Method, device, electronic device and computer program product for measuring loading volume

Abstract

The present application is applicable to the field of transportation and logistics technology, and provides a method, device, electronic device and computer program product for measuring loading volume. The method includes: determining the conveyor belt area in the carriage image captured by the image acquisition device; in the case where the carriage in the carriage image is divided into two or more first squares, based on the depth of the carriage point cloud captured by the point cloud acquisition device, determining the depth of the first type of square, the first type of square is the first square that is not in the conveyor belt area; based on the depth of the first type of square, determining the depth of the second type of square, the second type of square is the first square in the conveyor belt area, the depth of the second type of square represents the distance between the goods blocked by the conveyor belt and the electronic device; based on the depth of each first square, determining the loading volume of the carriage. The present application can improve the measurement accuracy of loading volume.

Description

Technical Field

[0001] The present application belongs to the field of transportation and logistics technology, and in particular, relates to a method, device, electronic equipment and computer program product for measuring loading volume. Background Art

[0002] With the development of the logistics industry, intelligent logistics is increasingly being applied to basic activities in the logistics industry, such as transportation, warehousing, distribution, packaging, loading and unloading. In the process of trucks carrying goods, intelligent measurement of the loading rate of truck compartments is one of the inevitable requirements for the logistics industry to improve efficiency. When calculating the loading rate, it is usually necessary to obtain the loading volume of the compartment (i.e. the volume of loaded goods). When obtaining the loading volume, the relevant technology does not consider the interference of non-loaded goods such as conveyor belts during cargo loading, resulting in a low measurement accuracy of the loading volume. Summary of the invention

[0003] The embodiments of the present application provide a method, device, electronic device and computer program product for measuring loading volume, which can improve the measurement accuracy of loading volume.

[0004] In a first aspect, an embodiment of the present application provides a method for measuring a loading volume, which is applied to an electronic device, and the method includes:

[0005] Determine a conveyor belt area in a carriage image captured by an image acquisition device;

[0006] In the case where the carriage in the carriage image is divided into two or more first squares, the depth of the first type of squares is determined based on the depth of the carriage point cloud collected by the point cloud collection device, and the first type of squares are first squares that are not in the conveyor belt area;

[0007] Determine the depth of a second type of square based on the depth of the first type of square, where the second type of square is the first square in the conveyor belt area, and the depth of the second type of square represents the distance between the goods blocked by the conveyor belt and the electronic device;

[0008] Based on the depth of each first square, the loading volume of the carriage is determined.

[0009] In the embodiment of the present application, by determining the conveyor belt area in the carriage image captured by the image acquisition device, when the carriage in the carriage image is divided into two or more first squares, the depth of the first square (i.e., the first type of square) that is not in the conveyor belt area can be determined based on the depth of the carriage point cloud captured by the point cloud acquisition device, and the depth of the first square (i.e., the second type of square) in the conveyor belt area (i.e., the distance between the goods blocked by the conveyor belt and the electronic device) can be determined based on the depth of the first type of square, thereby obtaining the depth of each first square, and the loading volume of the carriage can be determined based on the depth of each first square. By determining the conveyor belt area in the vehicle-borne image, this solution can determine the depth of the first square in the conveyor belt area based on the depth of the first square that is not in the conveyor belt area, that is, determine the distance between the goods blocked by the conveyor belt and the electronic device, and based on the depth of these first squares, the loading volume can be accurately measured, the interference problem of the conveyor belt during the loading process can be solved, and the measurement accuracy of the loading volume can be improved.

[0010] In a second aspect, an embodiment of the present application provides a device for measuring a loading volume, which is applied to an electronic device, and the device includes:

[0011] An area determination module, used to determine the conveyor belt area in the carriage image acquired by the image acquisition device;

[0012] A first depth determination module is used to determine the depth of a first type of square based on the depth of the point cloud of the carriage collected by the point cloud collection device when the carriage in the carriage image is divided into two or more first squares, wherein the first type of square is a first square that is not in the conveyor belt area;

[0013] The second depth determination module is used to determine the depth of the second type of squares based on the depth of the first type of squares, the second type of squares being the first squares in the conveyor belt area, and the depth of the second type of squares represents the distance between the goods blocked by the conveyor belt and the electronic device;

[0014] The loading volume determination module is used to determine the loading volume of the carriage based on the depth of each first square.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, 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 described in the first aspect above.

[0016] In a fourth aspect, 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 computer, the method described in the first aspect above is implemented.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, wherein when the computer program is executed, the method described in the first aspect above is executed.

[0018] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 is a schematic diagram of a system for measuring a loading volume provided in an embodiment of the application;

[0021] Figure 2 is a diagram showing an example of the structure of an electronic device;

[0022] Figure 3 This is a top view example diagram of a point cloud acquisition device and an image acquisition device;

[0023] Figure 4 is a schematic flow chart of a method for measuring a loading volume provided in an embodiment of the present application;

[0024] Figure 5 This is an example image of a carriage with a conveyor belt placed inside the carriage;

[0025] Figure 6 This is an example diagram of the first type of square and the second type of square;

[0026] Figure 7 is a diagram showing an example of deployment of electronic equipment;

[0027] Figure 8 This is an example diagram of the first square;

[0028] Fig. 9 is a schematic structural diagram of a loading volume measuring device provided in an embodiment of the present application;

[0029] Fig.10 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] The loading volume measurement method provided in the embodiment of the present application can be applied to electronic devices such as mobile phones, tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc. The embodiment of the present application does not impose any restrictions on the specific types of electronic devices.

[0037] For example, Figure 1 Schematic diagram of a system for measuring loading volume provided in an embodiment of the present application is shown. Figure 1 , the measurement system includes an electronic device 101 and a vehicle 102 .

