Loading rate determination method and device, electronic equipment and computer program product

Abstract

The embodiment of the invention is suitable for the technical field of image processing, and provides a loading rate determination method and device, electronic equipment and a computer program product, and the method comprises the steps: determining a classification region corresponding to a specified inner wall in a carriage when the carriage is in a no-load state; under the condition that the compartment is in the loading stage, obtaining a loading image of a loading object placed in the compartment; determining a loading boundary of each classification area according to the loading image; the loading rate of the carriage is determined according to the area boundary of each classification area and the loading boundary, so that the loading rate of the carriage can be automatically calculated in real time in the loading stage of the carriage, the classification areas and the loading boundary are obtained by processing the image, and the hardware implementation cost is low.

Description

Technical Field

[0001] The embodiments of the present application belong to the field of image processing technology, and in particular, relate to a method, device, electronic device and computer program product for determining a loading rate. Background Art

[0002] With the rapid development of e-commerce and other fields, the logistics industry has also ushered in great development. Therefore, the transportation management of tens of thousands of parcels has become a core issue facing the logistics industry. Among them, the logistics loading link is particularly important. The current loading and unloading of vehicles basically relies on manual records. The accuracy of the data cannot be verified and the labor cost is high. The timeliness of the data is poor. Therefore, the real-time scheduling of trucks is difficult. Insufficient or excessive volume in the loading process has a serious impact on production and manufacturing, and the efficiency is low.

[0003] In some existing solutions, the cargo volume is calculated after the carriage is detected by a structured light sensor, and then the loading rate is calculated based on the maximum volume of the carriage. These solutions rely on structured light technology and are costly. Since they involve a large amount of data calculation, the requirements for data processing are also high. In addition, since the carriage volumes of different models are not necessarily the same, the maximum volume of the carriage needs to be obtained in advance for different carriages. In various carriage application scenarios, the data collected by the structured light sensor needs to be adapted and calculated one by one, which is very costly. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a loading rate determination method, device, electronic device and computer program product to improve the efficiency of loading rate calculation of the carriage during the loading stage and reduce the hardware cost of loading rate calculation.

[0005] A first aspect of an embodiment of the present application provides a method for determining a loading rate, including: Determine a classification area corresponding to a designated inner wall in the carriage when the carriage is in an empty state; When the carriage is in a loading stage, acquiring a loading image in which a loading object is placed in the carriage; Determining a loading boundary of each of the classification areas according to the loading image; The loading rate of the carriage is determined according to the area boundaries of each of the classification areas and the loading boundaries.

[0006] In some implementations of the first aspect, determining the classification area corresponding to the designated inner wall in the carriage when the carriage is in an empty state includes: Acquire an empty image of the carriage in an empty state; the empty image includes a carriage contour element and a carriage wall element of each inner wall of the carriage; Semantic segmentation is performed on the empty image to generate a classification area corresponding to the designated inner wall.

[0007] In some implementations of the first aspect, determining the classification area corresponding to the designated inner wall in the carriage when the carriage is in an empty state includes: Acquire an empty image of the carriage in an empty state; the empty image includes a carriage contour element and a carriage wall element of each inner wall of the carriage; Performing key point detection on the idle image to generate key point data; A classification area corresponding to the designated inner wall is generated according to the key point data.

[0008] In some implementations of the first aspect, determining the loading boundary of each of the classification areas according to the loading image includes: identifying a target pixel in the loading image corresponding to the loading object; The loading boundary in each classification area is determined according to the target pixel.

[0009] In some implementations of the first aspect, the region boundary includes a first boundary and a second boundary that are parallel to each other; the length of the first boundary is shorter than the second boundary; In the classification area where the target pixel exists, the loading boundary is one of a plurality of line segments that include the target pixel and are parallel to the first boundary; In a classification area where no target pixel exists, the loading boundary is a first boundary.

[0010] In some implementations of the first aspect, determining the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundary includes: Determine the loading proportion according to the length of the loading boundary and the length of the first boundary and the length of the second boundary of the classification area where the loading boundary is located; The loading rate of the carriage is determined according to the loading proportions corresponding to each of the classification areas.

