391 results about "Vertical coordinate" patented technology

The invention relates to the technical field of motion detection, in particular to an old people falling early warning system based on motion trail analysis, which comprises a gravity center identification module, a trend identification module, an inertia pushing module, a phase judgment module and a grade response module. According to the method, the vertical coordinates of the key points of the waist and the two feet in the image frame are acquired, and the height difference change is continuously tracked, so that the potential falling initial state can be identified from the static posture, the vector included angles among the three groups of bone points of the hip knee, the knee ankle and the shoulder pelvis are subjected to sequence analysis, and whether synchronous disintegration occurs in the coordination action is identified; the identified trend sequence is mapped according to the risk level, a differential response mechanism is applied, a high-density corresponding relation is constructed between the behavior trend and the alarm level, graded response and time sequence triggering of the falling risk are achieved, the accurate identification capability of the falling precursor action is enhanced, the sensitivity and discrimination of the alarm response are also improved, and the safety of the falling risk is improved. And misjudgment and missed judgment are effectively avoided.

The invention discloses a tumble detection method based on multilayer screening and key point prediction. The method comprises the following steps: constructing a daily behavior data set; establishing an identification fall detection model; outputting the contents of the detection frames in e frames before and after the identified frame with the tag name being the tumble in parallel, and screening out a key frame set by using the image difference between continuous frames; generating human body key point information of a central frame and adjacent frames thereof; calculating the moving speed of the vertical coordinate of the human body mass center point; acquiring the maximum height of a shoulder joint point on the right side of the image in the 3D key point graph relative to the ground when the human body squats; and if the moving speed is greater than a preset moving speed threshold value and the vertical coordinates of the shoulder joint points, on the right side of the image, of all the frames in the period are greater than the maximum height, it is determined that falling may occur. The tumble detection and recognition precision is high, the requirements of robustness, accuracy and real-time performance of a detection system can be met, and meanwhile the method can be directly deployed on existing mobile intelligent equipment.

The invention relates to the technical field of gradient measurement, in particular to a method and device for dynamically detecting the perpendicularity of an underwater sinking pile body, and the method comprises the steps: collecting the laser point position of a laser plumb aligner and the torsion degree data of the pile body in the sinking process of the pile body; based on the jumping degree and the change trend characteristics of the light spot coordinate data collected by the laser plumb aligner, respectively calculating the offset coefficients of the light spot in the horizontal coordinate direction and the vertical coordinate direction at each moment; the method comprises the following steps: calculating an offset influence index caused by dynamic distortion by analyzing autocorrelation of a light spot coordinate sequence and related characteristics of an offset degree and a distortion state, calculating a vertical offset index based on a change state of the offset influence index, observing a pile body by adopting an underwater camera, and detecting the perpendicularity of the underwater pile body. The accuracy and the reliability of dynamic detection of the perpendicularity of the underwater sinking pile body are improved.

The invention provides a fish school resource quantity evaluation method based on fishery horizontal scanning sonar, and relates to the technical field of fish school detection. The method comprises the following steps: acquiring echo data sent by shipborne horizontal scanning sonar equipment; performing coordinate transformation on the original echo image according to the polar coordinate data of each pixel point in the original echo image to obtain an original echo image under a vertical coordinate system; performing denoising processing on the original echo image to obtain a denoised echo image; performing edge feature detection on the de-noised echo image to obtain a fish school contour feature map; determining fish school feature parameters according to the fish school contour feature map; and according to the fish school feature parameters and the original echo image, generating and displaying a fish school geographic plotting chart, so that the position information and the feature parameters of fish school resources in a large range can be known more visually, the purpose of evaluating the fish school resource quantity in the whole fishing ground is achieved, and the efficiency of ship fishing operation is effectively improved.