[0038] The electronic device 101 can automatically complete the measurement of the loading volume of the vehicle 102's compartment through the complementary installation of the point cloud acquisition device and the image acquisition device without modifying the compartment or accessing an external system. The specific implementation scheme can be found in the loading volume measurement method embodiment below.

[0039] As an example but not limitation, the point cloud acquisition device may be a time-of-flight (ToF) camera, a laser radar, or other device capable of acquiring point clouds. The image acquisition device may be a wide-angle camera, a fixed-focus camera, or other device capable of acquiring visible light images.

[0040] The field of view of the point cloud acquisition device covers part of the area in the car, and the field of view of the image acquisition device covers the entire area in the car. The far end of the car (the area in the car that is far from the electronic equipment) is mainly covered by the point cloud acquisition device, and the near end (that is, the area in the car that is close to the electronic equipment) is mainly covered by the image acquisition device. It is not necessary to cover the entire car of the vehicle 102 with point clouds. On the basis of saving the deployment cost of hardware, it is possible to realize the fully automatic and non-contact measurement of the loading volume during the loading process, and there is no need to collect the empty car in advance. The operation is relatively simple, which improves the measurement efficiency of the loading volume.

[0041] In order to achieve accurate measurement of the loading volume of the compartment of the vehicle 102, in one embodiment, the point cloud acquisition device and the image acquisition device can be integrated into the electronic device 101, and the axis of the optical axis of the point cloud acquisition device and the axis of the optical axis of the image acquisition device are parallel, ensuring that the deployment positions of the point cloud acquisition device and the image acquisition device in the electronic device 101 are as close as possible to avoid measurement errors caused by structural deformation. Of course, it is understandable that the point cloud acquisition device and the image acquisition device may not be integrated into the electronic device 101, and this application does not limit this.

[0042] In order to ensure that the point cloud acquisition device and the image acquisition device in the electronic device 101 can accurately measure the loading volume, the deployment position of the electronic device 101 can be determined based on the height of the lower side wall (i.e., the bottom surface of the compartment) and the height of the upper side wall (i.e., the top surface of the compartment) of the vehicle 102 (for example, if the height between the lower side wall and the upper side wall of the compartment is 5 meters, then the electronic device 101 can be deployed at a position about 2 meters from the lower side wall of the compartment), and the axis of the optical axis of the point cloud acquisition device and the axis of the optical axis of the image acquisition device are parallel to the longitudinal direction of the compartment (i.e., the length direction of the compartment). Since the depth measured by the point cloud acquisition device is relatively accurate, when deploying the electronic device 101, in the length direction of the compartment, the maximum coverage area of ​​the field of view of the point cloud acquisition device on the lower side wall of the compartment is kept to be more than half of the length of the compartment. For a shorter compartment, the length of the coverage area of ​​the point cloud acquisition device can be kept unchanged to shorten the length of the coverage blind area of ​​the point cloud acquisition device. On this basis, this solution can ensure the measurement accuracy and scene adaptability of the loading volume at a limited cost, adapt to multi-sized carriages, and realize the measurement of the loading volume of carriages of different sizes.

[0043] like Figure 2 The figure shows an example diagram of the structure of the electronic device 101. The electronic device 101 also includes a computing chip, which may be a processor. The computing chip is used to measure the loading volume of the carriage based on the carriage point cloud collected by the point cloud collection device and the carriage image collected by the image collection device. Among them, the above-mentioned carriage point cloud is a point cloud collected by the point cloud collection device. In this embodiment, the point cloud collection device performs point cloud collection on the carriage, so the point cloud collected by the point cloud collection device can be referred to as a carriage point cloud. The above-mentioned carriage image is an image collected by the image collection device. In this embodiment, the image collection device performs image collection on the carriage, so the image collected by the image collection device can be referred to as a carriage image.

[0044] like Figure 3 Shown is a top view example of a point cloud acquisition device and an image acquisition device. Figure 3 The field of view of the point cloud acquisition device is smaller than that of the image acquisition device, so that the far end of the car can be mainly covered by the point cloud acquisition device, and the near end can be mainly covered by the image acquisition device. There is no need for the entire car 102 to be covered with point clouds, saving hardware deployment costs.

[0045] See also Figure 4 , Figure 4 The flow chart of the method for measuring the loading volume provided in the embodiment of the present application is shown, which is applied to an electronic device. As an example but not limitation, the method includes the following steps:

[0046] Step 401, determining a conveyor belt area in a carriage image captured by an image acquisition device.

[0047] The electronic device can perform semantic segmentation on the carriage image to obtain the conveyor belt area. Figure 5 The following is an example of a carriage image with a conveyor belt placed inside the carriage. Figure 5 The image of the carriage is acquired by the image acquisition device from the rear view of the carriage. Figure 5 The black squares in the figure are the areas blocked by the conveyor belt.

[0048] Since the position of the conveyor belt in the carriage is usually not adjusted or the possibility of adjustment is small during the cargo loading process, in order to save the computing power of electronic equipment, the carriage image can be segmented and calculated at a relatively low frequency.

[0049] Step 402 , when the carriage in the carriage image is divided into two or more first squares, the depth of the first type of squares is determined based on the depth of the carriage point cloud collected by the point cloud collection device.

[0050] The first type of square is the first square that is not in the conveyor belt area. The depth of the first type of square is the depth of the carriage point cloud corresponding to the first type of square.

