Cargo statistics method and system

By using image acquisition equipment and computer vision technology on transport vehicles, the cargo transportation status is automatically identified and statistical results are updated, and the inaccuracy and inefficiency caused by manual recording is solved, and efficient and reliable cargo statistics and safe transportation are achieved. .

WO2024243766A1PCT designated stage expired Publication Date: 2024-12-05SUZHOU YIXINAN IND TECH CO LTD

Patent Information

Application Number
PCT/CN2023/096762
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-29
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

In scenarios such as factories, docks and warehouses, cargo statistics for transport vehicles usually rely on manual records, resulting in inaccurate results and low efficiency, and the reliability of cargo statistics cannot be guaranteed.

Method used

By installing image acquisition equipment on the transport vehicle, continuous frame image data is obtained, computer vision technology and object feature recognition are used to automatically determine the cargo status of cargo transport components, and the cargo statistical results are updated in real time according to state changes and feature information.

Benefits of technology

The automation and accuracy of cargo statistics are improved, manual misreading and misrecording are reduced, statistical efficiency and reliability are improved, labor costs are saved, and the feasible parameters are adjusted under cargo loading to ensure transportation safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023096762_05122024_PF_FP_ABST
    Figure CN2023096762_05122024_PF_FP_ABST
Patent Text Reader

Abstract

The present application provides a cargo statistics method and system. The method comprises: configuring an image acquisition device on a transport vehicle; performing image acquisition on a cargo transport component of the transport vehicle; obtaining continuous frames of image data, and then automatically performing object feature identification on the image data; and according to object feature information of a corresponding object region, automatically determining a transport state, such as loaded state or an empty state, of the cargo transport component, so that various cargo statistics results are automatically and accurately obtained according to a change in the transport state and / or the identified object feature information. There is no need to perform manual reading and recording, thereby preventing the technical problem of inaccurate cargo statistics results due to misreading, inaccurate recording / calculation, etc., improving the statistical efficiency and reliability of cargo statistics results and saving labor costs.
Need to check novelty before this filing date? Find Prior Art

Description

A cargo statistics method and system Technical Field

[0001] This application is mainly used in the field of vehicle safe driving, and more specifically relates to a cargo statistics method and system. Background Art

[0002] In factories, docks, warehouses, and other workplaces, goods are often transported using transport vehicles like forklifts. During the transport process, on-site staff or drivers typically record the number of times a vehicle transports goods, the types of goods transported, and the weighing results of the goods on the scales. This is time-consuming and labor-intensive, and cannot guarantee the reliability and accuracy of the cargo statistics.

[0003] Summary of the Invention

[0004] In view of this, in order to solve the above technical problems, this application provides the following technical solutions:

[0005] In one aspect, the present application proposes a cargo statistics method, comprising:

[0006] Acquire continuous frame image data of a cargo transport component of a transport vehicle; the image data is acquired by an image acquisition device installed on the transport vehicle;

[0007] performing object feature recognition on the image data to obtain object feature information of a corresponding object area in the image data;

[0008] Determining the transport state of the cargo transport component based on the object feature information in the continuous frame image data; the transport state includes a loaded state or an empty state;

[0009] According to the change of the transportation status and / or the object characteristic information, corresponding cargo statistics results are obtained.

[0010] Optionally, determining the transport status of the cargo transport component based on the object feature information in the continuous frame image data includes:

[0011] detecting that the object characteristic information only includes the component characteristics of the cargo transport component, and determining that the cargo transport component is in the empty state;

[0012] detecting that the object characteristic information includes the characteristic of the transported cargo, and determining that the cargo transport component is in the loaded state; wherein the object characteristic information includes the characteristic of the transported cargo comprises: the object characteristic information identified from any frame of image data includes the characteristic of the transported cargo, and the object characteristic information identified from multiple frames of image data subsequent to the frame of image data all include the characteristic of the transported cargo;

[0013] Obtaining corresponding cargo statistics results based on the change in the transportation status includes:

[0014] Monitor the change of the cargo transport component between the empty state and the loaded state, and update the cargo transport times of the transport vehicle.

[0015] Optionally, performing object feature recognition on the image data to obtain object feature information of a corresponding object area in the image data, and determining the transport status of the cargo transport component based on the object feature information in the continuous frame image data includes:

[0016] Performing regional segmentation on the image data to obtain regional images of different object regions in the image data; wherein the regional segmentation is performed based on the structure of the transport vehicle, the structure being a component located at a fixed position on the transport vehicle in the historical frame image data; the object region includes the region where the cargo transport component is located and / or the region where the transported cargo is located;

[0017] Performing object recognition on the region image to obtain object feature information corresponding to the object region;

[0018] Determining whether the transported cargo is within a preset position range of a preset structure of the transport vehicle based on the object characteristic information;

[0019] If the transported cargo is within the preset position range, it is determined that the cargo transport component is in a cargo-carrying state. Optionally, when it is determined that the cargo transport component is in the cargo-carrying state, the method further includes:

[0020] Adjusting the drivable parameters of the transport vehicle in the current cargo transport direction based on the object characteristic information to control the drivability of the transport vehicle in the current cargo transport direction;

[0021] The drivable parameters include one or more combinations of drivable speed, drivable distance and drivable time.

[0022] Optionally, adjusting the drivable parameters of the transport vehicle in the current cargo transport direction based on the object feature information includes:

[0023] determining a transport height of the transported cargo on the cargo transport component based on the object characteristic information;

[0024] Determining the current transport safety level of the transport height according to a preset transport safety level classification method; the transport safety level classification method can be determined based on the sight height of the driver of the transport vehicle;

[0025] Adjusting the drivable parameters of the transport vehicle in the current cargo transport direction according to the current transport safety level;

[0026] The lower the transport safety level is, the smaller the adjusted drivable parameter of the transport vehicle in the current cargo transport direction is.

[0027] Optionally, obtaining corresponding cargo statistics results based on the change in the transportation status and the object characteristic information includes:

[0028] Determining that the cargo transport component is in a loaded state, and determining a cargo type corresponding to the transported cargo based on the characteristics of the transported cargo included in the object characteristic information;

[0029] According to the change of the transportation status and the cargo type of the transported cargo, the transportation times of different types of transported cargo are obtained.

[0030] Optionally, the characteristics of the transported goods include: the size of the transported goods, and obtaining corresponding cargo statistics results based on the change in the transport status and the object characteristic information further includes:

[0031] Obtaining the quantity of the corresponding type of transported goods transported by the cargo transport component according to the size of the transported goods and the unit cargo size of the corresponding type of goods;

[0032] The total quantity of the transported goods of different types is obtained according to the quantity of the goods and the number of times the transported goods of different types are transported.

