Slope change identification method and system based on image processing

Abstract

The invention provides a slope change identification method and system based on image processing, and relates to the technical field of data processing, and the method comprises the steps: obtaining a to-be-identified slope original image; preprocessing the original image of the slope; according to the preprocessed image, generating a corresponding image sequence through frame extraction processing; extracting a moving slope image in the image sequence through a background difference algorithm; measuring the displacement of the surface of the moving slope image through an LSPIV algorithm to obtain a displacement vector field; eliminating an error vector in the displacement vector field by using a vector filtering mode; calculating an actual displacement value of a missing position in the displacement vector field through a neighborhood interpolation method; and carrying out binary segmentation on the displacement vector field, and identifying and marking the range contour of the moving slope. According to the invention, cracks, foreign matters and the like in the slope image can be sensitively identified, and identification and monitoring of a complete change area of the slope are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a slope change recognition method and system based on image processing. Background Art

[0002] Image processing is a technical means of using computer algorithms to enhance, repair, and identify images. It is usually used to automatically extract features or changes in images. Slope change recognition refers to monitoring the status of slopes (such as hillsides, cliffs, mounds, etc.) through certain technical means to identify whether the slope has changed or changed. A slope change recognition method based on image processing uses image processing technology to identify and monitor changes in slopes.

[0003] Landslide, or slope change, refers to the phenomenon in which rocks, soil, and other slope components slide downward along a specific inclined surface under the action of gravity. It is a widespread and common geological disaster that is sudden and extremely destructive. Compared with other natural disasters such as earthquakes, typhoons, and tsunamis, the consequences are more serious. Therefore, identifying slope changes is an important measure to mitigate the impact of landslide disasters and protect people's lives and property. It is of great significance to reducing the losses caused by landslide disasters.

[0004] With the continuous advancement of science and technology, slope monitoring technologies are becoming increasingly diverse and intelligent. Video-based slope change recognition and monitoring methods offer advantages such as intuitive results and surface measurement. However, these methods often rely on manual analysis or a single image processing algorithm to detect slope monitoring images. This results in poor recognition accuracy and is not suitable for direct measurement of outdoor objects. It is difficult to accurately capture subtle slope changes, leading to errors in recognition results and significantly reducing the effectiveness of the monitoring system. Summary of the Invention

[0005] In order to solve the technical problems that the existing methods for identifying and monitoring slope changes based on video images mostly detect slope monitoring images through manual analysis and processing or a single image processing algorithm, the effect is not ideal, resulting in low recognition accuracy, and is not suitable for directly measuring outdoor objects. It is difficult to accurately capture subtle changes in the slope, resulting in errors in the recognition results, and the effectiveness of the monitoring system will be greatly reduced. The present invention provides a slope change identification method and system based on image processing.

[0006] The technical solutions provided by the embodiments of the present invention are as follows: First aspect An embodiment of the present invention provides a slope change recognition method based on image processing, comprising: S1: Obtain the original image of the slope to be identified; S2: preprocessing the original image of the slope; S3: Generate a corresponding image sequence based on the pre-processed original slope image through frame extraction processing; S4: Extract the moving slope image from the image sequence through background subtraction algorithm; S5: Using the LSPIV algorithm, the displacement of the moving slope image surface is measured to obtain the displacement vector field; S6: Use vector filtering to eliminate error vectors in the displacement vector field; S7: Calculate the actual displacement value of the missing position in the displacement vector field by nearest neighbor interpolation method; S8: Binarize and segment the displacement vector field to identify and mark the range contour of the moving slope.

[0007] Second aspect

[0008] An embodiment of the present invention provides a slope change recognition system based on image processing, comprising: processor; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the slope change recognition method based on image processing as described in the first aspect is implemented.

[0009] The third aspect

[0010] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the image processing-based slope change identification method according to the first aspect is implemented.