[0051] Compared with the carriage, the conveyor belt occupies a smaller area in the carriage. Therefore, in order to more accurately obtain the depth of the first square (i.e., the second type of square) in the conveyor belt area, the carriage in the carriage image can be divided into more than two first squares. For the convenience of calculation, the first square is usually a square, and the side length of the square can be the pixel size corresponding to the depth resolution of the point cloud acquisition device in the head area of ​​the carriage. The first square can be extended into a cuboid in the length direction of the carriage to form a voxel, and the two bottom surfaces of the voxel are the head area of ​​the carriage and the target measured by the point cloud acquisition device. The head area of ​​the carriage usually does not change, so the head area of ​​the carriage can be called a fixed surface. The target measured by the point cloud acquisition device changes with the loading of the goods in the carriage, so the target measured by the point cloud acquisition device can be called a dynamically changing surface, and the carriage point cloud collected by the point cloud acquisition device is located on the dynamically changing surface. The electronic device can project the dynamically changing surface to the image coordinate system, thereby establishing a mapping relationship between the car point cloud and the pixel points in the car image. On this basis, the first square corresponding to the dynamically changing surface can be classified to determine the first square in the conveyor belt area (i.e., the second type of square) and the first square not in the conveyor belt area (i.e., the first type of square). Figure 6 The following are examples of the first and second types of squares. Figure 6 The white squares in the box are of the second type, and the black squares are of the first type.

[0052] like Figure 7 The following is an example diagram of the deployment of electronic equipment. Figure 7The tof area is the target coverage area, and the camera area is the coverage blind area of ​​the point cloud acquisition device. Figure 7 The field of view of the point cloud acquisition device covers part of the area inside the car, while the field of view of the image acquisition device covers the entire area inside the car. Figure 7 L and D1 represent the length of the car, W represents the width of the car, H represents the height of the car, and D2 represents the distance between the rear of the car and the electronic device. This application does not limit the method of obtaining these car data.

[0053] Among them, the target coverage area is the maximum coverage range of the field of view of the point cloud acquisition device on the lower side wall of the car.

[0054] In a possible implementation, the electronic device can determine whether the cargo exceeds the target coverage area based on the depth of the carriage point cloud collected by the point cloud collection device. If the cargo does not exceed the target coverage area, it can be determined that the cargo is within the coverage of the carriage point cloud. In this case, the depth of the first type of squares can be determined based on the depth of the carriage point cloud. If the cargo exceeds the target coverage area, the depth of the pixel points in the area where the cargo is located in the carriage image can be determined based on the depth of the carriage image and the carriage point cloud, and the depth of the first type of squares can be determined based on the depth of the pixel points in the area where the cargo is located.

[0055] In a possible implementation, the depth of the pixel point in the area where the goods are located is determined by:

[0056] Determine the depth of a first pixel point and the depth of a second pixel point, the first pixel point is a pixel point on the edge of the area where the cargo is located, and the second pixel point is a pixel point in the area where the cargo is located corresponding to the carriage point cloud;

[0057] Based on the depth of the first pixel and the depth of the second pixel, the depth of the third pixel is determined, where the third pixel is a pixel other than the first pixel and the second pixel in the area where the goods are located.

[0058] Based on the height and width of the carriage and the position information of the edge of the cargo area in the carriage image, the electronic device performs monocular ranging using the internal parameters of the image acquisition device. It can determine the distance between the edge of the cargo area and the electronic device. This distance is the depth of the pixel points on the edge of the cargo area.

[0059] Since the field of view of the point cloud acquisition device is small, the coverage of the measured car point cloud is small, resulting in unknown depth of the pixel points between the car point cloud and the edge of the cargo area in the car image. However, cargo loading is continuous, so the pixel point with unknown depth (i.e., the third pixel point) can be interpolated based on the depth of the first pixel point and the depth of the second pixel point (for example, smooth interpolation, of course, other interpolation methods can also be used, which is not limited in this application), so as to obtain the depth of all pixel points in the cargo area.

[0060] Step 403, based on the depth of the first type of squares, determine the depth of the second type of squares, the second type of squares being the first squares in the conveyor belt area.

[0061] Among them, the depth of the second type of square represents the distance between the goods blocked by the conveyor belt and the electronic device.

[0062] In one embodiment, after the second type of squares are determined, the second type of squares may be marked as occlusion areas, and the electronic device may perform depth prediction on the second type of squares marked as occlusion areas based on the depth of the first type of squares.

[0063] Since the conveyor belt is located on the lower wall of the carriage, that is, the conveyor belt blocks the goods from below, the electronic device can use a prediction method from top to bottom and from the left and right sides to the middle to perform depth prediction on the second type of squares.

[0064] In a possible implementation, the above prediction method of growing from top to bottom and from left to right to the middle includes:

[0065] Determine the depth of the first reference square as the bearing depth of the second type of square, the first reference square being the first first type square located directly above the second type of square;

[0066] Based on the depth of the second reference square, the depth of the third reference square, the first target distance and the second target distance, the second type of square is interpolated to obtain the horizontal predicted depth of the second type of square, the second reference square is the first first type square located on the left side of the second type of square, the third reference square is the first first type square located on the right side of the second type of square, the first target distance is the distance between the second type of square and the second reference square, and the second target distance is the distance between the second type of square and the third reference square;

[0067] The depth of the second type of grid is determined based on the horizontal predicted depth and the bearing depth.

[0068] When the electronic device predicts from top to bottom, based on the principle of cargo bearing capacity (i.e., the upper cargo must be supported by the lower cargo), the bearing depth of the second type of grid can be calculated. When the electronic device predicts from the left and right sides to the middle, the depth of the second reference grid, the depth of the third reference grid, the first target distance and the second target distance can be obtained. Based on these data, the second type of grid can be interpolated to obtain the horizontal predicted depth of the second type of grid. It should be noted that the present application does not limit the interpolation method, for example, it can be linear interpolation.

[0069] Based on the cargo load analysis, it can be determined that the depth of the upper cargo is usually greater than the depth of the lower cargo, and the first reference grid is located directly above the second type of grid. Therefore, the load depth can be used as the upper limit of the depth of the second type of grid, and the depth of the second type of grid is determined based on the comparison result of the horizontal predicted depth and the load depth.

