Earthwork volume identification method, device and electronic equipment

Abstract

The embodiment of the present application provides a method, device and electronic device for earthwork quantity identification, the method comprising: obtaining video data to be identified, wherein the duration of the video data to be identified is within a target duration interval, inputting the video data to be identified into a pre-trained earthwork quantity identification model, and obtaining a target identification result, wherein the target identification result includes vehicle information and earthwork quantity information corresponding to the vehicle information. The present application improves the convenience and accuracy of earthwork quantity information statistics by identifying the video data to be identified with a target duration based on the earthwork quantity identification model and then determining the earthwork quantity information, thereby ensuring the normal operation of related projects.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing technology, and in particular to a method, device and electronic equipment for identifying earthwork volume. Background Art

[0002] At the construction site, construction vehicles will enter and exit the construction site to carry out construction due to different project requirements. For example, construction vehicles can be used to level the site, dig foundation pits, fill the ground, fill the roadbed, and backfill the foundation pits.

[0003] In the prior art, when construction vehicles enter and exit the construction site, in order to facilitate the statistics and settlement of subsequent projects, it is necessary to first confirm the vehicle information of the construction vehicle and the earthwork volume information carried by the construction vehicle, and then allow the construction vehicle to enter the construction site after the confirmation is completed. When confirming the vehicle information and the earthwork volume information carried by the construction vehicle, usually when the construction vehicle enters the construction site, the relevant personnel will allocate a settlement list to each construction vehicle, and then later on, according to the allocated settlement list, the earthwork volume information completed by each construction vehicle in the project will be counted and settled.

[0004] However, due to the frequent entry and exit of vehicles at the construction site and the fact that the earthwork volume information contained in each settlement list is also filled in manually, it is easy for the actual information to be inconsistent with the subsequent statistical information, which affects the accuracy of the earthwork volume information statistics and thus affects the normal operation of related projects. Summary of the invention

[0005] The embodiments of the present application provide a method, device and electronic device for identifying earthwork volume, so as to improve the accuracy of earthwork volume information statistics.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying earthwork volume, comprising:

[0007] Acquire video data to be identified, wherein the duration of the video data to be identified is within a target duration interval;

[0008] The video data to be identified is input into a pre-trained earthwork volume identification model to obtain a target identification result, wherein the target identification result includes vehicle information and earthwork volume information corresponding to the vehicle information.

[0009] Optionally, before obtaining the video data to be identified, the method further includes:

[0010] Obtaining an earthwork volume recognition model obtained through training of a neural network model;

[0011] Inputting video test data of different durations into the earthwork volume recognition model for recognition, respectively, to obtain recognition results corresponding to the video test data of different durations;

[0012] The target duration interval is determined according to the recognition results corresponding to the video test data of different durations.

[0013] Optionally, determining the target duration interval according to the recognition results corresponding to the video test data of different durations includes:

[0014] Calculate the recognition accuracy of the recognition results corresponding to the video test data of different durations;

[0015] The target duration interval is determined according to the recognition accuracy rates corresponding to the video test data of different durations.

[0016] Optionally, determining the target duration interval according to the recognition accuracy rates corresponding to the video test data of different durations includes:

[0017] Acquire target video test data in which the recognition accuracy of the vehicle information recognition result exceeds a first preset threshold, and the recognition accuracy of the earthwork information recognition result exceeds a second preset threshold, wherein the first preset threshold is higher than the second preset threshold;

[0018] The target duration interval is determined according to the video duration of the target video test data.

[0019] Optionally, the acquiring the video data to be identified, wherein the duration of the video data to be identified is within a target duration interval, includes:

[0020] Obtaining initial video data to be identified collected by a collection device;

[0021] Determine the relationship between the video duration of the initial video data to be identified and the target duration interval;

[0022] If the video duration of the initial video data to be identified is greater than the maximum value of the target duration interval, the initial video data to be identified is cropped to obtain the video data to be identified whose duration is within the target duration interval.

[0023] Optionally, the cropping of the initial video data to be identified to obtain the video data to be identified whose duration is within the target duration interval includes:

[0024] Randomly obtain a target duration from the target duration interval;

[0025] Performing preliminary cropping processing on the initial video data to be identified according to the target duration to obtain a plurality of initial sub-video data to be identified, wherein the number of the initial sub-video data to be identified corresponds to the target duration;

[0026] Target initial sub-video data to be identified with a duration of one second is obtained from each of the initial sub-video data to be identified, and each target initial sub-video data to be identified is merged to obtain video data to be identified with a duration within the target duration interval.