[0011] In some implementations of the first aspect, determining the loading proportion according to the length of the loading boundary and the length of the first boundary and the length of the second boundary of the classification area in which the loading boundary is located includes: determining a first length difference between a length of the loading boundary and a length of the first boundary; determining a second length difference between the length of the second boundary and the length of the first boundary; For each of the classification areas, the loading proportion is determined according to the ratio of the first length difference to the second length difference.

[0012] A second aspect of an embodiment of the present application provides a loading rate determination device, including: A classification area determination module, used to determine a classification area corresponding to a designated inner wall in the carriage when the carriage is in an empty state; A loading image determination module, used for acquiring a loading image with a loading object placed in the carriage when the carriage is in a loading stage; A loading boundary determination module, used for determining the loading boundary of each of the classification areas according to the loading image; The loading rate determination module is used to determine the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundaries.

[0013] A third aspect of an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the loading rate determination method as described in the first aspect above.

[0014] A fourth aspect of an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed, the method for determining the loading rate as described in the first aspect above is executed.

[0015] A fifth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the loading rate determination method as described in the first aspect above is implemented.

[0016] Compared with the prior art, the embodiments of the present application have the following beneficial effects: In an embodiment of the present application, by determining the classification area corresponding to the designated inner wall in the carriage when the carriage is in an empty state; when the carriage is in a loading stage, obtaining a loading image with a loaded object placed in the carriage; determining the loading boundaries of each of the classification areas based on the loading image; determining the loading rate of the carriage based on the area boundaries of each of the classification areas and the loading boundaries, the loading rate of the carriage can be calculated in real time and automatically during the loading stage of the carriage, the classification areas and the loading boundaries are obtained by processing the image, and the hardware implementation cost is low. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1is a schematic diagram of a method for determining a loading rate provided in an embodiment of the present application; Figure 2 It is a schematic diagram of a classification area provided in an embodiment of the present application; Figure 3 is a schematic diagram of a loading image provided by an embodiment of the present application; Figure 4 is another schematic diagram of classification areas provided in an embodiment of the present application; Figure 5 is a schematic diagram of an idle image provided by an embodiment of the present application; Figure 6 is a schematic diagram of a carriage image provided in an embodiment of the present application; Figure 7 This is a schematic diagram of classification area division provided in an embodiment of the present application; Figure 8 is a schematic diagram of another method for determining a loading rate provided in an embodiment of the present application; Fig. 9 This is a key point detection schematic diagram provided in an embodiment of the present application; Fig.10 is a schematic diagram of a loading rate determination device provided in an embodiment of the present application; Fig.11 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0020] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0021] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0022] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0023] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0025] In the field of logistics, vehicles are usually needed to transport objects, for example, vehicles load objects in the carriage and transport them from place A to place B. In order to reduce energy waste during transportation, it is usually necessary to avoid too much remaining space in the carriage, so it is necessary to measure the loading rate of the carriage to evaluate the remaining space in the carriage.

[0026] The embodiment of the present application discloses a low-cost, efficient and automatic technical solution for determining the loading rate. The technical solution of the present application is explained below through specific embodiments.

[0027] First embodiment Reference Figure 1 , shows a schematic diagram of a method for determining a loading rate provided in an embodiment of the present application, which may specifically include the following steps: Step 101, determining a classification area corresponding to a designated inner wall in the carriage when the carriage is in an empty state; When the carriage is located in the preset loading and unloading area, relevant personnel or equipment (such as mechanical arms, robots, etc.) can load and unload objects in the carriage. An image acquisition device can be set in the loading and unloading area or near the loading and unloading area. When the carriage is located in the loading and unloading area, the image acquisition device can capture images of the carriage, and the rear of the carriage is arranged opposite to the image acquisition device, so that when the carriage is opened, the carriage opening is opposite to the sensing direction of the image acquisition device.

[0028] The loading object is an object placed in the carriage, and the loading phase is the process of placing the loading object in the carriage. The embodiment of the present application can determine the carriage loading rate through images captured by the image acquisition device.

[0029] When there is no loaded object in the carriage, the carriage is in an empty state. The embodiment of the present application requires an image acquisition device to capture an image of the carriage in an empty state, and to process the image to obtain a classification area corresponding to a designated inner wall of the carriage, that is, to divide the inner wall of the carriage into different classification areas.