[0070] In a possible implementation, if the horizontal prediction depth is greater than or equal to the bearing depth, the depth of the second type of grid is determined to be the bearing depth.

[0071] Since the bearing depth is the upper limit of the depth of the second type of grid, when the horizontal prediction depth is greater than or equal to the bearing depth, the depth of the second type of grid is determined to be the bearing depth.

[0072] In another possible implementation, if the horizontal prediction depth is less than the bearing depth, the bearing distance and the horizontal prediction distance of the second type of square are determined, the bearing distance is the distance between the second type of square and the first first type of square located directly above the second type of square, and the horizontal prediction distance is the minimum value of the first target distance and the second target distance;

[0073] The depth of the second type of grid is determined based on the bearing depth, bearing distance, horizontal prediction depth and horizontal prediction distance.

[0074] When the electronic device predicts from top to bottom, based on the cargo carrying capacity principle, the load distance of the second type of grid can be calculated. When the electronic device predicts from the left and right sides to the middle, the horizontal predicted distance of the second type of grid can be obtained.

[0075] Considering that the farther the distance between two first squares is, the smaller the correlation is, and the closer the distance between two first squares is, the greater the correlation is, the electronic device can perform depth compensation calculation on the second type of squares based on the carrying depth, carrying distance, horizontal predicted depth and horizontal predicted distance, thereby obtaining the depth of the second type of squares.

[0076] The formula for the above depth compensation calculation is as follows:

[0077]

[0078] in, Indicates the depth of the second type of square; represents the carrying distance of the second type of squares; represents the horizontal prediction distance of the second type of square; represents the bearing depth of the second type of square; Indicates the horizontal predicted depth of the second type of square.

[0079] Step 404 , determining the loading volume of the carriage based on the depth of each first grid.

[0080] The electronic device can calculate the free capacity of the carriage based on the depth of each first square; the loading volume can be obtained by subtracting the free capacity from the volume of the carriage.

[0081] In a possible implementation, the electronic device can calculate the volume of each first square based on the depth, width and height of each first square, and add the volumes of each first square to obtain the free capacity of the carriage. The width and height of the first square are related to the resolution of the point cloud acquisition device.

[0082] In another possible implementation, the electronic device may determine the depth of each second square based on the depth of each first square, where the second square includes more than two first squares; and determine the loading volume of the vehicle compartment based on the depth of each second square.

[0083] Since the number of the first squares is relatively large, the electronic device determines the loading volume based on the depth of each second square, which can reduce the amount of calculation.

[0084] According to the dynamic characteristics of interference objects during the loading process (such as loaders, loading aids, and other non-loaded goods), there is a large possibility of change on a short time scale. The loaded goods show a certain stability in a short time scale. In addition, in addition to being stable, the depth of the loaded goods is often greater than the depth of the foreground dynamic interference objects. Based on these related characteristics, the dynamic interference objects can be filtered out by the time domain sliding window method on the basis of dividing the carriage in the carriage image into more than two first squares, and then the depth confidence of the first square is calculated by the load filter method and the interference occlusion smoothing filter method in the spatial domain. Finally, the depth of each second square is calculated based on the depth confidence of the first square, and the loading volume is measured on this basis. It has high robustness and can reduce the impact of filtering dynamic interference objects such as loaders and loading aids on the measurement of the loading volume, thereby achieving accurate measurement of the loading volume during the loading process. Figure 8 Shown is an example diagram of the first grid, in which the carriage is divided into a large number of small squares, and the measurement of the loading volume is achieved based on a large square including a plurality of small squares.

[0085] The electronic device can calculate the volume of each second square based on the depth and area of ​​each second square, add up the volumes of each second square to obtain the free capacity of the carriage, and subtract the free capacity from the volume of the carriage to obtain the loading volume.

[0086] The area of ​​the second square may be the sum of the areas of two or more first squares included in the second square.

[0087] In a possible implementation, before determining the depth of each second square based on the depth of each first square, dynamic interferences may be filtered using a time domain sliding window method, the method comprising:

[0088] For any first square, based on the time scale of k*q, in each k time window, the depth of the first square is updated to the maximum value of the k depths corresponding to the k time windows, where k is an integer greater than 1, and q is the sliding step of the time window, which is an integer greater than zero.

[0089] Since the depth of loaded goods is often greater than the depth of dynamic interferers, the electronic device updates the depth of the first square to the maximum value of k depths corresponding to k time windows, which can filter out dynamic interferers.

[0090] As an example but not a limitation, k is 10, q is 1 second, and for each first square, the maximum value is selected from the 10 depths every 10 seconds as the depth of the first square in this loading volume measurement. If a dynamic interferer appears in the car at the 5th second, the depth of the first square at the 5th second can be filtered out by selecting the maximum value, thereby filtering out the dynamic interferer.

[0091] In a possible implementation, before determining the depth of each second square based on the depth of each first square, the electronic device may determine the target depth confidence of each first square; and determine the depth of each second square based on the depth of each first square and the target depth confidence.

[0092] The depth confidence of the first square may represent the credibility of the depth of the first square. The depth confidence of the first square here includes the target depth confidence of the first square and the first depth confidence and the second depth confidence described below.

[0093] The higher the depth confidence of the first square is, the smaller the possibility that the content of the first square is a dynamic distractor is; the lower the depth confidence of the first square is, the greater the possibility that the content of the first square is a dynamic distractor is.

[0094] For ease of calculation, the electronic device may normalize the target depth confidence of each first square, and then multiply the depth of each first square in the second square by the corresponding normalized target depth confidence and then add them together to obtain the depth of the second square.

