599 results about "Line fitting" patented technology

The invention relates to a vector-relation-based method for calibrating single-line laser radar and a CCD camera. Point set information of the laser radar for scanning a V-shaped target is extracted in a laser coordinate system, and direction vectors and intersection coordinates of straight lines in two different planes of the target are obtained by means of straight line fitting; the CCD camera is used for capturing images in a camera coordinate system, target plane equations and an equation of a plane passing through an original point and laser radar scanning lines are obtained by processing image information, a straight-line equation of laser radar scanning is built, and furthermore, the direction vectors and the intersection coordinates of the straight lines are obtained; finally, calibration is finished according to the relations between direction vectors and the intersection coordinates of the straight lines corresponding to the different coordinate systems. According to the method, no object in a calibration scene needs to be moved, collection of all calibration data can be completed at a time, and calibration efficiency is improved greatly. According to the method, the direction vectors of the straight lines of the laser scanning target planes under the coordinate systems of sensors to be calibrated are obtained directly, calibration precision is guaranteed, and meanwhile the calibration algorithm is simplified.

The invention discloses a fast image recognition method of an insulator contour, comprising the following steps: (1) transforming a taken color image to a gray image through brightness calculation and extracting the edge contour of the image, and obtaining the shape of a known region after the extraction; (2) carrying out ellipse fitting on the edge contour of the known region, utilizing hough transform to detect a boundary curve and obtain each parameter of a prolate axis, a minor axis and a central point of an ellipse; (3) carrying out threshold processing on contour area, and setting a proper area threshold according to the contour area; (4) carrying out linear fitting on the center of the ellipse, and fitting a line through a two-dimensional point set by seeking sumi rho(ri); and (5) demarcating and outputting insulator pixels. The invention aims at specific requirements of patrol and examination of a helicopter or a robot to an electric transmission line, realizes real-time and precise extraction of the insulator, provides solid foundation for realizing close shot and part defect diagnosis of a follow-up camera, and has favorable theory and application prospect.

The invention discloses a bend target identification system and method based on multi-sensor fusion, which mainly aims at a problem of front target detection of a vehicle at the bend of expressway. The lane line is divided into a straight line portion of the near view field and a curve portion of the far view field. For information acquisition of a camera, lane line fitting and tracking at the near view field are completed by using Hough transform and Kalman filtering, and curve fitting at the far view field is completed by using a BP neural network. For information acquisition of radar, information of a static object group is extracted, and curve fitting is performed by using the BP neural network. through space-time alignment, the lane line information acquired by vision and the lane line information acquired by the radar are fused to determine a travelable region of the lane where the vehicle is located, and finally a bend target identification algorithm based on the fusion of the camera and the millimeter wave radar is provided by combining the travelable region and the lane line type so as to realize detection for targets at the bend.

The invention discloses a rapid image-recognizing method of a power line profile. The method comprises the following steps: (1) conversing a shot color image into a grey image by brightness calculation and extracting the border profile of the image; (2) adopting an improved probability Hough transformation method to make self-adaptive adjustment of a line segment length and a statistics number obtained from the image in a known region; (3) adopting fitting of a line and a direction template for the two-dimensional fitting of a direction pixel template and a distance pixel template with linear characteristics and realizing linear fitting by deriving sumi rho(ri); and (4) calibrating and outputting power line pixels by storing and displaying the finally detected and calibrated linear pixels in a polar coordinate mode or a rectangular coordinate mode. Aiming at the concrete requirements of helicopters or robots for inspecting transmission lines, the invention precisely extracts the transmission lines in real time, provides a solid foundation for the subsequent zoom-in shooting of a camera and the defect detection of parts hereafter and has favorable theoretical and application prospects.

The invention relates to the field of automobile driving safety, in particular to a vehicle intelligent driving control method, which comprises the following steps: in the vehicle driving process, using a laser radar to obtain the reflection point information of the road environment in front of the vehicle; determining a road boundary according to the reflection point information; determining a lane line according to the reflection point information or a road boundary; obtaining the curvature of the lane centerline according to the road boundary and the lane line fitting the lane centerline; calculating a steering wheel rotation angle to be adjusted for driving the vehicle along the lane centerline according to the curvature of the lane centerline. Laser radar is used to collect data and calculate the curvature of the road ahead, and the curvature is used to control the lateral motion of the vehicle. It has the advantages of high reliability and can improve the driving comfort, especially suitable for the automatic driving of the expressway, and can also enhance the existing adaptive cruise system.