[0030] Reference Figure 2 , showing a schematic diagram of a classification area provided in an embodiment of the present application, Figure 2 It includes classification areas S0-S4, and different classification areas correspond to different inner walls of the car. Classification area S0 corresponds to the front inner wall, classification area S1 corresponds to the bottom inner wall, classification area S2 corresponds to the top inner wall, classification area S3 corresponds to the left inner wall, and classification area S4 corresponds to the right inner wall.

[0031] In the embodiment of the present application, the designated inner wall includes a bottom inner wall, a top inner wall, a left inner wall, and a right inner wall, that is, the classification area of ​​the designated inner wall includes classification areas S1-S4.

[0032] Step 102, when the carriage is in a loading stage, acquiring a loading image with a loading object placed in the carriage; Reference Figure 3 A schematic diagram of a loading image provided by an embodiment of the present application is shown. When the carriage is in the loading stage, the carriage is imaged by the above-mentioned image acquisition device to obtain a loading image. Since the carriage is loaded with objects during the loading stage, the device image contains an image corresponding to the object ( Figure 3 medium twill block).

[0033] Step 103, determining the loading boundary of each of the classification areas according to the loading image; Identify the positional relationship between the loading object and the specified inner wall in the loading image, and determine the loading boundary of each classification area (classification area S1-S4). Figure 4, shows another schematic diagram of classification areas provided by an embodiment of the present application. Through step 103, the loading boundary of the specified inner wall can be determined ( , , , ), where i is the image sequence identifier of the loaded image in the same loading stage.

[0034] Since the loading stage is a continuous process, loading images can be collected at different times during the loading stage to obtain an image sequence obtained from multiple loading images. i is used to identify the loading images at different times in the image sequence. The values ​​of i corresponding to different times are different, so that the loading boundaries of different classification areas at the same time can be determined.

[0035] Step 104 , determining the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundaries.

[0036] For each loading boundary, the loading rate of the carriage is determined by the length of the loading boundary and the length of the area boundary of the classification area where the loading boundary is located.

[0037] In the embodiment of the present application, since the classification area and the length of its area boundary can be determined before the loading stage, it is only necessary to determine the loading boundary and its length at different times during the loading stage to determine the loading rate of the car at each moment. Without a large amount or complex calculations, the loading rate can be determined quickly, thereby realizing real-time determination of the loading rate of the car during the loading stage.

[0038] In an embodiment of the present application, by determining the classification area corresponding to the designated inner wall in the car when the car is in an empty state; when the car is in a loading stage, obtaining a loading image with a loaded object placed in the car; determining the loading boundaries of each of the classification areas based on the loading image; determining the loading rate of the car based on the area boundaries of each of the classification areas and the loading boundaries, so that the loading rate of the car can be calculated in real time and automatically during the loading stage of the car, the classification areas and the loading boundaries are obtained by processing the image, and the hardware implementation cost is low.

[0039] In an optional embodiment of the present application, step 101 includes: obtaining an empty image of a car in an empty state; the empty image includes car contour elements and car wall elements of each inner wall of the car; performing semantic segmentation on the empty image to generate a classification area corresponding to the specified inner wall.

[0040] Reference Figure 5 , showing a schematic diagram of an idle image provided by an embodiment of the present application; referring to Figure 6, showing a schematic diagram of a carriage image provided by an embodiment of the present application. When the carriage is in an unloaded state, the carriage is located in a preset loading and unloading area and has not entered the loading stage, and no loading object is placed inside the carriage, the above-mentioned image acquisition device is called to perform image acquisition on the carriage, and the image captured at this time, which contains the carriage contour elements and the compartment wall elements of each inner wall of the carriage, is taken as an unloaded image. The carriage contour elements are image contents that match the vehicle contour, the compartment wall elements are image contents that match the inner walls of the carriage, and the compartment door elements are image contents that match the compartment doors. In actual applications, in order to avoid the loading rate determined by the embodiment of the present application being obviously inconsistent with the actual situation, the classification area needs to be obtained by the compartment wall elements of the complete inner wall. When the inner wall of the carriage is partially or completely blocked in the image captured by the image acquisition device (for example: as Figure 6 As shown), it is determined that the carriage is not in an empty state, that is, the image in which the inner wall of the carriage is partially or completely blocked is not regarded as an empty image.

