Method for rapid assessment of recycled aggregate quality based on hyperspectral imaging

Abstract

This application provides a rapid quality assessment method for recycled aggregates based on hyperspectral imaging. The method acquires hyperspectral reflectance data of the recycled aggregates, determines the target region of the aggregate to be tested based on the hyperspectral reflectance data, and extracts the geometric morphology parameters of the target region. It assesses the dispersion of reflectance energy distribution based on the reflectance sequence of each pixel in the characteristic band, determining the spectral disorder index. Based on the spectral disorder distribution of each pixel within a preset spatial neighborhood, it performs spatial correlation analysis to determine the mortar adhesion persistence index. Based on the mortar adhesion persistence index, spectral evolution rate, and geometric morphology parameters, it calculates a comprehensive quality index and assesses the quality. This method significantly improves the robustness of mortar identification in complex environments, corrects optical deviations in irregularly shaped aggregates, and enables real-time and accurate rapid quality assessment of recycled aggregates.

Description

Technical Field

[0001] This application relates to the field of materials measurement, and more particularly to a rapid method for evaluating the quality of recycled aggregates based on hyperspectral imaging. Background Technology

[0002] The recycling of construction waste is a core aspect of resource regeneration. Recycled aggregate, as a recycled resource obtained from crushed waste concrete, directly determines the strength and durability of recycled concrete. The biggest difference between recycled aggregate and natural aggregate lies in the layer of old cement mortar covering its surface. The high porosity, high water absorption, and weak interfacial effect between the mortar and the aggregate matrix are the fundamental reasons for the performance fluctuations of recycled concrete.

[0003] In current industrial production lines, traditional chemical titration or physical crushing methods, due to their long testing cycles (usually several hours or even days), cannot achieve real-time quality monitoring. Existing machine vision solutions mostly use visible light color recognition, but because old mortar and some natural rocks are highly similar in color, and because of severe dust interference in the production site, the recognition accuracy is extremely low. Although hyperspectral imaging technology provides rich spectral dimensions, existing processing algorithms often treat the spectrum as a purely mathematical vector.

[0004] Furthermore, existing processing methods ignore the physical scattering characteristics of light caused by the porous structure of mortar. This results in the algorithm lacking robust evaluation criteria when facing mortar with uneven thickness and different shapes. Especially on high-speed conveyor belts, changes in the lighting environment and background dust often cause simple spectral feature matching to fail. Summary of the Invention

[0005] The following is an overview of the topics described in detail in this article.

[0006] The purpose of this application is to at least partially solve one of the technical problems existing in the related technologies. The embodiments of this application provide a rapid evaluation method for the quality of recycled aggregates based on hyperspectral imaging, so as to achieve a rapid evaluation of the quality of recycled aggregates with high precision and high robustness.

[0007] An embodiment of this application provides a rapid method for evaluating the quality of recycled aggregates based on hyperspectral imaging, comprising: Obtain hyperspectral reflectance data of recycled aggregate, determine the target area of ​​the aggregate to be tested based on the hyperspectral reflectance data, and extract the geometric morphology parameters corresponding to the target area. The dispersion of reflectance energy distribution is evaluated based on the reflectance sequence of each pixel in the target area under the characteristic band, and the spectral disorder index corresponding to each pixel in the target area is determined. Spatial correlation analysis is performed based on the spectral disorder distribution of each pixel in the target area within a preset spatial neighborhood to determine the mortar adhesion persistence index corresponding to each pixel in the target area. The comprehensive quality index of the aggregate to be tested is calculated based on the mortar adhesion persistence index, spectral evolution rate and geometric morphology parameters. The quality of the aggregate to be tested is evaluated based on the comprehensive quality index.

[0008] According to certain embodiments of this application, obtaining the hyperspectral reflectance data of recycled aggregate includes: The original brightness images of the recycled aggregate were acquired using a linear array pushbroom hyperspectral camera; The original brightness image was normalized and corrected using standard whiteboard reflectance and standard blackboard reflectance to obtain reflectance cube data as hyperspectral reflectance data of recycled aggregate.