The invention discloses a document translation method, a document translation device and related products, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like. Translating the document text to obtain a text translation result; extracting a first picture from the first document, and identifying a picture text from a plurality of text regions in the first picture; translating the picture text to obtain a picture translation result; if the plurality of text areas comprise a first text area and a second text area which are intersected in the longitudinal coordinate interval, and the text length of a first translation result filled in the first text area in the picture translation result is greater than the target text length, reducing the word size of the first translation result; filling a plurality of text regions in the first picture with the adjusted picture translation result to obtain a second picture; and replacing the document text with the text translation result, and replacing the first picture with the second picture to obtain a second document. In this way, the original format of the document is maintained, and the document translation effect is greatly improved.

A visual image processing method based on brain-like processing belongs to the technical field of image recognition, and comprises the following steps: step 1, dividing an image into multiple rows and columns by taking pixels as units, scanning row by row, and obtaining digital visual waves of the rows by taking a pixel value of each point as a vertical coordinate and the number of the columns as a horizontal coordinate; step 2, screening out a to-be-screened wave band of each row; step 3, taking the central point of each to-be-screened wave band, and screening the front end point and the rear end point; and step 32, carrying out graph fitting identification on the central point and the end point of the to-be-screened wave band reserved in each row and each column to obtain an image. According to the method, the image pixel value change points are directly subjected to extraction reasoning and fitting clustering in a line-by-line scanning and operation mode to obtain and recognize the image, the image recognition speed and precision are improved, the hardware requirement is reduced, and the method is suitable for performing real-time automatic search recognition and tracking application on moving and small dim targets in various complex environments.

An optical fiber sensing method and sensing system for straightness of the scraper conveyor is provided. The sensing method includes the following steps: obtaining the horizontal strain and vertical strain of the corresponding grating measuring point of the scraper conveyor by the optical fiber shape sensor; calculating the horizontal curvature and vertical curvature of the grating measuring point; inserting multiple interpolation nodes between the curvature values of two adjacent grating measuring points; transforming the horizontal curvature and the vertical curvature into the horizontal coordinate value in the horizontal coordinate system and the vertical coordinate value in the vertical coordinate system respectively; superimposing the horizontal coordinate value and the vertical coordinate value to obtain the three-dimensional spatial coordinate values of the grating measuring point and the interpolation node; and obtaining the curves of the optical fiber shape sensor on the horizontal plane, the vertical plane, and the three-dimensional space respectively.

The invention discloses a submucous membrane multi-point thickness measuring method for endoscopic submucous membrane dissection. The submucous membrane multi-point thickness measuring method comprises the following steps that images are collected, wherein pathological images cut by the endoscopic submucous membrane dissection are obtained; image preprocessing: improving the brightness of the pathological image and the contrast ratio of a bright part, and smoothing the pathological image through Gaussian filtering; image feature extraction: extracting texture features of the pathological image, using a local binary pattern (LBP) algorithm, and generating a vertical coordinate feature map with the same size as the pathological image; feature fusion: superposing the preprocessed noise reduction image, the texture feature image and the ordinate feature map; submucous membrane pathological tissue segmentation: using a UNet neural network to carry out image segmentation task training on the superimposed image; calculating the thickness of multiple points; and quality evaluation. According to the method, the thickness of the submucous membrane is measured through the pathological tissue image, and ESD effect judgment and operation quality control are facilitated.

The invention relates to a tire tread multi-section arc profile parameterization design method based on segmentation constraint, and belongs to the field of tire design. Basic parameters of the tire tread are determined, wherein the basic parameters comprise the outer diameter, the tread width and the shoulder sinkage; transversely dividing the width of the driving surface into n sections of arcs according to a preset proportion; establishing a longitudinal coordinate double-boundary constraint system of the right end point of the crown arc, wherein the minimum value and the maximum value are determined by the whole section of arc passing through the left end point of the crown arc and the tire shoulder end point and the y value of the tangent line passing through the left end point of the crown arc at the right end point of the crown arc; selecting a y value in the extreme value interval, and calculating the coordinates of the center of circle of the crown arc on the Y axis; the minimum value and the maximum value of the vertical coordinate of the right end point of the arc close to one side of the tire shoulder are determined by the whole section of arc passing through the left end point of the arc and the end point of the tire shoulder and the y value of the tangent line passing through the left end point at the right end point of the arc; sequentially generating endpoint coordinates of each section of arc and corresponding circle centers; a tire shoulder arc Sn is generated through the tire shoulder endpoint, and a tread contour is formed.

