Slag stone block particle size detection device and method based on linear array camera scanning

Abstract

The invention provides a slag stone block particle size detection device and method based on linear array camera scanning. The invention discloses a slag stone block particle size detection method based on line-scan digital camera scanning. The method comprises the following steps: acquiring an original image of a slag stone block in a slag car by using a line-scan digital camera; the obtained original image is preprocessed; extracting contour and size information of the slag stone block; carrying out detection and particle size calculation on the slag stone block by utilizing a PointRCNN algorithm; transmitting the calculated particle size data to a control terminal and displaying the particle size data in real time; according to the invention, the high-resolution original image collected by the linear array camera provides a basis for the subsequent accurate measurement of the particle size of the slag stone block, the PointRCNN algorithm is utilized to detect the slag stone block and calculate the particle size, the PointRCNN algorithm can quickly process point cloud data, and quick and accurate real-time measurement is realized.

Description

Technical Field

[0001] The invention belongs to the technical field of tunnel blasting construction, and in particular relates to a device and method for detecting particle size of slag blocks based on linear array camera scanning. Background Art

[0002] In the construction of mining tunnels, blasting excavation is the core link, and the blasting effect directly affects the construction progress, cost and safety. The particle size distribution of blasting slag is one of the important indicators to measure the blasting effect. Reasonable particle size distribution helps to improve the slag discharge efficiency, reduce the workload of secondary crushing, and reduce dust generation.

[0003] Studies have shown that blasting parameters such as blasthole diameter, density coefficient and explosive consumption have a significant impact on the particle size distribution of blasted slag. For example, larger blasthole diameters and higher blasthole density coefficients can usually produce a more uniform particle size distribution of slag and reduce the generation of fine powdery rock particles.

[0004] However, current particle size detection methods mostly rely on manual measurement or simple image recognition technology, which has problems such as low efficiency, poor accuracy, and strong subjectivity, and it is difficult to meet the needs of fast and accurate detection at construction sites.

[0005] Therefore, it is particularly important to develop a technology that can quickly and accurately measure the particle size of slag blocks. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a device and method for detecting the particle size of slag blocks based on line array camera scanning, which can quickly and accurately measure the particle size of slag blocks.

[0007] The technical solution of the present invention is: a method for detecting the particle size of slag blocks based on line array camera scanning, comprising the following steps:

[0008] The original image of the slag blocks in the slag truck is obtained by using a linear array camera;

[0009] Preprocessing the acquired original image;

[0010] Extract the contour and size information of the slag rock block;

[0011] The PointRCNN algorithm is used to detect slag blocks and calculate their particle size;

[0012] The calculated particle size data is transmitted to the control terminal and displayed in real time.

[0013] Furthermore, the acquired original image is preprocessed, including:

[0014] Grayscale the original image;

[0015] The original image after grayscale processing is filtered and denoised to obtain a preprocessed image.

[0016] Furthermore, the contour and size information of the slag block is extracted, including:

[0017] Perform edge detection on the preprocessed image using edge detection algorithm;

[0018] The contour of the slag block is extracted using the contour extraction algorithm.

[0019] Furthermore, extracting the contour and size information of the slag rock block also includes:

[0020] For complex backgrounds, mathematical morphological operations are used to remove noise and interference to obtain a post-processed image; then edge detection and contour extraction are performed on the post-processed image.

[0021] Furthermore, the mathematical morphology operation includes: a dilation operation and an erosion operation.

[0022] Furthermore, the edge detection algorithm includes a Canny algorithm, and the contour extraction algorithm includes a findContours algorithm of OpenCV.

[0023] Furthermore, the PointRCNN algorithm is used to detect the slag block and calculate the particle size, which also includes:

[0024] Convert the extracted contour of the slag block into point cloud data;

[0025] The point cloud data is processed using the PointRCNN algorithm to detect the bounding box of the slag block;

[0026] Calculate the particle size parameters of the slag block based on the detected bounding box;

[0027] The pixel size in the image is converted to the actual physical size through the calibration method.

[0028] Furthermore, the point cloud data are processed using the PointRCNN algorithm to detect the bounding box of the slag block, which includes two stages;

[0029] The first stage is to extract features from point cloud data based on the PointNet++ network, thereby obtaining foreground points in the point cloud data and obtaining candidate bounding boxes for slag blocks;

[0030] In the second stage, the position and orientation of the candidate bounding box obtained in the first stage are optimized and converted to the local coordinate system to obtain the bounding box of the slag block.