[0009] According to certain embodiments of this application, extracting the geometric parameters corresponding to the target region includes: The sphericity factor corresponding to the target region is obtained as a geometric morphological parameter based on the ratio of the equivalent perimeter of the aggregate projection profile to the actual perimeter.

[0010] According to certain embodiments of this application, the dispersion of reflectance energy distribution is evaluated based on the reflectance sequence of each pixel in the target area under a characteristic band, and the spectral disorder index corresponding to each pixel in the target area is determined, including: Calculate the energy percentage of pixels in the target area under each characteristic band based on the reflectance sequence; Calculate the variance of reflectance of pixels within the target area across all feature bands based on the reflectance sequence; The spectral disorder index is calculated based on the energy proportion of pixels in the target area under each characteristic band and the variance of reflectance of pixels in the target area under all characteristic bands.

[0011] According to certain embodiments of this application, the spectral disorder index is expressed as: ; In the formula, This represents the spectral disorder index corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the energy percentage of pixel (i,j) in the k-th feature band. This represents the variance of reflectance of pixel (i,j) across all feature bands. Indicates the total number of characteristic bands. and These represent the row and column coordinates of a pixel, respectively.

[0012] According to certain embodiments of this application, spatial correlation analysis is performed based on the spectral disorder distribution of each pixel within the target area in a preset spatial neighborhood to determine the mortar adhesion persistence index corresponding to each pixel within the target area, including: Calculate the adaptive adjustment factor of the disorder mean of each pixel in the target area relative to all pixels in the spatial neighborhood window; Based on the adaptive adjustment factor, the spectral disorder index is accumulated using anisotropic diffusion kernels to obtain the mortar adhesion persistence index.

[0013] According to certain embodiments of this application, the mortar adhesion persistence index is expressed as follows: ; In the formula, Let (i,j) be the mortar adhesion persistence index corresponding to the pixel (i,j) in the i-th row and j-th column. Represents the neighborhood window Internal sampling coordinates are The spectral disorder index of pixels, This represents a preset spatial scale constant. This represents the adaptive adjustment factor corresponding to pixel (i,j). and These represent the row and column coordinates of a pixel, respectively.

[0014] According to certain embodiments of this application, a comprehensive quality index of the aggregate to be tested is calculated based on the mortar adhesion persistence index, spectral evolution rate, and geometric morphological parameters, including: Calculate the reflectance gradient of each pixel in the target area between adjacent bands, and determine the spectral evolution rate based on the reflectance gradient; The product of the mortar adhesion persistence index and the spectral evolution rate is summed within the target area. The summation result is then used to calculate the ratio of the product of the square of the sphericity factor and the total number of pixels to obtain the comprehensive quality index of the aggregate to be tested.

[0015] According to certain embodiments of this application, the overall quality index is expressed as: ; In the formula, As a comprehensive quality index, This represents the mortar adhesion persistence index corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the spectral evolution rate corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the total number of pixels within the target area. This represents the sphericity factor.

[0016] According to certain embodiments of this application, the step of evaluating the quality of the aggregate to be tested based on the comprehensive quality index includes: The comprehensive quality index is compared with a preset quality assessment threshold. If the comprehensive quality index is less than the first threshold in the quality assessment threshold, the recycled aggregate is determined to be of Grade 1 quality. If the comprehensive quality index is greater than the second threshold in the quality assessment threshold, the recycled aggregate is determined to be substandard and a rejection control signal is output. If the comprehensive quality index is not less than the first threshold and not greater than the second threshold, then the recycled aggregate is determined to be of secondary quality.

[0017] The above-mentioned scheme has at least the following beneficial effects: it can significantly improve the robustness of mortar identification in complex environments, correct the optical deviation of irregularly shaped aggregates, and complete the rapid evaluation of recycled aggregate quality in real time with high accuracy. By establishing a physical mapping between the spectral micro-response and the porous structure of the aggregate surface through the spectral disorder index, it solves the problem of traditional algorithms treating the spectrum as a purely mathematical vector and ignoring the physical background. By introducing anisotropic diffusion logic, it possesses adaptive suppression capabilities for isolated dust noise. Furthermore, by introducing the geometric sphericity parameter into the hyperspectral evaluation system, it eliminates the interference of irregularly shaped aggregates on the reflection path. The scheme is logically rigorous and computationally efficient, does not involve complex iterative processes, and can adapt to the high-speed sorting requirements of industrial sites, providing a reliable technical means for the high-value recycling of renewable resources. Attached Figure Description