The invention discloses a turnout switch rail section reduction value calculation method and system based on an actual measurement profile, electronic equipment and a storage medium, and belongs to the technical field of steel rail detection. In order to solve the problems of relatively poor measurement accuracy and relatively low efficiency of the section reduction value of the turnout switch rail, the method comprises the following steps: acquiring actually measured profile data of a stock rail and a switch rail measurement position; preprocessing the actually measured profile data, and forming profile data; executing a discrete difference calculation step; determining a point rail stock rail gap point according to the discrete difference curve; the highest points on the two sides of the open joint point are screened out, and the corresponding ordinate difference value is calculated; and determining a reduction value according to the vertical coordinate difference value. According to the method, the point rail reduction value is calculated based on the actually measured profile data, operation is easy, the environment requirement is low, efficiency is high, and precision is high.

The invention discloses an excavator operation pose monitoring method, system and equipment and a medium, and relates to the field of excavators. The method comprises the following steps: processing a video by using a rotating target detection model to obtain four-dimensional coordinates and a rotating angle of a forearm; the first distance between the tail end of the forearm and the cab is obtained according to the four-dimensional coordinates and the rotation angle, the first height of the tail end of the forearm is calculated according to the width and the vertical coordinates of the tail end of the forearm in the image frame of the video in combination with the height from the camera to the ground and the first distance, and the second distance and the second height are obtained through correction of the gradienter; working point coordinates of the tail end of the forearm are obtained according to cab positioning information, azimuth angle information, the second height and the second distance; when the working state of the excavator bucket is changed, working information is recorded, and whether the state of the excavator is normal or not is detected according to the working information. By implementing the technical scheme provided by the invention, the precision and reliability of monitoring the operation pose of the excavator are improved.

The invention relates to a microlens array spherical aberration correction method based on a high-order linear ordinary differential equation. The problem that an existing microlens array spherical aberration correction method is poor in microlens array spherical aberration correction effect is solved. The method comprises the following steps: firstly, establishing a high-order linear ordinary differential equation used for describing a single-lens light propagation path in a micro-lens array, and introducing a non-constant coefficient function; based on a set initial condition and the obtained pixel initial coordinates of the element image array, solving a simultaneous equation of the light field space geometrical relationship and a high-order linear ordinary differential equation by utilizing a formulation reduced-order iterative numerical solution algorithm to obtain an aberration matrix of the element image array; and feeding back the aberration matrix to a spatial function of the element image array mapped to the light field, and changing the pixel horizontal coordinate and vertical coordinate positions of the corresponding element image according to the distance from the pixel point to the optical axis of the corresponding lens to complete the spherical aberration correction of the microlens array. According to the invention, the spherical aberration correction capability of the integrated imaging system can be improved, and the stereo imaging quality is improved.

The invention relates to the technical field of computer vision, and discloses a personnel positioning method and device based on monocular vision, equipment and a storage medium, which are used for reducing the hardware deployment cost of personnel positioning and improving the personnel positioning accuracy. The monocular vision-based personnel positioning method comprises the following steps of: estimating depth information by utilizing a depth detection model, and determining an actual vertical distance from a ground contact point to a monocular camera and an actual horizontal distance of a horizontal point pair; fitting the depth information and the actual vertical distance through a polynomial regression equation so as to determine a vertical coordinate mapping relation of the pixel coordinates in a camera reference coordinate system; determining a horizontal coordinate mapping relation according to the actual horizontal distance of the horizontal point pair and the pixel pitch of the horizontal point pair; and determining target positioning information through a coordinate system conversion matrix between the working position and the correction position in combination with the vertical coordinate mapping relation, the horizontal coordinate mapping relation and the relative position information.

