A method for obtaining loading information, terminal equipment and computer storage medium

Abstract

The present application provides a method for obtaining loading information, a terminal device, and a computer storage medium. The method for obtaining loading information includes: obtaining a segmentation prediction map of a monitoring image; setting a dynamic calculation segmentation line based on the segmentation prediction map; using the dynamic calculation segmentation line as a boundary, obtaining the number of pixels of a first preset label and the number of pixels of a second preset label above the dynamic calculation segmentation line; using the number of pixels of the first preset label and the number of pixels of the second preset label to obtain the loading information corresponding to the monitoring image. In the above manner, the method for obtaining loading information of the present application can calculate the loading information in real time, effectively improving the efficiency and accuracy of obtaining loading information.

Description

Technical Field

[0001] The present application relates to the technical field of logistics management, and in particular to a method for acquiring loading information, a terminal device, and a computer storage medium. Background Art

[0002] In the logistics field, the load factor generally refers to the actual cargo volume divided by the maximum cargo volume. Load factors can be categorized as static and dynamic. The static load factor refers to the load factor when the cargo is stationary, while the dynamic load factor refers to the real-time load factor during loading and unloading. Load factors are a method for evaluating operational efficiency and can be used to reflect the performance of logistics transfer stations. Load factors can be used to optimize vehicle scheduling, thereby fully utilizing vehicle resources, reducing logistics costs, and improving operational efficiency.

[0003] Existing technologies typically assess car load rates based on manual judgment or calculations using measuring equipment. Manual judgment prevents timely feedback to management systems, while measuring equipment requires a separate measurement platform and equipment and is susceptible to external influences, resulting in inaccurate calculations. Relying on both measuring equipment and manual labor requires significant labor costs, resulting in high costs and slow measurement speeds. Summary of the Invention

[0004] The present application provides a method for obtaining loading information, a terminal device, and a computer storage medium.

[0005] The present application provides a method for obtaining loading information based on a logistics compartment, the method comprising:

[0006] Obtain a segmentation prediction map of the surveillance image;

[0007] Setting a dynamic calculation segmentation line based on the segmentation prediction map;

[0008] Taking the dynamically calculated segmentation line as a boundary, obtaining the number of pixels of the first preset label and the number of pixels of the second preset label above the dynamically calculated segmentation line;

[0009] The loading information corresponding to the monitoring image is obtained by using the number of pixels of the first preset label and the number of pixels of the second preset label.

[0010] in,

[0011] After obtaining the loading information corresponding to the monitoring image, the loading information obtaining method further includes:

[0012] Obtain multiple frames of continuous monitoring images and their corresponding loading information;

[0013] Acquire a current monitoring image and a preset number of historical monitoring images that precede the current monitoring image in time sequence;

[0014] The dynamic loading information of the current monitoring image is acquired by using the current loading information of the current monitoring image and the historical loading information of the preset number of historical monitoring images.

[0015] in,

[0016] The acquiring the dynamic loading information of the current monitoring image by using the current loading information of the current monitoring image and the historical loading information of the preset number of historical monitoring images includes:

[0017] removing the maximum value and the minimum value from the current loading information and a preset number of historical loading information;

[0018] An average value of the remaining loading information is calculated as the dynamic loading information of the current monitoring image.

[0019] in,

[0020] The dynamically calculating segmentation line based on the segmentation prediction map is set, comprising:

[0021] Acquire a first horizontal projection image of pixel points with a first preset label and a second horizontal projection image of pixel points with a second preset label based on the segmentation prediction image;

[0022] Obtain a first coordinate position value in the first horizontal projection image where the pixel value from top to bottom is greater than or equal to a preset pixel threshold;

[0023] Obtain a second coordinate position value in the second horizontal projection image where the pixel value from top to bottom is greater than or equal to a preset pixel threshold;

[0024] The dynamically calculated segmentation line is set using the first coordinate position value and the second coordinate position value.