[0033] Optionally, a method for obtaining the characteristics of the transported goods contained in the object characteristic information includes:

[0034] Determining that the object feature information includes a cargo label, adjusting configuration parameters of the image acquisition device to obtain a label image of an area where the cargo label is located;

[0035] The label image is subjected to label recognition, and the characteristics of the transported goods recorded in the recognized cargo label are read.

[0036] Optionally, the cargo statistics result can be dynamically updated, and the method further includes:

[0037] Sending the cargo statistics results obtained each time to a display device, which synchronously displays the cargo statistics results; the display device is located in the driving cabin of the transport vehicle;

[0038] detecting an input operation on any cargo data included in the displayed cargo statistics result, and updating the cargo statistics result; and / or;

[0039] The updated cargo statistics results are reported to the management system.

[0040] In another aspect, the present application further proposes a cargo statistics system, comprising:

[0041] Communication equipment, used to realize communication connection between different devices in the cargo statistics system;

[0042] An image acquisition device installed on a transport vehicle, for acquiring continuous frame image data of a cargo transport component of the transport vehicle;

[0043] A storage device for storing a program for implementing the above-mentioned cargo statistics method;

[0044] The processing device is used to load and execute the program stored in the storage device to implement the cargo statistics method as described above.

[0045] Optionally, also include:

[0046] A display device installed in the driving cabin of the transport vehicle and connected to the processing device, for synchronously displaying the cargo statistics results obtained each time;

[0047] The processing device is further configured to detect an input operation on any cargo data included in the cargo statistics result displayed by the display device, and update the cargo statistics result;

[0048] and / or,

[0049] The communication device is also used to connect to a management system and report the updated cargo statistics results to the management system.

[0050] It can be seen that the present application provides a cargo statistics method and system. By configuring an image acquisition device on a transport vehicle, image acquisition is performed on the cargo transport components of the transport vehicle. After obtaining continuous frame image data, the image data can be automatically identified as an object, and the object feature information of the corresponding object area can be accurately obtained. Based on this, the transport status of the cargo transport components, such as a loaded state or an empty state, is automatically determined. Various cargo statistics results are automatically and accurately obtained based on the changes in the transport status and / or the identified object feature information. There is no need for manual reading of records, which avoids technical problems such as inaccurate cargo statistics results caused by misreading, misrecording / calculation, improves the statistical efficiency and reliability of the cargo statistics results, and saves labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0052] FIG1 is a flow chart of an optional example of the cargo statistics method proposed in this application;

[0053] FIG2 is a flow chart of another optional example of the cargo statistics method proposed in this application;

[0054] FIG3 is a flow chart of another optional example of the cargo statistics method proposed in this application;

[0055] FIG4 is a schematic structural diagram of an optional example of a cargo statistics device proposed in this application;

[0056] FIG5 is a schematic structural diagram of an optional example of a cargo statistics system proposed in this application;

[0057] FIG6 is a schematic diagram of an optional deployment structure of an image acquisition device in the cargo statistics system proposed in this application;

[0058] FIG7 is a schematic diagram of an optional deployment structure of detection equipment in the cargo statistics system proposed in this application. DETAILED DESCRIPTION

[0059] In view of the technical content described in the background technology part, with the development and application of artificial intelligence technologies such as computer vision technology, image recognition technology, and machine learning technology, in order to improve the efficiency and accuracy of cargo statistics, this application proposes to automatically identify whether a vehicle is transporting cargo, the type of cargo being transported, and the visual characteristics of the weight and / or quantity of the transported cargo such as volume and size based on computer vision technology, and quickly and accurately obtain statistical results such as the number of cargo transportations, the type of cargo being transported, the number of transportations of each type of cargo, the weight and / or quantity of each type of cargo transported, etc., without the need for manual identification and recording of data, thereby avoiding the resulting erroneous statistical results and greatly improving the accuracy and efficiency of the statistical results.

[0060] In some embodiments, in order to improve the accuracy of object feature information recognition, feature extraction can be performed on the target object area in the captured image to obtain corresponding object feature information, reduce feature extraction of irrelevant area images, improve object feature recognition efficiency, and thereby improve the accuracy of the transportation status of the cargo transportation components determined accordingly.

[0061] Furthermore, to ensure cargo transportation safety and reduce safety incidents, upon determining that the cargo transport unit is loaded, the vehicle's drivable parameters in the current transport direction, such as at least one of the drivable speed, drivable distance, and drivable time, can be adjusted. This allows the vehicle to control its drivability in the current transport direction, such as limiting this drivability when loaded, thereby reducing the risk of cargo transport safety issues caused by excessive drivability parameters. Furthermore, the present application can also detect the transport height of the cargo being transported and accurately determine the extent of adjustments to these drivable parameters, thereby preventing accidents caused by cargo obstructing the driver's view and ensuring cargo safety.

[0062] 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.

[0063] It should be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of this application can be combined with each other.

[0064] It should be understood that the terms "system," "device," "unit," and / or "module" used in this application are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0065] As used in this application and the claims, unless the context clearly indicates an exception, the terms "a," "an," "an," and / or "the" are not intended to refer to the singular and may include the plural, unless the context clearly indicates otherwise. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements. The phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, product, or apparatus that includes the elements.

[0066] Among them, in the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" refers to two or more than two. The following terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0067] In addition, flow charts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0068] Referring to Figure 1, a flowchart of an optional example of the cargo statistics method proposed in this application is provided. This method can be applied to processing devices such as vehicle-mounted terminals (such as terminals integrated into vehicles, or mobile terminals fixed to vehicles via fixed components as vehicle-mounted terminals, etc., which are not limited in this application and can be used as needed), vehicle-mounted processors, etc. This application does not limit the product type and composition structure of such processing devices. As shown in Figure 1, the cargo statistics method proposed in this embodiment may include, but is not limited to, the following steps:

[0069] Step S11, acquiring continuous frame image data of cargo transport components of a transport vehicle;

[0070] In combination with the above description of the technical solution of this application, this application proposes to install image acquisition equipment on a transport vehicle, such as a camera device and / or a scanning device, so that when the transport vehicle is operating, it can enter an image acquisition state and obtain continuous frame image data. This application does not elaborate on the type of image acquisition equipment and its working principle.