[0011] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In an embodiment of the present invention, the original image of the slope to be identified is obtained and preprocessed. Subsequently, an image sequence is generated by frame extraction, laying the foundation for the identification of dynamic changes. A moving image of the slope is extracted using a background difference algorithm. The LSPIV algorithm is then used to measure the displacement of the surface of the moving slope image to obtain a displacement vector field. Based on the displacement vector field, vector filtering is used to eliminate error vectors in the displacement vector field. The actual displacement values ​​of missing locations in the displacement vector field are calculated using a nearest neighbor interpolation method, thereby ensuring data integrity. Finally, the displacement vector field is binarized and segmented to identify and label the range outline of the moving slope. This ensures high efficiency and accuracy from image acquisition to change identification. The system can also handle image noise and errors, improve the reliability and real-time performance of the monitoring system, and effectively enhance recognition accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0013] Figure 1 A schematic flow chart of a slope change identification method based on image processing provided by an embodiment of the present invention; Figure 2 A schematic structural diagram of a slope change recognition system based on image processing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0015] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0016] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0017] Reference Manual Figure 1 , which shows a flow chart of a slope change identification method based on image processing provided by an embodiment of the present invention.

[0018] An embodiment of the present invention provides a slope change recognition method based on image processing. This method can be implemented by an image processing-based slope change recognition device, which can be a terminal or a server. The process flow of the image processing-based slope change recognition method may include the following steps: S1: Obtain the original image of the slope to be identified.

[0019] Raw slope images refer to unprocessed, original slope image data. These images may contain noise, uneven lighting, and other issues, requiring optimization through subsequent processing steps. Acquiring raw slope images provides the most direct and authentic data source for subsequent change identification. Raw images capture the true state of the on-site environment and reflect the slope's actual condition in its natural environment. The acquisition process ensures comprehensiveness and accuracy, providing a reliable foundation for subsequent image preprocessing, change detection, and analysis.

[0020] S2: Preprocess the original slope image.

[0021] Among them, preprocessing refers to the process of performing a series of improvements and optimizations on the original data before actual analysis in order to improve the effect of subsequent processing.

[0022] In a possible implementation, the preprocessing specifically includes: image grayscale preprocessing, image contrast enhancement preprocessing, and image denoising preprocessing.

[0023] Image grayscale preprocessing refers to the process of converting a color image into a grayscale image, reducing unnecessary color information, focusing on brightness information, and simplifying subsequent processing. Image contrast enhancement preprocessing refers to increasing the difference between image brightness and dark details, enhancing the visual effect of the image and making important features more prominent, facilitating subsequent processing and analysis. Image denoising preprocessing removes noise from the image caused by the shooting environment or equipment defects, ensuring cleaner and clearer image data, thereby improving the accuracy of subsequent processing.

[0024] S3: Generate a corresponding image sequence based on the pre-processed original slope image through frame extraction processing.

[0025] Frame extraction refers to the process of extracting specific frames from a continuous video or image sequence. It is often used to extract key frames in dynamic scenes to analyze changes at specific moments. An image sequence is a series of images arranged in chronological order, with each frame recording a scene over a continuous period of time. This can be used to analyze dynamic changes in objects or scenes.

[0026] It's important to note that frame extraction, which extracts key static images from a continuous image stream, allows subsequent change recognition to focus on changes at important moments. This approach effectively reduces redundant data while retaining essential dynamic information, making the recognition process more efficient. By generating an image sequence, frame-by-frame analysis of slope changes at different points in time can be performed, helping to accurately capture subtle displacements and deformations.

[0027] S4: Extract the moving slope image from the image sequence through the background difference algorithm.

[0028] The background subtraction algorithm is commonly used in video surveillance or dynamic image processing to detect differences between the background and foreground. It extracts moving objects (such as a moving slope) by comparing the current frame with a background model. A moving slope image is an image in which the background subtraction algorithm is used to extract the changing portions of an image sequence, reflecting the motion or deformation of the slope.