[0027] Optionally, also include:

[0028] If the video duration of the initial video data to be identified is less than the minimum value of the target duration interval, deleting the initial video data to be identified;

[0029] Generate and display a prompt indicating abnormal video data duration.

[0030] In a second aspect, an embodiment of the present application provides an earthwork volume identification device, comprising:

[0031] An acquisition module, used for acquiring video data to be identified, wherein the duration of the video data to be identified is within a target duration interval;

[0032] The processing module is used to input the video data to be identified into a pre-trained earthwork volume identification model to obtain a target identification result, wherein the target identification result includes vehicle information and earthwork volume information corresponding to the vehicle information.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0034] The memory stores computer-executable instructions;

[0035] The processor executes the computer-executable instructions stored in the memory to implement the first aspect as well as various possible earthwork volume identification methods involved in the first aspect.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the earthwork volume identification method as described in the first aspect and various possible aspects of the first aspect are implemented.

[0037] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the earthwork volume identification method as described in the first aspect and various possible aspects of the first aspect.

[0038] The embodiments of the present application provide a method, device and electronic device for earthwork volume identification. After adopting the above scheme, video data to be identified within a target duration interval can be first obtained, and then the video data to be identified can be input into a pre-trained earthwork volume identification model to obtain a target identification result including vehicle information and earthwork volume information corresponding to the vehicle information. By identifying the video data to be identified with a target duration based on the earthwork volume identification model and then determining the earthwork volume information, the convenience and accuracy of earthwork volume information statistics are improved, thereby ensuring the normal operation of related projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0040] Figure 1 A schematic diagram of the architecture of an application system of the earthwork volume identification method provided in an embodiment of the present application;

[0041] Figure 2 A schematic diagram of a flow chart of a method for identifying earthwork volume provided in an embodiment of the present application;

[0042] Figure 3 A schematic diagram of a flow chart of a method for identifying earthwork volume provided in another embodiment of the present application;

[0043] Figure 4 A schematic diagram of the application of the video cropping process provided in the embodiment of the present application;

[0044] Figure 5 A schematic diagram of an application of abnormal duration prompts provided in an embodiment of the present application;

[0045] Figure 6 A schematic diagram of the structure of the earthwork volume identification device provided in an embodiment of the present application;

[0046] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can also include other sequential instances in addition to those illustrated or described. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0049] Due to the diversification of construction projects, the number of construction vehicles is increasing. When construction vehicles enter and exit the construction site, the vehicle information of the construction vehicle (for example, the license plate information) and the earthwork volume information carried by the construction vehicle can be confirmed before the construction vehicle is allowed to enter the construction site. When determining the vehicle information and the earthwork volume information carried by the construction vehicle, the relevant personnel generally assign a settlement list to each construction vehicle, in which the vehicle information and earthwork volume information are recorded. Later, the earthwork volume information completed by each construction vehicle in the project will be counted and settled according to the assigned settlement list. However, due to the frequent entry and exit of vehicles at the construction site, and the information contained in each settlement list is filled in manually, it is easy to have the problem of inconsistency between the actual information and the later statistical information, which affects the accuracy of the earthwork volume information statistics, and thus affects the normal operation of related projects.

[0050] Based on the above technical problems, this application identifies the video data to be identified of the target duration based on the earthwork volume recognition model, and then determines the earthwork volume information, thereby improving the convenience and accuracy of earthwork volume information statistics, and thus ensuring the normal operation of related projects.

[0051] Figure 1 A schematic diagram of the architecture of an application system for the earthwork volume identification method provided in an embodiment of the present application, such as Figure 1As shown, the application system includes: a collection device 101, a construction vehicle 102 and a server 103. The collection device 101 is set at the access control of the construction site, and is used to collect vehicle information and earthwork information of the construction vehicle 102 to enter the construction site to obtain video data to be identified. The collection device 101 can also send the collected video data to be identified to the server 103. The server 103 is deployed with a pre-trained earthwork identification model, which can identify the received video data to be identified and obtain a target identification result. Among them, the target identification result includes vehicle information and corresponding earthwork information.

[0052] In addition, the application system may further include a database 104. After obtaining the target recognition result, the target recognition result including the vehicle information and the corresponding earthwork volume information may be stored in the database 104 for subsequent query and statistics.