[0025] The step of setting the dynamically calculated segmentation line by using the first coordinate position value and the second coordinate position value includes:

[0026] Obtaining the minimum coordinate position value between the first coordinate position value and the second coordinate position value;

[0027] Performing smoothing filtering on the minimum coordinate position value using a preset exponential smoothing method to obtain a smoothed coordinate position value;

[0028] Setting the dynamically calculated segmentation line based on the smoothed coordinate position value;

[0029] Wherein, the preset exponential smoothing method is Holt's two-parameter linear exponential smoothing method.

[0030] in,

[0031] The acquiring the loading information corresponding to the monitoring image by using the number of pixels of the first preset label and the number of pixels of the second preset label includes:

[0032] Obtaining a ratio of the number of pixels of the first preset label to the number of pixels of the second preset label;

[0033] When the ratio is less than or equal to a preset threshold, obtaining loading information corresponding to the monitoring image according to a first loading rate estimation relationship;

[0034] When the ratio is greater than the preset threshold, the loading information corresponding to the monitoring image is obtained according to the second loading rate estimation relationship.

[0035] The method for obtaining loading information further includes:

[0036] generating vehicle dispatch information based on the loading information;

[0037] Dispatch logistics vehicles according to the vehicle dispatch information.

[0038] The present application also provides a terminal device, comprising:

[0039] A prediction module is used to obtain a segmentation prediction map of the monitoring image;

[0040] A segmentation module, configured to set a dynamic calculation segmentation line based on the segmentation prediction map;

[0041] A calculation module, configured to obtain the number of pixels of the first preset label and the number of pixels of the second preset label above the dynamically calculated dividing line, with the dynamically calculated dividing line as a boundary;

[0042] The calculation module is further configured to obtain the loading information corresponding to the monitoring image by using the number of pixels of the first preset label and the number of pixels of the second preset label.

[0043] The present application also provides another terminal device, comprising a memory and a processor, wherein the memory is coupled to the processor;

[0044] The memory is used to store program data, and the processor is used to execute the program data to implement the above-mentioned loading information acquisition method.

[0045] The present application also provides a computer storage medium, which is used to store program data. When the program data is executed by a processor, it is used to implement the above-mentioned loading information acquisition method.

[0046] The beneficial effects of this application are as follows: the terminal device sets a dynamic calculation segmentation line based on the segmentation prediction map; using the dynamic calculation segmentation line as the boundary, the number of pixels of the first preset label and the number of pixels of the second preset label above the dynamic calculation segmentation line are obtained; and the number of pixels of the first preset label and the number of pixels of the second preset label are used to obtain the loading information corresponding to the monitoring image. Through the above method, the loading information acquisition method of this application can calculate loading information in real time, effectively improving the efficiency and accuracy of loading information acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. Among them:

[0048] Figure 1 This is a flow chart of an embodiment of a method for obtaining loading information provided by the present application;

[0049] Figure 2 This is a schematic diagram of the framework of the loading and unloading monitoring image provided by this application;

[0050] Figure 3 This is a flowchart of an embodiment of a method for setting a dynamic calculation dividing line provided by the present application;

[0051] Figure 4 This application provides a dynamic calculation dividing line and horizontal projection Figure 1 Schematic diagram of an embodiment;

[0052] Figure 5 It is a schematic diagram of another embodiment of the dynamic calculation dividing line and horizontal projection diagram provided by the present application;

[0053] Figure 6 This is a schematic structural diagram of an embodiment of a terminal device provided by this application;

[0054] Figure 7 is a structural diagram of another embodiment of the terminal device provided by this application;

[0055] Figure 8 It is a structural diagram of an embodiment of a computer storage medium provided by this application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0057] See also Figure 1 , Figure 1 It is a flow chart of an embodiment of a method for obtaining loading information provided in this application.

[0058] The loading information acquisition method of the present application is applied to a terminal device, wherein the terminal device of the present application can be a server or a system comprising a server and an electronic device. Accordingly, the various components of the terminal device, such as the various units, subunits, modules, and submodules, can be all provided in the server or separately provided in the server and the electronic device.

