38 results about "Line fitting" patented technology

The invention discloses a ship water gauge scale line fitting algorithm, and relates to the technical field of ship water gauge scale calculation, and the method comprises the steps: obtaining a ship water gauge region image through an image collection device to extract a measurement point coordinate, and building a mapping relation between a pixel position and a physical draft; a weighted least square method is adopted to perform nonlinear curve fitting, a weight coefficient is calculated based on a local neighborhood standard deviation, a polynomial order p is dynamically adjusted according to an adjusted decision coefficient, and the decision coefficient is iteratively optimized to improve the balance between amplitude and model complexity. And the system repeatedly corrects model parameters through a dynamic verification mechanism of the residual sum of squares and a preset threshold value, and finally an accurate water gauge scale fitting curve is generated. The method effectively solves the problems that traditional manual observation is prone to environmental interference and large in measurement error, high robustness is kept in a complex water area environment, and reliable data support can be provided for the fields of ship load evaluation, channel safety management and the like.

The invention discloses a lane center line confirmation method for avoiding mistaken direction turning at an intersection in an intelligent navigation mode. According to the confirmation method, firstly, effectiveness and smoothness judgment is carried out on left and right side lane lines respectively, and a quantitative basis is provided for decision making; and then, based on a judgment result, according to a preset decision logic comprising four modes of double-side fitting, left-side single-side fitting, right-side single-side fitting and non-following line control, adaptively selecting a center line fitting mode. According to the technical scheme, the system can effectively screen and utilize reliable lane line information in a complex intersection environment, or give up line following in time when the lane line information is not suitable, so that the problem that a vehicle mistakenly turns the direction due to the fact that sensing information jumps or is wrong is fundamentally solved, and the driving safety of the vehicle is improved. And the transverse control safety and the system robustness during crossing are obviously improved.

This invention relates to the field of autonomous driving technology, and discloses a lane line fitting method, apparatus, electronic device, and storage medium. The method involves acquiring a lane line dataset at the current moment; this dataset includes the position of each sampling point among multiple sampling points located on the lane line; if the slope value of any two adjacent sampling points in the lane line dataset is greater than or equal to a first preset threshold, segmentation points are determined from the lane line dataset, and then a target lane line dataset is determined. Based on the target lane line dataset at the current moment, the vehicle motion state at the current moment, the vehicle running state at historical moments, and the predicted lane line state quantity at the current moment, an extended Kalman filter is performed to obtain the target lane line state quantity at the current moment; the target lane line at the current moment is determined based on the target lane line state quantity at the current moment. This invention provides a lane line fitting method with high accuracy and reliability in the fitting results.

A processor-based compressed memory system includes a memory partitioning circuit for dividing a memory region into data regions with different priority levels. The system also includes a cache line selection circuit for selecting a first cache line from a high-priority data region and a second cache line from a low-priority data region. The system further includes a compression circuit for compressing the cache line to obtain a first compressed cache line and a second compressed cache line. The system also includes a cache line encapsulation circuit for encapsulating the compressed cache line such that the first compressed cache line is written to a first predetermined portion of the candidate compressed cache line, and the second cache line, or a portion of the second compressed cache line, is written to a second predetermined portion of the candidate compressed cache line. The first predetermined portion is larger than the second predetermined portion.

The application discloses a centrifuge linear distortion correction method based on WIA-FA wireless communication, and the PID mode is adopted to form a closed loop control by using a frequency converter speed regulation and a Hall sensor speed measurement in centrifugal equipment design. By further optimizing the algorithm, the influence of the linear distortion of the control link on the system is eliminated, the problem that the set value deviates from the actual value is solved, the simulation loop is corrected by implementing the broken line fitting mode, and the control precision and the control performance are effectively improved. When metering, analog calibration is changed into digital calibration, and operation becomes simple. The centrifuge is provided with a WIA-FA communication module, the WIA-FA communication module is used for connecting the centrifuge to a WIA-FA wireless network, working parameters and result records are transmitted through the WIA-FA wireless network, data security can be realized, and leakage of secret data is avoided.

The application is a visual SLAM image line segment extraction method based on approximate line segment merging. Firstly, the CannyLines algorithm is used to perform edge detection on the image to obtain all pixel chains. Then, the RANSAC algorithm is used to perform line fitting on each pixel chain to extract line segments in the image. Finally, approximate line segments in all line segments are judged and merged. For the new line segment after merging, if the angle difference between the new line segment and the long line segment before merging is within a reasonable range, the new line segment after merging is retained; otherwise, the new line segment after merging is not retained, and the two similar line segments before merging are reset to continue traversing the remaining line segments. The method uses the approximate line segment merging strategy to merge the broken short line segments into longer line segments, and merge the approximate line segments into one line segment, thereby reducing the short and redundant line segments, improving the feature matching accuracy in the visual SLAM process, and reducing the time consumption of feature matching.