[0018] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0019] Figure 1 This is a flowchart illustrating the steps of a rapid quality assessment method for recycled aggregates based on hyperspectral imaging. Figure 2 This is a diagram showing the sub-steps for obtaining hyperspectral reflectance data of recycled aggregates; Figure 3 It is a sub-step diagram that evaluates the dispersion of reflectance energy distribution based on the reflectance sequence of each pixel in the target area under the characteristic band, and determines the spectral disorder index corresponding to each pixel in the target area. Figure 4This is a sub-step diagram that uses spatial correlation analysis based on the spectral disorder distribution of each pixel in the target area within a preset spatial neighborhood to determine the mortar adhesion persistence index corresponding to each pixel in the target area. Figure 5 It is a sub-step diagram that calculates the comprehensive quality index of the aggregate to be tested based on the mortar adhesion persistence index, spectral evolution rate and geometric morphology parameters. Figure 6 This is a diagram showing the sub-steps for evaluating the quality of aggregates under test based on a comprehensive quality index. Figure 7 This is a distribution map of the physical characteristic indicators of the surface of recycled aggregate; Figure 8 This is a diagram analyzing the sustainability index of spatial flow mortar. Figure 9 This is a comparison chart of the evaluation results of the rapid quality assessment method for recycled aggregates based on hyperspectral imaging provided by this invention and the traditional spectral averaging method. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0021] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0022] The embodiments of this application provide a rapid evaluation method for the quality of recycled aggregates based on hyperspectral imaging. This method can directly map the porous diffuse reflection characteristics of mortar by constructing a spectral disorder index, and uses manifold diffusion logic to filter isolated noise. Combined with geometric morphology correction, it achieves a rapid evaluation of the quality of recycled aggregates with high precision and high robustness.

[0023] The embodiments of this application will be further described below with reference to the accompanying drawings.

[0024] Reference Figure 1 A rapid assessment method for the quality of recycled aggregates based on hyperspectral imaging includes the following steps: Step S100: Obtain hyperspectral reflectance data of recycled aggregate, determine the target area of ​​the aggregate to be tested based on the hyperspectral reflectance data, and extract the geometric morphology parameters corresponding to the target area. Step S200: Evaluate the dispersion of reflectance energy distribution based on the reflectance sequence of each pixel in the target area under the characteristic band, and determine the spectral disorder index corresponding to each pixel in the target area. Step S300: Based on the spectral disorder distribution of each pixel in the target area within the preset spatial neighborhood, perform spatial correlation analysis to determine the mortar adhesion persistence index corresponding to each pixel in the target area. Step S400: Calculate the comprehensive quality index of the aggregate to be tested based on the mortar adhesion persistence index, spectral evolution rate, and geometric morphology parameters. Step S500: Evaluate the quality of the aggregate to be tested based on the comprehensive quality index.

[0025] Reference Figure 2 For step S100, obtaining the hyperspectral reflectance data of the recycled aggregate includes the following steps: Step S111: Acquire the original brightness image of the recycled aggregate using a linear array pushbroom hyperspectral camera; Step S112: Normalize and correct the original brightness image using standard white board reflectance and standard black board reflectance to obtain reflectance cube data as hyperspectral reflectance data of recycled aggregate.

[0026] Specifically, a linear pushbroom hyperspectral camera was first used to sample the rapidly moving recycled aggregate on the conveyor belt in the near-infrared band from 900 nm to 1700 nm. Due to unstable lighting in industrial settings and interference from the dark current of the sensor itself, the directly acquired raw brightness image contained a large amount of noise. Therefore, the raw image was normalized and corrected using standard white board reflectance and standard black board reflectance to obtain reflectance cube data as the hyperspectral reflectance data of the recycled aggregate.