[0041] After obtaining the idle image, the trained image processing model is used to perform semantic segmentation on the idle image. The image processing model can segment the idle image according to the preset categories to obtain the classification area. Figure 4 The unloaded image shown in the figure is semantically segmented to obtain Figure 2 Classification areas S1-S4 are shown.

[0042] As an example, the image processing model can be an artificial neural network model, such as a fully convolutional network (FCN) model, a U-Net model, a recurrent neural network (RNN) model, etc.

[0043] The embodiment of the present application does not limit the specific network structure of the image processing model. It only requires that the image processing model can perform semantic segmentation on the idle image and determine the classification area.

[0044] In an optional embodiment of the present application, determining the loading boundaries of each of the classification areas based on the loading image includes: identifying target pixels corresponding to the loading object in the loading image; and determining the loading boundaries in each of the classification areas based on the target pixels.

[0045] The target pixel is the pixel point of the loading object in the loading image. For each classification area, the loading boundary is determined in the classification area according to the distribution of the target pixel in the classification area. It can be understood that the loading boundary is determined by the pixel points of the loading object in the classification area, that is, the classification area can be divided into loaded sub-areas and unloaded sub-areas by the loading boundary. For example: Figure 7, a classification area separation schematic diagram provided in an embodiment of the present application. Figure 7 The classification area S3 and the loading boundary of the classification area S3 are shown. The classification region S3 contains a set of relative region boundaries and , Close to the opening of the carriage, Close to the front inner wall of the compartment, during the loading phase, the loaded objects will first be placed close to the front inner wall and as the number of loaded objects increases, the placed device objects will gradually approach the opening of the compartment, so the loading boundary of the classification area S3 can be determined by the pixel points of the loaded objects. After that, the classification area can be divided into loaded sub-areas ( to ), sub-regions are not loaded ( to The division method of the loaded sub-areas and the unloaded sub-areas of other classification areas is the same as that of the classification area S3, which will not be repeated here.

[0046] In an optional embodiment of the present application, the area boundary includes a first boundary and a second boundary parallel to each other; the length of the first boundary is smaller than the second boundary; in a classification area where a target pixel exists, the loading boundary is one of a plurality of line segments containing the target pixel and parallel to the first boundary; in a classification area where no target pixel exists, the loading boundary is the first boundary.

[0047] When dividing the classification area for the designated inner wall in the unloaded image, the division is performed in a trapezoidal manner, so that the classification area corresponding to the designated inner wall includes four area boundaries, and the four area boundaries include a set of mutually parallel area boundaries, and the shorter one of the mutually parallel area boundaries is the first boundary, and the longer one is the second boundary. Figure 7 As shown, in the classification area S3, the area boundary is the first boundary, is the second boundary.

[0048] Since the target pixel position range of the loading object may change in the loading image at different times, there may be a situation where the target pixel exists at the corresponding position of one or more classification areas at a certain time. In this case, a line segment containing the target pixel and parallel to the first boundary is determined as the loading boundary. Figure 3 As shown, combined Figure 4 It can be known that at this time, the target pixel exists in the classification area S3, and at this time, a line segment parallel to the first boundary of the classification area S3 and including the target pixel is determined as the loading boundary.

[0049] As an example, in the classification area where the target pixel exists, the loading boundary is the one with the largest length value among multiple line segments that contain the target pixel and are parallel to the first boundary. Figure 3 As shown, the line segment containing the target pixel and with the largest length value can be is the loading boundary of the segmented area S3. In other examples, since there may be actual unloaded space between the loading boundary and the first boundary, after determining the one with the largest length value among multiple line segments containing the target pixel and parallel to the first boundary, the loading boundary can be determined between the line segment and the first boundary.

[0050] At a certain moment, there may be a situation where there is no target pixel at the corresponding position of one or more classification areas. In this case, the first boundary of the classification area where there is no target pixel is determined as the loading boundary of the classification area. Figure 3 As shown, combined Figure 4 It can be seen that at this time, there is no target pixel in the classification area S2, and at this time, the first boundary of the classification area S2 is determined to be the loading boundary .

[0051] In an optional embodiment of the present application, determining the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundary includes: The loading proportion is determined according to the length of the loading boundary and the length of the first boundary and the second boundary of the classification area where the loading boundary is located; the loading rate of the carriage is determined according to the loading proportion corresponding to each of the classification areas.