The application discloses a kind of ship slotting V-type groove weld parameter extraction method and system, the method includes: using the statistical filtering method based on percentile to eliminate abnormal points, and based on neighborhood z coordinate range realizes positive side weld point cloud separation;Then for the geometric characteristics of two kinds of structures of blunt edge V-type weld and butt V-type weld, rectangular surface recognition algorithm and boundary detection algorithm are designed respectively, accurate separation and boundary positioning of groove point cloud are realized;Finally, the adaptive extraction of groove angle parameters is completed by fusing RANSAC straight line fitting and endpoint method.The application can be suitable for the above two kinds of structures simultaneously, can provide accurate groove geometric parameters for ship welding robot, effectively improve the automation welding level of ship and marine equipment.

The application discloses a steel structure welding method, and relates to the technical field of 3D visual welding, and comprises the following steps: step S1, scanning point cloud data of a steel structure; step S2, based on the scanned data in step S1, a random sample consensus method is used to find a plane; step S3, according to a visual coordinate, a normal line of the plane obtained in step S2 is unified; step S4, a boundary between planes is calculated according to the plane obtained in step S2; step S5, a nearest neighbor algorithm is used to search for the nearest neighbor points of each two groups of boundaries in step S4, and a common boundary is formed; step S6, straight line fitting is performed on the common boundary obtained in step S5, and end points are extracted as welds; and step S7, path planning is performed based on a distance method. The welding method provided by the application automatically solves the plate plate welding problem in a steel structure, uses a 3D visual system to identify welds, automatically plans a welding path, saves labor cost, improves welding precision stability, and shortens a welding cycle.

The embodiment of the invention provides a degree detection method and system based on pressure gauge occlusion, and the method comprises the steps: carrying out the occlusion processing of an original image of a pressure gauge, and obtaining a processed image; performing dial scale and pointer segmentation on the processed image to obtain a first segmentation result; performing fusion processing of a plurality of dial regions on the first segmentation result to obtain a fused dial region; performing circle center fitting on the fused dial plate area to obtain a circle center position of the pressure gauge; performing pointer straight line fitting on the first segmentation result to obtain a pointer direction; and determining the scale number of the pressure gauge based on the pointer direction and the circle center position. According to the method, even if the pressure gauge is shielded and reflected, the scale number of the pressure gauge can still be identified with relatively high precision.

The invention discloses a lane line fitting method. The method comprises the following steps: screening an original lane line point set to determine a first lane line point set; performing lane line fitting processing according to the first lane line point set to determine an initial fitting lane line; and performing compensation processing on the initial fitting lane line, determining a target lane line point set, and performing lane line fitting according to the target lane line point set. Thus, compensation processing is performed on the initial fitting lane line obtained through screening and fitting processing, the problems of line breakage and local missing possibly existing in the initial fitting lane line are reduced to a certain extent, and the completeness and continuity of the lane line are recovered by supplementing the missing lane line, so that the accuracy of the lane line is improved. The target lane line point set has time sequence continuity and space consistency to a certain extent, so that the requirements of vehicle path planning and driving control for high-quality lane line data in automatic driving are met to a certain extent, and the effectiveness of functions of an automatic driving system is guaranteed.

This invention provides a method and system for cargo positioning in an automated storage and retrieval system (AS / RS). The method includes acquiring point cloud data of stacked goods; preprocessing the point cloud data to obtain preprocessed point cloud data; performing iterative plane fitting on the preprocessed point cloud data to obtain a fitting plane; projecting the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud; extracting edges from the projected point cloud to obtain point cloud edges; performing line fitting and matrix determination based on the point cloud edges to obtain a transformation matrix; and outputting the coordinates of the target cargo based on the transformation matrix and the projected point cloud. This invention effectively improves the processing efficiency and accuracy of point cloud data by performing a series of processing steps on the original point cloud data, while effectively capturing the edge information of the cargo, thus improving the accuracy of subsequent positioning and recognition. A coordinate system is then established based on the boundaries, and the size and pose information of the target cargo are determined through affine transformation.

This invention relates to the field of image data processing, and more particularly to an image data processing method and system for lens plastic parts. The method includes: acquiring an edge image of the surface of the lens plastic part; performing path search based on the pixels in the edge image; for each search path obtained, fitting a corresponding fitted line based on the pixels on the search path; calculating the smoothness of the corresponding search path based on the fitted line; and determining that the area corresponding to the search path is a scratch defect when the smoothness is greater than a preset threshold. This invention, by combining edge detection, path search, and line fitting, can effectively distinguish between real scratches and random uneven textures, significantly reducing the false detection and false negative rates.