[0029] It's important to note that the background subtraction algorithm effectively extracts moving slope regions from image sequences, which is crucial for identifying dynamically changing slopes. By comparing the current image with the background model, the background subtraction algorithm automatically identifies changing slope regions, eliminating the need for manual intervention and improving computational speed.

[0030] In a possible implementation, S4 specifically includes: S401: Establishing a background model of the original slope image by using the pixel mean method.

[0031] The pixel mean method is a statistical method that calculates the average value of a group of pixels to obtain a representative value. In image processing, the mean method is often used to process certain image features, such as the average pixel value, as a background model or reference value. The background model refers to the mathematical model used to represent the static background portion of an image in background subtraction algorithms.

[0032] S402: Calculate the pixel difference between the original slope image and the background model to generate a differential image.

[0033] A difference image is an image obtained by calculating the pixel differences between the original image and a background model. This image highlights areas of change, such as moving slopes, and is often used to extract the foreground (moving areas) and ignore the background.

[0034] S403: Optimizing the maximum inter-class variance method through a genetic algorithm to perform foreground and background segmentation on the differential image.

[0035] The maximum inter-class variance method is an image threshold segmentation method that aims to automatically determine the optimal segmentation threshold by maximizing the variance between the foreground and background. This method assumes that the pixel value distribution of the foreground and background in the image is bimodal. It seeks a threshold that minimizes the intra-class variance of the background and foreground and maximizes the inter-class variance, thereby achieving effective image segmentation. Segmentation involves dividing an image into multiple regions or parts, typically based on certain characteristics (such as color, brightness, or texture).

[0036] S404: Based on the difference image after the foreground and background segmentation processing, extract the moving slope image in the difference image through morphological operation.

[0037] Morphological operations are image processing methods based on set theory that are used to extract structural features from images. Common morphological operations include erosion, dilation, opening, and closing. Morphological operations are primarily used to manipulate geometric shapes in images to remove noise, connect broken regions, or segment connected regions.

[0038] In this paper, morphological operations are combined to further improve the accuracy of extracting slope change regions in images, removing noise and enhancing the true change areas. This not only improves recognition accuracy but also reduces errors caused by environmental interference, making subsequent analysis more precise and efficient.

[0039] In a possible implementation, S403 specifically includes: S4031: Generate the initial population, set the population size, maximum number of iterations and crossover probability.

[0040] Here, each individual in the population represents a threshold.

[0041] S4032: Calculate the first fitness value of all individuals in the initial population with the goal of maximizing the between-class variance:

[0042] in, f ( i )1 means the i The first fitness value of the threshold, X i Indicates the i The pixel gray value of the threshold, Y q Indicates the q The features of the segmented region, , r Indicates the number of categories of foreground or background after segmentation.

[0043] S4033: According to the fitness value, select individuals with higher fitness value to form the optimal initial population.

[0044] S4034: Perform crossover and mutation operations on the optimal initial population to obtain a mutant population.

[0045] S4035: Calculate the second fitness value of each individual in the mutant population:

[0046] in, f ( i)2 means the i The second fitness value of the threshold, x ik Indicates the i The threshold value is k The grayscale value of a pixel.

[0047] S4036: According to the second fitness value, retain the mutant individual with the highest fitness.

[0048] S4037: Determine whether the mutant individual with the highest fitness meets the constraint conditions; if so, proceed to step S4036, otherwise return to step S4032.

[0049] S4038: When the maximum number of iterations is reached, the mutant individual with the highest fitness is output as the segmentation threshold.

[0050] It's important to note that genetic algorithms can gradually optimize image segmentation thresholds. Through crossover, mutation, and fitness evaluation, they can find the optimal image threshold within a given range, achieving optimal foreground-background separation. These steps can effectively improve image segmentation quality, particularly in tasks like slope change identification, where they can enhance the accuracy and robustness of image recognition.