[0027] The target region of the aggregate to be tested is determined based on hyperspectral reflectance data. Specifically, geometric morphological parameters reflecting macroscopic physical properties can be extracted for each target region. The aggregate is retained by removing the conveyor belt background using an adaptive background thresholding method, thereby locking the target region of individual aggregates. Extracting the geometric parameters corresponding to the target region includes the following steps: The sphericity factor of the target area is obtained as a geometric morphology parameter based on the ratio of the equivalent perimeter of the aggregate projection profile to the actual perimeter.

[0028] Specifically, the total number of pixels within the target area is counted, and the sphericity factor is calculated. The sphericity factor is obtained by calculating the ratio of the equivalent perimeter of the aggregate's projected profile to its actual perimeter. For example, for an approximately circular aggregate, its sphericity factor is close to 1; while for a slender or irregularly shaped aggregate, since its actual perimeter is much larger than the perimeter of a circle of the same area, its sphericity factor will be significantly smaller. This parameter is used to correct the spectral reflectance energy deviation caused by the irregular shape of the aggregate in subsequent steps.

[0029] Thus, by acquiring and photophysically correcting hyperspectral data, and combining it with morphological parameter extraction, accurate data support can be provided for subsequent precise identification of mortar.

[0030] Reference Figure 3 For step S200, the dispersion of reflectance energy distribution is evaluated based on the reflectance sequence of each pixel in the target area under the characteristic band, and the spectral disorder index corresponding to each pixel in the target area is determined, including the following steps: Step S210: Calculate the energy percentage of pixels in the target area under each characteristic band based on the reflectance sequence; Step S220: Calculate the variance of reflectance of pixels in the target area under all feature bands based on the reflectance sequence; Step S230: Spectral disorder index is calculated based on the energy proportion of pixels in the target area under each characteristic band and the variance of reflectance of pixels in the target area under all characteristic bands.

[0031] The relationship between the spectral disorder index and the spectral disorder index is expressed as follows: ; In the formula, This represents the spectral disorder index corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the energy percentage of pixel (i,j) in the k-th feature band. This represents the variance of reflectance of pixel (i,j) across all feature bands. Indicates the total number of characteristic bands. and These represent the row and column coordinates of a pixel, respectively.

[0032] Specifically, old mortar, due to its loose physical structure and rich in micropores, causes light to undergo multiple diffuse reflections, resulting in a high-entropy spectral response. This affects the pixels within the target area. First, obtain its in Reflectance sequence under each characteristic band And calculate the normalized probability distribution. Then, the calculation was performed using the spectral disorder index relationship.

[0033] In the relation, the numerator uses information entropy to assess the uncertainty of the spectral energy distribution; the denominator uses the reflectance variance. Noise suppression is performed.

[0034] For example, suppose there are two pixels, pixel A in the mortar area and pixel B in the smooth pebble area, and a feature band is defined. .

[0035] The reflectance sequence of pixel A is The sum of the energy percentages is Normalized The sequence is approximately The molecular information entropy term is approximately calculated as follows: Due to the flat reflectivity, the variance Minimal, set to ,but The reflectance of pixel B is dominated by its mineral composition, and the sequence is as follows: The sum of the energy percentages is , The sequence is The numerator is approximately At this time, variance Larger, approximately The denominator is Calculations yielded It can be seen that the disorder index of the mortar zone is significantly higher than that of the gravel zone, successfully widening the characteristic spacing.

[0036] Thus, by constructing a spectral disorder index, the porous physical properties of mortar can be effectively transformed into assessable feature values, thereby improving the accuracy of identification.

[0037] Reference Figure 4 For step S300, spatial correlation analysis is performed based on the spectral disorder distribution of each pixel in the target area within a preset spatial neighborhood to determine the mortar adhesion persistence index corresponding to each pixel in the target area, including the following steps: Step S310: Calculate the adaptive adjustment factor of the disorder mean of each pixel in the target area relative to all pixels in the spatial neighborhood window; Step S320: Based on the adaptive adjustment factor, the spectral disorder index is accumulated using the anisotropic diffusion kernel to obtain the mortar adhesion persistence index.