The application provides a fixed target pose deviation monitoring method based on single-line laser radar, belongs to the technical field of pose deviation monitoring, and comprises the following steps: point cloud data acquisition and preprocessing; point cloud clustering; target cluster screening and tracking; straight line fitting; pose deviation calculation and angle deviation output; the method has good lightweight advantage, and the hardware cost is much lower than that of multi-line radar or a complex vision system; the method has high precision and strong robustness: through multi-stage screening and random point filtering, the influence of environmental interference and noise points is effectively excluded, the processing time of each frame of data can be set to be in millisecond level, the demand of most real-time monitoring scenes can be met, the work is safe and reliable, and the method is suitable for popularization and application.

The invention relates to a lane line fitting method and device, a vehicle, a storage medium and a product. The method comprises the following steps: acquiring a lane line image acquired by image acquisition equipment; determining the type of a lane line in the lane line image; under the condition that the type is a curve, performing Bezier curve fitting processing on the lane line to obtain a Bezier lane line equation; the Bezier lane line equation is input into a first filter, initial key point coordinates in the Bezier lane line equation are updated through the first filter, first target key point coordinates are determined, and the initial key point coordinates comprise end point coordinates and control point coordinates in the Bezier curve; and determining a target lane line fitting result according to the first target key point coordinates and a Bezier curve equation. According to the invention, the fitting effect of the complex curve in the lane line can be improved, and the calculated amount of the overall lane line fitting is small.

The present application relates to a sigmoid activation function circuit based on linear broken line fitting, comprising: a data processing module, a compensation module, a first addition module and a second addition module; the data processing module, the first addition module and the second addition module are connected in sequence, and the compensation module is connected with the first addition module; the data processing module inputs and processes input data and outputs to the first addition module; the compensation module inputs and processes input data and outputs corresponding offset to the first addition module; the first addition module accumulates the data output by the data processing module and the offset, and outputs the accumulated data; the second addition module processes the accumulated data to obtain an output value. The present application simplifies the circuit module and introduces the rounding calculation based on the broken line fitting method, effectively reduces the operation power consumption and propagation delay under the condition of ensuring the accuracy, and at the same time realizes smaller hardware resource consumption.

The application discloses a lane line identification method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring a current road image and performing lane line segmentation to obtain a lane line segmentation result of the current road image; using a preset block strategy to block the lane line segmentation result to obtain lane line segmentation results of a plurality of block regions, wherein the plurality of block regions comprise a first block region and a second block region; determining a lane line fitting result of the first block region according to the lane line segmentation result of the first block region; and using a preset iterative optimization strategy to iteratively optimize the lane line fitting result of the first block region according to the lane line segmentation result of the second block region to obtain a lane line identification result of the current road image. The application iteratively optimizes the lane line fitting result, reduces the influence of inaccurate lane line instance segmentation results on lane line identification accuracy, and improves lane line identification accuracy and stability.

This invention discloses a weld detection method based on linear fitting of key points in one-dimensional ordered laser stripes, belonging to the field of automated welding technology. The steps are as follows: preprocessing the laser stripe image, extracting key points on the laser stripes and arranging them in ascending order; fitting the laser stripes with a 4-piece function and detecting strong interference regions; identifying and removing strong interference based on a one-dimensional nth-order polynomial fitting method; identifying and removing weak interference based on Gaussian filtering and moving average methods; dividing the key points into two parts, the left and right sides of the weld including the boundary point, and arranging the key points on the right side in descending order of x-axis coordinate values; calculating the standard deviation feature of the key points; using the zero-crossing point of the standard deviation feature as the inflection point, and selecting key points between the inflection point and the boundary point to fit straight lines, the intersection of the two lines is the weld location. This invention significantly reduces the amount of data in the calculation process, and the calculation method has strong anti-interference capabilities, effectively improving detection stability and accuracy.

The application particularly relates to a road edge line fitting and tracking method and device, equipment and a storage medium, the method comprising the following steps: scanning a region of interest (ROI) in a drivable area of a vehicle to obtain road edge line segmentation data points; performing interpolation processing on the road edge line segmentation data points to obtain a plurality of road edge line points; projecting the plurality of road edge line points from image coordinates to bird's-eye view coordinates based on a preset external parameter calibration result; performing road edge line fitting on the bird's-eye view coordinates to obtain a plurality of fitting parameters, traversing images in a preset order to obtain a vanishing point and a resolution of the image, calculating a real-time pitch angle and a real-time yaw angle of the vehicle, fitting new road edge line points, back-projecting the new road edge line points to the image coordinates, predicting a road edge line state according to the image coordinates obtained by back-projection, and obtaining a road edge fitting line to complete tracking of the road edge line. Thus, the problem of inaccurate line coordinate information caused by road surface changes and the like is eliminated.