[0053] The acquisition device 101 may be a camera.

[0054] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0055] Figure 2 1 is a flow chart of the earthwork volume identification method provided in the embodiment of the present application. The method of the present embodiment can be executed by the server 103. Figure 2 As shown, the method of this embodiment may include:

[0056] S201: Acquire video data to be identified, wherein the duration of the video data to be identified is within a target duration interval.

[0057] In this embodiment, when a construction vehicle enters a construction site, video data to be identified corresponding to the construction vehicle can be obtained, wherein the video data to be identified can include vehicle information (such as a license plate number) of the construction vehicle and also earthwork volume information on the construction vehicle.

[0058] In addition, in the process of multiple recognitions of the video to be identified, it was found that the recognition accuracy of different video lengths is different. Therefore, we can first obtain the target time interval with a higher recognition accuracy, and then obtain the video data to be identified with a video length within the target time interval, thereby improving the accuracy of subsequent video data recognition.

[0059] S202: Input the video data to be identified into a pre-trained earthwork volume identification model to obtain a target identification result, wherein the target identification result includes vehicle information and earthwork volume information corresponding to the vehicle information.

[0060] In this embodiment, after obtaining the video data to be identified whose video duration is within the target duration interval, the video data to be identified can be input into a pre-trained earthwork volume identification model for identification, and a target identification result including vehicle information and earthwork volume information corresponding to the vehicle information can be obtained. Subsequently, the total earthwork volume information corresponding to each vehicle information and the final earthwork volume information corresponding to all vehicle information can be counted according to the target identification result.

[0061] Among them, the earthwork volume recognition model can be obtained by training the existing network model, and the earthwork volume recognition model can be updated once every preset time period, thereby improving the recognition accuracy of the earthwork volume recognition model.

[0062] In addition, after obtaining the target recognition result, the target recognition result can be stored in the database to facilitate the subsequent statistics and settlement of earthwork information. The target recognition result can also be sent to the terminal device of the relevant personnel first, and then stored in the database after the relevant personnel confirm the target recognition result, which further improves the accuracy of the recognition result.

[0063] After adopting the above scheme, we can first obtain the video data to be identified within the target duration range, and then input the video data to be identified into the pre-trained earthwork quantity recognition model to obtain the target recognition result including vehicle information and earthwork quantity information corresponding to the vehicle information. By identifying the video data to be identified with the target duration based on the earthwork quantity recognition model and then determining the earthwork quantity information, the convenience and accuracy of earthwork quantity information statistics are improved, thereby ensuring the normal operation of related projects.

[0064] based on Figure 2 The method, the examples of this specification also provide some specific implementation plans of the method, which are described below.

[0065] Figure 3 A schematic diagram of a flow chart of a method for identifying earthwork volume provided in another embodiment of the present application is shown in FIG. Figure 3 As shown, before obtaining the video data to be identified, the method of this embodiment may further include:

[0066] S301: Obtaining an earthwork volume recognition model obtained through training of a neural network model.

[0067] S302: Inputting video test data of different durations into the earthwork volume recognition model for recognition, and obtaining recognition results corresponding to the video test data of different durations.

[0068] S303: Determine a target duration interval according to recognition results corresponding to video test data of different durations.

[0069] In this embodiment, a neural network model can be first trained to obtain an earthwork volume recognition model that can recognize vehicle information and earthwork volume information, and then video test data of different video durations can be recognized based on the earthwork volume recognition model to obtain recognition results corresponding to video test data of different durations. The recognition results corresponding to video test data of different durations can be the same or different, and then the target duration interval can be determined based on the recognition results corresponding to video test data of different durations.

[0070] Furthermore, determining the target duration interval according to the recognition results corresponding to the video test data of different durations may specifically include:

[0071] Calculate the recognition accuracy of the recognition results corresponding to the video test data of different durations.

[0072] The target duration interval is determined according to the recognition accuracy rates corresponding to the video test data of different durations.

[0073] Specifically, when determining the target duration interval based on the recognition results of video data of different durations, the recognition accuracy corresponding to the video test data can be determined based on the recognition results corresponding to the video test data of different durations, and then the target duration interval can be determined based on the recognition accuracy corresponding to the video test data of different durations. Among them, when determining the recognition accuracy corresponding to the video test data, for each video duration, the number of video test data accurately recognized can be determined based on the recognition results of the video test data, and then the number of video test data accurately recognized is divided by the total video test data to obtain the recognition accuracy of the video test data of the duration.

