Test method and system for excavator bucket tooth monitoring algorithm and program product

Abstract

The invention provides a testing method and system for an excavator bucket tooth monitoring algorithm and a program product, and relates to the field of algorithm testing. The test method for the excavator bucket tooth monitoring algorithm comprises the following steps: inputting a pre-stored camera data set about bucket teeth into an excavator bucket tooth monitoring algorithm to be tested so as to output an algorithm calculation result; performing data processing on the algorithm calculation result to obtain a final recognition result; and comparing the final identification result with a pre-stored reference identification result to output a test result of the excavator bucket tooth monitoring algorithm. According to the method and the system, field testing can be avoided.

Description

Technical Field

[0001] The present invention relates to the field of algorithm testing, and in particular, to a testing method, a testing system and a computer program product for an excavator bucket tooth monitoring algorithm. Background Art

[0002] During the mining of materials in the mining area, the bucket teeth of the excavator may fall off or break during the loading process of the excavator. Because the bucket teeth are made of steel, if they fall off or break into the coal of the transport vehicle, the transported coal will be mixed with broken teeth. This will cause the crushing station to be unable to crush the steel when the coal is unloaded to the crushing station, resulting in damage to the crushing station equipment and extremely high maintenance costs. Therefore, it is necessary to perform excavator bucket tooth monitoring to prompt the bucket tooth falling off or broken tooth alarm to solve this problem.

[0003] However, conventional on-site testing of bucket teeth monitoring requires no less than five people, as well as the cooperation of multiple vehicles such as excavators, wide-body vehicles, and command vehicles, so the cost of on-site personnel and equipment is high. In addition, due to weather reasons, repeated testing is difficult to achieve, so the efficiency and quality of on-site testing are poor. Summary of the invention

[0004] The purpose of the present invention is to propose a testing method, a testing system and a computer program product for an excavator bucket tooth monitoring algorithm, which solve the technical problems of high on-site testing cost, inability to accurately control on-site testing conditions, low efficiency and potential safety hazards during the testing process.

[0005] According to one aspect of the present invention, a testing method for an excavator bucket tooth monitoring algorithm is provided, the method comprising: inputting a pre-stored camera data set about the excavator bucket teeth into the excavator bucket tooth monitoring algorithm to be tested to output an algorithm calculation result; performing data processing on the algorithm calculation result to obtain a final recognition result; comparing the final recognition result with a pre-stored reference recognition result to output a test result of the excavator bucket tooth monitoring algorithm.

[0006] In an embodiment, the camera data set includes data obtained by collecting the excavator bucket teeth from different angles and at the same time using a first camera and a second camera, so that the camera data set includes first camera data from the first camera and second camera data from the second camera; and the algorithm calculation results include a first calculation result corresponding to the first camera data and a second calculation result corresponding to the second camera data.

[0007] In an embodiment, the first calculation result and the second calculation result respectively include health status indicators corresponding to each bucket tooth on the bucket; and performing data processing on the algorithm calculation result includes: performing compensatory calculations on the health status indicators corresponding to the same bucket tooth in the first calculation result and the second calculation result according to predetermined rules to merge the first calculation result and the second calculation result into the final recognition result.

[0008] In an embodiment, the health status indicator includes: a first number indicating that the bucket tooth is intact, a second number indicating that the bucket tooth is fallen off, and a third number indicating that the bucket tooth is broken.

[0009] In an embodiment, comparing the final recognition result with the reference recognition result includes: for each bucket tooth, performing a digital matching comparison of the health status indicator between the final recognition result and the reference recognition result to determine whether each bucket tooth is successfully recognized and record it in the test result; and when there is a mismatch, recording and feeding back the final recognition result and its related information.

[0010] In an embodiment, the camera data set also includes scene information, and the testing method further includes: inputting a plurality of camera data sets collected in a plurality of scenes into the excavator bucket tooth monitoring algorithm to be tested respectively to obtain test results for a plurality of scenes.

[0011] In an embodiment, the reference recognition result includes scene information, and comparing the final recognition result with the reference recognition result includes: obtaining a reference recognition result with the same scene information based on the scene information in the input camera data set, so as to compare the final recognition result with the reference recognition result based on the same scene.