[0095] In a possible implementation, before determining the target depth confidence of each first square, a spatial domain bearing filter method may be used to filter dynamic interferences, and the method includes:

[0096] Using a first sliding window with a scale of p *1, starting from the bottom first square of the p first squares in each column, the first sliding window is slid upward according to a preset step length to traverse each first square, where p is an integer greater than 1;

[0097] In each first sliding window, based on the depth of the first square at the bottom of the first sliding window, the depth of the first target square and the length of the carriage, a first depth confidence of the first target square is determined, where the first target square is the top first square in the first sliding window;

[0098] Determine that the first depth confidence of the first remaining square is a first preset value, the first remaining square is a square other than the first target square in the two or more first squares; the first target square and the first remaining square constitute each first square.

[0099] The present application does not limit the specific value of the preset step length, which can be preset according to scene requirements. As an example but not a limitation, in order to obtain more first depth confidences of the first target grid, the preset step length can be 1.

[0100] Since the cargo has a load-bearing characteristic (i.e., the cargo on the upper layer must be supported by the cargo on the lower layer), in each first sliding window, the first depth confidence is calculated based on the depth of the first square at the bottom of the first sliding window. In other words, the smaller the depth of the first target square is than the depth of the first square at the bottom of the first sliding window, the lower its first depth confidence is.

[0101] Since the first sliding window starts to slide from the bottom first square among the p first squares, the first remaining square is located below the first target square. Based on the carrying characteristics of the goods, it can be known that the lower the first square is, the higher the depth confidence is. Therefore, the above-mentioned first preset value can be 1.

[0102] The electronic device can calculate the depth percentage of the first target square (i.e., the ratio of the depth of the first target square to the length of the carriage) based on the depth of the first square at the bottom in the first sliding window and the length of the carriage; can calculate the depth percentage of the first square at the bottom in the first sliding window (i.e., the ratio of the depth of the first square at the bottom in the first sliding window to the length of the carriage) based on the depth of the first target square and the length of the carriage; and can calculate the first depth confidence of the first target square based on the depth percentage of the first target square and the depth percentage of the first square at the bottom in the first sliding window.

[0103] The calculation formula of the first depth confidence of the first target square is as follows:

[0104]

[0105] in, represents a first depth confidence of a first target square; Indicates the gain parameter, the default value is 1; Indicates the depth percentage of the first target square; Indicates the depth percentage of the first square at the bottom of the first sliding window.

[0106] In this manner, after obtaining the first depth confidence of each first square, the electronic device can determine the target depth confidence of the corresponding first square based on the first depth confidence of each first square. As an example and not a limitation, the target depth confidence of each first square can be determined as the first depth confidence of the corresponding first square. Of course, it can be understood that the target depth confidence of the corresponding first square can also be determined based on the first depth confidence of each first square in other ways, and this application does not limit this.

[0107] In another possible implementation, before determining the target depth confidence of each first square, an interference occlusion smoothing filter method may be used to filter dynamic interferences, and the method includes:

[0108] Using a second sliding window with a scale of m*n, sliding the second sliding window according to a preset rule to traverse each first square, where m and n are integers greater than 1;

[0109] In each second sliding window, determining the position difference between the deepest square in the second sliding window and the second target square, the deepest square is the first square with the largest depth in the second sliding window, and the second target square is the first square at the center of the second sliding window;

[0110] determining a second depth confidence of the second target square based on the position difference, the depth of the deepest square, the depth of the second target square, and the length of the carriage;

[0111] The second depth confidence of the second remaining square is determined to be a second preset value, and the second remaining square is the square other than the second target square in the two or more first squares; the first target square and the first remaining square constitute each first square.

[0112] Among them, the above-mentioned preset rules may include starting from the lower left corner of the carriage in the carriage image, first sliding horizontally according to the first step length, and then sliding vertically according to the second step length, or starting from the lower left corner of the carriage in the carriage image, first sliding vertically according to the second step length, and then sliding horizontally according to the first step length, or starting from the lower right corner of the carriage in the carriage image, first sliding horizontally according to the first step length, and then sliding vertically according to the second step length, or starting from the lower right corner of the carriage in the carriage image, first sliding vertically according to the second step length, and then sliding horizontally according to the first step length. The above-mentioned first step length and second step length are both preset, and can be the same or different, and this application does not limit this.

[0113] As an example but not a limitation, in order to obtain more first depth confidences of first target squares, the first step size and the second step size may be set to 1.

[0114] Since the depth of the dynamic interference is smaller than the actual depth of the loaded goods, the second depth confidence of the second target square is calculated based on the first square with the largest depth in the second sliding window in each second sliding window. That is to say, the smaller the depth of the second target square is than the depth of the deepest square, the greater the possibility that it is a dynamic interference.

[0115] Since the second sliding window starts to slide from the lower left corner or the lower right corner of the carriage, the second remaining square is usually located below the second target square. Based on the carrying characteristics of the cargo, it can be known that the lower the position of the first square, the higher the depth confidence, so the above-mentioned second preset value can be 1.

[0116] The electronic device can calculate the depth percentage of the second target square (i.e., the ratio of the depth of the second target square to the length of the carriage) based on the depth of the second target square and the length of the carriage; can calculate the depth percentage of the deepest square (i.e., the ratio of the depth of the deepest square to the length of the carriage) based on the depth of the deepest square in the second sliding window and the length of the carriage; and can calculate the second depth confidence of the second target square based on the depth percentage of the second target square and the depth percentage of the second square of the deepest square.

[0117] The position difference between the second target square and the deepest square may refer to the sum of the position difference between the deepest square and the second target square in the horizontal direction and in the vertical direction.

