any of the first aspects above.

[0036] The beneficial effects of this disclosure are as follows:

[0037] In summary, the embodiments of this disclosure provide a method, apparatus, and medium for determining the scene change rate of a target object. The method includes: for any grid cell in a grid map, determining the equivalent occupancy rate of any grid cell based on the change values ​​of each element in the target weight matrix corresponding to the grid cell and the occupancy status of the target grid group. The grid map is a map corresponding to the target object, and the target grid group includes multiple grid cells centered around the grid cell. Each grid cell in the target grid group corresponds one-to-one with each element. The target weight matrix is ​​used to characterize the contribution rate of the change in the occupancy status of the target grid group. Based on each grid cell with the equivalent occupancy rate as the target occupancy rate and all grid cells corresponding to the target object in the grid map, the scene change rate of the target object is determined. By considering the influence of the surrounding grid cells on the change in the occupancy rate of a certain grid cell, the accuracy of the scene change rate of the target object is improved.

[0038] Other features and advantages of this disclosure will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0039] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:

[0040] Figure 1 This is a flowchart illustrating the process of determining the scene change rate of the target object in an embodiment of this disclosure.

[0041] Figure 2 This is a schematic diagram illustrating the occupancy of a target object in an embodiment of this disclosure;

[0042] Figure 3 This is a schematic diagram of a grid map corresponding to the occupancy status of a target object in an embodiment of this disclosure;

[0043] Figure 4 This is a schematic diagram illustrating the occupancy of another target object in an embodiment of this disclosure;

[0044] Figure 5 This is a schematic diagram of a grid map corresponding to the occupancy of another target object in an embodiment of this disclosure;

[0045] Figure 6 This is a schematic diagram illustrating the three-dimensional correspondence between a grid and a target weight matrix in an embodiment of this disclosure;

[0046] Figure 7 This is a schematic diagram illustrating a method for determining a target grid group by supplementing idle grids in an embodiment of this disclosure;

[0047] Figure 8 This is a schematic diagram illustrating another method for determining a target grid group without supplementing empty grids in an embodiment of this disclosure;

[0048] Figure 9 This is a flowchart illustrating the process of determining the equivalent occupancy rate of any grid in an embodiment of this disclosure.

[0049] Figure 10 This is a flowchart illustrating the process of determining the scene change rate of the target object in an embodiment of this disclosure.

[0050] Figure 11 This is a schematic diagram of the logic architecture of a device for determining the scene change rate of a target object in an embodiment of this disclosure;

[0051] Figure 12 This is a schematic diagram of the physical architecture of the smart terminal in an embodiment of this disclosure. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the technical solutions of this disclosure, and not all embodiments. Based on the embodiments recorded in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the technical solutions of this disclosure.

[0053] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0054] First, let me introduce the main idea of ​​the grid map in this application embodiment: to decompose the environmental space of a target object (e.g., a warehouse) into local units and describe its state by whether these units are occupied by obstacles (e.g., shelves). Simply put, a grid map consists of a series of discrete grids, each with a value indicating whether that grid is occupied by an obstacle. This allows for a detailed description of the target object's obstacle occupancy, facilitating robot localization and path planning.

[0055] Raster maps are typically represented in two ways:

[0056] (1) Use 0 and 1 to represent free and occupied, that is, the raster map is represented by a binary image.

[0057] (2) Considering that the sensor’s judgment of obstacles is probabilistic, a probability value of 0 to 1 is generally used to describe the probability of obstacles in the grid, that is, the grid map is represented by a grayscale image.

[0058] The preferred embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0059] In this embodiment of the disclosure, the system includes at least one smart terminal. During implementation, when it is necessary to determine the scene change rate of a target object, a target weight matrix is ​​added to each grid in the grid map corresponding to the target object. Each element in the target weight matrix is ​​used to measure the change weight of the associated grid, so that the influence of surrounding grids is taken into account in the change of the occupancy rate of any grid, thereby making the determined scene change rate of the target object more accurate.

[0060] In this embodiment of the disclosure, a method for determining the scene change rate of a target object is implemented, mainly executed on the smart terminal side, and will be described in detail below.