This invention provides a method, apparatus, electronic device, and storage medium for detecting rolled materials. The method involves acquiring the center of the side boundary of the rolled material, scanning the side boundary along any direction from the center to obtain marker point and contour point data, fitting the contour point data to a reference line in the corresponding direction based on the marker points, and performing multiple straight line fittings on the contour point data using the reference line as a reference to obtain multiple fitted straight lines. The roll state is determined based on the reference line and the fitted straight lines. This application reduces labor costs by automatically detecting the contour point data of rolled materials. By fitting the shape of the rolled material to the contour point data, multiple fitted straight lines are obtained. The roll state of the rolled material is judged based on the relationship between the straight lines, and the output results are directly transmitted to subsequent processes, facilitating adjustments by the robot and improving production efficiency.

The application discloses a line design parameter automatic checking method and system for linear rectification calculation, parameter configuration is carried out on railway line design specifications, and a specification configuration file is generated; linear fitting is carried out on a railway line according to a plane and a longitudinal plane respectively, and plane fitting parameters and longitudinal plane fitting parameters to be checked are acquired; project configuration information of the railway line is acquired, the specification configuration file is parsed according to the project configuration information, and plane design specifications and longitudinal plane design specifications of the railway line are acquired; and the plane fitting parameters and the longitudinal plane fitting parameters to be checked are automatically checked based on the plane design specifications and the longitudinal plane design specifications. The fitting parameters that do not meet the requirements of the line design specifications are dynamically identified to prompt a user to optimize and adjust, and the software is high in automatic degree and smooth in algorithm through a joint linear fitting module, so that the workload of manual adjustment is greatly reduced on the basis of ensuring the accuracy of the line fitting result.

The application discloses a lane line fitting method, an electronic device and a storage medium. The method comprises the following steps: extracting lane line simulation point sets in a lane image obtained by shooting; mapping lane line simulation points in the lane line simulation point sets to a vehicle body coordinate system to obtain lane line simulation point sets in the vehicle body coordinate system; performing primary fitting on a lane line based on lane line simulation points in the lane line simulation point sets in the vehicle body coordinate system to obtain a primary fitting lane line in the vehicle body coordinate system; in a case where it is determined that there is abnormal fitting based on the primary fitting lane line, obtaining segmentation points based on abnormal fitting points; and performing segmented fitting on the lane line simulation point sets according to the segmentation points to obtain a final fitting lane line. According to the above scheme, whether there is abnormal fitting is determined based on the primary fitting lane line obtained after the primary fitting, and the segmentation points are obtained, so that the fitting accuracy can be improved.

Embodiments of the present disclosure disclose a three-dimensional lane line generation method, device, electronic equipment and computer readable medium. A specific implementation of the method comprises: performing curve fitting on each of the post-projection lane line sampling point coordinates in each post-projection lane line sampling point coordinate group in the post-projection lane line sampling point coordinate group sequence to generate a fitted lane line, thereby obtaining a fitted lane line sequence; performing adjustment processing on the coordinate system conversion matrix to generate a target conversion matrix; performing coordinate projection on each of the lane line sampling point coordinates in each lane line sampling point coordinate group in the lane line sampling point coordinate group sequence to generate a target lane line sampling point coordinate group, thereby obtaining a target lane line sampling point coordinate group sequence; and performing lane line fitting on each of the target lane line sampling points in each target lane line sampling point coordinate group in the target lane line sampling point coordinate group sequence, thereby obtaining a three-dimensional lane line equation set. The implementation can improve the accuracy of the generated three-dimensional lane line.

The application provides a lens cutting trajectory line fitting method, which comprises the following steps: S1, fitting a scanning straight line formed by point spectrum of a lens surface and a protective film surface under a random rotation angle; S2, intersecting the scanning straight line of the lens surface and the scanning straight line of the protective film surface at a point, and finding an intersection point of the two scanning straight lines, which is a cutting point; S3, rotating the lens and the protective film, and making the swing speed of the point spectrum greater than the rotation speed of the lens and the protective film, and then jumping to step S1, so that a large number of different cutting points can be found, and the cutting points are fitted into a cutting line, so that the problems of non-transmission of the protective film and non-imaging of the lens are overcome, and the real cutting trajectory line is found.