[0071] In an embodiment of the present application, in order to automatically detect whether a cargo transport component of a transport vehicle is transporting cargo and to generate statistical results such as the number of completed transports, the image acquisition device may be oriented toward the direction of the cargo transport component. Thus, before driving the transport vehicle to transport cargo, the image acquisition device may be activated to capture images. The captured image data may include or characterize the transport status of the cargo transport component, and the processing device may acquire the image data continuously captured by the image acquisition device in real time to obtain continuous frame image data. This application does not limit the method for controlling the image acquisition device to capture images and transmitting each frame of the obtained image data to the processing device in real time via wired or wireless communication.

[0072] Step S12, performing object feature recognition on the image data to obtain object feature information of the corresponding object area in the image data;

[0073] Step S13, determining the transport status of the cargo transport component based on the object feature information in the continuous frame image data;

[0074] Following the above analysis, the processing equipment can use artificial intelligence technologies such as machine vision, image recognition, and image segmentation to perform object feature recognition on continuous frame image data collected in real time, and determine whether each frame of image data contains object features such as component features of cargo transport components and cargo features of the transported cargo, thereby determining whether the cargo transport components are in an empty state or a loaded state. This application does not limit the implementation method of object feature recognition of image data.

[0075] Thus, the object feature information obtained in step S12 may include, but is not limited to, one or more object features, including features of cargo transport components, features of the transported cargo, and inherent structural features of the transport vehicle. It should be understood that, based on transportation safety requirements, various obstacle features present in the transport environment may also be identified, and the content of the object feature information may be determined based on actual circumstances. Furthermore, during the transport process, the image data collected at different times by the transport vehicle may vary, and the object feature information that can be identified from different frames of image data may vary. This is not a limitation of the present application.

[0076] Based on this, in some other embodiments proposed in the present application, the present application can perform regional segmentation on each frame of collected image data to obtain regional images of the area where the cargo transport components and / or the transported cargo are located. Subsequently, the image recognition range can be reduced, and there is no need to perform precise recognition processing on the image data outside the area. It is only necessary to perform object feature recognition on the regional image to obtain object feature information of the required object, such as the component features of the required cargo transport components and / or the features of the transported cargo, etc., and the transportation status of the cargo transport components is determined based on this, thereby improving the recognition accuracy.

[0077] Optionally, in order to further improve the efficiency and reliability of image recognition, the display ratio and / or position of the identified object (such as cargo transport components and / or transported cargo) in the entire regional image can be determined. Based on this, if the identified object is located at a preset position such as the middle position of the image data of the corresponding frame, and the display ratio reaches a preset ratio (a larger value), it means that the frame image data contains complete and clear image data of the identified object, and subsequent feature recognition is performed on the regional image. Otherwise, the regional image can be eliminated and other regional images or other frame image data can be processed.

[0078] It should be noted that the present application does not impose any restrictions on this image segmentation implementation method. Regional segmentation can be performed on each frame of image data based on, but not limited to, the structure of the transport vehicle. The structure can be a component located at a fixed position of the transport vehicle in the historical frame image data, such as the gantry of the transport vehicle, etc., which is a graphic that remains in a fixed area in the image acquisition frame for a long time. This type of image data is used as interference image data with obstacles, and image segmentation is achieved accordingly, thereby reducing the misjudgment rate of the transport status of cargo transport components.

[0079] Optionally, the present application may use the above-mentioned interference image data as negative sample data, and the image data containing cargo transport components and / or transported cargo as positive sample data, perform model training based on machine learning / deep learning algorithms, and obtain a feature extraction model for identifying component features of cargo transport components and / or features of transported cargo. In this way, after obtaining each frame of image data, it can be input into the feature extraction model to output the corresponding object feature information.

[0080] In order to improve the model output accuracy and processing efficiency, combined with the image data processing method in the corresponding part of the context, during the above-mentioned feature extraction model training process, the image segmentation method described in the corresponding part of the context can be combined to process each sample image data, and then the segmented sample image data is input into the initial machine learning / deep learning algorithm for model training to obtain a feature extraction model.

[0081] Step S14: Obtain corresponding cargo statistics results based on the change in the transportation status and / or object feature information.

[0082] To meet different cargo statistics requirements, such as the number of transports, the quantity of goods transported, and the type of goods transported, the corresponding cargo statistics can be obtained by combining, but not limited to, the changes in the transport status of the cargo transport components obtained above, and the object feature information or changes contained in each frame of image data to analyze the corresponding cargo statistics. Furthermore, as the acquired image data changes over time, the corresponding cargo statistics can be dynamically updated in accordance with the above.

[0083] Optionally, if a display device is provided in the cab of the transport vehicle, the cargo data included in the cargo statistics results can be synchronously sent to the display device for display, allowing the driver to verify the correctness of the displayed cargo data through the human-machine interface output by the display device. This allows errors to be discovered and corrected in a timely manner, ensuring the accuracy and reliability of the final cargo statistics results. This application does not limit the method for implementing the update of cargo statistics results.

[0084] In some other embodiments, the final cargo statistics results can also be reported to a management system, such as a warehouse management system or an enterprise management ERP system. In this way, the corresponding management system can be accessed later to query cargo data such as the number of times and / or quantity of transports of type D cargo by driver A using transport vehicle C at time B, so as to obtain the performance of each driver, the working conditions of each transport vehicle, etc., which is convenient for enterprise management, vehicle maintenance, etc. This application does not impose any restrictions on the structural composition and working content of the management system, which can be determined based on actual conditions.

[0085] In summary, in the embodiments of the present application, by configuring an image acquisition device on a transport vehicle, image acquisition is performed on the cargo transport components of the transport vehicle, and after obtaining continuous frame image data, object feature recognition can be automatically performed on the image data. Based on the object feature information of the corresponding object area obtained, the transport status of the cargo transport components, such as a loaded state or an empty state, is automatically determined. Thus, based on the changes in the transport status and / or the identified object feature information, various cargo statistical results are automatically and accurately obtained without the need for manual reading of records, thereby avoiding technical problems such as inaccurate cargo statistical results due to misreading, misrecording / calculation, etc., improving the statistical efficiency and reliability of the cargo statistical results, and saving labor costs.

[0086] 2 is a flow chart of another optional example of the cargo statistics method proposed in this application. This embodiment may describe an optional refined implementation method of the cargo statistics method proposed above. As shown in FIG2 , the method may include:

[0087] Step S21, acquiring continuous frame image data of cargo transport components of a transport vehicle;

[0088] Step S22, performing region segmentation on the image data to obtain regional images of different object regions in the image data, wherein the object regions include regions where cargo transport components are located and / or regions where transported cargo are located;

[0089] Step S23, performing object feature recognition on the region image to obtain object feature information of the corresponding object region;

[0090] In an embodiment of the present application, in order to improve the efficiency and accuracy of image recognition, for each frame of image data obtained, the area where object features need to be extracted can be first identified, such as the area where cargo transport components and the cargo they transport are located, etc. In this way, only the image data within the area can be accurately recognized subsequently, and the image data outside the area does not need to be accurately recognized, which greatly reduces the workload of accurate image recognition, improves the efficiency of object feature recognition, reduces the interference of object features outside the area, and can also improve recognition accuracy.

