Ore surface impurity identification method, device, electronic equipment and storage medium

Abstract

The present invention provides a method, device, electronic device and storage medium for identifying impurities on the surface of an ore. The method comprises: obtaining three-dimensional information, a detection image and a type of the ore to be detected; determining feature prediction data of the ore to be detected based on the three-dimensional information and the type; wherein the feature prediction data comprises a predicted value of reflected light intensity, a predicted value of reflected light color and a predicted value of reflected area; extracting feature measured data from the detection image; comparing the feature measured data with the feature prediction data, and identifying the surface impurities of the ore to be detected based on the comparison result. The present invention uses the optical properties of different types of ores as features, predicts the optical properties of the ore to be detected, uses the obtained feature prediction data as a benchmark, and then performs feature extraction and analysis on the image to be detected of the ore to be detected to obtain feature measured data. By comparing the feature measured data with the feature prediction data, it is possible to effectively determine whether there are impurities on the surface of the ore.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, electronic equipment and storage medium for identifying impurities on the surface of an ore. Background Art

[0002] With the rapid development of science and technology, the demand for resources in social life is increasing, and mineral resources have become an important area of ​​resource exploitation.

[0003] A large amount of useless impurities will be generated in the ore production process, such as vein quartz tailings, lead-zinc mine waste rock, coal mine gangue, and wood and rubber mixed in the ore. In order to improve the ore recovery efficiency and ensure the quality of mining, it is often necessary to sort the impurities of large pieces of ore. The current impurity sorting method still relies mainly on manual operation of workers. For example, the current impurity hand-sorting process is a method of manually picking out by human eyes. However, the process of manual hand-selection of ore impurities has always been criticized. The main reason is that the hand-selection workshop has a lot of smoke and dust, a dirty environment, and loud noise, which is extremely harmful to the human body. As a result, the hand-selection workshop is one of the main places where occupational diseases occur among mining practitioners. At the same time, the labor intensity of manual hand-selection of ore impurities is very high, the work efficiency is low, and the processing volume per unit time is limited. If the flow rate per unit time increases, it is easy to cause mis-picking. In addition, there are also major safety hazards in manual hand-selection of impurities, which can easily hurt hands and feet during transportation.

[0004] To solve this problem, X-rays or images are currently used to inspect and analyze ores. However, the X-ray detection method has a good recognition effect on ores with a large number of impurities embedded inside or embedded, but it is not effective for ores with impurities only on the surface. Although the image detection method can identify impurities on the surface of the ore, due to the irregular surface of the ore without fine processing, the image detection method cannot accurately identify every surface of the ore.

[0005] Therefore, at this stage, there is an urgent need for a means to effectively identify impurities on the surface of ore. Summary of the invention

[0006] The embodiments of the present invention provide a method, device, electronic device and storage medium for identifying impurities on the surface of an ore, so as to solve the problem of inaccurate identification of impurities existing on the surface of an ore at the current stage.

[0007] In a first aspect, an embodiment of the present invention provides a method for identifying impurities on the surface of an ore, comprising:

[0008] Obtain the three-dimensional information, detection images and types of the ore to be tested;

[0009] Determine the characteristic prediction data of the ore to be detected based on the three-dimensional information and the type; wherein the characteristic prediction data includes the predicted value of the reflected light intensity, the predicted value of the reflected light color and the predicted value of the reflected area;

[0010] Extracting feature measured data from the detection image;

[0011] The feature measured data and the feature predicted data are compared, and the surface impurities of the ore to be tested are identified based on the comparison results.

[0012] In a possible implementation, the three-dimensional data is determined based on structured light irradiated on the ore to be detected; the structured light is used to project an initial line structure on the ore to be detected; the three-dimensional data includes the line structure to be analyzed obtained after being projected on the surface of the ore to be detected;

[0013] Determine the characteristic prediction data of the ore to be tested based on the three-dimensional information and type, including:

[0014] Determine the degree of distortion of the line structure based on the initial line structure and the line structure to be analyzed;

[0015] Determine the curvature corresponding to each reflective surface of the ore to be detected based on the degree of distortion, and determine the reflection area prediction value of each target reflective surface according to the curvature corresponding to each reflective surface;

[0016] Determine the predicted value of the reflected light intensity of each target reflection surface of the ore to be detected based on the predicted value of the reflection area and curvature corresponding to each target reflection surface, as well as the type;

[0017] The predicted value of the color of the reflected light of the ore to be detected is determined based on the type.