[0118] The calculation formula of the second depth confidence of the second target square is as follows:

[0119]

[0120] in, A second depth confidence level representing a second target square; Indicates the gain parameter, the default value is 1; Indicates the depth percentage of the second target square; Indicates the depth percentage of the deepest square; It represents the position difference between the deepest square and the second target square. The larger the position difference is, the smaller its influence on the second depth confidence is; the smaller the position difference is, the greater its influence on the second depth confidence is.

[0121] In this manner, after obtaining the second depth confidence of each first square, the electronic device can determine the target depth confidence of the corresponding first square based on the second depth confidence of each first square. As an example and not a limitation, the target depth confidence of each first square can be determined as the second depth confidence of the corresponding first square. Of course, it can be understood that the target depth confidence of the corresponding first square can also be determined based on the second depth confidence of each first square in other ways, and this application does not limit this.

[0122] In order to further improve the accuracy of the target depth confidence of the first square, in another possible implementation method, after obtaining the first depth confidence and the second depth confidence of each first square based on the above two methods, the target depth confidence can be obtained based on a weighted sum of the first depth confidence and the second depth confidence of the same first square.

[0123] It should be noted that the present application does not limit the weight values ​​corresponding to the first depth confidence and the second depth confidence. For example, the weight of the first depth confidence and the weight of the second depth confidence are both 0.5, or the weight of the first depth confidence is 0.4 and the weight of the second depth confidence is 0.6.

[0124] The embodiment of the present application determines the conveyor belt area in the vehicle-mounted image and can determine the depth of the first square in the conveyor belt area based on the depth of the first square not in the conveyor belt area, that is, determine the distance between the goods blocked by the conveyor belt and the electronic device. Based on the depth of these first squares, the loading volume can be accurately measured, the interference problem of the conveyor belt during the loading process can be solved, and the real-time and accuracy of the loading volume measurement can be improved.

[0125] The embodiment of the present application can first perform loading status and loading volume detection, and after the volume detection and interference detection are started, the interference detection status is judged. In interference detection, occlusion is divided into static occlusion and dynamic occlusion. Static occlusion mainly refers to the conveyor belt placed in the carriage for transporting goods, and dynamic occlusion mainly refers to people, transported goods, and goods on the conveyor belt. This solution can solve the interference problem of static occlusion and dynamic occlusion during the loading process, perform non-sensing measurement during the continuous loading process, do not require clearance personnel, and can achieve accurate measurement of the loading volume during the loading process.

[0126] It should be understood 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.

[0127] Corresponding to the measurement method of the loading volume described in the above embodiment, Fig. 9 A schematic structural diagram of a loading volume measuring device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0128] Reference Fig. 9 , the device comprises:

[0129] The area determination module 901 is used to determine the conveyor belt area in the carriage image acquired by the image acquisition device;

[0130] A first depth determination module 902 is used to determine the depth of a first type of square based on the depth of the point cloud of the carriage collected by the point cloud collection device when the carriage in the carriage image is divided into two or more first squares, wherein the first type of square is a first square that is not in the conveyor belt area;

[0131] A second depth determination module 903, configured to determine the depth of a second type of square based on the depth of the first type of square, wherein the second type of square is the first square in the conveyor belt area, and the depth of the second type of square represents the distance between the goods blocked by the conveyor belt and the electronic device;

[0132] The loading volume determination module 904 is used to determine the loading volume of the carriage based on the depth of each first square.

[0133] Optionally, the second depth determination module 903 includes:

[0134] A first determining unit, configured to determine a depth of a first reference square as a bearing depth of the second-type square, wherein the first reference square is the first first-type square located directly above the second-type square;

[0135] an interpolation unit, configured to interpolate the second-type squares based on the depth of the second reference square, the depth of the third reference square, the first target distance, and the second target distance to obtain a horizontal predicted depth of the second-type squares, wherein the second reference square is the first first-type square located on the left side of the second-type squares, the third reference square is the first first-type square located on the right side of the second-type squares, the first target distance is the distance between the second-type squares and the second reference squares, and the second target distance is the distance between the second-type squares and the third reference squares;

[0136] The second determining unit is used to determine the depth of the second type of grid based on the horizontal predicted depth and the bearing depth.

[0137] Optionally, the second determining unit is specifically configured to:

[0138] If the horizontal prediction depth is greater than or equal to the bearing depth, the depth of the second type of grid is determined to be the bearing depth.

[0139] Optionally, the second determining unit is specifically configured to:

[0140] If the horizontal predicted depth is less than the bearing depth, determining the bearing distance and the horizontal predicted distance of the second type of square, the bearing distance being the distance between the second type of square and the first first type of square located directly above the second type of square, and the horizontal predicted distance being the minimum value between the first target distance and the second target distance;

[0141] The depth of the second-type grid is determined based on the bearing depth, the bearing distance, the horizontal prediction depth and the horizontal prediction distance.

[0142] Optionally, the loading volume determination module 904 includes:

[0143] A third determining unit, configured to determine the depth of each second square based on the depth of each first square, wherein the second square includes more than two first squares;

[0144] The fourth determining unit is used to determine the loading volume of the carriage based on the depth of each second square.

[0145] Optionally, the above device further comprises:

[0146] A depth update module is used to update the depth of any first square to the maximum value of k depths corresponding to the k time windows within each k time window based on a time scale of k*q, where k is an integer greater than 1, and q is a sliding step size of the time window, which is an integer greater than zero.

[0147] Optionally, the above device further comprises:

[0148] A target determination module, used to determine the target depth confidence of each first square;

[0149] The second determining unit is specifically used for:

[0150] The depth of each of the second squares is determined based on the depth of each of the first squares and the target depth confidence.