The embodiment of the invention discloses a hard box stay wire deviation correction method and device, electronic equipment and a storage medium. The method comprises the following steps: after glancing a strip-shaped light source to the surface of a stay wire, controlling an acquisition device to shoot the surface of the stay wire to obtain a real-time stay wire image, and performing center line fitting processing on the real-time stay wire image to obtain a fitted pixel line; determining a current parallelism deviation according to the fitting pixel line and the target correction line, and determining an output increment according to the current parallelism deviation; and according to the output increment, a deviation rectifying guide roller is controlled to rectify deviation, and when deviation rectifying is completed and it is determined that wire drawing is finished, it is determined that the deviation rectifying process is finished. According to the method, in the transparent paper packaging process of the high-speed hard box packaging machine, the deviation rectifying guide roller is controlled to rectify deviation automatically, the problem caused by the fact that longitudinal and transverse deviation rectifying parameters are rectified only based on manual experience at present is solved, and the deviation rectifying precision and the deviation rectifying efficiency in the high-speed wire drawing process are improved.

This invention discloses a machine vision-based method for extracting the Region of Interest (ROI) of rail pads under unlimited positioning conditions, belonging to the fields of image processing and automated inspection technology. The technical problem it solves is how to accurately extract the Region of Interest (ROI) of rail pads under unlimited positioning conditions using a camera to support subsequent measurements. The implementation of the machine vision-based ROI extraction method for rail pads under unlimited positioning conditions includes: enhancing the brightness and converting the captured rail pad image to grayscale; extracting edges using a Canny edge detection algorithm combined with adaptive median filtering; accurately locating the outer contour of the pad using a line fitting and filtering algorithm, determining the reference point, and then performing geometric transformation to align the image; and accurately extracting the ROI based on the reference point and the geometrically transformed pad image. This invention effectively solves the problems of severe image noise interference and difficulty in locating rail pads under unlimited positioning conditions, providing an efficient and reliable technical solution for the automated inspection of rail pads.

The invention belongs to the technical field of image processing, and particularly relates to an intelligent positioning method and system for plate cutting, and the method comprises the steps: obtaining an industrial image of a to-be-cut plate, and extracting all straight line segments to form an initial candidate set; calculating color uniformity and processing texture responsivity of each line segment to obtain physical material characteristics of the line segments; calculating the local structure consistency by combining the deflection angle and distance relation of the neighborhood line segments; constructing a candidate line segment connection diagram, searching a path with the maximum potential energy sum by using a dynamic programming algorithm, and screening out a real plate edge line segment set; and determining a positioning result through robust straight line fitting. According to the method, interference of real edges, scratches, stains and the like can be distinguished, and the accuracy of plate positioning in a complex industrial environment is improved.

The application provides a mower calibration method and device, electronic equipment, a storage medium and a mower. The method comprises the following steps: collecting a preset number of position data of the mower during movement relative to a charging pile; performing straight line fitting using the preset number of position data; and if the preset number of position data fits a straight line, determining the orientation of the charging pile according to the slope of the fitted straight line. Accordingly, the application can accurately determine the orientation of the charging pile, and has the advantages of high calibration accuracy and low calibration cost.

The invention discloses a wiring path planning method based on GIS coordinates. The method comprises the following steps: collecting original track coordinate information; the core distance and the reachable distance of each track coordinate point are calculated and compared with a global threshold value, and if the core distance and the reachable distance are larger than the global threshold value, noise points are removed; determining a turning point of the track according to the vector angle; segmenting the track and carrying out linear fitting; and determining an intersection point between the straight lines and a wiring direction, and generating a wiring path. By using the method, abnormal noise points in the GIS trajectory data can be intelligently identified and eliminated, and the planning rationality of the wiring path is improved. The method can be widely applied to the field of engineering wiring.

The application discloses a battery welding mark defect detection method and device based on 3D point cloud segmentation and a medium, relates to the technical field of welding mark defect detection, and establishes quick indexing to realize batch data reading and quick regional segmentation by organizing original point cloud data in a matrix form; after any rectangular region is segmented by columns, each column sub-point cloud retains trajectory continuity along a scanning direction, direct line fitting can be performed to construct a local reference line, and calculation amount is reduced; by calculating distance deviation of point clouds in each segmented region to the corresponding reference line, abnormal points deviating from the reference line can be quickly located, the application only needs once matrix indexing conversion, once regional segmentation and once line fitting operation, avoids time-consuming nearest neighbor search, surface reconstruction or voxelization process in traditional point cloud processing, can accurately identify typical defect types such as broken welding, cracks and welding tumors, and effectively improves detection precision and efficiency.