The invention discloses a method and system for detecting surface defects of power equipment based on machine learning, and belongs to the technical field of defect detection.The method specifically comprises the steps that a target area is set, and an infrared monitoring video and an optical monitoring video of a power transmission line are obtained in real time through an unmanned aerial vehicle; the method comprises the following steps of: framing an infrared monitoring video according to a preset frame length, selecting any infrared image and inputting the selected infrared image into a preset equipment identification model to obtain an equipment image, generating a positioning frame of any power transmission line, acquiring an infrared temperature and a positioning frame width of any power transmission line, constructing a point location map by taking the positioning frame width as a horizontal coordinate and the infrared temperature as a vertical coordinate, and identifying the equipment image according to the point location map. And fitting the point map to obtain a fitting function, correcting the infrared temperature of any power transmission line, determining a target infrared image, extracting an optical image corresponding to the target infrared image, and substituting the optical image into a preset defect identification model to obtain an equipment defect identification result of the power transmission line.

The invention discloses a gas leakage rate temperature compensation method and system based on an internet-of-things gas appliance, and belongs to the technical field of gas metering. The method specifically comprises the steps that a monitoring period is set, and monitoring data of an internet-of-things ultrasonic gas meter in the monitoring period is obtained in real time; clustering the monitoring data by taking the gas temperature and the pipeline pressure as feature vectors to generate a plurality of category clusters; selecting any category cluster, acquiring external temperature data and gas flow data corresponding to all feature points in the category cluster, constructing a point location diagram by taking the external temperature data as a horizontal coordinate and the gas flow data as a vertical coordinate, and fitting the point location diagram to obtain a fitting function; monitoring data of the current Internet of Things ultrasonic gas meter are obtained, the gas flow data are corrected according to the fitting function, and final gas flow data are obtained; according to the invention, the gas metering precision is improved, and the possibility of misjudgment and missed judgment of gas leakage is reduced.

The invention discloses a chip unit detection method and apparatus, an electronic device and a storage medium. The detection method comprises the steps of determining a preset pixel coordinate of each chip unit and a preset pixel coordinate of each positioning hole on a substrate; determining a first image of the substrate; determining a pixel coordinate of each positioning hole in the first image; determining an image mapping relation according to the pixel coordinate of each positioning hole and a preset pixel coordinate; determining a pixel coordinate of each chip unit; determining a second image; determining a horizontal coordinate and a vertical coordinate of a mark point of each chip unit according to the second image; acquiring a preset abscissa and a preset ordinate of the preset physical coordinates of the mark point of each chip unit; and detecting all the chip units at the same time, and determining that the product is a good product under the condition that the difference value between the abscissa and the preset abscissa is smaller than a first difference value and the difference value between the ordinate and the preset ordinate is smaller than a second difference value. According to the invention, the substrate can be automatically detected, and the detection efficiency and accuracy are improved.

The invention belongs to the technical field of ocean engineering, and provides a deep sea riser spatial configuration inversion method. Dividing the deep sea riser into a plurality of pipe section units by taking the tilt angle sensor as a node; discretizing each pipe section unit into a plurality of infinitesimal sections, and projecting each infinitesimal section in a horizontal coordinate system and a vertical coordinate system to obtain a space curve length equation of each pipe section unit; constructing projection expressions of the space curve of each pipe section in a horizontal coordinate system and a vertical coordinate system in combination with inclination angle information; relative coordinates of the upper end point and the lower end point of each pipe section unit in the pipe section unit local coordinate system where the pipe section unit is located are solved through iteration; and converting the relative coordinates of each pipe section unit in the local coordinate system of each pipe section unit into absolute coordinates under the global coordinate system, and integrating the absolute coordinates of each pipe section unit under the global coordinate system to obtain the deep sea riser spatial configuration. The method realizes spatial configuration reconstruction of the riser in a complex marine environment, and has higher robustness.