[0091] As analyzed above, the region segmentation process of the above image data can be implemented based on the structure of the transport vehicle. The structure can be a component located at a fixed position of the transport vehicle. This application does not elaborate on the image region segmentation implementation process.

[0092] In some other embodiments proposed in this application, combined with the above analysis, this application can also adjust the configuration parameters of the image acquisition device, such as the acquisition direction, viewing angle, and focal length, and adjust the image data contained in the image acquisition frame, so that the object to be acquired is as complete as possible and occupies the image acquisition frame, reducing the image data of interfering objects within the image acquisition frame. In this way, after the processing device obtains continuous frames of image data, it can directly perform object feature recognition on each frame of image data to quickly and accurately obtain the required object feature information. Optionally, the driver can dynamically adjust the configuration parameters of the image acquisition device based on the preview image data displayed by the display device. This implementation process is not described in detail in this application.

[0093] Step S24: detecting that the object feature information only includes the component features of the cargo transport component, and determining that the cargo transport component is in an empty state;

[0094] Step S25, detecting that the object characteristic information includes characteristics of the transported cargo, and determining that the cargo transport component is in a cargo-carrying state;

[0095] In an embodiment of the present application, after using artificial intelligence technology to obtain the object feature information contained in each frame of image data, it is possible to detect whether the object feature information includes component features of the cargo transport component, such as the fork pallet features of a forklift. Since the image acquisition direction of the image acquisition device is configured toward the cargo transport component, under normal circumstances, the image data acquired by the image acquisition device should include component features of the cargo transport component. Therefore, if it is detected that the object feature information of a certain frame of image data only includes component features of the cargo transport component, it means that the cargo transport component is in an empty state at the corresponding moment; if it is detected that the object feature information of a certain frame of image data only includes cargo features of the transported cargo, or includes the cargo features and component features, it means that the cargo transport component is in a loaded state at the corresponding moment.

[0096] By analyzing the object feature information of continuous frame image data according to the above method, the transportation state of the cargo transport component contained in each frame of image data can be determined. Optionally, in order to improve the detection accuracy of the loading state, a delay mechanism can be added on the basis of the above detection, such as determining that the cargo must appear for more than 3 seconds before it is considered to have entered the loading state. Based on this, the processing device can determine that the cargo transport component is in the loading state when it detects that the object feature information identified in any frame of image data contains the features of the transported cargo, and the object feature information identified in the image data of multiple consecutive frames (this application does not limit the number of frames, it can be determined as appropriate) after the frame of image data contains the features of the transported cargo.

[0097] In some embodiments proposed in the present application, according to but not limited to the above method, after determining the transportation status of the transported component by visual recognition, a corresponding loading status label or non-loading status label can be configured, and these status labels can be subsequently analyzed to determine the number of cargo transportations of the corresponding transported component.

[0098] In some other embodiments proposed in this application, in combination with the image segmentation method described above, after obtaining object feature information of an object such as the transported goods in each frame of image data, it is possible to determine whether the transported goods are within a preset position range of a preset structure of the transport vehicle based on the object feature information. If the transported goods are within the preset position range, it is determined that the cargo transport component is in a loaded state. The preset position range may refer to the normal position range of the transported goods during the transport process of the transport vehicle, which can be determined based on actual transportation conditions, and this application does not impose any restrictions on its value.

[0099] Optionally, the above-mentioned preset position range can be displayed in each frame of image data according to its numerical value, such as displaying a boundary box of the preset position range in each frame of image data output by the display device. Subsequently, object feature recognition can be performed only on the area image within the boundary box to obtain corresponding object feature information, thereby determining whether the cargo transport component is in a loaded state. The implementation process can be combined with the description of the corresponding part of the above embodiment.

[0100] Optionally, the preset position range can be determined in conjunction with the transport vehicle's safety requirements to ensure cargo safety. Based on this, if the transported cargo in a frame of image data exceeds the bounding box, it can be considered that the cargo currently being transported presents a safety hazard, and a corresponding prompt message can be output to remind the driver or on-site personnel to adjust the transport vehicle's transport status for the cargo, such as reducing the quantity of cargo being transported, lowering the transport height and weight, etc. This can be determined based on the actual safety hazards detected.

[0101] In addition, after determining that the cargo transport component is in a loaded state and obtaining the object characteristic information of the transported cargo according to the method described above, the drivable parameters of the transport vehicle in the current cargo transport direction can be adjusted based on the object characteristic information, such as one or more combinations of drivable speed, drivable distance and drivable time, to control the drivability of the transport vehicle in the current cargo transport direction and ensure the safety of cargo operation.

[0102] Specifically, the transport height of the transported goods on the cargo transport component can be determined based on the object feature information, such as the height of the transported goods relative to the driving ground or relative to the position of the driver's eyes, and then the current transport safety level of the transport height can be determined according to the preset transport safety level division method; the transport safety level division method can be determined based on the line of sight height of the driver of the transport vehicle, and can be a classification of the cargo transport height range, etc. In actual application, the lower the transport safety level, the higher the risk of a safety accident if the transport vehicle transports goods according to the current state. This application does not limit the implementation method of the transport safety level division.

[0103] In this way, the transport vehicle's drivability parameters in the current cargo transport direction can be precisely adjusted based on the current transport safety level to improve cargo transport safety. As described above regarding the transport safety level, the lower the transport safety level, the smaller the adjusted drivability parameters of the transport vehicle in the current cargo transport direction (e.g., in front of the forklift), which in turn imposes a greater degree of restriction on the transport vehicle's ability to travel in the current cargo transport direction. This prevents the transported cargo from being transported too high, obstructing the driver's field of view, or causing incomplete object features of the transported cargo in the collected image data, thereby creating driving safety hazards.