[0038] The relationship between the mortar adhesion persistence index and the following formula is expressed as: ; In the formula, Let (i,j) be the mortar adhesion persistence index corresponding to the pixel (i,j) in the i-th row and j-th column. Represents the neighborhood window Internal sampling coordinates are The spectral disorder index of pixels, This represents a preset spatial scale constant. This represents the adaptive adjustment factor corresponding to pixel (i,j). and These represent the row and column coordinates of a pixel, respectively.

[0039] Due to isolated noise points caused by dust interference in industrial settings, spatial correlation analysis can be performed using manifold diffusion logic, combining the spectral disorder distribution of each pixel within a preset spatial neighborhood, to determine the mortar adhesion persistence index corresponding to each pixel. This index accumulates the disorder in the spatial neighborhood through anisotropic diffusion kernels, and is then calculated using the mortar adhesion persistence index relationship.

[0040] Adaptive adjustment factor Used to calculate the mean of the center point and its neighborhood. The difference adjusts the diffusion range. For example, suppose the center pixel is an isolated dust point, its... The mean of the surrounding background ,at this time Larger This will cause the denominator of the exponential term to become larger, making the diffusion kernel extremely wide and flat, thereby diluting the isolated point. The contribution of [the technology / method] effectively filters out false features, while in the real mortar connectivity region, When the value approaches 1, the signal can be effectively accumulated.

[0041] Thus, by using manifold diffusion logic for spatial correlation analysis, environmental noise can be autonomously identified and suppressed, ensuring that the identification results have real physical meaning.

[0042] Reference Figure 5 For step S400, the comprehensive quality index of the aggregate to be tested is calculated based on the mortar adhesion persistence index, spectral evolution rate, and geometric morphology parameters, including the following steps: Step S410: Calculate the reflectance gradient of each pixel in the target area between adjacent bands, and determine the spectral evolution rate based on the reflectance gradient. Step S420: Summing the product of mortar adhesion persistence index and spectral evolution rate within the target area, and calculating the ratio of the summation result to the product of the square of the sphericity factor and the total number of pixels to obtain the comprehensive quality index of the aggregate to be tested.

[0043] The relationship between the comprehensive quality index and the following formula is expressed as: ; In the formula, As a comprehensive quality index, This represents the mortar adhesion persistence index corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the spectral evolution rate corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the total number of pixels within the target area. This represents the sphericity factor.

[0044] Specifically, the reflectance gradient of each pixel in adjacent bands is calculated, and the spectral evolution rate is determined based on the reflectance gradient. Then, by integrating microscopic, spatial and macroscopic features, the comprehensive quality index of recycled aggregate is calculated based on the mortar adhesion persistence index, spectral evolution rate and geometric morphology parameters.

[0045] For example, the total number of pixels in the target area of ​​a certain aggregate to be tested is set. Due to its relatively regular shape but slightly angular, the sphericity factor... Measured as The average persistence index of pixels calculated by the design Average spectral evolution rate Then the numerator term denominator The final calculation yielded If the mortar on the surface of the aggregate increases, the mortar adhesion persistence index will rise; if the aggregate shape is more irregular, the Q value will further increase, and the system will determine its quality grade based on the preset threshold.

[0046] Reference Figure 6 For step S500, the quality of the aggregate to be tested is evaluated based on the comprehensive quality index, including the following steps: Step S510: Compare the overall quality index with the preset quality assessment threshold. Step S520: If the comprehensive quality index is less than the first threshold in the quality assessment threshold, the recycled aggregate is determined to be of Grade 1 quality. Step S530: If the comprehensive quality index is greater than the second threshold in the quality assessment threshold, the recycled aggregate is determined to be unqualified and a rejection control signal is output. Step S540: If the comprehensive quality index is not less than the first threshold and not greater than the second threshold, then the recycled aggregate is determined to be of secondary quality.

[0047] For example, a preset quality assessment threshold is set, such as a first threshold of 0.05 and a second threshold of 0.2. The calculated comprehensive quality index is compared with the quality assessment threshold. If the comprehensive quality index is less than 0.05, the recycled aggregate is determined to be of Grade 1 quality. If the comprehensive quality index is greater than 0.2, the recycled aggregate is determined to be of unqualified quality, and a rejection control signal is output. If the comprehensive quality index is not less than 0.05 and not greater than 0.2, the recycled aggregate is determined to be of Grade 2 quality.