The invention discloses an ileum bladder replacement stoma preoperative positioning method based on CT body surface projection. The ileum bladder replacement stoma preoperative positioning method comprises the following steps that S1, region division is conducted on the abdomen; s2, externally adhering developing grid paper to the lower right abdomen of the patient, wherein the developing grid paper is consistent with the human body coordinate system of the lower right abdomen; s3, performing CT scanning on the right lower abdomen of the patient, and establishing a horizontal and vertical coordinate system in an image generated by CT scanning; s4, a plurality of rectus abdominis outer edge positioning points are marked in the foot side direction; s5, inputting the horizontal coordinate values of the plurality of rectus abdominis outer edge positioning points into a laser positioning system on the CT machine tool, finding corresponding longitudinal grid lines on the developing grid paper according to the longitudinal coordinate values corresponding to the horizontal coordinate values and the path information, and dotting and marking on the abdominal skin; s6, the rectus abdominis outer edge positioning points are connected into a line, projection marking is completed, and therefore a final stoma positioning area is determined.

The invention provides a deep sea underwater sound long baseline navigation method and system, relates to the technical field of underwater navigation, predicts the position and speed at the current moment on the basis of the position and speed predicted value of an underwater vehicle at the previous moment, and comprises the following steps: predicting the position and speed of the underwater vehicle at the previous moment through an improved sound ray tracking method on the basis of the position and speed predicted value of the underwater vehicle at the previous moment; calculating a distance observation value between the underwater vehicle and the seabed base station at the current moment; calculating the geodetic height observation value of the underwater vehicle by using the real-time depth observation value of the underwater vehicle; the distance observation value and the geodetic height observation value are substituted into a constructed observation model, and prediction of the position and the speed at the current moment is obtained through Kalman filtering solution; according to the method, the sound ray tracking stability and the earth curvature are considered, distance measurement errors caused by sound ray bending and vertical coordinate deviation and length deformation caused by the earth curvature are corrected, the sound ray tracking stability is improved, and the navigation precision is improved.

The invention discloses a dynamic layout method and system for washing label printing and a medium, and the method comprises the steps: obtaining definition data of a draft template, including initial attributes of a plurality of layout elements; determining a rendering sequence of the layout elements; constructing a dependency relationship among the layout elements based on the rendering sequence, wherein the dependency relationship is used for identifying a response element corresponding to each layout element; obtaining label data to be rendered, wherein the label data comprises multi-language text data and variable data; traversing the layout elements in sequence, and performing line feed processing on the text elements based on the corresponding multi-language text data to determine the actual occupation height of the text elements; for the bar code element, performing centering positioning processing based on the corresponding variable data, and determining the horizontal position of the bar code element; identifying the trigger element with the actual occupation height different from the initial occupation height; calculating the placeholder height variation of the trigger element, and dynamically adjusting the vertical coordinate of the response element corresponding to the trigger element based on the dependency relationship and the placeholder height variation; and generating and outputting a printed draft of the washing label.

The invention provides an industrial site soil pollutant concentration prediction method using three-dimensional distribution interpolation, and belongs to the field of soil pollution prediction, and the method comprises the following steps: S1, extracting soil pollution distribution characteristics based on sample point positions and attribute information; s2, measuring the anisotropy of the pollution concentration value in the two directions by estimating the ratio R of the vertical direction gradient to the horizontal direction gradient of the soil pollutant concentration through the soil sample point pollution concentration and a difference method, and multiplying the z value in the original coordinate space by the R by taking the R as an expansion factor to obtain a new vertical coordinate value; s3, expanding the spatial position representation module of the DKNN from a two-dimensional space to a three-dimensional space; s4, selecting a space encoder; and S5, on the basis of the spatial encoder, performing spatial prediction by using a general Kriging equation. According to the method, a GeoAI framework based on deep learning and geoscience knowledge fusion is introduced and expanded, the problem of three-dimensional distribution simulation of industrial site soil pollutants can be solved, and soil pollution can be accurately predicted.