[0051] In a possible implementation, S404 specifically includes: S4041: Remove noise from the background image through corrosion operation:

[0052] in, Indicates the differential image after corrosion at position The pixel value at Indicates the midpoint of the image The pixel value at Represents the points inside the structural unit matrix The pixel value at .

[0053] It should be noted that, in contrast to dilation, the erosion operation will change the pixel values ​​of all points within a certain range on the boundary between the foreground and background to 0 according to the size of the kernel. Intuitively, it can achieve the effect of eliminating noise and separating two contacting objects.

[0054] S4042: Dilate the differential image to extract the moving slope image:

[0055] in, Indicates that the differential image after expansion is at position The pixel value at Indicates the midpoint of the image The pixel value at Represents the points inside the structural unit matrix The pixel value at .

[0056] It should be noted that basic morphological operations include dilation, erosion, opening, and closing, which can achieve a variety of effects, such as changing image morphology, feature extraction, and noise removal. The dilation operation changes the pixel values ​​of all points within a certain range on the boundary between the foreground and background to a preset value based on the size of the structural unit. This can expand the area of ​​the foreground region in the image (the white portion in a binary image), reduce the gaps between different foreground parts, and make the contours of the changed area detected by the background difference algorithm appear fuller.

[0057] S5: Using the LSPIV algorithm, the displacement of the moving slope image surface is measured to obtain the displacement vector field.

[0058] The Large Scale Particle Image Velocimetry (LSPIV) algorithm is an image-based motion measurement technology used to obtain displacement information for each point on the surface of an object in an image. It tracks particles or feature points in the image to calculate their motion trajectories. It is commonly used in fluid dynamics and ground deformation monitoring. A displacement vector field is a field composed of multiple vectors in which the displacement of each point in an image or spatial region can be represented by a vector (including direction and magnitude). Each vector represents the displacement of an object or surface at a specific location relative to a reference position, typically expressed as displacement components along the x- and y-axes.

[0059] It's important to note that the LSPIV algorithm accurately measures displacements in slope images and aligns the physical world with the image coordinate system through a three-dimensional mapping relationship. This process not only accurately locates slope changes but also effectively converts these changes in three-dimensional space into image data, providing a reliable basis for subsequent analysis.

[0060] In a possible implementation, S5 specifically includes: S501: Establishing a physical coordinate system corresponding to the original image of the slope ( X , Y , Z ) and the image coordinate system corresponding to the moving slope image ( x , y ) to achieve the registration of the original slope image and the moved slope image:

[0061] in, A Represents the transformation matrix.

[0062] S502: Based on the change of slope gradient, establish the slope surface equation:

[0063] in, Z represents the slope surface equation, D 1 means X The coefficient of coordinate correlation, D 2 means Y The coefficient of coordinate correlation, D 3 means Z Coordinate correlation coefficient.

[0064] S503: Adjust the three-dimensional mapping relationship according to the slope surface equation:

[0065] B Represents the adjusted transformation matrix.

[0066] S504: Divide the adjusted moving slope image and the original slope image into multiple calculation windows.

[0067] S505: Calculate the similarity of each window between the adjusted moving slope image and the original image using the normalized cross-correlation method:

[0068] in, represents the normalized cross-correlation coefficient, Indicates that the moving slope image is at position The pixel value at Indicates that the moving slope image is at position After displacement The pixel value after I Represents an image function.

[0069] S506: Complete window matching based on the similarity.

[0070] S507: Calculate the displacement between the pixels at the window position and generate a displacement vector field.

[0071] It's important to note that the improved LSPIV method corrects image distortion by introducing a three-dimensional mapping relationship. This is particularly true at shallow tilt angles, where traditional two-dimensional image transformation methods are not sufficiently accurate. Especially when the shooting angle is near horizontal, this precise registration and displacement measurement can accurately track subtle changes in the slope surface, improving the accuracy of change detection. This has important applications in dynamic monitoring and disaster warning.

[0072] S6: Use vector filtering to eliminate error vectors in the displacement vector field.