[0059] Furthermore, the above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here. In some possible implementations, the loading information acquisition method of the embodiment of the present application can be implemented by a processor calling computer-readable instructions stored in a memory.

[0060] Specifically, if Figure 1 As shown, the method for obtaining loading information in the embodiment of the present application specifically includes the following steps:

[0061] Step S11: Obtain a segmentation prediction map of the monitoring image.

[0062] In an embodiment of the present application, the terminal device uses a surveillance camera installed in a factory or above a logistics truck to collect loading and unloading videos inside the logistics truck, and then intercepts several surveillance images from the loading and unloading videos to analyze the cargo loading rate of the compartment inside the logistics truck.

[0063] Specifically, the terminal device extracts the monitoring images from the loading and unloading video, such as Figure 2As shown, if the size of the monitoring image does not meet the preset size of the segmentation network model of the embodiment of the present application, the size of the monitoring image is scaled to the preset size. For example, the preset size can be set to 512×512, and the terminal device scales the size of the monitoring image to 512×512 to meet the size requirements of the segmentation network model. Furthermore, the terminal device can also divide the three RGB channels of the monitoring image by 255 respectively to normalize the monitoring image. The normalized data processing method is conducive to the convergence of the segmentation network model and accelerates the segmentation efficiency of the segmentation network model.

[0064] Furthermore, the terminal device inputs the monitoring image into the segmentation network model to obtain the segmentation label of each pixel of the monitoring image to form a segmentation prediction map.

[0065] In the process of segmenting the network model, the staff needs to fit and label the scene in the car. The main segmentation labels include but are not limited to: package labels, car side wall labels, car top wall labels, car bottom wall labels, conveyor belt labels, logistics personnel labels and other labels. After fitting and labeling, a label image with the same size as the original image is obtained. Figure 1 One pair constitutes a training set, and then the loss function of the segmentation network model is used for training.

[0066] In actual applications, the terminal device sends the video frames in the surveillance video to the segmentation network model frame by frame, and obtains the predicted image of the scene inside the car for each frame of the video. Each pixel point of the predicted image is composed of predicted labels of different categories.

[0067] Since the labels of different categories of scenes in the car are quite different, in order to enable the constructed segmentation network model to better learn the features of each label and thus achieve a more accurate segmentation effect, the embodiment of the present application provides the following loss function:

[0068]

[0069] Among them, M is the number of labels of the segmentation network model, w c is the weight parameter of label c; y c is the label value of label c, where is a one-hot vector with only two possible values: 0 and 1; p c is the probability that the predicted sample belongs to label c.

[0070] Among them, the weight parameter w c is calculated as follows:

[0071]

[0072] Where N is the total number of pixels of the monitoring image, N c is the number of pixels of label c.

[0073] Step S12: setting a dynamic calculation segmentation line based on the segmentation prediction map.

[0074] In the embodiment of the present application, the terminal device obtains the pixel distribution of each label in step S11, and can use the pixel points of one label or the pixel points of multiple labels to set a dynamic calculation dividing line. The embodiment of the present application provides a method for setting a dynamic calculation dividing line using the pixels of the conveyor belt label and the pixels of the bottom wall label in the carriage. For details, please refer to Figure 3 , Figure 3 This is a flow chart of an embodiment of a method for setting a dynamically calculated segmentation line provided by the present application. In other embodiments, pixels of other labels may also be used to set a dynamically calculated segmentation line, which will not be described in detail here.

[0075] Specifically, the dynamic calculation dividing line setting method of the present application includes the following steps:

[0076] Step S121: obtaining a first horizontal projection image of pixel points with a first preset label and a second horizontal projection image of pixel points with a second preset label based on the segmentation prediction image.

[0077] In the embodiment of the present application, the terminal device calculates the horizontal projection of the pixels of the conveyor belt label according to the segmentation prediction map to obtain a first horizontal projection map; calculates the horizontal projection of the pixels of the bottom wall label in the carriage to obtain a second horizontal projection map. For details, please refer to Figure 4 and Figure 5 .exist Figure 4 and Figure 5 In the figure, the left image is the segmentation prediction map and its dynamically calculated segmentation line, the middle image is the second horizontal projection map, and the right image is the first horizontal projection map.