[0074] Optionally, after determining the recognition accuracy corresponding to the video test data of different durations, the video duration with the highest recognition accuracy can be obtained, and then the target duration interval can be obtained based on the video duration. Among them, the preset threshold can be floated based on the video duration to obtain the target duration interval. Exemplarily, the video duration with the highest recognition accuracy is 10S, the preset threshold is 3S, and the target duration interval is 7S-13S.

[0075] In addition, the target duration interval may also include only the video duration with the highest recognition accuracy.

[0076] Optionally, after determining the recognition accuracy corresponding to the video test data of different durations, the video duration with a recognition accuracy higher than a preset accuracy threshold can be obtained, and the target duration interval can be obtained based on the video duration. Exemplarily, the accuracy threshold is 85%, and the video durations exceeding the accuracy threshold are 10S, 14S, and 8S, respectively, and the target duration interval is 8S-14S.

[0077] Furthermore, determining the target duration interval according to the recognition accuracy rates corresponding to the video test data of different durations may specifically include:

[0078] Target video test data is obtained in which the recognition accuracy of the vehicle information recognition result exceeds a first preset threshold, and the recognition accuracy of the earthwork information recognition result exceeds a second preset threshold, wherein the first preset threshold is higher than the second preset threshold.

[0079] The target duration interval is determined according to the video duration of the target video test data.

[0080] Specifically, when determining the target duration interval according to the recognition accuracy corresponding to the video test data of different durations, since the video test data contains vehicle information and earthwork information, and the recognition accuracy requirements for the recognition results of the vehicle information and the earthwork information are different, different accuracy thresholds can be set for the vehicle information and the earthwork information. After respectively determining the recognition accuracy of the vehicle information recognition result and the recognition accuracy of the earthwork information recognition result, obtain the target video test data in which the recognition accuracy of the vehicle information recognition result exceeds the first preset threshold, and the recognition accuracy of the earthwork information recognition result exceeds the second preset threshold, wherein the first preset threshold represents the accuracy of vehicle information recognition, and the second preset threshold represents the accuracy of earthwork information recognition. Since the accuracy requirement for vehicle information recognition is higher than that for earthwork information recognition, the first preset threshold is higher than the second preset threshold. Exemplarily, the first preset threshold can be any value between 95% and 98%, and the second preset threshold can be any value between 85% and 90%.

[0081] In summary, by setting the target duration interval, video data to be identified with a higher recognition accuracy can be obtained, thereby improving the recognition accuracy of construction vehicles.

[0082] In addition, after determining the target duration interval, the target duration interval can be displayed on the terminal device of the relevant personnel. The relevant personnel can also adjust the target duration interval according to the actual application scenario, so that the adjusted target duration interval can be more in line with the actual application scenario, thereby improving the accuracy of the target duration interval setting and further improving the recognition accuracy of the video data.

[0083] In addition, in another embodiment, the acquiring of the to-be-recognized video data, wherein the duration of the to-be-recognized video data is within a target duration interval, may specifically include:

[0084] Obtain the initial video data to be recognized collected by the collection device.

[0085] Determine the relationship between the video duration of the initial video data to be identified and the target duration interval.

[0086] If the video duration of the initial video data to be identified is greater than the maximum value of the target duration interval, the initial video data to be identified is cropped to obtain the video data to be identified whose duration is within the target duration interval.

[0087] In this embodiment, the duration of the video data captured by the acquisition device may be within the target duration interval, may be longer than the target duration interval, or may be shorter than the target duration interval. In order to make the duration of the video data to be identified within the target duration interval, after the acquisition device captures the initial video data to be identified, the relationship between the video duration of the initial video data to be identified and the target duration interval can be determined, and then based on the relationship between the video duration of the initial video data to be identified and the target duration interval, it can be determined whether the initial video data to be identified needs to be reprocessed.

[0088] Furthermore, if the video duration of the initial video data to be identified is greater than the maximum value of the target duration interval, the initial video data to be identified is cropped to obtain video data to be identified whose duration is within the target duration interval. There are multiple ways to crop the initial video data to be identified.

[0089] Optionally, in one implementation, the initial video data to be identified is cropped to obtain the video data to be identified whose duration is within the target duration interval, which may specifically include:

[0090] A target duration is randomly obtained from the target duration interval.