[0073] Vector filtering is a filtering method applied to the displacement vector field. It aims to detect and remove erroneous vectors (such as unreasonable displacements caused by image noise or mismatching). These erroneous vectors may not conform to the actual situation, such as abnormally large displacement values ​​or vectors with incorrect directions. These errors may be caused by factors such as noise, shadows, lighting changes, and calculation errors, and need to be eliminated through vector filtering.

[0074] It's important to note that vector filtering effectively removes erroneous vectors from the displacement vector field, improving the accuracy and reliability of slope change identification. During slope monitoring, erroneous displacement vectors may appear due to factors such as lighting variations, camera jitter, and image matching errors. Without filtering, these erroneous vectors can lead to inaccurate change identification results, compromising subsequent slope risk assessment.

[0075] In a possible implementation, S6 specifically includes: S601: Calculate the difference between each vector in the displacement vector field and the neighboring vectors:

[0076] in, d i Indicates the i The displacement vector and the j The Euclidean distance between displacement vectors, v xi Indicates the i The displacement vector in x The displacement value in the direction, v xj Indicates the neighborhood j The displacement vector in x The displacement value in the direction, v yi Indicates the i The displacement value of the displacement vector in the y direction, v yj Indicates the neighborhood j The displacement vector in y The displacement value in the direction.

[0077] S602: Determine the mean and standard deviation of the neighborhood vector based on the difference:

[0078] in, represents the mean of the neighborhood vector,n represents the total number of displacement vectors in the neighborhood, Indicates the neighborhood j displacement vectors, represents the standard deviation of the neighborhood vector, C Represents a neighborhood.

[0079] S603: Eliminate the erroneous vector based on the difference and the standard deviation if the vector is an erroneous vector.

[0080] It should be noted that erroneous vectors can lead to incorrect change identification results, affecting subsequent slope risk assessment. By calculating the mean and standard deviation of neighborhood vectors, it is possible to accurately determine which vectors are outliers and remove them, thereby ensuring the stability and authenticity of the displacement vector field.

[0081] S7: Calculate the actual displacement value of the missing position in the displacement vector field through the nearest neighbor interpolation method.

[0082] Among them, near-neighbor interpolation is a method that uses information from the nearest neighboring data points to infer missing values. For example, inverse distance weighted interpolation (IDW) or kriging interpolation can reasonably estimate the value of missing data points, making the data more complete. The actual displacement value is the final displacement value of the missing point calculated through interpolation, including displacement in the x-direction and y-direction. It is used to complete the displacement vector field, making it closer to the actual slope movement.

[0083] It should be noted that inverse distance weighted interpolation is used to fill missing data in the displacement vector field to improve data integrity. In slope change identification, after filtering out erroneous vectors, some missing data points may be generated. If not filled, the displacement field will be broken, affecting subsequent analysis and modeling. Therefore, interpolation methods are needed to fill these missing values ​​to ensure data integrity and smoothness, making slope change identification more accurate.

[0084] In a possible implementation, S7 specifically includes: S701: Determine the missing position according to the position of the error vector.

[0085] S702: Calculate the weight of each point in the neighborhood of the error vector using the inverse distance weighting method:

[0086] in, w j Indicates the j The weight of the point, x i Indicates interpolation points i exist x The coordinate value in the direction,y i Indicates interpolation points i exist y The coordinate value in the direction, x j Represents neighborhood points j exist x The coordinate value in the direction, y j Represents neighborhood points j exist y The coordinate value in the direction, Represents the decay exponent.

[0087] S703: Determine the actual displacement value of the missing position based on the weight:

[0088] in, v xi Indicates interpolation points exist x The interpolated displacement results in the direction, v yi Indicates interpolation points exist y The interpolated displacement results in the direction.

[0089] S704: Update the actual displacement value to the missing position.