[0018] In a possible implementation, the target reflective surface is a reflective surface whose predicted reflection area value is greater than a first preset threshold;

[0019] According to the curvature corresponding to each reflecting surface, the reflection area prediction value of each target reflecting surface is determined, including:

[0020] For any reflecting surface, if the curvature difference between the reflecting surface and other reflecting surfaces adjacent to the reflecting surface is less than a first preset difference, the reflecting surface and the reflecting surfaces adjacent to the reflecting surface whose curvature difference is less than the first preset difference are taken as target reflecting surfaces;

[0021] Based on the three-dimensional data of the reflecting surface and the reflecting surfaces adjacent to the reflecting surface, a predicted value of the reflecting area of ​​the target reflecting surface where the reflecting surface is located is determined.

[0022] In a possible implementation, based on the reflection area prediction value and curvature corresponding to each target reflection surface, as well as the type, the reflection light intensity prediction value of each target reflection surface of the ore to be detected is determined, including:

[0023] Determine the reflectivity of the ore to be tested based on its type;

[0024] For any target reflective surface, based on the preset illumination intensity and incident angle of the detection light, determine the predicted value of the initial reflected light intensity of the target reflective surface in the preset collection direction;

[0025] Determine a correction value of a predicted value of reflected light intensity of the target reflective surface in a preset collection direction according to predicted values ​​of reflection areas, curvatures and preset detection lights corresponding to other target reflective surfaces adjacent to the target reflective surface;

[0026] The predicted value of the reflected light intensity of the target reflective surface is obtained according to the initial predicted value of the reflected light intensity and the corrected value of the predicted value of the reflected light intensity.

[0027] In a possible implementation, determining a correction value of a predicted value of reflected light intensity of the target reflective surface in a preset collection direction according to predicted values ​​of reflection areas, curvatures, and preset detection lights corresponding to other target reflective surfaces adjacent to the target reflective surface includes:

[0028] Determine, according to the predicted values ​​of the reflection areas and curvatures corresponding to other target reflection surfaces adjacent to the target reflection surface, the relative reflection angles and relative reflected light intensities of the other target reflection surfaces relative to the target reflection surface under the preset detection light;

[0029] According to the relative reflection angle and the relative reflected light intensity, a correction value of the predicted value of the reflected light intensity of the target reflective surface in the preset collection direction is determined.

[0030] In a possible implementation, extracting feature measured data from a detection image includes:

[0031] Inputting the image to be detected into a pre-trained extraction model to extract the reflection surface data of the ore to be detected in the image to be detected; wherein the reflection surface data includes a feature map corresponding to each target reflection surface;

[0032] Based on the reflection surface data, the feature measured data of each target reflection surface in the detection image is calculated; wherein the feature measured data includes the measured value of the reflected light intensity, the measured value of the reflected light color and the measured value of the reflection area.

[0033] In a possible implementation, the feature measured data and the feature predicted data are compared, and the surface impurities of the ore to be tested are identified based on the comparison result, including:

[0034] Perform the following steps for any target reflective surface:

[0035] If the error between the predicted value of the reflected light intensity and the measured value of the reflected light intensity is greater than the preset light intensity error, it is determined that the ore to be tested has impurities on the target reflection surface;

[0036] If the color difference between the predicted color value of the reflected light and the actual color value of the reflected light is greater than the preset color difference, it is determined that the ore to be tested has impurities on the target reflection surface;

[0037] If the error between the predicted reflection area value and the measured reflection area value is greater than a preset area error value, it is determined that the ore to be detected has impurities on the target reflection surface.