[0091] The initial video data to be identified is preliminarily cropped according to the target duration to obtain a plurality of initial sub-video data to be identified, wherein the number of the initial sub-video data to be identified corresponds to the target duration.

[0092] Target initial sub-video data to be identified with a duration of one second is obtained from each of the initial sub-video data to be identified, and each target initial sub-video data to be identified is merged to obtain video data to be identified with a duration within the target duration interval.

[0093] Specifically, a target duration can be randomly obtained from the target duration interval, and then the initial video data to be identified can be preliminarily cropped according to the target duration to obtain multiple initial sub-video data to be identified corresponding to the number of target durations, and then target initial sub-video data to be identified with a duration of one second can be obtained from each initial sub-video data to be identified, and the target initial sub-video data to be identified can be merged to obtain the video data to be identified with a duration in the target duration interval.

[0094] For example, Figure 4The application diagram of the video cropping process provided in the embodiment of the present application is as follows: Figure 4 As shown, in this embodiment, the initial video data to be identified is 10s, and the target duration is 5s. The initial video data to be identified can be divided into 5 parts to obtain 5 parts of initial sub-video data to be identified, and then 1 second of video is obtained from each of the 5 parts of the initial sub-video data to be identified for merging and processing to obtain video data to be identified with a duration of 5 seconds.

[0095] In summary, by processing the initial video data to be identified collected by the acquisition device, the duration of the video data finally identified by the model is made to be in line with the target duration range, thereby improving the accuracy of video data identification.

[0096] In addition, the method may further include:

[0097] If the video duration of the initial video data to be identified is less than the minimum value of the target duration interval, the initial video data to be identified is deleted.

[0098] Generate and display a prompt indicating abnormal video data duration.

[0099] Specifically, if the video length of the initial video data to be identified is less than the minimum value of the target duration interval, it indicates that the length of the initial video data to be identified is short, which may reduce the recognition accuracy of vehicle information and earthwork information. Therefore, the initial video data to be identified can be directly deleted.

[0100] In addition, after deleting the initial video data to be identified, a video data duration abnormality prompt can be generated and displayed on the display interface of the server. In addition, the video data duration abnormality prompt can also be sent to the terminal device corresponding to the operation and maintenance personnel for display, so as to remind the operation and maintenance personnel that the video duration collected by the acquisition device is short, and the acquisition duration of the acquisition device can be adjusted in time, thereby improving the accuracy of data collection.

[0101] For example, Figure 5 The following is a schematic diagram of an application of abnormal time duration prompts provided in an embodiment of the present application, such as Figure 5 As shown, in this embodiment, the minimum value of the target duration interval is 10s, and the initial video duration of the video data to be identified is 7s, which is less than the minimum value of the target duration interval of 10s. Therefore, a video data abnormality prompt can be generated and sent to the terminal device corresponding to the operation and maintenance personnel for display. Among them, the display content of the video data abnormality prompt can be "video duration is less than 10s", and there is a confirmation button under the text "video duration is less than 10s". The user touches (for example, it can be a click operation) the confirmation button, indicating that the user has understood the abnormal prompt content and can exit to the homepage of the operation and maintenance management program.

[0102] In addition, the method may further include:

[0103] If the video duration of the initial video data to be identified is within the target duration range, the initial video data to be identified is directly identified through the earthwork quantity identification model to obtain vehicle information and corresponding earthwork quantity information.

[0104] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method. Figure 6 A schematic diagram of the structure of the earthwork volume identification device provided in the embodiment of the present application is shown in FIG. Figure 6 As shown, the device provided in this embodiment may include:

[0105] The acquisition module 601 is used to acquire the video data to be identified, wherein the duration of the video data to be identified is within a target duration interval.

[0106] The processing module 602 is used to input the video data to be identified into a pre-trained earthwork volume identification model to obtain a target identification result, wherein the target identification result includes vehicle information and earthwork volume information corresponding to the vehicle information.

[0107] After adopting the above scheme, we can first obtain the video data to be identified within the target duration range, and then input the video data to be identified into the pre-trained earthwork quantity recognition model to obtain the target recognition result including vehicle information and earthwork quantity information corresponding to the vehicle information. By identifying the video data to be identified with the target duration based on the earthwork quantity recognition model and then determining the earthwork quantity information, the convenience and accuracy of earthwork quantity information statistics are improved, thereby ensuring the normal operation of related projects.