[0090] Furthermore, the inverse distance weighted interpolation method uses the displacement information of known data points, combined with the distance weights between them and the missing points, to calculate the most likely displacement value, effectively filling in the missing information. Furthermore, this method exhibits good smoothness, avoiding discontinuities in the interpolated data and making the overall trend of slope changes clearer and more realistic. Compared to other interpolation methods (such as linear interpolation), inverse distance weighted interpolation is more adaptable to the heterogeneity of geological changes, can improve the accuracy of slope change identification, and assist in monitoring potential risks such as slope slip and subsidence.

[0091] S8: Binarize and segment the displacement vector field to identify and mark the range contour of the moving slope.

[0092] Binarization segmentation involves converting the image's pixel values ​​into a binary representation of 0 or 1, where 1 represents moving areas (i.e., portions of the slope that are changing) and 0 represents stationary areas (i.e., portions of the slope that remain unchanged). Through binarization, morphological processing, and contour extraction, the slope's range of motion is accurately identified, making the changing areas more clearly visible. Binarization segmentation effectively highlights the changing areas, making the slope's motion information easier to analyze.

[0093] In a possible implementation, S8 specifically includes: S801: Calculate the modulus of each vector in the displacement vector field:

[0094] in, M i Indicates the i The modulus of the displacement vector, Indicates the i The magnitude of the displacement vector.

[0095] S802: Convert the displacement vector field into a binary image using an adaptive threshold method:

[0096] in, B i Indicates the binary image i The value of the pixel, 1 represents a moving slope, 0 represents a stationary slope, T Indicates the threshold value.

[0097] S803: Perform morphological processing on the binary image to eliminate noise:

[0098] in, B processed represents the binary image after morphological processing, B represents the original binary image, represents the corrosion operation, SE Represents a structural element, Represents an expansion operation.

[0099] S804: Using the contour extraction algorithm, extract the range contour of the moving slope:

[0100] in, Contours Represents the extracted range contour set, findContours Represents the contour extraction function.

[0101] It should be noted that the adaptive threshold method ensures the stability and accuracy of recognition results under varying lighting and environmental conditions. Morphological processing removes spurious change regions caused by noise or misdetection, making recognition more precise. It also fills in missed small change regions, improving recognition integrity. The contour extraction algorithm visualizes the slope change regions, more intuitively demonstrating their size and shape, providing clearer boundary information for subsequent risk assessment and disaster warning. These optimization measures work together to make slope change identification more accurate and robust, improving the reliability and practical application value of the slope monitoring system.

[0102] This invention combines background subtraction technology with LSPIV technology to enhance comprehensive identification of slope changes. The former boasts faster computational speeds and can process high-frame-rate video in real time, enabling sensitive and real-time identification of subtle slope changes. The latter calculates high-resolution velocity vector fields, effectively identifying and measuring areas of overall slope displacement.

[0103] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In an embodiment of the present invention, the original image of the slope to be identified is obtained and preprocessed. Subsequently, an image sequence is generated by frame extraction, laying the foundation for the identification of dynamic changes. A moving image of the slope is extracted using a background difference algorithm. The LSPIV algorithm is then used to measure the displacement of the surface of the moving slope image to obtain a displacement vector field. Based on the displacement vector field, vector filtering is used to eliminate error vectors in the displacement vector field. The actual displacement values ​​of missing locations in the displacement vector field are calculated using a nearest neighbor interpolation method, thereby ensuring data integrity. Finally, the displacement vector field is binarized and segmented to identify and label the range outline of the moving slope. This ensures high efficiency and accuracy from image acquisition to change identification. The system can also handle image noise and errors, improve the reliability and real-time performance of the monitoring system, and effectively enhance recognition accuracy and efficiency.

[0104] Reference Manual Figure 2 , which shows a structural schematic diagram of a slope change identification system based on image processing provided by the present invention.

[0105] The present invention further provides a slope change recognition system 20 based on image processing, which is applied to the above-mentioned slope change recognition method based on image processing, comprising: Processor 201.