[0151] Optionally, the above device further includes a first filtering module, and the first filtering module is specifically used for:

[0152] Using a first sliding window with a scale of p *1, starting from the bottom first square of the p first squares in each column, sliding the first sliding window upward according to a preset step length to traverse the first squares, where p is an integer greater than 1;

[0153] In each of the first sliding windows, based on the depth of the first square at the bottom of the first sliding window, the depth of the first target square and the length of the carriage, determining a first depth confidence of the first target square, wherein the first target square is the first square at the top of the first sliding window;

[0154] Determine that a first depth confidence of a first remaining square is a first preset value, where the first remaining square is a square other than the first target square in the two or more first squares; the first target square and the first remaining square constitute the first squares;

[0155] The above target determination module is specifically used for:

[0156] Based on the first depth confidences of the first squares, a target depth confidence corresponding to the first square is determined.

[0157] Optionally, the above device further includes a second filtering module, and the second filtering module is specifically used for:

[0158] Using a second sliding window with a scale of m*n, sliding the second sliding window according to a preset rule to traverse each of the first squares, where m and n are integers greater than 1;

[0159] In each of the second sliding windows, determining a position difference between the deepest square in the second sliding window and a second target square, wherein the deepest square is the first square with the largest depth in the second sliding window, and the second target square is the first square at the center of the second sliding window;

[0160] determining a second depth confidence level of the second target square based on the position difference, the depth of the deepest square, the depth of the second target square, and the length of the carriage;

[0161] Determine a second depth confidence level of a second remaining square as a second preset value, where the second remaining square is a square other than the second target square in the two or more first squares; the second target square and the second remaining square constitute the first squares;

[0162] The above target determination module is specifically used for:

[0163] Based on the second depth confidence of each first square, a target depth confidence of the corresponding first square is determined.

[0164] Optionally, the above device further includes a third filtering module, and the third filtering module is specifically used for:

[0165] Using a first sliding window with a scale of p *1, starting from the bottom first square of the p first squares in each column, sliding the first sliding window upward according to a preset step length to traverse the first squares, where p is an integer greater than 1;

[0166] In each of the first sliding windows, based on the depth of the first square at the bottom of the first sliding window, the depth of the first target square and the length of the carriage, determining a first depth confidence of the first target square, wherein the first target square is the first square at the top of the first sliding window;

[0167] Determine that a first depth confidence of a first remaining square is a first preset value, where the first remaining square is a square other than the first target square in the two or more first squares; the first target square and the first remaining square constitute the first squares;

[0168] Using a second sliding window with a scale of m*n, sliding the second sliding window according to a preset rule to traverse each of the first squares, where m and n are integers greater than 1;

[0169] In each of the second sliding windows, determining a position difference between a second target square and the deepest square in the second sliding window, wherein the deepest square is the first square with the largest depth in the second sliding window, and the second target square is the first square at the center of the second sliding window;

[0170] determining a second depth confidence level of the second target square based on the position difference, the depth of the deepest square, the depth of the second target square, and the length of the carriage;

[0171] Determine a second depth confidence level of a second remaining square as a second preset value, where the second remaining square is a square other than the second target square in the two or more first squares; the second target square and the second remaining square constitute the first squares;

[0172] The above target determination module is specifically used for:

[0173] A weighted sum is performed on the first depth confidence and the second depth confidence of the same first square to obtain the target depth confidence.

[0174] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0175] Fig.10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.10 As shown, the electronic device of this embodiment includes: at least one processor 1000 ( Fig.10 Only one is shown in the figure), a memory 1001 and a computer program 1002 stored in the memory 1001 and executable on the at least one processor 1000, wherein the processor 1000 implements the steps of any of the above-mentioned method embodiments when executing the computer program 1002.

[0176] The electronic device may include, but is not limited to, a processor 1000 and a memory 1001. Those skilled in the art will appreciate that Fig.10 These are merely examples of electronic devices and do not constitute a limitation on the electronic devices. The electronic devices may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, the electronic devices may also include input and output devices, network access devices, etc.

[0177] The processor 1000 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 any conventional processor, etc.

[0178] In some embodiments, the memory 1001 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. In other embodiments, the memory 1001 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 1001 may also include both an internal storage unit of the electronic device and an external storage device. The memory 1001 is used to store an operating system, an application program, a boot loader (BootLoader), data and other programs, such as the program code of the computer program, etc. The memory 1001 may also be used to temporarily store data that has been output or is to be output.

[0179] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0180] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0181] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0182] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0183] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0184] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for measuring loading volume, characterized in that: Applied to electronic equipment, the method comprises: Determine a conveyor belt area in the carriage image captured by the image acquisition device, where the conveyor belt is not loaded with goods; In the case where the carriage in the carriage image is divided into two or more first squares, the depth of the first type of squares is determined based on the depth of the carriage point cloud collected by the point cloud collection device, and the first type of squares are first squares that are not in the conveyor belt area; Determine the depth of a second type of square based on the depth of the first type of square, where the second type of square is the first square in the conveyor belt area, and the depth of the second type of square represents the distance between the goods blocked by the conveyor belt and the electronic device; Based on the depth of each first square, the loading volume of the carriage is determined.

2. The method according to claim 1, characterized in that The determining the depth of the second type of squares based on the depth of the first type of squares comprises: Determine the depth of a first reference square as the bearing depth of the second-type square, the first reference square being the first first-type square located directly above the second-type square; interpolating the second-type squares based on the depth of the second reference square, the depth of the third reference square, the first target distance, and the second target distance to obtain a horizontal predicted depth of the second-type squares, wherein the second reference square is the first first-type square located on the left side of the second-type squares, the third reference square is the first first-type square located on the right side of the second-type squares, the first target distance is the distance between the second-type squares and the second reference squares, and the second target distance is the distance between the second-type squares and the third reference squares; The depth of the second type of grid is determined based on the horizontal predicted depth and the bearing depth.