[0104] Optionally, as analyzed above, if the current transport safety level of the transported cargo is less than the preset transport safety level, such as if the transport height of the transported cargo reaches a preset height range (which may correspond to the preset transport safety level), the drivable parameters of the transport vehicle in the current cargo transport direction are adjusted; otherwise, no adjustment is made, and the number of drivable parameter adjustments is reduced while ensuring the driving safety of the transport vehicle. Step S26: Determine the cargo type corresponding to the transported cargo based on the characteristics of the transported cargo;

[0105] According to the above analysis, it is determined that the cargo transport component is in a loaded state. The cargo type of the transported cargo can be determined based on the characteristics of the transported cargo detected on each cargo transport component. This application does not limit the implementation method of the cargo type, and it can be determined based on the content of the characteristics of the transported cargo.

[0106] In some other embodiments proposed in the present application, object feature recognition can also be performed directly on the image data according to the method described in the context, and the obtained object feature information can be analyzed. After identifying the characteristics of the transported goods, the characteristics of the transported goods can be further analyzed to determine the type of the transported goods. After that, at least the cargo data such as the cargo type and / or the characteristics of the transported goods can be labeled to generate a corresponding cargo label, and the corresponding labeling device can be controlled to paste or draw the cargo label on the surface of the transported goods, so that the cargo label can be directly identified according to the method described below, the required cargo data can be obtained, and the number of times different types of goods are handled can be counted.

[0107] Step S27, obtaining the transport times of different types of transported goods according to the change of the cargo transport component between the empty state and the loaded state, and the types of the transported goods.

[0108] In practical applications, the changes between empty and loaded states of a cargo transport component can be monitored to dynamically update the number of cargo transports by the transport vehicle, i.e., to accumulate the number of cargo transports for that cargo transport component. Alternatively, the number of transports of different types of cargo can be calculated based on the types of cargo transported by different cargo transport components, as described above.

[0109] It should be understood that if a transport vehicle has multiple cargo transport components, the method described above can be used to separately count the number of cargo transports by each cargo transport component and sum them to obtain the total number of cargo transports for each cargo transport component. One transport represents one transport of cargo by a cargo transport component. Of course, it is also possible to combine the types of cargo transported by each cargo transport component to count the number of transports of different types of cargo, but this implementation process is not described in detail in this application.

[0110] It can be seen that, according to the above detection method, the present application determines the transport status of the cargo transport component in each frame of image data in the continuous frame image data. It can dynamically update the cargo transport times of the cargo transport component by monitoring the changes between the empty state and the loaded state. After that, it can determine the cargo transport times of the transport vehicle in combination with the number of cargo transport components possessed by the transport vehicle. It can also further count the transport times of different types of cargo based on the type of cargo transported each time. In this way, the present application can detect and analyze in real time through the above method, and count the cargo statistics results of the required different cargo data. The entire process does not require the driver or transport site staff to observe and record cargo data such as the cargo transport times and the types of cargo transported, thereby ensuring the reliability and accuracy of the obtained cargo transport times.

[0111] 3 is a flow chart of another optional example of the cargo statistics method proposed in this application. This embodiment may be used to describe another optional and refined implementation method of the cargo statistics method proposed above. As shown in FIG3 , the method may include:

[0112] Step S31, acquiring any frame of image data of a cargo transport component of a transport vehicle;

[0113] Step S32, performing object feature recognition on the image data to obtain corresponding object feature information;

[0114] Step S33: determining that the object feature information includes a cargo label, adjusting the configuration parameters of the image acquisition device to obtain a label image of the area where the cargo label is located;

[0115] Step S34: performing label recognition on the label image and reading the characteristics of the transported goods recorded on the recognized cargo label;

[0116] In an embodiment of the present application, the cargo label can be a visual label such as a cargo barcode, a QR code, or a pattern displayed on the surface of the transported cargo by pasting or printing. It can be obtained by labeling preset cargo characteristics. Therefore, the cargo label can be identified and the cargo characteristic content recorded therein can be read. The present application does not limit the configuration implementation method of the cargo label.

[0117] In order to accurately identify cargo labels, according to the above-mentioned image recognition method, it is determined that the current frame image data collected contains cargo labels, that is, the obtained object feature information contains cargo label features, and the corresponding configuration parameters of the image acquisition device can be adjusted, such as focusing on the cargo label to obtain a clearer cargo label image, or updating clear image data, etc. This application does not limit the method for adjusting the configuration parameters of the image acquisition device.

[0118] According to the image acquisition adjustment implementation method described in this embodiment, the next frame of image data obtained can be a clear label image, which greatly reduces the image content unrelated to the cargo label. In this way, label recognition is directly performed on the label image, which can quickly and accurately identify the cargo label therein and read the cargo characteristics recorded on the cargo label. This application does not impose any restrictions on the content of the cargo characteristics, which can be determined according to the circumstances.

[0119] Step S35, determining the transport status of the cargo transport component based on the object feature information in the continuous frame image data;

[0120] Step S36, obtaining the transport times of different types of transported goods based on the types of goods included in the characteristics of the transported goods and the changes in the transport status of the goods transport components.

[0121] Regarding the implementation process of the transport status of the cargo transport component and its changes, reference may be made to the description of the corresponding part of the context embodiment, which will not be elaborated in this embodiment.

[0122] In some other embodiments proposed in the present application, different types of goods such as mineral water, cola or beer are usually transported in boxes. At least one box of goods can be transported each time, and the number of goods contained in each box of goods (the number of bottles or cans, etc.) is known and determined. Therefore, the present application can use three-dimensional vision technology to determine the size and other cargo characteristics of such transported goods. After that, the detected cargo size (such as the size of multiple boxes of goods being transported) can be transported with the unit cargo size (such as the size of a box of goods) to determine the number of transported goods (such as the number of boxes, or further combined with the number of pieces of goods contained in a box, the total number of pieces of goods transported this time, etc., which can be determined based on the statistical unit of the cargo quantity).

[0123] Based on this, the present application analyzes the image data collected in real time to determine the size and type of the transported goods transported by each cargo transport component. Then, based on the size of the transported goods and the unit cargo size of the corresponding type of goods, the quantity of the corresponding type of transported goods transported by the corresponding cargo transport component can be obtained, such as the quantity of goods = size of transported goods / unit cargo size. If there are multiple different types of goods on a cargo transport component, the size of each type of goods can be identified. According to this calculation method, the size of the goods is calculated with the unit cargo size of the corresponding type of goods to obtain the quantity of goods of this type transported on the cargo transport component.

[0124] Afterwards, according to the method described above, after determining the number of transportation times of different types of transported goods, the total number of goods of different types transported can be obtained by combining the number of goods of the corresponding type transported by each cargo transport component each time. The calculation process will not be described in detail in this application.