[0038] In a second aspect, an embodiment of the present invention provides a device for identifying impurities on the surface of an ore, comprising:

[0039] An acquisition module is used to obtain the three-dimensional information, detection images and types of the ore to be detected;

[0040] A prediction module, used to determine the characteristic prediction data of the ore to be detected based on the three-dimensional information and the type; wherein the characteristic prediction data includes the predicted value of the intensity of the reflected light, the predicted value of the color of the reflected light and the predicted value of the reflected area;

[0041] An extraction module, used to extract feature measured data from the detection image;

[0042] The identification module is used to compare the feature measured data with the feature predicted data, and identify the surface impurities of the ore to be tested based on the comparison results.

[0043] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the processor implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0045] The embodiment of the present invention provides a method, device, electronic device and storage medium for identifying impurities on the surface of an ore. Through the three-dimensional information of the ore to be detected, the optical characteristics of different types of ores are used as features to predict the optical characteristics of the ore to be detected, and obtain the feature prediction data of the ore to be detected. The obtained feature prediction data is used as a benchmark, and then the image feature extraction technology is used to perform feature extraction and analysis on the image to be detected of the ore to be detected, and the optical characteristic measured data of the ore to be detected, that is, the feature measured data, is obtained. By comparing the feature measured data with the feature predicted data used as a benchmark, it can be effectively judged whether there are impurities on the ore surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0047] Figure 1 is a flow chart of an implementation method of an ore surface impurity identification method provided by an embodiment of the present invention;

[0048] Figure 2 It is a simplified diagram of the surface structure of the ore to be tested;

[0049] Figure 3 is a schematic diagram of the structure of an ore surface impurity identification device provided by an embodiment of the present invention;

[0050] Figure 4 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0052] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0053] Figure 1 FIG. 1 is a flowchart of the method for identifying impurities on the surface of an ore provided by an embodiment of the present invention. Figure 1 As shown, the method includes:

[0054] Step 110: Obtain the three-dimensional information, detection image and type of the ore to be detected.

[0055] In this embodiment, the ore to be detected can be conveyed on a conveyor belt of the detection device; the detection device is provided with a camera, a structured light source, an irradiation light source and other devices. Among them, the camera is used to collect the detection image of the ore to be detected; the structured light source is used to emit structured light, and the structured light can be used to project an initial line structure on the ore to be detected to obtain three-dimensional information of the ore to be detected. The initial line structure can be a grid or a stripe, which is not limited here. The irradiation light source is used to illuminate the surface of the ore to be detected to provide a basis for subsequent detection.

[0056] Step 120: Determine feature prediction data of the ore to be detected based on the three-dimensional information and the type; wherein the feature prediction data includes a predicted value of reflected light intensity, a predicted value of reflected light color, and a predicted value of reflected area.

[0057] In this embodiment, considering that different types of ores have different optical properties, the standard optical characteristics corresponding to the ore without impurities, that is, the characteristic prediction data, are predicted based on the three-dimensional information and type of the ore to be detected.

[0058] The step 120 is described below through an optional embodiment.

[0059] In an optional embodiment, the three-dimensional data includes the line structure to be analyzed obtained after being projected onto the surface of the ore to be detected.

[0060] Determining the characteristic prediction data of the ore to be detected based on the three-dimensional information and the type in step 120 may include:

[0061] Step 121: Determine the degree of distortion of the line structure based on the initial line structure and the line structure to be analyzed.

[0062] Step 122: Determine the curvature corresponding to each reflection surface of the ore to be detected based on the degree of distortion, and determine the reflection area prediction value of each target reflection surface according to the curvature corresponding to each reflection surface.

[0063] Step 123: Based on the predicted reflection area and curvature corresponding to each target reflection surface, as well as the type, determine the predicted value of the reflected light intensity of each target reflection surface of the ore to be detected.

[0064] Step 124: Determine the predicted value of the color of the reflected light of the ore to be detected based on the type.