[0012] In an embodiment, comparing the final recognition result with the reference recognition result further comprises: performing statistical processing on the test results of the multiple scenes to calculate the recognition success rate of each bucket tooth.

[0013] According to another aspect of the present invention, a test system for an excavator bucket tooth monitoring algorithm is provided, the test system executes a test method according to an embodiment of the present invention, the test system comprising: a publishing module, the publishing module being configured to input a camera data set about the excavator bucket teeth into the excavator bucket tooth monitoring algorithm to be tested, the camera data set being pre-stored in the publishing module; an algorithm execution module, the algorithm execution module being configured to cause the excavator bucket tooth monitoring algorithm to perform calculations according to the input camera data set to output algorithm calculation results; a subscription module, the subscription module being configured to perform data processing on the algorithm calculation results to obtain a final recognition result.

[0014] In an embodiment, the camera data set includes data obtained by collecting the excavator bucket teeth from different angles and at the same time using a first camera and a second camera, so that the camera data set includes first camera data from the first camera and second camera data from the second camera; the algorithm calculation results include a first calculation result corresponding to the first camera data and a second calculation result corresponding to the second camera data.

[0015] In an embodiment, the subscription module includes a data processing unit, which is configured to perform compensatory calculations on the health status indicators corresponding to the same bucket tooth in the first calculation result and the second calculation result according to predetermined rules to merge the first calculation result and the second calculation result into the final recognition result.

[0016] In an embodiment, the publishing module also stores a reference identification result and is configured to send the reference identification result to the subscription module; and the subscription module also includes a comparison unit, which is configured to compare the final identification result with the reference identification result to output the test result of the excavator bucket tooth monitoring algorithm.

[0017] In an embodiment, the subscription module further includes a feedback unit, which is configured to record and feedback the corresponding final recognition result and related information according to the test result.

[0018] According to yet another aspect of the present invention, a computer program product is provided. The computer program product stores computer instructions, and the computer instructions are used to enable a computer to execute a testing method according to an embodiment of the present invention.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present invention.

[0021] Figure 1 A schematic diagram of a testing system for an excavator bucket tooth monitoring algorithm according to an embodiment of the present invention is shown.

[0022] Figure 2 A schematic diagram of a subscription module according to an embodiment of the present invention is shown.

[0023] Figure 3 An example of an algorithm calculation result and a final recognition result according to an embodiment of the present invention is shown.

[0024] Figure 4 A flow chart of a method for testing an excavator bucket tooth monitoring algorithm according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0025] In order to more clearly explain the purpose, technical solutions and advantages of the present invention, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the following description of the embodiments is intended to explain and illustrate the overall concept of the present invention, and should not be understood as limiting the present invention. In the specification and the drawings, the same or similar reference numerals refer to the same or similar parts or components. For the sake of clarity, the drawings are not necessarily drawn to scale, and some well-known parts and structures may be omitted in the drawings.

[0026] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. The wording "one" or "an" does not exclude multiple. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right", "top" or "bottom" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. When an element such as a layer, a film, a region or a substrate substrate is referred to as being "on" or "under" another element, the element may be "directly" located "on" or "under" another element, or there may be an intermediate element.

[0027] Figure 1 A schematic diagram of a testing system 1000 for an excavator bucket tooth monitoring algorithm according to an embodiment of the present invention is shown. Figure 2 FIG. 4 shows a schematic diagram of a subscription module according to an embodiment of the present invention. Figure 1-2 As shown, the test system 1000 according to the embodiment of the present invention may include a publishing module 10, an algorithm execution module 20 and a subscription module 30. The subscription module 30 may include a data processing unit 310, a comparison unit 320 and a feedback unit 330.

[0028] According to an embodiment of the present invention, the publishing module 10 may pre-store a camera data set CDS about the bucket teeth of the excavator. In this article, "camera data set CDS about the bucket teeth" may be understood as image information (e.g., image information in the form of a picture) obtained by pre-shooting the bucket teeth of the excavator, and the image information may present the status of all bucket teeth on the entire excavator bucket. The acquired camera data set CDS may be stored in the memory of the publishing module 10 for use when testing the excavator bucket teeth monitoring algorithm.