The invention provides a temperature drift compensation method for gyroscope. The method comprises the following steps: 1) collecting temperatures of the gyroscope and angular velocity data of three axis of the gyroscope under a stable state; 2) carrying out sorting according to the temperatures to divide the temperatures into a plurality of intervals with a equal interval; 3) carrying out equivalent sampling for the angular velocity data within the intervals; 4) calculating arithmetic means for the sampled angular velocity data in each temperature interval, and adopting the arithmetic means as angular velocity representative values; 5) carrying out linear fitting for numerical value pairs of the temperature and the zero angular velocity through a linear fitting formula of y=a+bx to obtain values of a parameter a and a parameter b, wherein the x represents the temperature, the y represents the zero value; 6) measuring the angular velocity values and the temperature values of the three axis of the current gyroscope, and calculating the zero value through the linear fitting formula, then subtracting the zero value from the measured angular velocity values to complete the temperature drift compensation of the gyroscope. The method is applicable for a temperature drift compensation correction condition of general gyroscopes and can provides a compensation factor without a plurality of tests and emulations, and is simple and available.

The invention discloses a power line extracting and modeling method based on airborne LiDAR data. The power line extracting and modeling method includes the steps of (1) LiDAR point cloud data obtaining, wherein the LiDAR point cloud data are obtained through an airborne LiDAR measuring system; (2) power line extracting and modeling, wherein the step (201) of power line extracting includes the substeps that Hough transformation straight line detection is used for detection to obtain a plurality of straight line point sets, single-power-line detection is carried out on all the straight line point sets until all power lines are detected out, and the single-power-line detection process includes least square method straight line fitting and single-power-line point cloud data recognition; the step (202) of power line modeling includes the substeps that with a parabola as a modeling model, the least square method is adopted for curve fitting to obtain a power line model. The power line extracting and modeling method is simple in step, convenient to implement and good in using effect, the extraction precision of the power lines is high, the built power line model is accurate, and the problems that according to an existing power line extracting and modeling method, power line recognition is inaccurate, and requirements for data quality are high can be effectively solved.

The invention discloses a reading method of a pointer type meter based on depth learning, belonging to the field of depth learning and computer vision. The method of the invention utilizes Mask- RCNNobject detection and instance segmentation algorithm to divide the dial and pointer images firstly, then correcting the dial by perspective transformation, Then using PCA (Principal Component Analysis) algorithm to fit the segmented instrument pointer, Then judging the direction of the pointer according to the center coordinate of the smallest oblique circumscribed rectangle of the pointer and thecenter coordinate of the dial; Finally, calculating the pointer reading according to the slope and direction of the pointer by using the angle method. As that method of the invention can accurately classify the type of the instrument, high precision pixel level segmentation of the pointer and dial, under non-uniform illumination conditions, different scales still have good robustness, to solve the traditional pointer instrument recognition field of the dial and pointer positioning difficulties, uneven light, mirror reflection, blurred pictures caused by low recognition accuracy.

The invention discloses a detecting algorithm for identifying a meter needle. A color image I of an instrument to be detected is acquired; a computer reads the color image I of the instrument to be detected; graying processing is conducted on the color image I to obtain a gray level image I 1; the gray level image I 1 is cut to obtain a cut image I2; binarization processing is conducted on the cut image I2 to obtain an image I3 processed in a binarization mode; needle searching is conducted on the image I3 processed in the binarization mode, the needle is extracted from the image I3, and a needle image B1 is obtained; then slope of a starting scale line is solved through straight line fitting. According to the method, deflected angles of the needle are calculated by respectively conducting clockwise and anticlockwise radian scanning with the circle center as the center and the forward direction of the x axis as the starting scale line, then an average value of the deflected angles solved at two times is taken, then corresponding mathematical calculation is conducted to obtain a read scale pointed by the needle according to the average value of the angles and the slope of the starting scale line. The method is efficient and high in precision and can detect large patches of instruments.

The invention relates to a target vehicle course angle calculation method based on a three-dimensional laser radar. The method comprises the following steps of 1) using the three-dimensional laser radar installed on a vehicle top to collect a target vehicle and acquiring point cloud data of the target vehicle; 2) establishing a corresponding course angle parameter model of the target vehicle at a moment in a radar coordinate system; 3) according to the point cloud data of the target vehicle, calculating a distribution type of the target vehicle; 4) according to the distribution type of the target vehicle, carrying out cluster on target vehicle point cloud respectively so as to acquire an area of interest, wherein the area of interest indicates a main portion of a representation course angle; 5) according to a cluster result and the distribution type of the target vehicle, carrying out straight line fitting on two kinds of point cloud components respectively; 6) through combining the distribution type of the target vehicle with a corresponding straight line fitting result of the two kinds of point cloud components, calculating the course angle of the target vehicle. The method can be widely used in an intelligent vehicle environment perception technology field.