[0065] In this embodiment, the structured light includes an initial line structure of a preset size. After being irradiated onto the ore to be detected, the initial line structure will be distorted due to the irregular structure of the ore to be detected, and the line structure to be analyzed is obtained, that is, the three-dimensional information of the ore to be detected. By comparing and analyzing the initial line structure and the line structure to be analyzed, the degree of distortion of the line structure can be determined. The degree of distortion can reflect the concavity and convexity of any reflective surface of the ore to be detected. Here, the curvature corresponding to the horizontal plane can be defined as 0, the curvature of the convex surface can be defined as positive, and the curvature of the concave surface can be defined as negative. According to the concavity and convexity corresponding to the reflective surface, it is determined whether the corresponding curvature is positive or negative. After determining the curvature of each reflective surface, the predicted value of the reflection area of ​​each target reflective surface can be determined according to the curvature of each reflective surface.

[0066] The intensity of reflected light from each target reflection surface is affected by the type of ore to be detected, the predicted value of the reflection area corresponding to the target reflection surface, the curvature and other data. Therefore, the predicted value of the reflected light intensity from each target reflection surface of the ore to be detected can be determined based on the predicted value of the reflection area and the curvature corresponding to each target reflection surface, as well as the type.

[0067] After describing the process of determining the feature prediction data, the process of determining the reflection area prediction value of each target reflection surface is described below.

[0068] Accordingly, in an optional embodiment, determining the reflection area prediction value of each target reflection surface according to the curvature corresponding to each reflection surface in step 122 may include:

[0069] For any reflecting surface, if the curvature difference between the reflecting surface and other reflecting surfaces adjacent to the reflecting surface is less than a first preset difference, the reflecting surface and the reflecting surfaces adjacent to the reflecting surface whose curvature difference is less than the first preset difference are taken as target reflecting surfaces;

[0070] Based on the three-dimensional data of the reflecting surface and the reflecting surfaces adjacent to the reflecting surface, a predicted value of the reflecting area of ​​the target reflecting surface where the reflecting surface is located is determined.

[0071] In this embodiment, in order to reduce the amount of calculation, when the curvature difference between multiple adjacent reflection surfaces is small, these reflection surfaces can be approximately regarded as one reflection surface, that is, a target reflection surface. Specifically, for any reflection surface, it can have multiple adjacent reflection surfaces, for example, it has four adjacent reflection surfaces A, B, C, and D. If the curvature difference between the reflection surface and the reflection surfaces A and B is less than the first preset difference, and the curvature difference between the reflection surface and the reflection surfaces C and D is greater than the first preset difference, then the reflection surface and the reflection surface A are regarded as an initial target reflection surface. Similarly, if the reflection surfaces adjacent to the reflection surface A are E and F, the same judgment method can be used until all the reflection surfaces in the obtained initial target reflection surface do not have other adjacent reflection surfaces with a curvature difference less than the first preset difference, and the initial target reflection surface obtained at this time is regarded as a target reflection surface.

[0072] After the target reflection surface is determined, the reflection area prediction value of the target reflection surface can be obtained by calculating the line structure to be analyzed of the reflection surface included in the target reflection surface.

[0073] After determining the reflection area prediction value corresponding to each target reflection surface, the process of determining the reflection light intensity prediction value of each target reflection surface is described below.

[0074] Accordingly, in an optional embodiment, in step 123, based on the predicted reflection area and curvature corresponding to each target reflection surface, as well as the type, determining the predicted value of the reflected light intensity of each target reflection surface of the ore to be detected may include:

[0075] The reflectivity of the ore to be tested is determined based on its type.

[0076] For any target reflective surface, based on the preset illumination intensity and incident angle of the detection light, a predicted value of the initial reflected light intensity of the target reflective surface in a preset collection direction is determined.

[0077] A correction value of the predicted value of the reflected light intensity of the target reflective surface in the preset collection direction is determined according to the predicted values ​​of the reflected areas, the curvatures and the preset detection light corresponding to other target reflective surfaces adjacent to the target reflective surface.

[0078] The predicted value of the reflected light intensity of the target reflective surface is obtained according to the initial predicted value of the reflected light intensity and the corrected value of the predicted value of the reflected light intensity.