[0029] The algorithm execution module 20 may be configured to receive an excavator tooth monitoring algorithm ALO to be tested. In this article, "excavator tooth monitoring algorithm ALO" may be understood as an algorithm for performing computational processing on image information about excavator teeth to output health status information about the excavator teeth. As an example, the health status information may include health status indicators that respectively indicate the health status of each tooth on the entire bucket being monitored. In other words, the health status information may include multiple health status indicators, each health status indicator corresponding to the health status of each tooth. According to an embodiment of the present invention, the algorithm execution module 20 may receive multiple excavator tooth monitoring algorithms ALO, and optionally delete or replace the received excavator tooth monitoring algorithms ALO. For example, after testing the excavator tooth monitoring algorithm ALO, if the excavator tooth monitoring algorithm ALO test fails and needs to be adjusted, the adjusted algorithm may be input into the algorithm execution module 20 after updating for a new test. For another example, after the excavator bucket tooth monitoring algorithm ALO is updated to match the usage scenario or usage needs, it can also be directly input into the algorithm execution module 20 for testing.

[0030] According to an embodiment of the present invention, the publishing module 10 can input the pre-stored camera data set CDS about bucket teeth into the algorithm execution module 20, so that the excavator bucket tooth monitoring algorithm ALO to be tested performs calculation according to the input camera data set CDS to output the algorithm calculation result ARE. The subscription module 30 is configured to receive the output algorithm calculation result ARE and perform data processing on the algorithm calculation result ARE to obtain the final recognition result FRE. In this way, the recognition result calculated by the tested excavator bucket tooth monitoring algorithm ALO can be obtained.

[0031] According to an embodiment of the present invention, the publishing module 10 also pre-stores a reference recognition result RRE, and is also configured to send the reference recognition result RRE to the subscription module 30, so that the subscription module 30 compares the final recognition result FRE with the reference recognition result RRE to obtain the test result TR of the excavator bucket tooth monitoring algorithm ALO. In this article, the "reference recognition result RRE" can be understood as the reference information obtained and recorded at the same time when the camera data set CDS about the bucket tooth is photographed, so that when the algorithm calculation result ARE is calculated according to the camera data set CDS, the corresponding reference information can be used for comparison to determine whether the test passes. As an example, the camera data set CDS and the corresponding reference recognition result RRE can include the same mapping information (for example, scene information, shooting time information, etc.), so that the subscription module 30 can compare the corresponding final recognition result FRE with the reference recognition result RRE based on the same mapping information, thereby ensuring the accuracy and reliability of the test.

[0032] In this way, the excavator bucket tooth monitoring algorithm can be tested in a simulated manner, so that the test can be completed on the computer without going to the actual mining site. As a result, the manpower cost, equipment cost, time cost, etc. required for on-site testing can be significantly reduced, while reducing possible safety hazards. In addition, for the adjusted excavator bucket tooth monitoring algorithm, it is also easy to perform repeated tests under the same test conditions to obtain accurate improvement results.

[0033] In one embodiment, the camera data set CDS includes data collected from the excavator bucket teeth at different angles and at the same time using the first camera and the second camera, so that the camera data set CDS includes the first camera data CD1 from the first camera and the second camera data CD2 from the second camera. As an example, the angles and positions of the first camera and the second camera relative to the excavator bucket teeth can be set with reference to the angles and positions of the two cameras installed on the excavator in the excavator bucket tooth monitoring system actually used. Generally, the excavator bucket tooth monitoring system is a prompt system installed on the excavator to identify and alarm the broken teeth or falling off of the bucket teeth. The excavator bucket tooth monitoring system generally includes two cameras installed on the excavator, an excavator bucket tooth monitoring algorithm, and other related data processing equipment. The two cameras are installed at different angles, and real-time image information of the excavator bucket teeth in operation is obtained to input the excavator bucket tooth monitoring algorithm for calculation, thereby obtaining the health status of the bucket teeth. Therefore, in this embodiment, the environment can be set up, for example, in an indoor laboratory. For example, a bucket is placed in the laboratory, and according to the relative position and angle of the camera in the excavator tooth monitoring system, the first camera and the second camera are arranged relative to the placed bucket, so that the first camera and the second camera can collect the image information of the bucket teeth in the bucket according to the shooting angle in the excavator tooth monitoring system. In this way, the camera data set CDS can be easily obtained, and the test results can be consistent with the excavator tooth monitoring system actually used, so that the tested excavator tooth monitoring algorithm can be well used with the two cameras in the excavator tooth monitoring system, thereby ensuring the accuracy and reliability of the monitoring results.