The invention discloses a lane line extraction method, apparatus and system, relates to the technical field of traffic, and mainly aims to improve lane line extraction precision and efficiency. The method comprises the steps of collecting a measureable real scene road image; by analyzing the measureable real scene road image, constructing a grid dynamic window-based lane identification region of interest, and performing lane line edge detection on the lane identification region of interest; and extracting lane lines according to lane line information obtained by detection and a lane line extraction model subjected to line fitting correction in a preset lane. The lane line extraction method, apparatus and system is suitable for measureable real scene road image-based lane line extraction.

The invention discloses a road lane line detection method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps of: generating a parallax image according to a binocular image of a vehicle running direction, and generating a U-parallax image and a V-parallax image according to the parallax image; carrying out linear fitting on pixel points, the gray values of which are not 0, in the U-parallax image and the V-parallax image, and extracting straight lines with different parallax values from the U-parallax image and the V-parallax image; determining a candidate lane line area according to a corresponding area, in the parallax image, of the straight line extracted in the U-parallax image and a corresponding area, in the parallax image, of the straight line extracted in the V-parallax image; obtaining image features of the candidate lane line area according to a corresponding position, in the binocular image, of the candidate lane line area; and obtaining a lane line detection result of the candidate lane line area according to the image features of the candidate lane line area. Through above technical scheme, the correctness and reliability of lane line detection is enhanced.

A dynamic road surface detecting method based on a three-dimensional sensor is provided. The three-dimensional sensor receives a plurality of laser-emitting points reflected from a road surface to generate a plurality of three-dimensional sensor scan point coordinates which is transmitted to a point cloud processing module. The point cloud processing module transforms the three-dimensional sensor scan point coordinates to a plurality of vehicle scan point coordinates according to a coordinate translation equation, and then transforms a plurality of vehicle coordinate height values of the vehicle scan point coordinates to a road surface height reference line according to a folding line fitting algorithm. An absolute difference of two scan point height values of any two adjacent scan points on each of the scan lines is analyzed to generate a discontinuous point. The point cloud processing module links the discontinuous points to form a road boundary.

The invention discloses a fast intelligent programming method for a spraying robot for planar/approximate planar workpieces. Firstly, laser is adopted to scan the surface of a workpiece to acquire a set of original point clouds, the point cloud of the workpiece is then intercepted, the point clouds are simplified and noise points are filtered; secondly, a two-dimensional plane point cloud representing the spraying surface is separated from a three-dimensional point cloud, the polygonal boundary features of the point cloud are further extracted, and straight line fitting is carried out; thirdly, the boundary polygonal features of the spraying surface are extracted through operations such as polygon fitting, correction and vertex sorting; and finally, the full-coverage path on the surface ofthe workpiece is planned. According to the fast, intelligent and de-teaching programming method for the planar/approximate planar workpieces, a tedious manual teaching process is not needed, the workpiece surface features are extracted through automatic scanning of low-cost 2D line laser, the full-coverage path of the robot is automatically optimized and generated, and the spraying efficiency andthe spraying operation quality of a specific workpiece surface can be effectively improved.

The invention discloses a method, a device and a system for determining lane departure, which relates to the technical field of intelligent vehicles, can accurately judge whether lane departure occurs under the conditions of no a plurality of types of sensors and no need of camera calibration results, and saves the system cost. The method provided by the embodiment of the invention is as follows that: edge detection is carried out to a lane image, to obtain the gradient size and the gradient direction of all pixels in the lane image; the gradient direction of the lane boundary is determined according to the gradient size and the gradient direction of all the pixels; the lane boundary is fitted by a straight line with the gradient size and the gradient direction of all the pixels as well as the gradient direction of the lane boundary to obtain the lane boundary straight line; and whether the lane departure occurs is determined according to the inclination angle of the lane boundary straight line. The invention is applicable to occasions on which lane departure needs to be determined.