[0061] See Figure 1 As shown in the embodiments of this disclosure, a specific process for determining the scene change rate of a target object is as follows:

[0062] Step 201: For any grid cell in the grid map, determine the equivalent occupancy rate of any grid cell based on the elements in the target weight matrix corresponding to that grid cell and the change in the occupancy of the target grid group. Here, the grid map is the map corresponding to the target object, the target grid group includes multiple grid cells centered on any grid cell, and each grid cell in the target grid group corresponds one-to-one with each element. The target weight matrix is ​​used to characterize the contribution rate of the change in the occupancy of the target grid group.

[0063] First, refer to Figure 2As shown, taking warehouse A as an example, warehouse A contains a large number of shelves, meaning the shelves occupy the area of ​​warehouse A. To facilitate people accessing the goods on the shelves, aisles are provided between the shelves, meaning these aisles do not occupy the area of ​​warehouse A. Thus, see... Figure 3 As shown, when the target object is converted into a grid map, the grid corresponding to the shelf is the occupied grid, and the grid corresponding to the alley is the unoccupied free grid.

[0064] If you refer to Figure 4 As shown, the layout of the shelves and aisles in the example above has changed in warehouse A. Therefore, refer to... Figure 5 As shown, the occupancy status of the grids originally occupied by shelves will change, and correspondingly, the occupancy status of the empty grids originally corresponding to the aisles will also change.

[0065] It should be noted that when the target object is rectangular, it can be directly converted into the corresponding raster map; when the target object is not rectangular, the corresponding raster map is determined using the following method:

[0066] If the raster map is not rectangular, add raster cells to the edges of the raster map until the raster map is rectangular.

[0067] Specifically, for non-rectangular raster maps, such as triangular raster maps, during implementation, raster cells are added to the edges of the raster map until the raster map is rectangular. For example, cells are added to both sides of the apex of the aforementioned triangular raster map to obtain a rectangular raster map.

[0068] It should be added that if the raster map of the target object is large, the target object can be divided first. For example, a triangular warehouse. First, the target object needs to be refined. At the same time, in order to ensure the integrity of the target object, it can be divided into multiple connected sub-target objects. For example, the triangular warehouse can be divided into three small triangles and a rectangle, etc.

[0069] If the resulting sub-objects are rectangular, they are converted into corresponding sub-raster maps. If the resulting sub-objects are not rectangular, additional raster maps are needed until all sub-raster maps are rectangular.

[0070] Additionally, it should be noted that the change in grid occupancy includes two types: one is a grid changing from occupied to idle, and the other is a grid changing from idle to occupied. In practice, this is typically represented using a binary image or a grayscale image. For example, in a binary image, 0 represents an idle grid, and 1 represents an occupied grid. In a grayscale image, probability values ​​from 0 to 1 describe the probability that a grid is occupied by an obstacle (e.g., a shelf). The larger the value, the more occupied the grid; conversely, the smaller the value, the more unoccupied the grid.

[0071] Specifically, the change in the occupancy of the target grid group is determined in the following way:

[0072] Perform the following operations on any cell in the target raster group:

[0073] (1) Determine the first occupancy status of the grid at a first preset time, wherein the first occupancy status is used to characterize the probability that the grid is occupied by an obstacle.

[0074] To effectively describe changes in grid occupancy, different preset time points must first be determined, i.e., how often the grid occupancy status should be checked for changes. Typically, these preset time points include at least a first preset time point and a second preset time point, with the first preset time point corresponding to a time point earlier than the second preset time point. During implementation, the first occupancy status of the grid is determined at the first preset time point. This is achieved by measuring the area occupied by obstacles within the grid using sensors, and then dividing this area by the total area of ​​the grid to obtain the area ratio.

[0075] (2) Determine the second occupancy status of the grid at the second preset time, wherein the second occupancy status is used to characterize the probability that the grid is occupied by an obstacle, and the duration between the second preset time and the first preset time is greater than the preset duration.