[0108] In addition, in another embodiment, the processing module 602 is further configured to:

[0109] Obtain the earthwork volume recognition model obtained through training of the neural network model.

[0110] The video test data of different durations are respectively input into the earthwork volume recognition model for recognition, and recognition results corresponding to the video test data of different durations are obtained.

[0111] The target duration interval is determined according to the recognition results corresponding to the video test data of different durations.

[0112] In this embodiment, a neural network model can be first trained to obtain an earthwork volume recognition model that can recognize vehicle information and earthwork volume information, and then video test data of different video durations can be recognized based on the earthwork volume recognition model to obtain recognition results corresponding to video test data of different durations. The recognition results corresponding to video test data of different durations can be the same or different, and then the target duration interval can be determined based on the recognition results corresponding to video test data of different durations.

[0113] Furthermore, the processing module 602 is further configured to:

[0114] Calculate the recognition accuracy of the recognition results corresponding to the video test data of different durations.

[0115] The target duration interval is determined according to the recognition accuracy rates corresponding to the video test data of different durations.

[0116] Specifically, when determining the target duration interval based on the recognition results of video data of different durations, the recognition accuracy corresponding to the video test data can be determined based on the recognition results corresponding to the video test data of different durations, and then the target duration interval can be determined based on the recognition accuracy corresponding to the video test data of different durations. Among them, when determining the recognition accuracy corresponding to the video test data, for each video duration, the number of video test data accurately recognized can be determined based on the recognition results of the video test data, and then the number of video test data accurately recognized is divided by the total video test data to obtain the recognition accuracy of the video test data of the duration.

[0117] Furthermore, the processing module 602 is further configured to:

[0118] Target video test data is obtained in which the recognition accuracy of the vehicle information recognition result exceeds a first preset threshold, and the recognition accuracy of the earthwork information recognition result exceeds a second preset threshold, wherein the first preset threshold is higher than the second preset threshold.

[0119] The target duration interval is determined according to the video duration of the target video test data.

[0120] Specifically, when determining the target duration interval according to the recognition accuracy corresponding to the video test data of different durations, since the video test data contains vehicle information and earthwork information, and the recognition accuracy requirements for the recognition results of the vehicle information and the earthwork information are different, different accuracy thresholds can be set for the vehicle information and the earthwork information. After respectively determining the recognition accuracy of the vehicle information recognition result and the recognition accuracy of the earthwork information recognition result, obtain the target video test data in which the recognition accuracy of the vehicle information recognition result exceeds the first preset threshold, and the recognition accuracy of the earthwork information recognition result exceeds the second preset threshold, wherein the first preset threshold represents the accuracy of vehicle information recognition, and the second preset threshold represents the accuracy of earthwork information recognition. Since the accuracy requirement for vehicle information recognition is higher than that for earthwork information recognition, the first preset threshold is higher than the second preset threshold. Exemplarily, the first preset threshold can be any value between 95% and 98%, and the second preset threshold can be any value between 85% and 90%.

[0121] In summary, by setting the target duration interval, video data to be identified with a higher recognition accuracy can be obtained, thereby improving the recognition accuracy of construction vehicles.

[0122] In addition, in another embodiment, the acquisition module 601 is further used for:

[0123] Obtain the initial video data to be recognized collected by the collection device.

[0124] Determine the relationship between the video duration of the initial video data to be identified and the target duration interval.

[0125] If the video duration of the initial video data to be identified is greater than the maximum value of the target duration interval, the initial video data to be identified is cropped to obtain the video data to be identified whose duration is within the target duration interval.

[0126] Furthermore, the acquisition module 601 is further used for:

[0127] A target duration is randomly obtained from the target duration interval.

[0128] The initial video data to be identified is preliminarily cropped according to the target duration to obtain a plurality of initial sub-video data to be identified, wherein the number of the initial sub-video data to be identified corresponds to the target duration.

[0129] Target initial sub-video data to be identified with a duration of one second is obtained from each of the initial sub-video data to be identified, and each target initial sub-video data to be identified is merged to obtain video data to be identified with a duration within the target duration interval.

[0130] In addition, the acquisition module 601 is also used for:

[0131] If the video duration of the initial video data to be identified is less than the minimum value of the target duration interval, the initial video data to be identified is deleted.

[0132] Generate and display a prompt indicating abnormal video data duration.