[0078] Step S122: obtaining a first coordinate position value of a pixel whose value from top to bottom in the first horizontal projection image is greater than or equal to a preset pixel threshold.

[0079] Step S123: obtaining second coordinate position values ​​of pixels whose pixel values ​​from top to bottom in the second horizontal projection image are greater than or equal to a preset pixel threshold.

[0080] In this embodiment of the present application, since logistics packages are generally transported from the doorway to the interior of the train, the lower area in the segmentation prediction map is the doorway area, and the upper area is the interior area of ​​the train. Therefore, the terminal device obtains the first coordinate position and the second coordinate position of the first horizontal projection map and the second horizontal projection map from top to bottom, respectively, where the pixel value is greater than or equal to the preset pixel threshold. In other words, it obtains the projection position of the first horizontal projection map and the second horizontal projection map where the pixel value first reaches the preset pixel threshold.

[0081] Step S124: using the first coordinate position value and the second coordinate position value to set a dynamically calculated dividing line.

[0082] In an embodiment of the present application, the terminal device can take the minimum coordinate position value between the first coordinate position value and the second coordinate position value, and set the dynamically calculated dividing line according to the minimum coordinate position value; the terminal device can also take the average coordinate position value between the first coordinate position value and the second coordinate position value, and set the dynamically calculated dividing line according to the average coordinate position value; the terminal device can also take the maximum coordinate position value between the first coordinate position value and the second coordinate position value, and set the dynamically calculated dividing line according to the maximum coordinate position value.

[0083] Furthermore, taking the minimum coordinate position value as an example, the terminal device can also use a preset exponential smoothing method to smooth the minimum coordinate position value to obtain a smoothed coordinate position value, and then set a dynamic calculation dividing line according to the smoothed coordinate position value, which can effectively avoid the deviation of the loading rate value caused by the movement of goods and provide a basis for the calculation of the dynamic loading rate.

[0084] The preset exponential smoothing method provided in the embodiment of the present application is the Holt two-parameter linear exponential smoothing method. The specific expression of the Holt two-parameter linear exponential smoothing method is as follows:

[0085] S t =αC0+(1-α)(S t-1 +b t-1 )

[0086] b t =γ(S t -S t-1 )+(1-γ)b t-1

[0087] C h =S t +b t

[0088] Wherein, α and γ are smoothing parameters. In the embodiment of the present application, α can be 0.4 and γ can be 0.1; C0 is the minimum coordinate position value, C h is the smoothed coordinate position value, S t and b t is an intermediate variable.

[0089] Step S13: taking the dynamically calculated dividing line as a boundary, obtaining the number of pixels of the first preset label and the number of pixels of the second preset label above the dynamically calculated dividing line.

[0090] In an embodiment of the present application, the terminal device uses the dynamically calculated dividing line generated by the above process as the boundary, and counts the number of pixels P of the wrapped label above the dynamically calculated dividing line within the segmentation prediction map, as well as the number of pixels S of the label on the inner wall of the vehicle.

[0091] Step S14: using the number of pixels of the first preset label and the number of pixels of the second preset label, obtaining the loading information corresponding to the monitoring image.

[0092] In this embodiment of the present application, the terminal device calculates the ratio R = P / S, the number of pixels P on the package label and the number S on the inner wall label. The terminal device then substitutes this ratio R into the loading rate estimation function provided in this embodiment of the present application to obtain the initial value Rt of the loading rate corresponding to the monitoring image.

[0093] Specifically, the expression of the load rate estimation function provided in the embodiment of the present application is as follows:

[0094]

[0095] Furthermore, the terminal device may also use a median sliding average filtering method to smooth the loading rate Rt to obtain a final dynamic loading rate Rf.