[0076] Similarly, at the second preset time, the second occupancy status of the grid is determined. This involves measuring the area occupied by obstacles within the grid using sensors, and then dividing the area occupied by obstacles by the total area of ​​the grid described above to obtain the area ratio again. It should be noted that, to effectively describe the changes in grid occupancy, the duration between the second preset time and the first preset time is longer than a preset duration; that is, the duration between the second preset time and the first preset time will not be too short.

[0077] (3) The absolute value of the difference between the first occupancy situation and the second occupancy situation is determined as the change value of the grid occupancy situation.

[0078] After determining the first and second occupancy situations, the difference between the first and second occupancy situations is calculated, and the absolute value of the difference is taken as the change value of the grid occupancy situation.

[0079] The above method can be used to determine the change in the occupancy of any grid cell in a raster map.

[0080] In addition, since the shelves and other structures occupying warehouse A are usually quite large, the number of grids occupied by the shelves is also large. Consequently, the occupancy of a grid is affected by the surrounding grids, and the magnitude of this effect is also related to the distance of the surrounding grids from the grid in question.

[0081] In this embodiment of the application, considering the influence of the surrounding grids on a grid located at the center, when calculating the change in the occupancy of a grid, a target grid group is divided with that grid as the center. At the same time, a target weight matrix is ​​matched to the target grid group. It should be noted that the target grid group and the target weight matrix are in one-to-one correspondence, that is, the number of grids in the target grid group is the same as the number of elements in the target weight matrix. The specific values ​​of the elements in the target weight matrix are used to represent the contribution rate of the change in the occupancy of the corresponding grid, so as to distinguish the influence of different surrounding grids on the occupancy of the grid located at the center.

[0082] During implementation, after converting the target object into a raster map, each raster in the raster map will be used as the object for explanation. In the following description, each raster will be referred to as any raster in the raster map. First, a target raster group is constructed centered on this arbitrary raster. The number of surrounding raster cells in the target raster group depends on the order of the target weight matrix. Typically, the target weight matrix can be pre-set, with the principle that elements located at the edges of the target weight matrix represent zero contribution rates to changes in the occupancy of the corresponding raster.

[0083] Specifically, the target raster group corresponding to any given raster is determined in the following way:

[0084] 1) Determine the order of the preset target weight matrix, wherein the target weight matrix is ​​of the type of mean filter matrix or Gaussian operator matrix, and the order is N*N.

[0085] During implementation, after pre-setting the target weight matrix for the raster map, the order of the target weight matrix is ​​further determined, i.e., the total number of elements included in the target weight matrix is ​​N*N. It should be noted that the target weight matrix is ​​either a mean filter matrix or a Gaussian operator matrix, thus more accurately representing the impact of changes in the occupancy of surrounding rasters on any given raster.

[0086] It should be noted that, see reference Figure 6 As shown, if the map corresponding to the target object is a 3D map, then the order of the target weight matrix is ​​N*N*N.

[0087] During implementation, when the map corresponding to the target object is converted into a 3D map, the order of the corresponding target weight matrix is ​​also three-dimensional, specifically represented as N*N*N. Typically, each element in the aforementioned 3D map is called a voxel.

[0088] 2) If any row or column of any grid cell is located at the edge of the grid map, then add blank grid cells outside the edge of the grid map so that the number of rows or columns of the grid group centered on any grid cell and including at least one blank grid cell is the same as the order. The grid group centered on any grid cell and including at least one blank grid cell is determined as the target grid group corresponding to any grid cell, wherein the change value of the occupancy of blank grid cells is zero.

[0089] Since every cell in a raster map must perform the same operation, when any cell's row or column is located at the edge of the raster map (i.e., any cell is not located in the center of the raster map), refer to... Figure 7 As shown, in order to define the target grid group, multiple blank grids need to be added outside the edges of the grid map. The occupancy of these blank grids changes by 0; typically, the occupancy of these blank grids is always zero by default. In this way, any one of the added grids will be located in the center of the grid map. Furthermore, with any one grid as the center, a grid group including at least one blank grid can be defined as the target grid group corresponding to that grid.