[0133] In addition, the acquisition module 601 is also used for:

[0134] If the video duration of the initial video data to be identified is within the target duration range, the initial video data to be identified is directly identified through the earthwork quantity identification model to obtain vehicle information and corresponding earthwork quantity information.

[0135] The device provided in the embodiment of the present application can realize the above-mentioned Figure 2 The implementation principle and technical effect of the method in the embodiment shown are similar and will not be described in detail here.

[0136] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the device 700 provided in this embodiment includes: a processor 701 and a memory connected to the processor in communication. The processor 701 and the memory 702 are connected via a bus 703 .

[0137] In a specific implementation process, the processor 701 executes the computer-executable instructions stored in the memory 702, so that the processor 701 executes the method in the above method embodiment.

[0138] The specific implementation process of the processor 701 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0139] In the above Figure 7 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0140] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0141] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0142] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the earthwork volume identification method of the above method embodiment is implemented.

[0143] An embodiment of the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the earthwork volume identification method as described above is implemented.

[0144] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0145] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0146] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying earthwork volume, characterized in that: include: Acquire video data to be identified, wherein the duration of the video data to be identified is within a target duration interval; Input the video data to be identified into a pre-trained earthwork volume identification model to obtain a target identification result, wherein the target identification result includes vehicle information and earthwork volume information corresponding to the vehicle information; Before obtaining the video data to be identified, the method further includes: Obtaining an earthwork volume recognition model obtained through training of a neural network model; Inputting video test data of different durations into the earthwork volume recognition model for recognition, respectively, to obtain recognition results corresponding to the video test data of different durations; The target duration interval is determined according to the recognition results corresponding to the video test data of different durations.

2. The method according to claim 1, characterized in that The determining the target duration interval according to the recognition results corresponding to the video test data of different durations includes: Calculate the recognition accuracy of the recognition results corresponding to the video test data of different durations; The target duration interval is determined according to the recognition accuracy rates corresponding to the video test data of different durations.

3. The method according to claim 2, characterized in that The determining the target duration interval according to the recognition accuracy rates corresponding to the video test data of different durations includes: Acquire target video test data in which the recognition accuracy of the vehicle information recognition result exceeds a first preset threshold, and the recognition accuracy of the earthwork information recognition result exceeds a second preset threshold, wherein the first preset threshold is higher than the second preset threshold; The target duration interval is determined according to the video duration of the target video test data.

4. The method according to any one of claims 1 to 3, characterized in that: The acquiring of the video data to be identified, wherein the duration of the video data to be identified is within a target duration interval, comprises: Obtaining initial video data to be identified collected by a collection device; Determine the relationship between the video duration of the initial video data to be identified and the target duration interval; If the video duration of the initial video data to be identified is greater than the maximum value of the target duration interval, the initial video data to be identified is cropped to obtain the video data to be identified whose duration is within the target duration interval.

5. The method according to claim 4, characterized in that The cropping of the initial video data to be identified to obtain the video data to be identified whose duration is within the target duration interval includes: Randomly obtain a target duration from the target duration interval; Performing preliminary cropping processing on the initial video data to be identified according to the target duration to obtain a plurality of initial sub-video data to be identified, wherein the number of the initial sub-video data to be identified corresponds to the target duration; Target initial sub-video data to be identified with a duration of one second is obtained from each of the initial sub-video data to be identified, and each target initial sub-video data to be identified is merged to obtain video data to be identified with a duration within the target duration interval.

6. The method according to claim 4, characterized in that Also includes: If the video duration of the initial video data to be identified is less than the minimum value of the target duration interval, deleting the initial video data to be identified; Generate and display a prompt indicating abnormal video data duration.

7. A device for identifying earthwork volume, characterized in that: include: An acquisition module, used for acquiring video data to be identified, wherein the duration of the video data to be identified is within a target duration interval; A processing module, used for inputting the video data to be identified into a pre-trained earthwork volume identification model to obtain a target identification result, wherein the target identification result includes vehicle information and earthwork volume information corresponding to the vehicle information; The processing module is also used to obtain an earthwork volume recognition model obtained through training of a neural network model; Inputting video test data of different durations into the earthwork volume recognition model for recognition, respectively, to obtain recognition results corresponding to the video test data of different durations; The target duration interval is determined according to the recognition results corresponding to the video test data of different durations.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the earthwork volume identification method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the earthwork volume identification method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The method comprises a computer program, and when a processor executes the computer program, the method for identifying the earthwork volume according to any one of claims 1 to 6 is implemented.

Images