[0125] Optionally, in the implementation process of the cargo statistics method described in the above embodiments, for the above-mentioned identified cargo characteristics such as cargo type, cargo size, and the counted cargo quantity / transportation times of different cargo transport components, the cargo type transported each time, the cargo quantity of different cargo types, the total cargo quantity, and other cargo statistics results, the cargo statistics results obtained each time can be sent to a display device, and the display device synchronously displays the cargo statistics results, so that the driver can check the various cargo data contained in the cargo statistics results (such as the above-mentioned cargo characteristics, cargo quantity, transportation times, etc.), and modify the abnormal cargo data in time after discovering an error. In this way, the processing device detects the input operation for the displayed abnormal cargo data and can update the cargo statistics results in time to ensure that the final cargo statistics results are accurate. Afterwards, the cargo statistics results can also be reported to the management system so that the cargo statistics results of different transport vehicles can be queried by accessing the management system. The implementation process can refer to the description of the corresponding part of the above embodiment, and this embodiment will not be described in detail here.

[0126] Optionally, the cargo statistics results for the above-mentioned different cargo data can be dynamically updated to ensure that the reported cargo statistics results are accurate and reliable. If the driver determines that the automatically detected cargo statistics results are incorrect according to the above-mentioned method, they can be updated. In this way, the processing equipment detects the input operation for any cargo data included in the displayed cargo statistics results and updates the cargo statistics results; thereafter, the updated cargo statistics results can be reported to the management system. The implementation process is not described in detail in this application.

[0127] 4 is a schematic diagram showing a structure of an optional example of a cargo statistics device proposed in this application. The device may include:

[0128] The image data acquisition module 410 is used to acquire continuous frame image data of the cargo transport component of the transport vehicle; the image data is acquired by an image acquisition device installed on the transport vehicle;

[0129] A feature recognition module 420 is configured to perform object feature recognition on the image data to obtain object feature information of a corresponding object region in the image data;

[0130] The transport state determination module 430 is configured to determine the transport state of the cargo transport component based on the object feature information in the continuous frame image data; the transport state includes a loaded state or an empty state;

[0131] The cargo statistics result obtaining module 440 is configured to obtain corresponding cargo statistics results according to the change in the transportation status and / or the object characteristic information.

[0132] Optionally, the transportation status determination module 430 may include:

[0133] an empty state determining unit, configured to detect that the object feature information only includes the component features of the cargo transport component, and determine that the cargo transport component is in the empty state;

[0134] a cargo state determining unit, configured to detect that the object characteristic information includes the characteristics of the transported cargo, and determine that the cargo transport component is in the cargo state;

[0135] Based on this, the cargo statistics result obtaining module 440 may include:

[0136] A cargo transport times updating unit is used to monitor the change of the cargo transport component between the empty state and the loaded state, and update the cargo transport times of the transport vehicle.

[0137] Optionally, the cargo state determination unit may include:

[0138] The first determination unit is configured to detect that the object feature information identified in any frame of image data includes the features of the transported cargo, and that the object feature information identified in multiple consecutive frames of image data following the frame of image data all include the features of the transported cargo, and determine that the cargo transport component is in the loaded state.

[0139] In some further embodiments, the feature recognition module 420 may include:

[0140] a region image obtaining unit, configured to perform region segmentation on the image data to obtain region images of different object regions in the image data; wherein the region segmentation is performed based on the structure of the transport vehicle, wherein the structure refers to a component located at a fixed position on the transport vehicle in the historical frame image data; and the object region includes the region where the cargo transport component is located and / or the region where the transported cargo is located;

[0141] An object recognition unit, configured to perform object recognition on the region image to obtain object feature information corresponding to the object region;

[0142] Based on this, the transportation status determination module 430 may include:

[0143] a cargo position determination unit, configured to determine whether the transported cargo is within a preset position range of a preset structure of the transport vehicle based on the object characteristic information;

[0144] The cargo state determining unit is configured to determine that the cargo transport component is in a cargo state when the transported cargo is within the preset position range.

[0145] Based on the description of the above embodiments, the cargo statistics result obtaining module 440 may include:

[0146] a cargo type determination unit, configured to determine whether the cargo transport component is in a loaded state and determine a cargo type corresponding to the transported cargo based on the characteristics of the transported cargo included in the object characteristic information;

[0147] The transport frequency obtaining unit is used to obtain the transport frequency of different types of transported goods according to the change of the transport status and the types of the transported goods.

[0148] Optionally, when the characteristics of the transported goods include the size of the transported goods, the above-mentioned cargo statistics result obtaining module 440 may further include:

[0149] A cargo quantity obtaining unit, configured to obtain the cargo quantity of the corresponding type of cargo being transported by the cargo transport component according to the size of the cargo being transported and the unit cargo size of the corresponding type of cargo;

[0150] The total cargo quantity obtaining unit is used to obtain the total cargo quantity of different types of transported cargo according to the cargo quantity and the number of transportation times of different types of transported cargo.

[0151] Optionally, the transportation status determination module 430 may further include:

[0152] a label image obtaining unit, configured to determine that the object feature information includes a cargo label, adjust configuration parameters of the image acquisition device, and obtain a label image of the area where the cargo label is located;

[0153] The transported goods feature reading unit is used to perform label recognition on the label image and read the transported goods feature recorded by the recognized cargo label.

[0154] In some further embodiments, based on the cargo statistics device described above, the device may further include:

[0155] A cargo statistics result sending module, configured to send each obtained cargo statistics result to a display device, which synchronously displays the cargo statistics result; the display device is located in the driving cabin of the transport vehicle;

[0156] a cargo statistics result updating module, configured to detect an input operation on any cargo data included in the displayed cargo statistics result, and update the cargo statistics result; and / or;

[0157] The cargo statistics result reporting module is used to report the updated cargo statistics result to the management system.

[0158] It should be noted that the various modules, units, etc. in the above-mentioned device embodiments can be stored in the memory as program modules, and the processor executes the above-mentioned program modules stored in the memory to implement the corresponding functions. Regarding the functions implemented by each program module and its combination, as well as the technical effects achieved, please refer to the description of the corresponding parts of the above-mentioned method embodiments, which will not be repeated in this embodiment.

[0159] Referring to Figure 5, there is shown a schematic diagram of an optional example of a cargo statistics system proposed in this application. This system can be fixedly deployed on each transport vehicle, or deployed in at least one movable terminal device. This terminal device can be placed or fixed on the transport vehicle so that after the transport vehicle enters cargo transportation, the cargo statistics results can be obtained according to the cargo statistics method described above. As shown in Figure 5, the cargo statistics system proposed in this embodiment may include: a communication device 510, an image acquisition device 520, a storage device 530, and a processing device 540, wherein:

[0160] The communication device 510 can be used to realize the communication connection between different devices in the cargo statistics system to support data interaction between different devices. Therefore, the communication device 510 may include but is not limited to different types of first communication interfaces such as USB interface, serial / parallel port, multimedia data interface, etc. to meet the transmission requirements of different types of data. This application does not impose any restrictions on the interface type of the first communication interface, which can be determined as appropriate.