[0096] Specifically, the terminal device treats N consecutively acquired load rates as a queue with a fixed length of N. Each time a new data point is calculated, it is placed at the end of the queue according to the first-in, first-out principle, and the data point at the head of the queue is discarded. For the current surveillance image and its current load rate, the terminal device places the current load rate at the end of the queue. After removing the maximum and minimum load rates in the current queue, the terminal device calculates the arithmetic average of the load rates in the current queue to obtain the dynamic load rate of the current surveillance image.

[0097] In actual applications, the terminal device sends the dynamic loading rate generated by the above process to the control server, which facilitates the control server to record and further analyze the dynamic loading rate information, providing a reference basis for reasonable vehicle scheduling.

[0098] Specifically, the control server uses the recorded dynamic loading rate to set thresholds according to demand, issues scheduling information, and reasonably schedules vehicles to fully utilize vehicle resources, reduce logistics costs, and improve operational efficiency.

[0099] The terminal device of the embodiment of the present application combines the convolutional neural network of semantic segmentation to analyze the logistics truck loading and unloading video captured by the camera, uses the horizontal projection algorithm to calculate the dynamic segmentation line, and calculates the dynamic loading rate in real time through the filtering smoothing algorithm and the loading rate estimation function. The device not only reduces the calculation error caused by the movement of goods, but also can intuitively display the cargo loading rate of the carriage in real time and send the loading rate to the central server for server recording and analysis. The loading information acquisition method of the embodiment of the present application helps to reasonably dispatch vehicles so as to make full use of vehicle resources, reduce logistics costs and improve operating efficiency.

[0100] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0101] In order to implement the method for obtaining loading information in the above embodiment, this application also proposes a terminal device, for details, please refer to Figure 6 , Figure 6 It is a structural diagram of an embodiment of a terminal device provided by this application.

[0102] like Figure 6 As shown, the terminal device 400 provided in this application includes a prediction module 41 , a segmentation module 42 and an acquisition module 43 .

[0103] The prediction module 41 is used to obtain a segmentation prediction map of the monitoring image.

[0104] The segmentation module 42 is configured to set a dynamic segmentation line based on the segmentation prediction map.

[0105] The acquisition module 43 is used to obtain the number of pixels of the first preset label and the number of pixels of the second preset label above the dynamically calculated dividing line with the dynamically calculated dividing line as the boundary; and is also used to use the number of pixels of the first preset label and the number of pixels of the second preset label to obtain the loading information corresponding to the monitoring image.

[0106] In order to implement the method for obtaining loading information in the above embodiment, this application also proposes another terminal device, for details, please refer to Figure 7 , Figure 7 It is a structural diagram of another embodiment of the terminal device provided by this application.

[0107] The terminal device 500 of the embodiment of the present application includes a memory 51 and a processor 52, wherein the memory 51 and the processor 52 are coupled.

[0108] The memory 51 is used to store program data, and the processor 52 is used to execute the program data to implement the loading information acquisition method described in the above embodiment.

[0109] In this embodiment, the processor 52 may also be referred to as a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip having signal processing capabilities. The processor 52 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor, or the processor 52 may be any conventional processor.

[0110] This application also provides a computer storage medium, such as Figure 8 As shown, the computer storage medium 600 is used to store program data 61. When the program data 61 is executed by the processor, it is used to implement the loading information acquisition method as described in the above embodiment.

[0111] The present application also provides a computer program product, wherein the computer program product includes a computer program, and the computer program is operable to enable a computer to execute the method for obtaining loading information as described in the embodiment of the present application. The computer program product can be a software installation package.

[0112] The loading information acquisition method described in the above embodiment of the present application, when implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a device, such as a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0113] The above description is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for obtaining loading information, characterized in that: The loading information acquisition method comprises: Obtain a segmentation prediction map of the surveillance image; Setting a dynamically calculated segmentation line based on the segmentation prediction map; Taking the dynamically calculated segmentation line as a boundary, obtaining the number of pixels of the first preset label and the number of pixels of the second preset label above the dynamically calculated segmentation line; Acquire loading information corresponding to the monitoring image by using the number of pixels of the first preset label and the number of pixels of the second preset label; The dynamically calculating segmentation line based on the segmentation prediction map is set, comprising: Acquire a first horizontal projection map of pixel points with a first preset label and a second horizontal projection map of pixel points with a second preset label based on the segmentation prediction map; Obtain a first coordinate position value in the first horizontal projection image where the pixel value from top to bottom is greater than or equal to a preset pixel threshold; Acquire a second coordinate position value in the second horizontal projection image where the pixel value from top to bottom is greater than or equal to a preset pixel threshold; The dynamically calculated segmentation line is set using the first coordinate position value and the second coordinate position value.