[0079] Figure 2 This is a schematic diagram of the surface structure of the ore to be tested. Figure 2This embodiment is described. In this embodiment, when the ore to be detected is detected, a preset detection light source is required to emit a preset detection light with a fixed incident angle and light intensity. Then, the image of the ore to be detected is collected by a camera. Among them, the camera is fixed, so the collection angle of the detection image of the ore to be detected is determined by the fixed position and collection range of the camera.

[0080] Theoretically, for any target reflective surface, we only need to calculate the reflected light intensity based on its incident light and reflectivity. Figure 2 As shown, in the actual detection process, the reflected light intensity detected by a target reflective surface includes not only the initial reflected light intensity prediction value directly obtained based on the preset detection light, but also includes the reflected light intensity reflected by other target reflective surfaces to the target reflective surface, that is, the correction value. Therefore, it is necessary to further analyze the initial reflected light intensity prediction value and the correction value of the reflected light intensity prediction value to obtain the reflected light intensity prediction value of the target reflective surface.

[0081] Accordingly, in an optional embodiment, determining a correction value of a predicted value of reflected light intensity of the target reflective surface in a preset collection direction according to a predicted value of a reflection area, a curvature and a preset detection light corresponding to other target reflective surfaces adjacent to the target reflective surface may include:

[0082] Determine, according to the predicted values ​​of the reflection areas and curvatures corresponding to other target reflection surfaces adjacent to the target reflection surface, the relative reflection angles and relative reflected light intensities of the other target reflection surfaces relative to the target reflection surface under the preset detection light;

[0083] According to the relative reflection angle and the relative reflected light intensity, a correction value of the predicted value of the reflected light intensity of the target reflective surface in the preset collection direction is determined.

[0084] In this embodiment, since the illumination intensity and incident angle of the preset detection light are fixed, the relative reflection angle of other target reflection surfaces can be determined according to the curvature and incident angle of other target reflection surfaces, and the relative reflection times and the relative reflected light intensity corresponding to each reflection can be determined according to the reflection area prediction value, illumination intensity and the type of ore to be detected. According to the relative reflection angle, it can be determined whether the relative reflected light reflected by the other target reflection surface can be incident on the target reflection surface. If it can, the correction value of the predicted value of the reflected light intensity of the target reflection surface in the preset collection direction is determined according to the relative reflected light intensity.

[0085] Step 130: extracting feature measured data in the detection image.

[0086] In this embodiment, the model may be used to extract features in the detection image to obtain measured feature data in the detection image.

[0087] Accordingly, in an optional embodiment, extracting the feature measured data in the detection image in step 130 may include:

[0088] The image to be detected is input into a pre-trained extraction model to extract the reflection surface data of the ore to be detected in the image to be detected; wherein the reflection surface data includes a feature map corresponding to each target reflection surface.

[0089] Based on the reflection surface data, the feature measured data of each target reflection surface in the detection image is calculated; wherein the feature measured data includes the measured value of the reflected light intensity, the measured value of the reflected light color and the measured value of the reflection area.

[0090] In this embodiment, the pre-trained extraction model can be a deep learning model, which can be trained by historical images. After the image to be detected is input into the pre-trained extraction model, the deep learning model can locate and extract the ore surface image of the ore to be detected included in the image to be detected. In the extracted ore surface image, in order to calculate accurately, the ore surface image is first gray-scale converted, and then each target reflection surface included in the ore surface image is segmented to obtain feature maps corresponding to multiple target reflection surfaces; finally, the feature measured data of each target reflection surface is calculated based on the pixel value in the feature map, that is, the measured value of the reflected light intensity, the measured value of the reflected light color, and the measured value of the reflection area.

[0091] Step 140: Compare the feature measured data with the feature predicted data, and identify surface impurities of the ore to be tested based on the comparison result.

[0092] In this embodiment, the following steps may be performed for any target reflective surface:

[0093] If the error between the predicted value of the reflected light intensity and the measured value of the reflected light intensity is greater than the preset light intensity error, it is determined that the ore to be detected has impurities on the target reflection surface.

[0094] If the color difference between the predicted value of the reflected light color and the measured value of the reflected light color is greater than the preset color difference, it is determined that the ore to be detected has impurities on the target reflection surface.