[0090] Since each grid cell in the target grid group corresponds one-to-one with each element, the number of rows or columns of the grid group of the blank grid cells in the target grid group is the same as the order, thus achieving the matching between the target grid group and the target weight matrix.

[0091] 3) Otherwise, define a surrounding grid around any grid so that the number of rows or columns of the grid group centered on any grid and including the surrounding grids are the same as the order, and define the grid group consisting of any grid and the surrounding grids as the target grid group corresponding to any grid.

[0092] If any of the above grid cells is not located at the edge of the grid map, refer to the following during implementation: Figure 8As shown, by directly defining surrounding grids around any one of the above grids, it is possible to form a grid group centered on any one grid, which includes the grid and surrounding grids, and define it as the target grid group corresponding to the grid.

[0093] Similarly, the number of rows or columns of the surrounding grids in the target grid group are the same as the order, thereby achieving the matching between the target grid group and the target weight matrix.

[0094] After determining the target weight matrix and target grid group, the equivalent occupancy rate is determined based on these components. Specifically, the equivalent occupancy rate of any given grid is determined by the changes in the occupancy of each element in the target weight matrix corresponding to that grid and the target grid group. (See [link to relevant documentation]). Figure 9 As shown, it specifically includes:

[0095] Step 2011: Associate the target weight matrix with each grid in the target grid group to obtain a set of association relationships between grids and elements. In the set of association relationships, the element located at the center of the target weight matrix corresponds one-to-one with the change value of the occupancy of the grid located at the center of the target grid group, and the element located around the target weight matrix corresponds one-to-one with the change value of the occupancy of the grid located at the edge of the target grid group.

[0096] During implementation, in order to determine the equivalent occupancy rate of any grid, it is necessary to multiply the change in occupancy of each grid in the grid group to which the grid belongs by the corresponding element in the target weight matrix. The correspondence between the change in occupancy and the element needs to be determined through the set of association relationships. That is, the change in occupancy of which grid corresponds to the element is specified by an association relationship in the set of association relationships.

[0097] It should be noted that the principle of associating the target weight matrix with each grid in the target grid group is positional correspondence. That is, during the implementation process, the element located at the center of the target weight matrix is ​​matched one-to-one with the change value of the occupancy of the grid located at the center of the target grid group, and the element located at the periphery of the target weight matrix is ​​matched one-to-one with the change value of the occupancy of the grid located at the edge of the target grid group.

[0098] Step 2012: Multiply the element in any association with the change in the occupancy of the grid in any association to obtain the association product value corresponding to any association.

[0099] After determining the set of association relationships, for example, for a target weight matrix of order N*N, a set of association relationships including N*N relationships will be established accordingly. During the implementation process, the element in any association relationship is multiplied by the change value of the grid occupancy in any association relationship. In this way, for N*N association relationships, N*N association product values ​​will be obtained.

[0100] Step 2013: Sum the product values ​​of each association in the association set to determine the equivalent occupancy rate of any grid cell.

[0101] For a set of association relationships, after obtaining all the association product values, each association product value is summed. The final summation result is determined as the equivalent occupancy rate of any grid cell. Thus, the calculation of the equivalent occupancy rate of any grid cell takes into account the occupancy of surrounding grid cells.

[0102] Step 202: Based on the equivalent occupancy rate of each grid and all grids corresponding to the target object in the grid map, determine the scene change rate of the target object.

[0103] During implementation, when measuring the scene change rate of target objects corresponding to the entire grid map, it needs to be represented by the ratio of the sum of the actual occupied areas of each grid to the area corresponding to the entire grid map. (See [reference needed]). Figure 10 As shown, it includes:

[0104] Step 2021: Determine the grid area corresponding to each grid with an equivalent occupancy rate of the target occupancy rate, and add up the grid areas to obtain the grid occupancy area.

[0105] Considering that in practical applications, the grid occupancy rate can be represented by a binary image or a grayscale image, the target occupancy rate can be flexibly set. Furthermore, the target occupancy rate can be a specific numerical value or a data range. Preferably, the target occupancy rate is 100%, meaning that the entire area of ​​the grid is occupied.