[0031] The device for detecting particle size of slag blocks based on scanning by a linear array camera comprises:

[0032] Linear array camera module, used to obtain the original image of the slag blocks in the slag truck;

[0033] An image processing module, which is connected to the linear array camera module and is used to pre-process the acquired original image and extract the contour and size information of the slag rock block;

[0034] A particle size calculation module, which is connected to the image processing module and is used to detect and calculate the particle size of the slag block using the PointRCNN algorithm;

[0035] The data transmission and display module and the particle size calculation module are used to receive the particle size data calculated by the particle size calculation module and transmit it to the control terminal for real-time display.

[0036] Furthermore, the linear array camera module has a linear array camera installed on the top of the tunnel, and the linear array camera is used to collect original images of slag blocks in the slag truck below it.

[0037] Beneficial effects of the present invention:

[0038] (1) In the present invention, the high-resolution original image collected by the linear array camera provides a basis for the subsequent accurate measurement of the particle size of the slag block. The PointRCNN algorithm is used to detect the slag block and calculate the particle size. The PointRCNN algorithm can quickly process point cloud data and realize fast and accurate real-time measurement;

[0039] (2) The slag block particle size detection device based on line array camera scanning can automatically and quickly complete the particle size measurement of slag blocks in the slag truck instead of manual work, reducing the error and labor intensity of manual measurement and improving construction efficiency;

[0040] (3) The particle size data is transmitted to the control terminal and displayed in real time. Construction personnel can adjust blasting parameters in time according to the display of particle size distribution and optimize construction effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 The present invention is a flowchart of the method for detecting the particle size of slag blocks based on line array camera scanning.

[0042] Figure 2 This is an example diagram of the original image of the slag blocks in the slag truck obtained by using the line array camera in the present invention.

[0043] Figure 3 It is a principle block diagram of the slag block particle size detection device based on line array camera scanning in the present invention.

[0044] Figure 4 This is a schematic diagram of the installation position of the line array camera in the tunnel according to the present invention. DETAILED DESCRIPTION

[0045] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the present invention and its application or use. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present invention thorough and complete and to fully express the scope of the present invention to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the parts and steps, the composition of the materials, the numerical expressions and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary, rather than as limitations.

[0046] The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different parts. The words "include" or "comprise" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0047] like Figure 1 As shown, the method for detecting the particle size of slag blocks based on line array camera scanning includes the following steps:

[0048] The original image of the slag block in the slag truck is obtained by using a linear array camera. The high-resolution original image collected by the linear array camera provides the basis for the subsequent accurate measurement of the particle size of the slag block. Figure 2 The middle is an example of using a linear array camera to obtain the original image of the slag blocks in the slag truck;

[0049] Preprocess the acquired original image to improve image quality and enhance image recognizability;

[0050] Extract the contour and size information of the slag rock block;

[0051] The PointRCNN algorithm is used to detect the slag blocks and calculate the particle size. The PointRCNN algorithm can quickly process point cloud data and achieve fast and accurate real-time measurement.

[0052] The calculated particle size data is transmitted to the control terminal and displayed in real time. Construction personnel can adjust blasting parameters in time and optimize construction effects based on the display of particle size distribution.

[0053] In some embodiments, as a specific implementation of preprocessing the acquired original image, preprocessing the acquired original image includes:

[0054] Grayscale the original image;

[0055] Filter and denoise the original image after grayscale processing to obtain a preprocessed image;

[0056] Specifically, use image processing libraries (such as OpenCV, scipy.ndimage) to read and process raw image data, decompose the image into a pixel matrix, apply the grayscale formula to generate a grayscale image, apply filters to remove noise in the image, and retain and enhance the image structure; use histogram equalization or histogram straightening, and apply contrast enhancement filters (such as cv2ContrastEnhance in OpenCV) to further enhance image contrast and clarity, making the features of the slag block more obvious.

[0057] In some embodiments, extracting the contour and size information of the slag rock block includes:

[0058] Perform edge detection on the preprocessed image using edge detection algorithm;

[0059] The contour of the slag block is extracted using the contour extraction algorithm.

[0060] In some embodiments, extracting the contour and size information of the slag rock block further includes:

[0061] For complex backgrounds, mathematical morphological operations are used to remove noise and interference to obtain post-processed images;

[0062] Then edge detection and contour extraction are performed on the post-processed image.