[0048] like Figure 7 As shown, Figure 7 The diagram shows the distribution of physical characteristics of the surface of recycled aggregate in this application embodiment. As can be seen, the aggregate particles have clear edges and obvious color differences inside. The dark red highlighted areas correspond to the random attachment points of old mortar on the surface of the stones. Due to the introduction of the variance correction term, even if there is local reflection in the stone body, it will be represented as a cool color with low disorder in the diagram, which effectively achieves the separation of mortar and stones.

[0049] like Figure 8 As shown, Figure 8 This is a spatial manifold mortar sustainability index analysis diagram of an embodiment of this application. Through the manifold diffusion algorithm, the original scattered noise points in the image are smoothed and flattened, forming blocky connected regions with physical significance. The edges of these regions have natural transitions, showing the envelope morphology of the mortar layer on the aggregate surface.

[0050] like Figure 9 As shown, Figure 9 This is a comparison chart of the evaluation results of the rapid quality assessment method of recycled aggregate based on hyperspectral imaging provided by the present invention and the traditional spectral averaging method; the horizontal axis represents aggregate samples from different sources, and the vertical axis represents the identification accuracy. In the figure, the column of the present invention shows higher stability, while the column of the prior art shows a significant decrease in accuracy when facing samples with a lot of dust.

[0051] Thus, by generating a comprehensive quality index, objective and accurate aggregate grading conclusions can be given, providing a reliable basis for the automated sorting of recycled aggregates.

[0052] Embodiments of this application provide an electronic device. The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the rapid assessment method for the quality of recycled aggregate based on hyperspectral imaging as described above.

[0053] This electronic device can be any smart terminal, including computers.

[0054] In general, for the hardware structure of electronic devices, the processor can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, to execute relevant programs and implement the technical solutions provided in the embodiments of this application.

[0055] The memory can be implemented in the form of read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory and is called and executed by the processor.

[0056] Input / output interfaces are used to implement information input and output.

[0057] The communication interface is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0058] The bus transmits information between various components of a device, such as the processor, memory, input / output interfaces, and communication interfaces. The processor, memory, input / output interfaces, and communication interfaces communicate with each other within the device via the bus.

[0059] Embodiments of this application provide a computer storage medium. The computer storage medium stores computer-executable instructions for performing the rapid assessment method for recycled aggregate quality based on hyperspectral imaging as described above.

[0060] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium. In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0061] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0062] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0063] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0064] If the integrated unit is implemented as 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 technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0065] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed between each other may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms. Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0066] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for rapid assessment of recycled aggregate quality based on hyperspectral imaging, characterized by, include: Obtain hyperspectral reflectance data of recycled aggregate, determine the target area of ​​the aggregate to be tested based on the hyperspectral reflectance data, and extract the geometric morphology parameters corresponding to the target area. The dispersion of reflectance energy distribution is evaluated based on the reflectance sequence of each pixel in the target area under the characteristic band, and the spectral disorder index corresponding to each pixel in the target area is determined. Spatial correlation analysis is performed based on the spectral disorder distribution of each pixel in the target area within a preset spatial neighborhood to determine the mortar adhesion persistence index corresponding to each pixel in the target area. The comprehensive quality index of the aggregate to be tested is calculated based on the mortar adhesion persistence index, spectral evolution rate and geometric morphology parameters. The quality of the aggregate to be tested is evaluated based on the comprehensive quality index.

2. The method for rapid assessment of recycled aggregate quality based on hyperspectral imaging according to claim 1, characterized in that, The acquisition of hyperspectral reflectance data of recycled aggregate includes: The original brightness images of the recycled aggregate were acquired using a linear array pushbroom hyperspectral camera; The original brightness image was normalized and corrected using standard whiteboard reflectance and standard blackboard reflectance to obtain reflectance cube data as hyperspectral reflectance data of recycled aggregate.