[0106] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201 , the slope change recognition method based on image processing as described in the method embodiment is implemented.

[0107] The image processing-based slope change identification system 20 provided in the present invention can execute the above-mentioned image processing-based slope change identification method and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate on them.

[0108] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In an embodiment of the present invention, the original image of the slope to be identified is obtained and preprocessed. Subsequently, an image sequence is generated by frame extraction, laying the foundation for the identification of dynamic changes. A moving image of the slope is extracted using a background difference algorithm. The LSPIV algorithm is then used to measure the displacement of the surface of the moving slope image to obtain a displacement vector field. Based on the displacement vector field, vector filtering is used to eliminate error vectors in the displacement vector field. The actual displacement values ​​of missing locations in the displacement vector field are calculated using a nearest neighbor interpolation method, thereby ensuring data integrity. Finally, the displacement vector field is binarized and segmented to identify and label the range outline of the moving slope. This ensures high efficiency and accuracy from image acquisition to change identification. The system can also handle image noise and errors, improve the reliability and real-time performance of the monitoring system, and effectively enhance recognition accuracy and efficiency.

[0109] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), but may also be 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. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0110] It should also be understood that the memory in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0111] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). A computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0112] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0113] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0114] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not 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 embodiments of the present invention.

[0115] 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. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0116] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, 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, and can be electrical, mechanical, or other forms.

[0118] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0119] 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.

[0120] If a function 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 the present invention, or the portion that contributes to the prior art, or the portion 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 several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0121] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the image processing-based slope change identification method according to the method embodiment is implemented.

[0122] The computer-readable storage medium provided by the present invention can implement the steps and effects of the slope change identification method based on image processing of the above method embodiment. To avoid repetition, the present invention will not elaborate on them.

[0123] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In an embodiment of the present invention, the original image of the slope to be identified is obtained and preprocessed. Subsequently, an image sequence is generated by frame extraction, laying the foundation for the identification of dynamic changes. A moving image of the slope is extracted using a background difference algorithm. The LSPIV algorithm is then used to measure the displacement of the surface of the moving slope image to obtain a displacement vector field. Based on the displacement vector field, vector filtering is used to eliminate error vectors in the displacement vector field. The actual displacement values ​​of missing locations in the displacement vector field are calculated using a nearest neighbor interpolation method, thereby ensuring data integrity. Finally, the displacement vector field is binarized and segmented to identify and label the range outline of the moving slope. This ensures high efficiency and accuracy from image acquisition to change identification. The system can also handle image noise and errors, improve the reliability and real-time performance of the monitoring system, and effectively enhance recognition accuracy and efficiency.

[0124] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0125] There are a few points to note: (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0126] (2) For the sake of clarity, the thickness of layers or regions in the drawings used to describe the embodiments of the present invention are exaggerated or reduced, that is, these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly on" or "under" the other element or intervening elements may be present.

[0127] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to form new embodiments.

[0128] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A slope change recognition method based on image processing, characterized in that: include: S1: Obtain the original image of the slope to be identified; S2: preprocessing the original image of the slope; S3: Generate a corresponding image sequence based on the pre-processed original slope image through frame extraction processing; S4: extracting a moving slope image from the image sequence by a background difference algorithm; S5: Using the LSPIV algorithm, the displacement of the moving slope image surface is measured to obtain the displacement vector field; S6: using a vector filtering method to eliminate error vectors in the displacement vector field; S7: Calculating actual displacement values ​​of missing positions in the displacement vector field by a nearest neighbor interpolation method; S8: performing binary segmentation on the displacement vector field to identify and mark the range outline of the moving slope.

2. The slope change identification method based on image processing according to claim 1 is characterized in that: The preprocessing specifically includes: image grayscale preprocessing, image contrast enhancement preprocessing and image denoising preprocessing.