[0161] Optionally, the communication device 510 may also include a second communication interface for connecting to the management system to report the updated cargo statistics results to the management system. The second communication interface may be a communication interface that supports wireless communication or wired communication, such as a WIFI module, a 5G / 6G (fifth-generation mobile communication network / sixth-generation mobile communication network) module, an NFC (Near Field Communication, short-range wireless communication technology) module, and / or a GPRS module and other communication modules. The type of the second communication interface can be determined based on the communication conditions of the operating environment, and this application does not impose any restrictions on this.

[0162] The image acquisition device 520 can be installed on the transport vehicle. The installation location of each image acquisition device 520 on the transport vehicle can be determined based on the image acquisition requirements, and this application does not impose any restrictions on this. For example, as shown in Figure 6, the image acquisition device 520 can include a front camera with the image acquisition direction facing the cargo transport component, which can capture continuous frame image data of the cargo transport component of the transport vehicle, and transmit each frame of the captured image data to the processing device 540 via the communication device 510 for processing. If necessary, the most recent frames of images can also be cached. In this way, each frame of the captured image data can also be sent to the storage device 530 for caching. The implementation process is not described in detail in this application.

[0163] Optionally, in order to authenticate the driver, prevent illegal users from driving the transport vehicle, and / or monitor the driver's working status when driving the transport vehicle to prevent the driver from driving while fatigued, as shown in FIG6 , the image acquisition device 520 may also include a driver camera with the image acquisition direction facing the driver's seat, to collect image data of users entering the driving compartment of the transport vehicle, perform facial recognition on the user image data, and determine whether the user has the driving authority of the transport vehicle, that is, authenticate the user. After determining that the user has the driving authority of the transport vehicle, the user's start-up operation of the transport vehicle can be responded to; otherwise, the start-up of the transport vehicle can be prohibited.

[0164] In some other embodiments, in order to ensure the driving safety of the transport vehicle, as shown in Figure 6, the image acquisition device 520 may also include a rear camera with an image acquisition direction facing the rear of the transport vehicle (i.e., the back of the driver's seat, that is, the opposite direction of the cargo transport component), which is used to collect image data from the rear of the transport vehicle, and through artificial intelligence technologies such as image recognition and visual recognition, it is detected in real time whether there are obstacles in the image data, so as to output obstacle prompt information in time to remind the driver to adjust the driving route, or automatically generate corresponding control instructions to control the transport vehicle to adjust the driving route. This application does not elaborate on the obstacle detection implementation method.

[0165] It can be seen that the above-mentioned image acquisition device 520 can include multiple cameras, and these multiple cameras can be installed at different positions of the transport vehicle, so that the processing device 540 can perform object recognition on the image data collected by each camera, such as the above-mentioned cargo recognition, face recognition and / or obstacle recognition, etc., and meet different application requirements based on the corresponding object recognition results obtained, including but not limited to the statistical requirements such as the number / quantity of transportation described above, obstacle recognition and detour requirements, identity verification requirements, etc.

[0166] The storage device 530 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device. This application does not elaborate on the device type of the storage device 530. It can store the program that implements the cargo statistics method proposed in this application. As needed, it can also store various image data collected by the image acquisition device 520, cargo statistics results obtained by the processing device 540, and / or various intermediate data generated during the execution of the cargo statistics method. This application does not limit the storage content of the storage device 530, which can be determined according to the actual situation.

[0167] The processing device 540 can be used to load and execute the program stored in the storage device 530 to implement the cargo statistics method proposed in this application. The implementation process can refer to the description of the corresponding part of the method embodiment above, and this application will not describe it in detail here.

[0168] In an embodiment of the present application, the processing device 540 may be a vehicle-mounted terminal, a vehicle-mounted processor, etc., wherein the vehicle-mounted terminal may be a terminal integrated in a transport vehicle, or a mobile terminal fixed in the vehicle by a fixed component, such as a smart phone, a tablet computer, a wearable device, a personal computer (PC), a netbook, etc. The present application does not impose any restrictions on the product type of the processing device 540 and its composition structure.

[0169] It can be understood that when the processing device 540 is a mobile terminal, the above-mentioned storage device 530 can be integrated into the processing device 540, and the program stored in the storage device 530 can be loaded and executed by a processor in the processing device 540, such as a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, to implement the various steps of the cargo statistics method described in the corresponding method embodiment.

[0170] In some other embodiments proposed in the present application, the cargo statistics system may also include detection equipment, such as identity sensors, distance sensors, speed detectors, position sensors, etc. Different types of detection equipment can be installed at different positions of the transport vehicle. In order to ensure detection reliability, multiple detection equipment of the same type can also be installed at different positions of the transport vehicle. As shown in Figure 7, different types of detection equipment or multiple detection equipment of the same type can also be installed above or below the overhead guardrail of the transport vehicle, on the rear pillar of the rear overhead guardrail and / or on the bottom of the driver's seat, etc. The present application does not impose any restrictions on the type of equipment included in the detection equipment, the number of equipment included in the detection equipment, the installation position on the transport vehicle, etc., which can be determined based on actual conditions.

[0171] Among them, the above-mentioned detection devices can be connected to the processing device 540, and the corresponding sensing parameters obtained can be sent to the processing device 540 for analysis to achieve application requirements such as position tracking detection of transport vehicles and obstacle distance detection. This application does not limit the analysis implementation method.

[0172] In some other embodiments proposed in the present application, as shown in Figure 6, the cargo statistics system may further include: a display device installed in the driving cabin of the transport vehicle and capable of being connected to the processing device, such as an independent display, or a display integrated in the above-mentioned processing device 540 (in the case of a mobile terminal), etc. The present application does not elaborate on the product type of the display device and its working principle. In this way, the intermediate data and / or cargo statistics results obtained during the execution of the cargo statistics method by the processing device 540 can be sent to the display device for synchronous display.

[0173] In this way, the driver can judge the cargo data displayed on the display device and, if any erroneous cargo data is found, promptly correct it. The processing device 540 can also be used to detect input operations on any cargo data included in the cargo statistics displayed on the display device and update the cargo statistics. The methods for adjusting other displayed data are similar and will not be described in detail in this application.