[0034] However, the embodiments of the present invention are not limited thereto, and may include less than or more than two cameras according to actual needs, so as to collect video data from more angles.

[0035] Further, the excavator bucket tooth monitoring algorithm ALO can perform calculations on the first camera data CD1 and the second camera data CD2, respectively, so that the algorithm calculation result ARE can include a first calculation result RE1 corresponding to the first camera data CD1 and a second calculation result RE2 corresponding to the second camera data CD2. As described above, the excavator bucket tooth monitoring algorithm ALO can perform calculations on the image information about the excavator bucket teeth to obtain the health status of the bucket teeth. Since the image information is obtained by two cameras respectively, the excavator bucket tooth monitoring algorithm ALO performs calculations on different image information respectively to obtain the first calculation result RE1 and the second calculation result RE2 respectively, and thus constitute the algorithm calculation result ARE and output it to the subscription module 30.

[0036] In one embodiment, the first calculation result RE1 and the second calculation result RE2 may respectively include a health status indicator IND corresponding to each tooth on the bucket. The health status indicator IND may include a first number indicating that the tooth is intact, a second number indicating that the tooth is off, and a third number indicating that the tooth is broken. For example, the first number is 0, the second number is 1, and the third number is 2. However, the embodiments of the present invention are not limited thereto. According to actual needs, any form (such as letters, etc.) or any number of health status indicators can be used as long as they can indicate the health status of each tooth.

[0037] Figure 3 2 shows an example of the algorithm calculation result and the final recognition result according to an embodiment of the present invention. Figure 3 As shown, it is shown that the first calculation result RE1 includes six health status indicators IND, and the second calculation result RE2 includes six health status indicators IND. This means that the photographed bucket includes six bucket teeth, so that each calculation result includes a health status indicator IND corresponding to each bucket tooth. However, this is only an example, and different numbers of bucket teeth may be included depending on the model, so that each calculation result may include a different number of health status indicators. As an example, each bucket tooth can be numbered, and the excavator bucket tooth monitoring algorithm ALO can calculate the health status of each bucket tooth based on the image information, that is, obtain the health status indicator IND of each bucket tooth, and then record the health status indicator IND of the bucket tooth under the corresponding bucket tooth number. In this way, the following can be formed. Figure 3 The algorithm calculation results shown in the figure are as follows. Figure 3 As shown, the first calculation result RE1 includes the following health status indicators IND: 0, 1, 2, 0, 1, 0; the second calculation result RE2 includes the following health status indicators IND: 0, 1, 1, 0, 0, 0.

[0038] In one embodiment, the data processing unit 310 in the subscription module 30 may perform data processing on the algorithm calculation result ARE to obtain the final recognition result FRE. In this embodiment, the data processing unit 310 may perform compensation calculation on the health status indicator IND corresponding to the same bucket tooth in the first calculation result RE1 and the second calculation result RE2 according to a predetermined rule to merge the first calculation result RE1 and the second calculation result RE2 into the final recognition result FRE.

[0039] In this article, "predetermined rules" can be understood as a data processing method that integrates two calculation results into one final result, or calculates one final result based on two calculation results. By performing compensation calculations according to predetermined rules, the final recognition result FRE outputted can be obtained by combining the two calculation results, so that the output result has higher accuracy and more comprehensive angle coverage. As an example, Figure 3 As shown, the predetermined rule may be: when the numbers of the two health status indicators IND corresponding to the same bucket tooth (i.e., bucket teeth with the same number) are the same, the number is output (for example, when the two health status indicators IND in the first column are both 0 indicating that the bucket teeth are intact, 0 is output); when the two health status indicators IND are different, as long as one of the health status indicators IND is 1 indicating that the bucket teeth are detached, 1 is output (for example, if the two health status indicators IND in the third column are 2 and 1 respectively, 1 is output; if the two health status indicators IND in the fifth column are 1 and 0 respectively, 1 is also output); if the two health status indicators IND are different, and one is 0 indicating that the bucket teeth are intact and the other is 2 indicating that the bucket teeth are broken, 2 is output (for example, if the two health status indicators IND in the fourth column are 0 and 2 respectively, 2 is output). Therefore, the compensation calculation can be performed through the predetermined rule to obtain the final recognition result FRE. As shown Figure 3 As shown, the final recognition result FRE may include the following health status indicators IND: 0, 1, 1, 2, 1, 0.