2. The method for obtaining loading information according to claim 1, characterized in that: After obtaining the loading information corresponding to the monitoring image, the loading information obtaining method further includes: Obtain multiple frames of continuous monitoring images and their corresponding loading information; Acquire a current monitoring image and a preset number of historical monitoring images that precede the current monitoring image in time sequence; The dynamic loading information of the current monitoring image is acquired by using the current loading information of the current monitoring image and the historical loading information of the preset number of historical monitoring images.

3. The method for obtaining loading information according to claim 2, characterized in that: The obtaining the dynamic loading information of the current monitoring image by using the current loading information of the current monitoring image and the historical loading information of the preset number of historical monitoring images includes: Remove the maximum value and the minimum value from the current loading information and a preset number of historical loading information; An average value of the remaining loading information is calculated as the dynamic loading information of the current monitoring image.

4. The method for obtaining loading information according to claim 1, characterized in that: The step of setting the dynamically calculated segmentation line by using the first coordinate position value and the second coordinate position value includes: Obtaining the minimum coordinate position value between the first coordinate position value and the second coordinate position value; Performing smoothing filtering on the minimum coordinate position value using a preset exponential smoothing method to obtain a smoothed coordinate position value; Setting the dynamically calculated segmentation line based on the smoothed coordinate position value; The preset exponential smoothing method is Holt's two-parameter linear exponential smoothing method.

5. The method for obtaining loading information according to claim 1, characterized in that: The acquiring the loading information corresponding to the monitoring image by using the number of pixels of the first preset label and the number of pixels of the second preset label includes: Obtaining a ratio of the number of pixels of the first preset label to the number of pixels of the second preset label; When the ratio is less than or equal to a preset threshold, obtaining loading information corresponding to the monitoring image according to a first loading rate estimation relationship; When the ratio is greater than the preset threshold, the loading information corresponding to the monitoring image is obtained according to the second loading rate estimation relationship.

6. The method for obtaining loading information according to claim 1, characterized in that: The loading information acquisition method further includes: generating vehicle dispatch information based on the loading information; The logistics vehicles are dispatched according to the vehicle dispatching information.

7. A terminal device, characterized in that: The terminal device comprises: A prediction module, used to obtain a segmentation prediction map of a surveillance image; A segmentation module, used for setting a dynamic calculation segmentation line based on the segmentation prediction map; A calculation module, used to obtain the number of pixels of the first preset label and the number of pixels of the second preset label above the dynamically calculated segmentation line with the dynamically calculated segmentation line as a boundary; The calculation module is further used to obtain the loading information corresponding to the monitoring image by using the number of pixels of the first preset label and the number of pixels of the second preset label; The segmentation module is also used to obtain a first horizontal projection image of pixel points of a first preset label and a second horizontal projection image of pixel points of a second preset label based on the segmentation prediction image; obtain a first coordinate position value in which the pixel value from top to bottom in the first horizontal projection image is greater than or equal to a preset pixel threshold; obtain a second coordinate position value in which the pixel value from top to bottom in the second horizontal projection image is greater than or equal to the preset pixel threshold; and use the first coordinate position value and the second coordinate position value to set the dynamically calculated segmentation line.

8. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory is coupled to the processor; The memory is used to store program data, and the processor is used to execute the program data to implement the loading information acquisition method according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that: The computer storage medium is used to store program data, and when the program data is executed by the processor, it is used to implement the loading information acquisition method according to any one of claims 1 to 6.

Images