[0095] If the error between the predicted reflection area value and the measured reflection area value is greater than a preset area error value, it is determined that the ore to be detected has impurities on the target reflection surface.

[0096] In this embodiment, due to the quality of the camera and the error of the algorithm, even if the surface of the ore to be detected does not contain impurities, the feature measured data and the feature predicted data will have errors. Therefore, it is necessary to perform error calculation based on the historical feature measured data and historical feature predicted data corresponding to the historical ore to be detected, and perform mean calculation on the error values ​​obtained each time to obtain the corresponding preset illumination intensity error, preset color difference value and preset area error value. When the feature measured data is less than or equal to the corresponding feature predicted data, it can be considered that there are no impurities on the surface of the ore to be detected.

[0097] Correspondingly, if there are impurities on the surface of the ore to be tested, the ore to be tested can be taken out by a mechanical arm installed on the testing equipment.

[0098] In summary, through the three-dimensional information of the ore to be detected, the optical characteristics of different types of ores are used as features to predict the optical characteristics of the ore to be detected, and the feature prediction data of the ore to be detected is obtained. The obtained feature prediction data is used as a benchmark, and then the image feature extraction technology is used to perform feature extraction and analysis on the image to be detected of the ore to be detected to obtain the measured data of the optical characteristics of the ore to be detected, that is, the feature measured data. By comparing the feature measured data with the feature predicted data as a benchmark, it can be effectively judged whether there are impurities on the ore surface.

[0099] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0100] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0101] Figure 3 The schematic diagram of the structure of the ore surface impurity identification device provided by the embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0102] like Figure 3 As shown, the ore surface impurity identification device 3 includes:

[0103] An acquisition module 31 is used to acquire the three-dimensional information, detection image and type of the ore to be detected;

[0104] Prediction module 32, used to determine characteristic prediction data of the ore to be detected based on the three-dimensional information and the type; wherein the characteristic prediction data includes a reflection light intensity prediction value, a reflection light color prediction value and a reflection area prediction value;

[0105] An extraction module 33 is used to extract feature measured data in the detection image;

[0106] The identification module 34 is used to compare the feature measured data with the feature predicted data, and identify the surface impurities of the ore to be detected based on the comparison result.

[0107] In a possible implementation, the three-dimensional data is determined based on structured light irradiated on the ore to be detected; the structured light is used to project an initial line structure on the ore to be detected; the three-dimensional data includes the line structure to be analyzed obtained after being projected on the surface of the ore to be detected;

[0108] The prediction module 32 is specifically used for:

[0109] Determine the degree of distortion of the line structure based on the initial line structure and the line structure to be analyzed;

[0110] Determine the curvature corresponding to each reflective surface of the ore to be detected based on the degree of distortion, and determine the reflection area prediction value of each target reflective surface according to the curvature corresponding to each reflective surface;

[0111] Determine the predicted value of the reflected light intensity of each target reflection surface of the ore to be detected based on the predicted value of the reflection area and curvature corresponding to each target reflection surface, as well as the type;

[0112] The predicted value of the color of the reflected light of the ore to be detected is determined based on the type.

[0113] In a possible implementation, the target reflective surface is a reflective surface whose predicted reflection area value is greater than a first preset threshold;

[0114] The prediction module 32 is specifically used for:

[0115] For any reflecting surface, if the curvature difference between the reflecting surface and other reflecting surfaces adjacent to the reflecting surface is less than a first preset difference, the reflecting surface and the reflecting surfaces adjacent to the reflecting surface whose curvature difference is less than the first preset difference are taken as target reflecting surfaces;

[0116] Based on the three-dimensional data of the reflecting surface and the reflecting surfaces adjacent to the reflecting surface, a predicted value of the reflecting area of ​​the target reflecting surface where the reflecting surface is located is determined.