[0052] The first boundary, the second boundary and the loading boundary have corresponding lengths. As an example, a single pixel can be used as a unit length, and the lengths of the loading boundary, the first boundary and the second boundary can be determined by the unit length. For example, if the loading boundary includes 300 pixels, the length of the loading boundary is determined to be 300. As another example, a number of pixels can be used as a unit length, for example, if 300 pixels are used as a unit, when the loading boundary includes 600 pixels, the length of the device boundary is 2.

[0053] In a specific implementation, it is only necessary to determine the length of the first boundary, the second boundary, and the loading boundary in each classification area with a unified unit length. The method of determining the unit length does not affect the implementation of the embodiments of the present application.

[0054] For each classification area of ​​the designated inner wall, after determining the loading boundary, the loading ratio of the classification area can be determined according to the length of the loading boundary, the length of the first boundary, and the length of the second boundary. The loading ratio of the carriage is determined according to the loading ratio of each classification area.

[0055] For example, the loading rate of the carriage at time i can be determined by the following formula (1): .

[0056] in, is the load ratio of classification area j at time i. j is the classification area identifier, and the value range of j is [1,4], corresponding to classification areas S1-4 respectively. For example: Loading ratio of classification area S2 at time i.

[0057] In an optional embodiment of the present application, the loading proportion is determined based on the length of the loading boundary, and the length of the first boundary and the length of the second boundary of the classification area where it is located, including: determining a first length difference between the length of the loading boundary and the length of the first boundary; determining a second length difference between the length of the second boundary and the length of the first boundary; for each of the classification areas, determining the loading proportion based on the ratio of the first length difference to the second length difference.

[0058] At any moment, for each classification area, the difference between the length of its loading boundary and the length of its first boundary can be determined as the first length difference, and the difference between the length of its second boundary and the length of its first boundary can be determined as the second length difference, and the ratio of the first length difference to the second length difference can be determined as the loading share of the classification area at that moment.

[0059] In the specific implementation, the load ratio of the classification area at time i can be determined by the following method (2): .

[0060]

[0061] in, is the length of the loading boundary of classification area Sj at time i, is the length of the first boundary of the classification area Sj, is the length of the second boundary of the classification area Sj.

[0062] The above formula (2) is used to determine the load ratio of each classification area at time i , and then determine the loading rate of the carriage at time i through formula (1) .

[0063] The embodiment of the present application uses the loading rate of the four inner walls of the carriage and the position of the loading object, without relying on the measurement of the volume of the carriage, so that the loading rate can be determined without measuring the volume of the carriage, thereby improving the efficiency of determining the loading rate. In addition, in the embodiment of the present application, the loading rate can be obtained by processing the visual image, without the need to use sensors such as radar or structured light, and the hardware cost is low. The loading rate is calculated by the length of the loading boundary, the first boundary, the second boundary, etc. of the classification area corresponding to each inner wall. The calculation process is simple, and the loading rate of the carriage at different times can be quickly calculated.

[0064] Second embodiment Reference Figure 8 , shows a schematic diagram of another method for determining a loading rate provided in an embodiment of the present application, which may specifically include the following steps: Step 801, obtaining an empty image of the carriage in an empty state; The empty image includes the carriage contour element and the carriage wall elements of each inner wall of the carriage; Step 802, performing key point detection on the idle image to generate key point data; Step 803, generating a classification area corresponding to the designated inner wall according to the key point data; Step 804, when the carriage is in a loading stage, acquiring a loading image with a loading object placed in the carriage; Step 805, determining the loading boundary of each of the classification areas according to the loading image; Step 806, determining the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundaries.

[0065] Reference Fig. 9 , a schematic diagram of a key point detection provided by an embodiment of the present application. In another embodiment of the present application, key point data can be generated by performing key point detection on an idle image. The key points include: Fig. 9 The relevant information of the key points shown (including but not limited to the key point location information) is used to generate the classification area corresponding to the specified inner wall based on the key point data (such as Figure 2 as shown).

[0066] The difference between the second embodiment and the first embodiment lies in the different ways of generating classification areas. The process of steps 804 to 806 in the second embodiment is the same as steps 102 to 104 in the first embodiment, and will not be described in detail herein.