[0106] During implementation, the first step is to determine each grid cell whose equivalent occupancy rate matches the target occupancy rate. After determining each grid cell, the area of ​​each grid cell is then determined. The areas of all grid cells are then added together, and the sum represents the grid occupancy area.

[0107] Step 2022: Determine the total area of ​​all grid cells corresponding to the target object in the grid map.

[0108] At the same time, the total area of ​​all grid cells in the grid map generated by the target object is determined, that is, the area of ​​each grid cell in the grid map is superimposed to obtain the total area of ​​the grid cells.

[0109] Step 2023: Determine the scene change rate of the target object as the ratio of the area occupied by the grid to the total area of ​​the grid.

[0110] After determining the area occupied by the grid and the total area of ​​the grid, the ratio of the area occupied by the grid to the total area of ​​the grid is calculated, and this ratio is determined as the scene change rate of the target object.

[0111] Based on the same inventive concept, see [reference] Figure 11 As shown, this embodiment of the present disclosure provides an apparatus for determining the scene change rate of a target object, comprising:

[0112] The first determining unit 1101 is used to determine the equivalent occupancy rate of any grid cell in the grid map based on the change values ​​of each element in the target weight matrix corresponding to the grid cell and the occupancy of the target grid group. The grid map is the map corresponding to the target object, the target grid group includes multiple grid cells centered on the grid cell, and each grid cell in the target grid group corresponds one-to-one with each element. The target weight matrix is ​​used to characterize the contribution rate of the change in the occupancy of the target grid group.

[0113] The second determining unit 1102 is used to determine the scene change rate of the target object based on each grid and all grids corresponding to the target object in the grid map, with the equivalent occupancy rate as the target occupancy rate.

[0114] Based on the same inventive concept, see [reference] Figure 12 As shown, this embodiment of the present disclosure provides a smart terminal, including: a memory 1201 for storing executable instructions; and a processor 1202 for reading and executing the executable instructions stored in the memory, and executing any of the methods described in the first aspect above.

[0115] Based on the same inventive concept, embodiments of this disclosure provide a computer-readable storage medium that, when instructions in the storage medium are executed by a processor, enables the processor to perform the method described in any of the first aspects above.

[0116] In summary, the embodiments of this disclosure provide a method, apparatus, and medium for determining the scene change rate of a target object. The method includes: for any grid cell in a grid map, determining the equivalent occupancy rate of any grid cell based on the change values ​​of each element in the target weight matrix corresponding to the grid cell and the occupancy status of the target grid group. The grid map is a map corresponding to the target object, and the target grid group includes multiple grid cells centered around the grid cell. Each grid cell in the target grid group corresponds one-to-one with each element. The target weight matrix is ​​used to characterize the contribution rate of the change in the occupancy status of the target grid group. Based on each grid cell with the equivalent occupancy rate as the target occupancy rate and all grid cells corresponding to the target object in the grid map, the scene change rate of the target object is determined. By considering the influence of the surrounding grid cells on the change in the occupancy rate of a certain grid cell, the accuracy of the scene change rate of the target object is improved.

[0117] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program product systems. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product system implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0118] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program product systems according to this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0119] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0120] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0121] Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.

Claims

1. A method of determining a scene change rate of a target object, characterized by, The method comprises: For any one grid in a grid map, the target weight matrix is associated with each grid in a target grid group to obtain a set of grid-element association relationships, the element in any one association relationship is multiplied by the change value of the occupation of the grid in the any one association relationship to obtain an association product value corresponding to the any one association relationship, and the association product values corresponding to each association relationship in the set of association relationships are summed to determine the equivalent occupation rate of the any one grid, wherein the grid map is a map corresponding to a target object, the target grid group comprises a plurality of grids centered on the any one grid, each grid in the target grid group corresponds to each element one by one, the target weight matrix is used to represent the contribution rate of the change in the occupation of the target grid group, the element located at the center position of the target weight matrix in the set of association relationships corresponds to the change value of the occupation of the grid located at the center of the target grid group one by one, and the element located at the peripheral position of the target weight matrix corresponds to the change value of the occupation of the grid located at the edge of the target grid group one by one; Based on the equivalent occupation rate, the scene change rate of the target object is determined based on each grid with the target occupation rate and all grids corresponding to the target object in the grid map.