3. The method for rapid assessment of recycled aggregate quality based on hyperspectral imaging according to claim 1, characterized in that, The extraction of geometric parameters corresponding to the target region includes: The sphericity factor corresponding to the target region is obtained as a geometric morphological parameter based on the ratio of the equivalent perimeter of the aggregate projection profile to the actual perimeter.

4. The method for rapid assessment of quality of recycled aggregates based on hyperspectral imaging as claimed in claim 1 wherein, The dispersion of reflectance energy distribution is evaluated based on the reflectance sequence of each pixel in the target area under the characteristic band, and the spectral disorder index corresponding to each pixel in the target area is determined, including: Calculate the energy percentage of pixels in the target area under each characteristic band based on the reflectance sequence; Calculate the variance of reflectance of pixels within the target area across all feature bands based on the reflectance sequence; The spectral disorder index is calculated based on the energy proportion of pixels in the target area under each characteristic band and the variance of reflectance of pixels in the target area under all characteristic bands.

5. The rapid quality assessment method for recycled aggregate based on hyperspectral imaging according to claim 4, characterized in that, The spectral disorder index is expressed as: ； In the formula, This represents the spectral disorder index corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the energy percentage of pixel (i,j) in the k-th feature band. This represents the variance of reflectance of pixel (i,j) across all feature bands. Indicates the total number of characteristic bands. and These represent the row and column coordinates of a pixel, respectively.

6. The rapid quality assessment method for recycled aggregate based on hyperspectral imaging according to claim 1, characterized in that, Spatial correlation analysis is performed based on the spectral disorder distribution of each pixel within the target area in a preset spatial neighborhood to determine the mortar adhesion persistence index corresponding to each pixel within the target area, including: Calculate the adaptive adjustment factor of the disorder mean of each pixel in the target area relative to all pixels in the spatial neighborhood window; Based on the adaptive adjustment factor, the spectral disorder index is accumulated using anisotropic diffusion kernels to obtain the mortar adhesion persistence index.

7. The rapid quality assessment method for recycled aggregate based on hyperspectral imaging according to claim 6, characterized in that, The mortar adhesion persistence index is expressed as follows: ； In the formula, Let (i,j) be the mortar adhesion persistence index corresponding to the pixel (i,j) in the i-th row and j-th column. Represents the neighborhood window Internal sampling coordinates are The spectral disorder index of pixels, This represents a preset spatial scale constant. This represents the adaptive adjustment factor corresponding to pixel (i,j). and These represent the row and column coordinates of a pixel, respectively.

8. The rapid quality assessment method for recycled aggregate based on hyperspectral imaging according to claim 1, characterized in that, Based on the mortar adhesion persistence index, spectral evolution rate, and geometric morphology parameters, the comprehensive quality index of the aggregate to be tested is calculated, including: Calculate the reflectance gradient of each pixel in the target area between adjacent bands, and determine the spectral evolution rate based on the reflectance gradient; The product of the mortar adhesion persistence index and the spectral evolution rate is summed within the target area. The summation result is then used to calculate the ratio of the product of the square of the sphericity factor and the total number of pixels to obtain the comprehensive quality index of the aggregate to be tested.

9. The rapid quality assessment method for recycled aggregate based on hyperspectral imaging according to claim 8, characterized in that, The comprehensive quality index is expressed as follows: ； In the formula, As a comprehensive quality index, This represents the mortar adhesion persistence index corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the spectral evolution rate corresponding to the pixel (i,j) in the i-th row and j-th column. This represents the total number of pixels within the target area. This represents the sphericity factor.

10. The rapid quality assessment method for recycled aggregate based on hyperspectral imaging according to claim 1, characterized in that, The evaluation of the quality of the aggregate under test based on the comprehensive quality index includes: The comprehensive quality index is compared with a preset quality assessment threshold. If the comprehensive quality index is less than the first threshold in the quality assessment threshold, the recycled aggregate is determined to be of Grade 1 quality. If the comprehensive quality index is greater than the second threshold in the quality assessment threshold, the recycled aggregate is determined to be substandard and a rejection control signal is output. If the comprehensive quality index is not less than the first threshold and not greater than the second threshold, then the recycled aggregate is determined to be of secondary quality.

Images