[0067] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0068] Reference Fig.10 , shows a schematic diagram of a loading rate determination device provided in an embodiment of the present application, which may specifically include a classification area determination module 1001, a loading image determination module 1002, a loading boundary determination module 1003, and a loading rate determination module 1004, wherein: A classification area determination module 1001 is used to determine a classification area corresponding to a specified inner wall in the carriage when the carriage is in an empty state; A loading image determining module 1002 is used to obtain a loading image with a loading object placed in the carriage when the carriage is in a loading stage; A loading boundary determination module 1003, configured to determine the loading boundary of each of the classification areas according to the loading image; The loading rate determination module 1004 is used to determine the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundaries.

[0069] In an optional embodiment of the present application, the classification area determination module 1001 includes: The empty-carriage image acquisition submodule is used to acquire an empty-carriage image when the carriage is in an empty state; the empty-carriage image includes the carriage contour elements and the carriage wall elements of each inner wall of the carriage; The semantic segmentation submodule is used to perform semantic segmentation on the empty image to generate a classification area corresponding to the specified inner wall.

[0070] In an optional embodiment of the present application, the classification area determination module 1001 includes: The empty-carriage image acquisition submodule is used to acquire an empty-carriage image when the carriage is in an empty state; the empty-carriage image includes the carriage contour elements and the carriage wall elements of each inner wall of the carriage; A key point detection submodule, used to perform key point detection on the idle image and generate key point data; The classification area generation submodule is used to generate a classification area corresponding to the specified inner wall according to the key point data.

[0071] In an optional embodiment of the present application, the loading boundary determination module 1003 includes: A target pixel identification submodule, used to identify a target pixel in the loading image corresponding to the loading object; The loading boundary determination submodule is used to determine the loading boundary in each classification area according to the target pixel.

[0072] In an optional embodiment of the present application, the region boundary includes a first boundary and a second boundary parallel to each other; the length of the first boundary is smaller than the second boundary; in the classification region where the target pixel exists, the loading boundary is one of a plurality of line segments containing the target pixel and parallel to the first boundary; In a classification area where no target pixel exists, the loading boundary is a first boundary.

[0073] In an optional embodiment of the present application, the loading rate determination module 1004 includes: A loading ratio determination submodule, used to determine the loading ratio according to the length of the loading boundary, and the length of the first boundary and the length of the second boundary of the classification area where the loading boundary is located; The loading rate determination submodule is used to determine the loading rate of the carriage according to the loading proportions corresponding to each of the classification areas.

[0074] In an optional embodiment of the present application, the loading ratio determination submodule includes: a first length difference determination unit, configured to determine a first length difference between the length of the loading boundary and the length of the first boundary; a second length difference determining unit, configured to determine a second length difference between the length of the second boundary and the length of the first boundary; The loading ratio determination unit is used to determine the loading ratio for each of the classification areas according to the ratio of the first length difference to the second length difference.

[0075] An embodiment of the present application provides a loading rate determination device, and by using the device, each step in the aforementioned method embodiments can be implemented.

[0076] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment part.

[0077] Reference Fig.11 , shows a schematic diagram of an electronic device provided by an embodiment of the present application. Fig.11 As shown, the electronic device 1100 in the embodiment of the present application includes: a processor 1110, a memory 1120, and a computer program 1121 stored in the memory 1120 and executable on the processor 1110. When the processor 1110 executes the computer program 1121, the steps in each embodiment of the above-mentioned method for determining the loading rate are implemented, for example Figure 1 Alternatively, when the processor 1110 executes the computer program 1121, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 1Functions of modules 1101 to 1104 are shown.

[0078] Exemplarily, the computer program 1121 may be divided into one or more modules / units, which are stored in the memory 1120 and executed by the processor 1110 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which may be used to describe the execution process of the computer program 1121 in the electronic device 1100. For example, the computer program 1121 may be divided into a classification area determination module, a loading image determination module, a loading boundary determination module, and a loading rate determination module, and the specific functions of each module are as follows: Classification area determination module, loading image determination module, loading boundary determination module, loading rate determination module, wherein: A classification area determination module, used to determine a classification area corresponding to a designated inner wall in the carriage when the carriage is in an empty state; A loading image determination module, used for acquiring a loading image with a loading object placed in the carriage when the carriage is in a loading stage; A loading boundary determination module, used for determining the loading boundary of each of the classification areas according to the loading image; The loading rate determination module is used to determine the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundaries.