2. The method of claim 1, wherein, The change value of the occupation of the target grid group is determined in the following manner: The following operations are performed for any one grid in the target grid group: A first occupation of the grid is determined at a first preset time, wherein the first occupation is used to represent the probability that the grid is occupied by an obstacle; A second occupation of the grid is determined at a second preset time, wherein the second occupation is used to represent the probability that the grid is occupied by an obstacle, and the time length between the second preset time and the first preset time is greater than a preset time length; The absolute value of the difference between the first occupation and the second occupation is determined as the change value of the occupation of the grid.

3. The method of claim 1, wherein, The target grid group corresponding to the any one grid is determined in the following manner: The order of a preset target weight matrix is determined, wherein the type of the target weight matrix is a mean filter matrix or a Gaussian operator matrix, and the order is N*N; If the row or column where the any one grid is located is located at the edge of the grid map, a blank grid is supplemented outside the edge of the grid map, so that the number of rows or columns of a grid group centered on the any one grid and including at least one blank grid is the same as the order, and the grid group centered on the any one grid and including at least one blank grid is determined as the target grid group corresponding to the any one grid, wherein the change value of the occupation of the blank grid is zero. Otherwise, a peripheral grid is drawn around the arbitrary grid, so that the number of rows or columns of the grid group centered on the arbitrary grid and including the peripheral grid is the same as the order, and the grid group composed of the arbitrary grid and the peripheral grid is determined as the target grid group corresponding to the arbitrary grid.

4. The method of claim 3, wherein, If the map corresponding to the target object is a three-dimensional map, the order of the target weight matrix is N*N*N.

5. The method of claim 1, wherein, The method further includes determining a scene change rate of the target object based on all grids corresponding to the target object in the grid map and all grids in which the equivalent occupancy rate is the target occupancy rate. The method further includes determining a grid area corresponding to each of the grids in which the equivalent occupancy rate is the target occupancy rate, and adding the grid areas to obtain a grid occupancy area. The method further includes determining a total sum of grid areas of all grids corresponding to the target object in the grid map. The method further includes determining the scene change rate of the target object as a ratio of the grid occupancy area to the total sum of grid areas.

6. The method according to any one of claims 1 to 5, wherein, If the shape of the target object is not a rectangle, the grid map corresponding to the target object is determined in the following manner. If the shape of the grid map is not a rectangle, grids are supplemented at edges of the grid map until the shape of the grid map is a rectangle.

7. A device for determining the rate of change of a scene for a target object, characterized in that, The method further includes: The first determining unit is configured to, for an arbitrary grid in a grid map, associate a target weight matrix with each grid in a target grid group to obtain a set of association relationships between grids and elements, multiply an element in the arbitrary association relationship with a change value of an occupancy situation of a grid in the arbitrary association relationship to obtain an association product value corresponding to the arbitrary association relationship, and sum the association product values corresponding to each of the association relationships in the set of association relationships to determine an equivalent occupancy rate of the arbitrary grid. The grid map is a map corresponding to a target object. The target grid group includes a plurality of grids centered on the arbitrary grid, and each grid in the target grid group corresponds to one of the elements. The target weight matrix is used to represent a contribution rate of a change in an occupancy situation of the target grid group. An element located at a center position of the target weight matrix corresponds to the change value of the occupancy situation of the grid located at the center of the target grid group. An element located at a peripheral position of the target weight matrix corresponds to the change value of the occupancy situation of the grid located at an edge of the target grid group. The second determining unit is configured to determine a scene change rate of the target object based on all grids corresponding to the target object in the grid map and all grids in which the equivalent occupancy rate is the target occupancy rate.

8. A smart terminal, characterized by The method further includes: The memory is configured to store executable instructions. The processor is configured to read and execute the executable instructions stored in the memory to implement the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor, the processor can execute the method of any one of claims 1-6.

Images