[0174] It should be understood that the structure of the cargo counting system shown in the above figures does not constitute a limitation on the system structure in the embodiments of the present application. In actual applications, the system may include more equipment than shown in the figures. The transport vehicles deploying the cargo counting system include but are not limited to the forklifts shown in the figures. The details may vary depending on the circumstances and are not listed one by one in this application.

[0175] The present application also provides a computer-readable storage medium on which a computer program can be stored. The computer program can be called and loaded by a processor to implement the various steps of the cargo statistics method described in the above embodiment. The implementation process can refer to the description of the corresponding part of the above embodiment, and this embodiment will not be described in detail here.

[0176] Finally, it should be noted that the various embodiments in this specification are described in a progressive or parallel manner. Each embodiment focuses on the differences from other embodiments, and reference can be made to the same or similar parts between the various embodiments. For the devices and systems disclosed in the embodiments, relevant parts can be referred to the method description.

[0177] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A cargo statistics method, characterized in that: The method comprises: Acquire continuous frame image data of a cargo transport component of a transport vehicle; the image data is acquired by an image acquisition device installed on the transport vehicle; Performing object feature recognition on the image data to obtain object feature information of a corresponding object area in the image data; Determining the transport state of the cargo transport component according to the object feature information in the continuous frame image data; the transport state includes a loaded state or an empty state; According to the change of the transportation status and / or the object characteristic information, the corresponding cargo statistical result is obtained.

2. The method according to claim 1, characterized in that: The determining the transport status of the cargo transport component based on the object feature information in the continuous frame image data includes: detecting that the object feature information only includes the component features of the cargo transport component, and determining that the cargo transport component is in the empty state; It is detected that the object feature information includes the feature of the transported goods, and it is determined that the cargo transport component is in the cargo-carrying state; wherein the object feature information includes the feature of the transported goods includes: the object feature information identified from any frame of image data includes the feature of the transported goods, and the object feature information identified from multiple consecutive frames of image data after the frame of image data all include the feature of the transported goods; The obtaining of corresponding cargo statistics results according to the change of the transportation status includes: The change of the cargo transport component between the empty state and the loaded state is monitored, and the cargo transport times of the transport vehicle are updated.

3. The method according to claim 1, characterized in that The performing object feature recognition on the image data to obtain object feature information of a corresponding object area in the image data, and determining the transport status of the cargo transport component according to the object feature information in the continuous frame image data, comprises: Performing regional segmentation on the image data to obtain regional images of different object regions in the image data; wherein the regional segmentation is implemented based on the structure of the transport vehicle, and the structure refers to a component located at a fixed position of the transport vehicle in the historical frame image data; the object region includes the region where the cargo transport component is located and / or the region where the transported cargo is located; Performing object recognition on the region image to obtain object feature information corresponding to the object region; Determining whether the transported cargo is within a preset position range of a preset structure of the transport vehicle based on the object feature information; If the transported cargo is within the preset position range, it is determined that the cargo transport component is in a cargo-carrying state.

4. The method according to any one of claims 1 to 3, characterized in that: When it is determined that the cargo transport component is in the cargo-carrying state, the method further includes: According to the object characteristic information, adjusting the drivable parameters of the transport vehicle in the current cargo transport direction to control the drivability of the transport vehicle in the current cargo transport direction; The drivable parameters include one or more combinations of drivable speed, drivable distance and drivable time.

5. The method according to claim 4, characterized in that The adjusting the drivable parameters of the transport vehicle in the current cargo transport direction according to the object feature information includes: Determining the transport height of the transported goods on the cargo transport component according to the object characteristic information; According to a preset transportation safety level classification method, the current transportation safety level of the transportation height is determined; the transportation safety level classification method can be determined according to the sight height of the driver of the transportation vehicle; According to the current transportation safety level, adjusting the drivable parameters of the transportation vehicle in the current cargo transportation direction; The lower the transport safety level is, the smaller the adjusted drivable parameter of the transport vehicle in the current cargo transport direction is.

6. The method according to any one of claims 1 to 3, characterized in that: The obtaining corresponding cargo statistics results according to the change of the transport status and the object characteristic information includes: Determining that the cargo transport component is in a cargo-carrying state, and determining the cargo type corresponding to the cargo to be transported according to the characteristics of the cargo to be transported included in the object characteristic information; According to the change of the transportation status and the cargo type of the transported cargo, the transportation times of different types of transported cargo are obtained.

7. The method according to claim 6, characterized in that The characteristics of the transported goods include: the size of the transported goods, and the obtaining of corresponding goods statistics results according to the change of the transport state and the object characteristic information also includes: According to the size of the transported goods and the unit cargo size of the corresponding type of goods, the quantity of the corresponding type of goods transported by the cargo transport component is obtained; According to the quantity of goods and the number of transportation times of different types of transported goods, the total quantity of goods of different types transported is obtained.

8. The method according to claim 6, characterized in that The method for acquiring the characteristics of the transported goods contained in the object characteristic information includes: Determining that the object feature information includes a cargo label, adjusting the configuration parameters of the image acquisition device to obtain a label image of the area where the cargo label is located; The label image is subjected to label recognition, and the characteristics of the transported goods recorded in the recognized goods label are read.

9. The method according to claim 6, characterized in that The cargo statistics result can be dynamically updated, and the method further comprises: The cargo statistics results obtained each time are sent to a display device, and the cargo statistics results are synchronously displayed by the display device; the display device is located in the driving cabin of the transport vehicle; detecting an input operation for any cargo data included in the displayed cargo statistics result, and updating the cargo statistics result; and / or; The updated cargo statistics results are reported to the management system.

10. A cargo statistics system, characterized in that: The system comprises: Communication equipment, used to realize the communication connection between different devices in the cargo statistics system; An image acquisition device installed on a transport vehicle, used to acquire continuous frame image data of a cargo transport component of the transport vehicle; A storage device for storing a program for implementing the cargo statistics method according to any one of claims 1 to 9; A processing device, used for loading and executing the program stored in the storage device to implement the cargo statistics method according to any one of claims 1 to 9.

Citation Information

Patent Citations

  • Data processing method, device and system

    CN107203804A

  • A system and method for detecting an operating state of a cargo convey device

    CN109544631A

  • Vehicle loading rate determination method and device and vehicle management system

    CN114067295A

  • Intelligent logistics monitoring system

    CN114140043A

  • Transport vehicle operation analysis system, transport vehicle operation analysis device, transport vehicle operation analysis method, and program

    WO2022030347A1

Cited By

  • Intelligent slag transportation monitoring method and system applied to hydropower station construction project

    CN122391987A