[0063] Among them, mathematical morphology operations include: dilation operation and erosion operation; the erosion operation can be understood as using the structural element to "scrape" the foreground pixels in the image. During processing, the structural element slides on the image and traverses each pixel. For the pixels covered by the center of the structural element, only when all the pixels of the structural element are foreground pixels, the pixel is retained as a foreground pixel, otherwise the pixel is eroded to a background pixel; the dilation operation can be understood as using the structural element to "fill" the background pixels in the image. During processing, the structural element slides on the image and traverses each pixel. For the pixels covered by the center of the structural element, as long as there is a pixel in the structural element that is a foreground pixel, the pixel is set as a foreground pixel, otherwise the pixel remains unchanged; the erosion operation followed by the dilation operation can effectively eliminate noise.

[0064] Among them, the edge detection algorithm includes the Canny algorithm. Through multi-step processing, the Canny algorithm can effectively extract clear and complete edges of slag blocks from the image; the contour extraction algorithm includes OpenCV's findContours algorithm. OpenCV's findContours algorithm effectively extracts the contours of slag blocks from the image, providing a basis for subsequent image processing and analysis.

[0065] In some embodiments, the detection and particle size calculation of slag blocks using the PointRCNN algorithm also includes:

[0066] Convert the extracted contour of the slag block into point cloud data;

[0067] The point cloud data is processed using the PointRCNN algorithm to detect the bounding box of the slag block;

[0068] Calculate the particle size parameters of the slag block based on the detected bounding box;

[0069] The pixel size in the image is converted to the actual physical size through the calibration method.

[0070] Among them, the PointRCNN algorithm is used to process the point cloud data and detect the bounding box of the slag block, which includes two stages;

[0071] The first stage is to extract features from point cloud data based on the PointNet++ network, thereby obtaining foreground points in the point cloud data and obtaining candidate bounding boxes for slag blocks;

[0072] In the second stage, the position and orientation of the candidate bounding box obtained in the first stage are optimized and converted to the local coordinate system to obtain the bounding box of the slag block.

[0073] In the above embodiment, the particle size parameters of the slag block are calculated according to the detected boundary box, and the following method can be used:

[0074] (1) Minimum circumscribed sphere method: calculate the minimum circumscribed sphere enclosing the block and define its diameter d eq Is the equivalent particle size:

[0075] d eq =2×R min sphere

[0076] Among them, R min sphere is the minimum circumscribed sphere radius; the minimum circumscribed sphere method is used to calculate the minimum sphere that can enclose a block. Its geometric meaning is to approximate the maximum size of the block and is applicable to regular-shaped blocks.

[0077] (2) Maximum inscribed sphere method: calculate the largest inscribed sphere inside the block and define its diameter d eq Is the equivalent particle size:

[0078] d eq =2×R max inscribed

[0079] Among them, R max inscribed is the maximum inscribed sphere radius; the maximum inscribed sphere method is used to calculate the largest sphere that can be accommodated inside the block. Its geometric meaning is to approximate the minimum channel size of the block and is suitable for blocks with complex shapes and irregular shapes;

[0080] (3) Ellipsoid fitting method: calculate the three main axis lengths (a, b, c) of the ellipsoid of the fitted block and define the equivalent particle size d eq :

[0081]

[0082] Count the equivalent particle sizes of all blocks, draw the cumulative particle size distribution curve, that is, the grading curve; calculate the cumulative particle size distribution.

[0083] As a specific implementation of the calibration method, a camera calibration tool (such as checkerboard calibration) is used to determine the intrinsic parameters of the camera, including focal length (f), pixel size (pixel_size, unit: mm) and the distance between the camera and the object (distance, unit: mm); then the image is preprocessed and contours are extracted, and for each contour, the distance between its boundary points (such as the perimeter of the contour or the length of a specific side) is calculated; the pixel size is converted into the actual physical size using the formula: actual_size = pixel_size × distance / f; after the calibration is completed, verification and calibration can be performed, marking an object of known size (such as A4 paper), taking its image, using the above method to calculate its actual size, verifying the accuracy of the result, and adjusting the camera parameters and calculation formula according to the verification result to improve the accuracy of the measurement.

[0084] In the above embodiment, the calculated particle size data is transmitted to the control terminal and displayed in real time, and the particle size data includes a visualized block detection frame, a segmentation result, and a particle size gradation curve.