[0117] In a possible implementation, the prediction module 32 is specifically configured to:

[0118] Determine the reflectivity of the ore to be tested based on its type;

[0119] For any target reflective surface, based on the preset illumination intensity and incident angle of the detection light, determine the predicted value of the initial reflected light intensity of the target reflective surface in the preset collection direction;

[0120] Determine a correction value of a predicted value of reflected light intensity of the target reflective surface in a preset collection direction according to predicted values ​​of reflection areas, curvatures and preset detection lights corresponding to other target reflective surfaces adjacent to the target reflective surface;

[0121] The predicted value of the reflected light intensity of the target reflective surface is obtained according to the initial predicted value of the reflected light intensity and the corrected value of the predicted value of the reflected light intensity.

[0122] In a possible implementation, the prediction module 32 is specifically configured to:

[0123] Determine, according to the predicted values ​​of the reflection areas and curvatures corresponding to other target reflection surfaces adjacent to the target reflection surface, the relative reflection angles and relative reflected light intensities of the other target reflection surfaces relative to the target reflection surface under the preset detection light;

[0124] According to the relative reflection angle and the relative reflected light intensity, a correction value of the predicted value of the reflected light intensity of the target reflective surface in the preset collection direction is determined.

[0125] In a possible implementation, the extraction module 33 is specifically configured to:

[0126] Inputting the image to be detected into a pre-trained extraction model to extract the reflection surface data of the ore to be detected in the image to be detected; wherein the reflection surface data includes a feature map corresponding to each target reflection surface;

[0127] Based on the reflection surface data, the feature measured data of each target reflection surface in the detection image is calculated; wherein the feature measured data includes the measured value of the reflected light intensity, the measured value of the reflected light color and the measured value of the reflection area.

[0128] In a possible implementation, the identification module 34 is specifically configured to:

[0129] Perform the following steps for any target reflective surface:

[0130] If the error between the predicted value of the reflected light intensity and the measured value of the reflected light intensity is greater than the preset light intensity error, it is determined that the ore to be tested has impurities on the target reflection surface;

[0131] If the color difference between the predicted color value of the reflected light and the actual color value of the reflected light is greater than the preset color difference, it is determined that the ore to be tested has impurities on the target reflection surface;

[0132] If the error between the predicted reflection area value and the measured reflection area value is greater than a preset area error value, it is determined that the ore to be detected has impurities on the target reflection surface.

[0133] Figure 4 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned ore surface impurity identification method embodiments are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 3 The functions of each module / unit are shown.

[0134] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 42 in the electronic device 4. For example, the computer program 42 may be divided into Figure 3 The modules / units shown.

[0135] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0136] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0137] The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used to store the computer program and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0138] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0139] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0141] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0144] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various ore surface impurity identification method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0145] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for identifying impurities on the surface of an ore, characterized in that: include: Obtain the three-dimensional information, detection image and type of the ore to be tested; Determine the characteristic prediction data of the ore to be detected based on the three-dimensional information and the type; wherein the characteristic prediction data includes a predicted value of reflected light intensity, a predicted value of reflected light color, and a predicted value of reflected area; Extracting feature measured data from the detection image; The characteristic measured data and the characteristic predicted data are compared, and the surface impurities of the ore to be detected are identified based on the comparison result.

2. The method for identifying impurities on the surface of an ore according to claim 1, characterized in that: The three-dimensional data is determined based on the structured light irradiated on the ore to be detected; the structured light is used to project an initial line structure on the ore to be detected; the three-dimensional data includes the line structure to be analyzed obtained after being projected on the surface of the ore to be detected; The step of determining the characteristic prediction data of the ore to be detected based on the three-dimensional information and the type includes: Determining the degree of distortion of the line structure based on the initial line structure and the line structure to be analyzed; Determine the curvature corresponding to each reflective surface of the ore to be detected based on the degree of distortion, and determine the reflection area prediction value of each target reflective surface according to the curvature corresponding to each reflective surface; Determine the predicted value of the reflected light intensity of each target reflection surface of the ore to be detected based on the predicted value of the reflection area and the curvature corresponding to each target reflection surface, as well as the type; A predicted value of the color of the reflected light of the ore to be detected is determined based on the type.