[0040] However, it should be noted that this is only an example, and other suitable predetermined rules can be used to perform the compensation calculation. In addition, as described above, more cameras can be used to obtain more calculation results, and other suitable predetermined rules can be used to merge more calculation results into a final recognition result FRE.

[0041] In one embodiment, the final recognition result FRE may be compared with the reference recognition result RRE by the comparison unit 320 in the subscription module 30. The comparison unit 320 may be configured to perform a digital matching comparison of the health status indicator between the final recognition result FRE and the reference recognition result RRE for each bucket tooth to determine whether each bucket tooth is successfully recognized and recorded in the test result TR. As described above, the reference recognition result RRE may be recorded in advance and may be recorded in the same form as the final recognition result FRE. For example, the health status indicator IND of each bucket tooth determined manually may be recorded and formed into a configuration file and stored in the publishing module 10 to be sent to the comparison unit 320 in the subscription module 30 when the test is performed. As an example, the comparison unit 320 may compare the health status indicator IND of each bucket tooth one by one according to the number of the bucket tooth to see if they are consistent. For example, when all are consistent, it may be determined that all are successfully recognized and recorded in the test result TR. When there are inconsistent bucket teeth, it may be determined that the recognition fails, and the number of the bucket tooth that failed to be recognized is recorded in the test result TR.

[0042] In one embodiment, the comparison unit 320 may send the test result TR to the feedback unit 330 in the subscription module 30. The feedback unit 330 is configured to record and feedback the corresponding final recognition result FRE and related information thereof according to the test result TR. As an example, when the feedback unit 330 indicates recognition failure according to the test result TR, the final recognition result FRE forming the test result TR may be recorded, and information related to the final recognition result FRE may be obtained, such as a picture showing the final recognition result FRE, time information for outputting the final recognition result FRE, and scene information relative to the final recognition result FRE, etc. The feedback unit 330 may feed back the final recognition result FRE and related information thereof to the tester for updating and improving the excavator bucket tooth monitoring algorithm ALO in subsequent steps.

[0043] In this way, the final recognition results of all recognition failures can be clearly and comprehensively fed back. For example, when multiple final recognition results are output, by recording relevant information, the formation conditions of each final recognition result of recognition failure can be clearly known. By summarizing and analyzing this information, it can help to find the cause of the problem more quickly and accurately and make targeted improvements.

[0044] In one embodiment, the camera data set CDS may further include scene information. As described above, an environment may be built indoors to collect the camera data set CDS. In this embodiment, multiple camera data sets CDS may be collected in the environment in multiple different scenes. For example, the multiple scenes may include: scenes based on light changes such as cloudy days, foggy days, snowy days, backlighting, and front light; scenes with different bucket tooth falling positions; and scenes with different bucket tooth breaking positions, etc. Each scene may be named or numbered to form scene information, and the formed scene information may be included in the camera data set CDS.

[0045] Further, the publishing module 10 may pre-store multiple camera data sets CDS collected in multiple scenarios, and be configured to input the multiple camera data sets CDS into the excavator bucket tooth monitoring algorithm ALO to be tested, respectively, to obtain test results TR for multiple scenarios. As an example, during the test of the excavator bucket tooth monitoring algorithm ALO, the publishing module 10 may continuously input multiple camera data sets CDS in multiple scenarios into the excavator bucket tooth monitoring algorithm ALO, to continuously output multiple test results TR.