[0079] The electronic device 1100 may be a computing device such as a desktop computer or a cloud server. The electronic device 1100 may include, but is not limited to, a processor 1110 and a memory 1120. Those skilled in the art will appreciate that Fig.11 It is only an example of the electronic device 1100 and does not constitute a limitation of the electronic device 1100. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 1100 may also include input and output devices, network access devices, buses, etc.

[0080] The processor 1110 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0081] The memory 1120 may be an internal storage unit of the electronic device 1100, such as a hard disk or memory of the electronic device 1100. The memory 1120 may also be an external storage device of the electronic device 1100, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1100. Further, the memory 1120 may also include both an internal storage unit of the electronic device 1100 and an external storage device. The memory 1120 is used to store the computer program 1121 and other programs and data required by the electronic device 1100. The memory 1120 may also be used to temporarily store data that has been output or is to be output.

[0082] The embodiment of the present application further discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the loading rate determination method as described in the above-mentioned embodiments is implemented.

[0083] An embodiment of the present application further discloses a computer program product, including a computer program. When the computer program is executed, the loading rate determination method described in the above-mentioned embodiments is executed.

[0084] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application is described in detail with reference to the above-mentioned embodiments, a person skilled in the art should understand that the technical solutions described in the above-mentioned embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for determining a loading rate, characterized in that: include: Determine a classification area corresponding to a designated inner wall in the carriage when the carriage is in an empty state; When the carriage is in a loading stage, acquiring a loading image in which a loading object is placed in the carriage; Determining a loading boundary of each of the classification areas according to the loading image; The loading rate of the carriage is determined according to the area boundaries of each of the classification areas and the loading boundaries.

2. The method according to claim 1, characterized in that: The determining of the classification area corresponding to the designated inner wall in the carriage when the carriage is in an empty state includes: Acquire an empty image of the carriage in an empty state; the empty image includes a carriage contour element and a carriage wall element of each inner wall of the carriage; Semantic segmentation is performed on the empty image to generate a classification area corresponding to the designated inner wall.

3. The method according to claim 1, characterized in that The determining of the classification area corresponding to the designated inner wall in the carriage when the carriage is in an empty state includes: Acquire an empty image of the carriage in an empty state; the empty image includes a carriage contour element and a carriage wall element of each inner wall of the carriage; Performing key point detection on the idle image to generate key point data; A classification area corresponding to the designated inner wall is generated according to the key point data.

4. The method according to claim 1, characterized in that: The step of determining the loading boundary of each of the classification areas according to the loading image comprises: identifying a target pixel in the loading image corresponding to the loading object; The loading boundary in each classification area is determined according to the target pixel.

5. The method according to any one of claims 1 to 4, characterized in that: The region boundary includes a first boundary and a second boundary parallel to each other; the length of the first boundary is shorter than the length of the second boundary; In the classification area where the target pixel exists, the loading boundary is one of a plurality of line segments that include the target pixel and are parallel to the first boundary; In a classification area where no target pixel exists, the loading boundary is a first boundary.

6. The method according to claim 5, characterized in that The determining the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundaries includes: Determine the loading proportion according to the length of the loading boundary and the length of the first boundary and the length of the second boundary of the classification area where the loading boundary is located; The loading rate of the carriage is determined according to the loading proportions corresponding to each of the classification areas.

7. The method according to claim 6, characterized in that The determining of the loading proportion according to the length of the loading boundary and the length of the first boundary and the second boundary of the classification area where the loading boundary is located includes: determining a first length difference between a length of the loading boundary and a length of the first boundary; determining a second length difference between the length of the second boundary and the length of the first boundary; For each of the classification areas, the loading proportion is determined according to the ratio of the first length difference to the second length difference.

8. A loading rate determination device, characterized in that: include: A classification area determination module, used to determine a classification area corresponding to a designated inner wall in the carriage when the carriage is in an empty state; A loading image determination module, used for acquiring a loading image with a loading object placed in the carriage when the carriage is in a loading stage; A loading boundary determination module, used for determining the loading boundary of each of the classification areas according to the loading image; The loading rate determination module is used to determine the loading rate of the carriage according to the area boundaries of each of the classification areas and the loading boundaries.

9. An electronic device, characterized in that: The electronic device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program, which, when being executed, enables the method according to any one of claims 1 to 7 to be performed.

Images