The invention belongs to the technical field of thunder and lightning signal noise reduction, and particularly relates to a noise reduction method and noise reduction system for very low frequency thunder and lightning signals and a storage medium. The noise reduction method comprises the steps of obtaining a plurality of position points of a current mixed lightning signal in a dung beetle algorithm after the mixed lightning signal is obtained; after a position point corresponding to the minimum envelope entropy in the current mixed lightning signal is calculated based on a VMD algorithm, the abscissa and the ordinate of the position point corresponding to the minimum envelope entropy are respectively recorded as an optimal decomposition mode number and an optimal penalty factor; decomposing the current mixed lightning signal into a linear superposition form of a plurality of decomposed signals by using a VMD algorithm based on the optimal decomposition mode number and the optimal penalty factor; after the decomposition signals representing the noise are removed, linear superposition of the remaining decomposition signals is reconstructed, and the very-low-frequency thunder and lightning signals are obtained. According to the method, the noise signal deeply coupled with the very low frequency lightning signal can be efficiently and accurately removed, and the real very low frequency lightning signal is restored.

A method performed by a vehicle system for enabling estimation of a condition of a road comprising obtaining, from a sensor mounted on a vehicle, first data comprising a first plurality of data points, each comprising longitudinal, lateral and vertical coordinates representing dimensions of a part of the road at a first time, obtaining a second plurality of data points, each comprising longitudinal, lateral and vertical coordinates representing dimensions of the part of the road at a second time, wherein the first time is more recent than the second time, segmenting the first plurality of data points into a plurality of segmented data areas based on longitudinal and lateral coordinates of the first plurality of data points, and estimating a respective vertical position in each segmented data area based on vertical coordinates of the second plurality of data points and a motion state of the vehicle at the second time.

The application provides a human transcranial ultrasound irradiation method, device, electronic equipment and storage medium. The target head sagittal plane tomographic image and the transverse plane tomographic image are acquired; a vertical coordinate system is established based on the sagittal plane tomographic image, and the target point coordinates of the insula in the vertical coordinate system are determined; based on the transverse plane tomographic image, the horizontal distance from the insula to the target head brain midline is measured; the world coordinate point of the insula is mapped in the world coordinate system according to the target point coordinates and the horizontal distance; and the ultrasound transducer is controlled to irradiate the real position of the insula, so that accurate targeted irradiation can be realized, the use cost of the low-intensity focused ultrasound technology is effectively reduced, and the operation is simpler.

The present invention discloses an asset allocation method and system. The method comprises acquiring the returns of each asset and determining the annual return rate and the annual volatility of each asset; determining expected returns according to the annual return rate, determining expected volatility according to the annual volatility, and constructing an efficient frontier by taking the expected returns as a horizontal coordinate and the expected volatility as a vertical coordinate; acquiring the Sharpe ratio and the Sharpe return rate of each point within the efficient frontier, and determining the optimal asset allocation according to the weight of each required asset corresponding to the Sharpe ratio and the Sharpe return rate.

The embodiments of this specification disclose a point cloud calibration method, device and medium for a robot depth camera, the method comprising: placing the depth camera in a ground observation environment, controlling the robot coordinate system and the depth camera coordinate system to perform step iterations of a first rotation increment and a second rotation increment, respectively, to determine a first calibration rotation increment and a second calibration rotation increment; performing step iterations of a third rotation increment on the depth camera under the first calibration rotation increment and the second calibration rotation increment, to obtain a third calibration rotation increment of the depth camera; obtaining the median value of the vertical coordinates in each ground point cloud data collected by the depth camera, to obtain a first calibration displacement increment of the depth camera; placing the depth camera in a preset target observation environment, to determine a second calibration displacement increment and a third calibration displacement increment of the depth camera based on a preset adjustment strategy, to achieve calibration of the depth camera according to a relative angular coordinate relationship and a relative coordinate relationship.