[0046] In one embodiment, the reference recognition result RRE may include scene information. The comparison unit 320 may also be configured to obtain a reference recognition result RRE having the same scene information based on the scene information in the input camera data set CDS, so as to compare the final recognition result FRE with the reference recognition result RRE based on the same scene. As an example, the publishing module 10 may continuously input multiple camera data sets CDS into the excavator bucket tooth monitoring algorithm ALO to calculate multiple final recognition results FRE, while also continuously sending multiple reference recognition results RRE to the comparison unit 320. The comparison unit 320 may extract the scene information included in the camera data set CDS corresponding to the final recognition result FRE to be compared, and search for a reference recognition result RRE having the same scene information from the multiple reference recognition results RRE based on the extracted scene information, thereby comparing the final recognition result FRE with the searched reference recognition result RRE.

[0047] In this way, algorithm testing in multiple scenarios can be achieved, thereby increasing the test dimensions to improve the comprehensiveness, accuracy and stability of the test results. By using the simulation test method according to an embodiment of the present invention, algorithm testing in multiple scenarios can be easily performed without having to go to the outdoor site to wait for the natural environment to change. This reduces the time required for field testing from 30 days to only 3 hours to complete multi-dimensional algorithm testing in multiple scenarios. In addition, for scene conditions that are difficult to obtain outdoors, they can also be easily created manually indoors, thereby obtaining test results with greater dimensional coverage, thereby improving the accuracy of the test and accelerating the improvement of the excavator bucket tooth monitoring algorithm ALO.

[0048] In one embodiment, the comparison unit 320 can also be configured to perform statistical processing on the test results TR of multiple scenarios to calculate the recognition success rate of each bucket tooth. As described above, in each test result TR, it can be identified and recorded whether the health status indicator IND of each bucket tooth matches consistently. When multiple test results TR are output, the recognition success rate of each bucket tooth can be calculated based on the recorded bucket tooth matching results. For example, for each bucket tooth, the recognition success rate = the number of successful recognitions / the total number × 100%. Additionally or optionally, the recognition success rate of the overall data can be calculated, for example, the recognition success rate of the overall data = the number of all successful recognitions / the total number of comparisons × 100%. In this way, the calculation success rate of the excavator bucket tooth monitoring algorithm ALO under multiple dimensions can be calculated to reflect the performance of the excavator bucket tooth monitoring algorithm ALO at least in terms of the success rate. In addition, for bucket teeth with a low recognition success rate, the excavator bucket tooth monitoring algorithm ALO can be improved in a targeted manner by extracting the relevant final recognition result FRE and its related information (for example, scene information, output time information, and pictures showing the final recognition result FRE, etc.) for viewing and analysis. However, the embodiments of the present invention are not limited thereto, and other data statistical processing may be performed on the test results TR of multiple scenarios according to actual needs to reflect the performance of the excavator bucket tooth monitoring algorithm ALO.

[0049] Figure 4 The flowchart of the testing method for the bucket tooth monitoring algorithm of an excavator according to the embodiment of the present invention is shown.

[0050] like Figure 4 As shown, in step S401, a pre-stored camera data set CDS about the excavator bucket teeth is input into the excavator bucket teeth monitoring algorithm ALO to be tested, so as to output an algorithm calculation result ARE.

[0051] In step S402, data processing is performed on the algorithm calculation result ARE to obtain the final recognition result FRE.

[0052] In step S403, the final recognition result FRE is compared with the pre-stored reference recognition result RRE to output the test result TR of the excavator bucket tooth monitoring algorithm ALO.

[0053] Advantageously, by using the test system and method for the excavator bucket tooth monitoring algorithm according to the embodiment of the present invention, the problems of high field test cost, inability to accurately control field test conditions, low efficiency, and potential safety hazards in the existing test process are solved. In addition, outdoor field deployment is not required, and the occupation of operating resources and costs such as excavators, wide-body vehicles, and command vehicles is saved. The manpower requirement can be reduced from 5 people to 1 person, thereby making the test coverage complete, the retest cost low, and improving the test efficiency.