3. The slope change identification method based on image processing according to claim 1 is characterized in that: The S4 specifically includes: S401: Establishing a background model of the original slope image by using a pixel mean method; S402: Calculating pixel differences between the original slope image and the background model to generate a differential image; S403: Optimizing the maximum inter-class variance method through a genetic algorithm to perform foreground and background segmentation on the difference image; S404: Based on the difference image after the foreground and background segmentation processing, extract the moving slope image in the difference image through morphological operation.

4. The slope change identification method based on image processing according to claim 3 is characterized in that: The S404 specifically includes: S4041: Remove noise from the background image through corrosion operation: in, Indicates the differential image after corrosion at position The pixel value at Indicates the midpoint of the image The pixel value at Represents the points inside the structural unit matrix The pixel value at ; S4042: Perform expansion processing on the differential image to extract the moving slope image: in, Indicates that the differential image after expansion is at position The pixel value at Indicates the midpoint of the image The pixel value at Represents the points inside the structural unit matrix The pixel value at .

5. The slope change identification method based on image processing according to claim 1 is characterized in that: The S5 specifically includes: S501: Establishing a physical coordinate system corresponding to the original image of the slope ( X , Y , Z ) and the image coordinate system corresponding to the moving slope image ( x , y ) to achieve registration of the slope original image and the moved slope image: in, A represents the transformation matrix; S502: Based on the change of slope gradient, establish the slope surface equation: in, Z represents the slope surface equation, D 1 means X The coefficient of coordinate correlation, D 2 means Y The coefficient of coordinate correlation, D 3 means Z Coefficient of coordinate correlation; S503: Adjust the three-dimensional mapping relationship according to the slope surface equation: B Represents the adjusted transformation matrix; S504: Dividing the adjusted moving slope image and the original slope image into multiple calculation windows; S505: Calculate the similarity of each window between the adjusted moving slope image and the original image by using the normalized cross-correlation method: in, represents the normalized cross-correlation coefficient, Indicates that the moving slope image is at position The pixel value at Indicates that the moving slope image is at position After displacement The pixel value after I represents an image function; S506: completing the window matching according to the similarity; S507: Calculate the displacement between the pixels at the window position to generate the displacement vector field.

6. The slope change identification method based on image processing according to claim 1 is characterized in that: The S6 specifically includes: S601: Calculate the difference between each vector in the displacement vector field and the neighboring vectors: in, d i Indicates the i The displacement vector and the j The Euclidean distance between displacement vectors, v xi Indicates the i The displacement vector in x The displacement value in the direction, v xj Indicates the neighborhood j The displacement vector in x The displacement value in the direction, v yi Indicates the i The displacement value of the displacement vector in the y direction, v yj Indicates the neighborhood j The displacement vector in y Displacement value in direction; S602: Determine the mean and standard deviation of the neighborhood vector based on the difference: in, represents the mean of the neighborhood vector, n represents the total number of displacement vectors in the neighborhood, Indicates the neighborhood j displacement vectors, represents the standard deviation of the neighborhood vector, C represents the neighborhood; S603: Eliminate the erroneous vector according to the difference and the standard deviation if the vector is an erroneous vector.

7. The slope change identification method based on image processing according to claim 1 is characterized in that: The S7 specifically includes: S701: Determine the missing position according to the position of the error vector; S702: Calculate the weight of each point in the neighborhood of the error vector using an inverse distance weighted method; S703: Determine the actual displacement value of the missing position according to the weight; S704: Update the actual displacement value to the missing position.

8. The slope change identification method based on image processing according to claim 1 is characterized in that: The S8 specifically includes: S801: Calculating the modulus of each vector in the displacement vector field; S802: Converting the displacement vector field into a binary image using an adaptive threshold method; S803: performing morphological processing on the binary image to eliminate noise; S804: Using a contour extraction algorithm, extract the range contour of the moving slope.

9. A slope change recognition system based on image processing, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the slope change identification method based on image processing according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the slope change identification method based on image processing according to any one of claims 1 to 8 is implemented.

Images