The application belongs to the technical field of building structure damage identification, and particularly relates to a model-free detection method for lateral stiffness mutation position of a high-rise structure, comprising the following steps: step one, obtaining the displacement time history response of the same height interval measuring points in the same vertical line of the high-rise structure in the same horizontal direction; step two, calculating the second-order statistical moment of the relative displacement of each measuring point according to the time history response, and solving the lower-to-upper value corresponding to the statistical moment of the measuring point; step three, taking the height of each measuring point as the horizontal coordinate and the lower-to-upper value corresponding to the statistical moment of the measuring point as the vertical coordinate to draw a curve; and step four, observing the mutation of the curve to identify the lateral stiffness mutation position.

The present invention relates to the field of image recognition technology. The present invention relates to a method and system for detecting the printing quality of anti-counterfeiting wire-drawn wide-width coils based on machine vision. The method includes: obtaining a wide-width coil image, and marking and selecting each character through a marking frame to obtain the number of pixels belonging to the character in the marking frame; determining the horizontal / vertical coordinate of the center of the marking frame as the horizontal / vertical coordinate of the character, and dividing all characters into multiple wire-drawn clusters and multiple identical character clusters; calculating the outlier degree of each character; fitting a first straight line according to the horizontal / vertical coordinates of each character in the wire-drawn cluster, and calculating a first included angle between the first straight line and the horizontal axis; fitting a second straight line according to the horizontal / vertical coordinates of each character in the identical character cluster, and calculating a second included angle between the second straight line and the vertical axis; calculating the abnormality degree of each character and alarming when the abnormality degree of at least one character is less than a preset second threshold. The present invention improves the automatic detection accuracy and reliability of anti-counterfeiting wire-drawn wide-width coils.

The invention provides a converter copper smelting sampling drill rod image correction and extraction method and system, and belongs to the technical field of converter copper smelting. The method comprises the steps that a sampling drill rod RGB image is collected and scaled, and a preprocessed image is obtained; extracting a red channel and a blue channel of the preprocessed image, calculating a difference image, and carrying out binarization threshold processing to generate a preliminary binary mask; performing morphological corrosion operation and connected domain analysis on the preliminary binary mask, and removing a background connected domain to obtain an accurate binary mask; on the precise binary mask, selecting a sampling column and calculating a vertical coordinate centroid to obtain a two-dimensional coordinate point set; performing linear fitting on the two-dimensional coordinate point set to obtain a mathematical equation, and calculating the inclination angle and the center point of the drill rod; and taking the center point as a rotation center, performing affine transformation on the preprocessed image based on the inclination angle, and taking the center point of the drill rod after rotation correction as a reference to cut a standardized drill rod image. According to the invention, automatic correction and extraction of the drill rod image are realized, precision is improved, and safety is enhanced.

The present application belongs to the technical field of road construction materials, and relates to a method and device for testing the interaction of a sandwich structure asphalt aggregate interface by means of a pull-out test, the method comprising: S1, using a set aggregate type and asphalt type, producing a plurality of sandwich structure standard test pieces; S2, obtaining an interaction standard value and a bonding strength standard value, and constructing a standard database; S3, according to the constructed standard database, taking the bonding strength standard value as the horizontal coordinate and the interaction standard value as the vertical coordinate, constructing a standard model of the interaction and the bonding strength; S4, producing a sandwich structure test piece to be tested, obtaining a bonding strength test value, substituting the bonding strength test value into the standard model of the interaction and the bonding strength, and calculating an actual interaction value. The present application tests the interaction of a sandwich structure asphalt aggregate interface by means of a pull-out test, so that the test of the interaction is simpler, and the performance of the interaction between the asphalt-aggregate interface can be well reflected.