[0054] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0055] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A testing method for an excavator bucket tooth monitoring algorithm, characterized in that: The method comprises: Inputting a pre-stored camera data set about the excavator bucket teeth into the excavator bucket teeth monitoring algorithm to be tested to output the algorithm calculation result; Performing data processing on the algorithm calculation result to obtain a final recognition result; The final recognition result is compared with a pre-stored reference recognition result to output a test result of the excavator bucket tooth monitoring algorithm.

2. The testing method according to claim 1, characterized in that: The camera data set includes data acquired by using a first camera and a second camera to collect the bucket teeth of the excavator from different angles at the same time, so that the camera data set includes first camera data from the first camera and second camera data from the second camera; and The algorithm calculation result includes a first calculation result corresponding to the first camera data and a second calculation result corresponding to the second camera data.

3. The testing method according to claim 2, characterized in that: The first calculation result and the second calculation result respectively include a health status indicator corresponding to each tooth on the bucket; as well as Performing data processing on the algorithm calculation result includes: performing compensation calculation on the health status indicators corresponding to the same bucket tooth in the first calculation result and the second calculation result according to a predetermined rule to merge the first calculation result and the second calculation result into the final recognition result.

4. The testing method according to claim 3, characterized in that: The health status indicator includes: a first number indicating that the bucket tooth is intact, a second number indicating that the bucket tooth has fallen off, and a third number indicating that the bucket tooth is broken.

5. The testing method according to claim 4, characterized in that: Comparing the final recognition result with the reference recognition result includes: for each bucket tooth, performing a digital matching comparison of a health status indicator between the final recognition result and the reference recognition result to determine whether each bucket tooth is successfully recognized and record it in the test result; and When there is a mismatch, the final recognition result and related information are recorded and fed back.

6. The testing method according to claim 1, characterized in that: The camera data set also includes scene information, and The testing method further includes: inputting a plurality of camera data sets collected in a plurality of scenes into the excavator bucket tooth monitoring algorithm to be tested respectively, so as to obtain test results for a plurality of scenes.

7. The testing method according to claim 6, characterized in that: The reference recognition result includes scene information, and Comparing the final recognition result with the reference recognition result includes: obtaining a reference recognition result with the same scene information according to the scene information in the input camera data set, so as to compare the final recognition result with the reference recognition result based on the same scene.

8. The testing method according to claim 7, characterized in that: Comparing the final recognition result with the reference recognition result further includes: performing statistical processing on the test results of the multiple scenes to calculate the recognition success rate of each bucket tooth.

9. A test system for an excavator bucket tooth monitoring algorithm, characterized in that: The test system performs the test method according to any one of claims 1 to 8, and the test system comprises: a publishing module, the publishing module being configured to input a camera data set about an excavator bucket tooth into the excavator bucket tooth monitoring algorithm to be tested, the camera data set being pre-stored in the publishing module; An algorithm execution module, wherein the algorithm execution module is configured to cause the excavator bucket tooth monitoring algorithm to perform calculations according to the input camera data set to output algorithm calculation results; A subscription module is configured to perform data processing on the algorithm calculation result to obtain a final recognition result.

10. The test system according to claim 9, characterized in that: The camera data set includes data acquired by using a first camera and a second camera to collect the bucket teeth of the excavator from different angles and at the same time, so that the camera data set includes first camera data from the first camera and second camera data from the second camera; The algorithm calculation result includes a first calculation result corresponding to the first camera data and a second calculation result corresponding to the second camera data.

11. The test system according to claim 10, characterized in that: The subscription module includes a data processing unit, which is configured to perform a compensatory calculation on the health status indicators corresponding to the same bucket tooth in the first calculation result and the second calculation result according to a predetermined rule, so as to merge the first calculation result and the second calculation result into the final recognition result.

12. The test system according to claim 11, characterized in that: The publishing module also stores a reference identification result and is configured to send the reference identification result to the subscription module; as well as The subscription module further includes a comparison unit configured to compare the final recognition result with the reference recognition result to output a test result of the excavator bucket tooth monitoring algorithm.

13. The test system according to claim 12, characterized in that: The subscription module further includes a feedback unit, which is configured to record and feedback the corresponding final recognition result and related information according to the test result.

14. A computer program product, wherein the computer program product stores computer instructions, wherein the computer instructions are used to enable a computer to execute the testing method according to any one of claims 1 to 8.

Images