3. The method for identifying impurities on the surface of an ore according to claim 2, characterized in that: The target reflective surface is a reflective surface whose predicted reflection area value is greater than a first preset threshold; The step of determining the predicted reflection area value of each target reflection surface according to the curvature corresponding to each reflection surface includes: For any reflecting surface, if the curvature difference between the reflecting surface and other reflecting surfaces adjacent to the reflecting surface is less than a first preset difference, the reflecting surface and the reflecting surface adjacent to the reflecting surface whose curvature difference is less than the first preset difference are taken as target reflecting surfaces; Based on the three-dimensional data of the reflecting surface and the reflecting surfaces adjacent to the reflecting surface, a predicted value of the reflecting area of ​​the target reflecting surface where the reflecting surface is located is determined.

4. The method for identifying impurities on the surface of an ore according to claim 2, characterized in that: The step of determining the predicted value of the reflected light intensity of each target reflection surface of the ore to be detected based on the predicted value of the reflection area and the curvature corresponding to each target reflection surface, as well as the type, includes: Determining the reflectivity of the ore to be detected based on the type; For any target reflective surface, based on the preset illumination intensity and incident angle of the detection light, determine the predicted value of the initial reflected light intensity of the target reflective surface in the preset collection direction; Determine a correction value of the predicted value of the reflected light intensity of the target reflective surface in a preset collection direction according to the predicted values ​​of the reflection areas corresponding to other target reflective surfaces adjacent to the target reflective surface, the curvature and the preset detection light; The predicted value of the reflected light intensity of the target reflective surface is obtained according to the predicted value of the initial reflected light intensity and the corrected value of the predicted value of the reflected light intensity.

5. The method for identifying impurities on the surface of an ore according to claim 4, characterized in that: The method of determining a correction value of a predicted value of reflected light intensity of the target reflective surface in a preset collection direction according to predicted values ​​of reflection areas corresponding to other target reflective surfaces adjacent to the target reflective surface, curvatures and the preset detection light comprises: Determine, according to the predicted values ​​of reflection areas and curvatures corresponding to other target reflection surfaces adjacent to the target reflection surface, the relative reflection angles and relative reflected light intensities of the other target reflection surfaces relative to the target reflection surface under the preset detection light; According to the relative reflection angle and the relative reflected light intensity, a correction value of the predicted value of the reflected light intensity of the target reflective surface in the preset collection direction is determined.

6. The method for identifying impurities on the surface of an ore according to claim 1, characterized in that: The step of extracting the feature measured data from the detection image comprises: Inputting the image to be detected into a pre-trained extraction model to extract the reflection surface data of the ore to be detected in the image to be detected; wherein the reflection surface data includes a feature map corresponding to each target reflection surface; Based on the reflection surface data, characteristic measured data of each target reflection surface in the detection image is calculated; wherein the characteristic measured data includes a measured value of the intensity of the reflected light, a measured value of the color of the reflected light, and a measured value of the reflection area.

7. The method for identifying impurities on the surface of an ore according to claim 1, characterized in that: The step of comparing the measured characteristic data with the predicted characteristic data and identifying the surface impurities of the ore to be detected based on the comparison result includes: Perform the following steps for any target reflective surface: If the error between the predicted value of the reflected light intensity and the measured value of the reflected light intensity is greater than the preset light intensity error, it is determined that the ore to be detected has impurities on the target reflection surface; If the color difference between the predicted color value of the reflected light and the measured color value of the reflected light is greater than a preset color difference value, it is determined that the ore to be detected has impurities on the target reflection surface; If the error between the predicted reflection area value and the measured reflection area value is greater than a preset area error value, it is determined that the ore to be detected has impurities on the target reflection surface.

8. A device for identifying impurities on the surface of an ore, characterized in that: include: An acquisition module is used to obtain the three-dimensional information, detection images and types of the ore to be detected; A prediction module, used to determine the characteristic prediction data of the ore to be detected based on the three-dimensional information and the type; wherein the characteristic prediction data includes a predicted value of reflected light intensity, a predicted value of reflected light color and a predicted value of reflected area; An extraction module, used to extract feature measured data from the detection image; The identification module is used to compare the characteristic measured data with the characteristic predicted data, and identify the surface impurities of the ore to be detected based on the comparison result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images