3. The method according to claim 2, characterized in that The step of determining the depth of the second type of grid based on the horizontal predicted depth and the bearing depth comprises: If the horizontal prediction depth is greater than or equal to the bearing depth, the depth of the second type of grid is determined to be the bearing depth.

4. The method according to claim 2, characterized in that: The step of determining the depth of the second type of grid based on the horizontal predicted depth and the bearing depth comprises: If the horizontal predicted depth is less than the bearing depth, determining the bearing distance and the horizontal predicted distance of the second type of square, the bearing distance being the distance between the second type of square and the first first type of square located directly above the second type of square, and the horizontal predicted distance being the minimum value between the first target distance and the second target distance; The depth of the second-type grid is determined based on the bearing depth, the bearing distance, the horizontal prediction depth and the horizontal prediction distance.

5. The method according to claim 1, characterized in that The step of determining the loading volume of the carriage based on the depth of each first grid comprises: Determining the depth of each second square based on the depth of each first square, wherein the second square includes more than two first squares; Based on the depths of the second squares, the loading volume of the carriage is determined.

6. The method according to claim 5, characterized in that Before determining the depth of each second square based on the depth of each first square, the method further includes: For any first square, based on the time scale of k*q, within each k time window, the depth of the first square is updated to the maximum value of the k depths corresponding to the k time windows, where k is an integer greater than 1, and q is the sliding step of the time window, which is an integer greater than zero.

7. The method according to claim 5 or 6, characterized in that: Before determining the depth of each second square based on the depth of each first square, the method further includes: Determining the target depth confidence of each first square; The determining the depth of each second square based on the depth of each first square comprises: The depth of each of the second squares is determined based on the depth of each of the first squares and the target depth confidence.

8. The method according to claim 7, characterized in that Before determining the target depth confidence of each first grid, the method further includes: Using a first sliding window with a scale of p*1, starting from the bottom first square of the p first squares in each column, the first sliding window is slid upward according to a preset step length to traverse the first squares, where p is an integer greater than 1; In each of the first sliding windows, based on the depth of the first square at the bottom of the first sliding window, the depth of the first target square and the length of the carriage, determining a first depth confidence of the first target square, wherein the first target square is the first square at the top of the first sliding window; Determine that a first depth confidence of a first remaining square is a first preset value, where the first remaining square is a square other than the first target square in the two or more first squares; the first target square and the first remaining square constitute the first squares; The determining of the target depth confidence of each first square comprises: Based on the first depth confidences of the first squares, a target depth confidence corresponding to the first square is determined.

9. The method according to claim 7, characterized in that: Before determining the target depth confidence of each first grid, the method further includes: Using a second sliding window with a scale of m*n, sliding the second sliding window according to a preset rule to traverse each of the first squares, where m and n are integers greater than 1; In each of the second sliding windows, determining a position difference between the deepest square in the second sliding window and a second target square, wherein the deepest square is the first square with the largest depth in the second sliding window, and the second target square is the first square at the center of the second sliding window; determining a second depth confidence level of the second target square based on the position difference, the depth of the deepest square, the depth of the second target square, and the length of the carriage; Determine a second depth confidence level of a second remaining square as a second preset value, where the second remaining square is a square other than the second target square in the two or more first squares; the second target square and the second remaining square constitute the first squares; The determining of the target depth confidence of each first square comprises: Based on the second depth confidence of each first square, a target depth confidence of the corresponding first square is determined.

10. The method according to claim 7, characterized in that Before determining the target depth confidence of each first grid, the method further includes: Using a first sliding window with a scale of p*1, starting from the bottom first square of the p first squares in each column, the first sliding window is slid upward according to a preset step length to traverse the first squares, where p is an integer greater than 1; In each of the first sliding windows, based on the depth of the first square at the bottom of the first sliding window, the depth of the first target square and the length of the carriage, determining a first depth confidence of the first target square, wherein the first target square is the first square at the top of the first sliding window; Determine that a first depth confidence of a first remaining square is a first preset value, where the first remaining square is a square other than the first target square in the two or more first squares; the first target square and the first remaining square constitute the first squares; Using a second sliding window with a scale of m*n, sliding the second sliding window according to a preset rule to traverse each of the first squares, where m and n are integers greater than 1; In each of the second sliding windows, determining a position difference between a second target square and the deepest square in the second sliding window, wherein the deepest square is the first square with the largest depth in the second sliding window, and the second target square is the first square at the center of the second sliding window; determining a second depth confidence level of the second target square based on the position difference, the depth of the deepest square, the depth of the second target square, and the length of the carriage; Determine a second depth confidence level of a second remaining square as a second preset value, where the second remaining square is a square other than the second target square in the two or more first squares; the second target square and the second remaining square constitute the first squares; The determining of the target depth confidence of each first square comprises: A weighted sum is performed on the first depth confidence and the second depth confidence of the same first square to obtain the target depth confidence.

11. A device for measuring loading volume, characterized in that: Applied to electronic equipment, the device comprises: The area determination module is used to determine the conveyor belt area in the carriage image acquired by the image acquisition device, where the conveyor belt is not loaded with goods; A first depth determination module is used to determine the depth of a first type of square based on the depth of the point cloud of the carriage collected by the point cloud collection device when the carriage in the carriage image is divided into two or more first squares, wherein the first type of square is a first square that is not in the conveyor belt area; A second depth determination module, configured to determine the depth of a second type of square based on the depth of the first type of square, wherein the second type of square is the first square in the conveyor belt area, and the depth of the second type of square represents the distance between the goods blocked by the conveyor belt and the electronic device; The loading volume determination module is used to determine the loading volume of the carriage based on the depth of each first square.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the electronic device implements the method according to any one of claims 1 to 10.

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

Images