[0085] In some embodiments, Figure 3 As shown, a device for detecting particle size of slag blocks based on scanning with a linear array camera is disclosed, which is characterized by comprising:

[0086] The linear array camera module 1 is used to obtain the original image of the slag block in the slag truck 6;

[0087] An image processing module 2, which is connected to the linear array camera module 1 and is used to pre-process the acquired original image and extract the contour and size information of the slag rock block;

[0088] The particle size calculation module 3 is connected to the image processing module 2 and is used to detect and calculate the particle size of the slag block using the PointRCNN algorithm;

[0089] The data transmission and display module 4 and the particle size calculation module 3 are used to receive the particle size data calculated by the particle size calculation module 3 and transmit it to the control terminal for real-time display.

[0090] The data transmission and display module 4 communicates with the control terminal via a wireless or wired network to achieve data transmission.

[0091] In some embodiments, the line array camera module 1 has a line array camera 11 installed on the top of the tunnel 5, and the line array camera 11 is used to collect original images of slag blocks in the slag truck 6 below it.

[0092] So far, various embodiments of the present invention have been described in detail. In order to avoid obscuring the concept of the present invention, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0093] The above-mentioned embodiments only express some implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. A method for detecting particle size of slag blocks based on line array camera scanning, characterized in that: The following steps are involved: The original image of the slag blocks in the slag truck is obtained by using a linear array camera; Preprocessing the acquired original image; Extract the contour and size information of the slag rock block; The PointRCNN algorithm is used to detect slag blocks and calculate their particle size; The calculated particle size data is transmitted to the control terminal and displayed in real time.

2. The method for detecting particle size of slag blocks based on line array camera scanning according to claim 1 is characterized in that: Preprocess the acquired original image, including: Grayscale the original image; The original image after grayscale processing is filtered and denoised to obtain a preprocessed image.

3. The method for detecting particle size of slag blocks based on line array camera scanning according to claim 1, characterized in that: Extract the contour and size information of the slag block, including: Perform edge detection on the preprocessed image using edge detection algorithm; The contour of the slag block is extracted using the contour extraction algorithm.

4. The method for detecting particle size of slag blocks based on line array camera scanning according to claim 3 is characterized in that: Extract the contour and size information of the slag block, including: For complex backgrounds, mathematical morphological operations are used to remove noise and interference to obtain post-processed images; Then edge detection and contour extraction are performed on the post-processed image.

5. The method for detecting particle size of slag blocks based on line array camera scanning according to claim 4 is characterized in that: The mathematical morphology operation includes: dilation operation and erosion operation.

6. The method for detecting particle size of slag blocks based on line array camera scanning according to claim 3 is characterized in that: The edge detection algorithm includes the Canny algorithm, and the contour extraction algorithm includes the findContours algorithm of OpenCV.

7. The method for detecting particle size of slag blocks based on line array camera scanning according to claim 1, characterized in that: The PointRCNN algorithm is used to detect slag blocks and calculate particle size, which also includes: Convert the extracted contour of the slag block into point cloud data; The point cloud data is processed using the PointRCNN algorithm to detect the bounding box of the slag block; Calculate the particle size parameters of the slag block based on the detected bounding box; The pixel size in the image is converted to the actual physical size through the calibration method.

8. The method for detecting particle size of slag blocks based on line array camera scanning according to claim 7 is characterized in that: The point cloud data is processed using the PointRCNN algorithm to detect the bounding box of the slag block, which includes two stages; The first stage is to extract features from point cloud data based on the PointNet++ network, thereby obtaining foreground points in the point cloud data and obtaining candidate bounding boxes for slag blocks; In the second stage, the position and orientation of the candidate bounding box obtained in the first stage are optimized and converted to the local coordinate system to obtain the bounding box of the slag block.

9. A device for detecting particle size of slag blocks based on scanning with a linear array camera, characterized in that: include: Linear array camera module, used to obtain the original image of the slag blocks in the slag truck; An image processing module, which is connected to the linear array camera module and is used to pre-process the acquired original image and extract the contour and size information of the slag rock block; A particle size calculation module, which is connected to the image processing module and is used to detect and calculate the particle size of the slag block using the PointRCNN algorithm; The data transmission and display module and the particle size calculation module are used to receive the particle size data calculated by the particle size calculation module and transmit it to the control terminal for real-time display.

10. The device for detecting particle size of slag blocks based on line array camera scanning according to claim 9, characterized in that: The linear array camera module has a linear array camera installed on the top of the tunnel, and the linear array camera is used to collect original images of slag blocks in the slag truck below it.

Images