The invention discloses a method for detecting a full line of a lane based on optical flow point locus statistics. The method comprises the steps of step 1, mounting a camera above the middle part of a one-way road; step 2, performing preprocessing on a video frame image; step 3, acquiring optical flow point sets of moving vehicles; step 4, dividing the optical flow point set of each moving vehicle by means of a DBSCAN clustering algorithm, and representing the divided optical flow point sets by a rectangular area with a fixed size; step 5, performing statistical stacking on the divided area of each moving vehicle, and performing binarization processing on a result; step 6, performing linear fitting on the middle point set of contour points of a white pixel area which accords with a condition in a binary image; and step 7, determining the full line of the lane by means of a line which is obtained through fitting the middle point set. The method provided by the invention is not affected by illumination, weather, vehicle and road condition. Furthermore the method realizes high detection precision for the full line of the lane and high robustness.

The invention discloses a deep learning based automatic checking method against a vehicle lane-pressing illegal behavior. The method comprises the following steps that a snapshot picture of a camera is obtained, cut and ordered; the license plate number of a target vehicle is obtained; a deep learning based target vehicle detection module is used to detect the target vehicle in different ordered images, and a target vehicle detection frame is obtained; scene cutting is carried out on the ordered image by means of deep learning based scene cutting module, and segmented solid line pixels are obtained; in each ordered image, a vehicle lane pressing illegal behavior determining module determines whether there is an intersection point between a solid line fitting straight line and a straight line of a lower frame of the target vehicle detection frame by calculation; and whether the target vehicle in the group of ordered images has a lane pressing illegal behavior is determined according toposition of the intersection point. Thus, the method is suitable for illegal behavior checking via the pictures shot by traffic cameras in the real scene.

The invention relates to a mobile phone screen defect detection method based on regular texture background reconstruction. The method comprises the following steps of firstly, carrying out Fourier transform on an image and calculating an amplitude spectrum of an image frequency spectrum; carrying out Hoff straight line fitting on a binary amplitude spectrum so as to acquire a filtering template; using the template to carry out filtering on a real portion and an imaginary portion of the image; then carrying out Fourier inverse transformation and normalization so as to acquire a background reconstruction graph without defects; and finally using an original graph to subtract the background reconstruction graph, and carrying out adaptive binarization so as to acquire a binary image which only contains the defects. By using the method, a screen defect under a regular texture background can be effectively positioned.

The invention relates to a correction method for an incomplete or deformed quadrangular image. The method comprises the five steps of edge point detection, abnormal edge point elimination, linear fitting, vertex calculation and image correction. The correction method for the incomplete or deformed quadrangular image is applied to an identification method identification system for certificates such as valuable documents, notes, identification cards and the like, and can be used for rapidly performing edge detection and tilt correction on defect and deformed valuable documents, notes or certificate images.

The invention discloses a multi-strategy adaptive lane line detection method based on stereoscopic vision, and the method is based on the stereoscopic vision, and improves the robustness of a lane line detection task through the fusion of the three-dimensional depth information of a disparity map and the RGB semantic information of a two-dimensional image. In the detection stage, a road surface area is adaptively segmented by priori knowledge of three-dimensional environment information to serve as a lane line estimation area, obstacles which are not related to detection are filtered out, andthe problem of interference is solved. In the lane line extraction stage, RGB semantic information of a two-dimensional image is used, and a multi-strategy fusion mechanism and a sliding window technology in an image time domain are adopted to further eliminate interference of areas such as tree shadows, road signs and local fouling related to detection. A three-order Bezier curve model is adoptedin the lane line fitting process, and order characteristics of different lane lines can be better expressed. According to the method, the robustness of a vision-based lane line detection task is greatly improved, and the data point search speed and accuracy are improved.

In a plane detection apparatus, a plane detection unit (3) includes a line fitting block (4) to select a group of distance data points being in one plane from distance data forming an image and extract lines from the distance data point group, and a region growing block (5) to detect one or more planar regions existing in the image from a group of all lines included in the image and extracted by the line fitting block (4). The line fitting block (4) first draws a line D1 connecting end points of the distance data point group, searches a point of interest brk whose distance to the line L1 is largest, segments the data point group by the point of interest brk when the distance is larger than a predetermined threshold, and determines a line L2 by the least-squares method when the distance is smaller than the predetermined threshold. In case there exists a larger number of data points than a predetermine number on one side of the line L2, the data point group is determined to be in a zig-zag shape, the data point group is segmented by the point of interest brk. These operations are done repeatedly. Thus, a plurality of planes robust against noises is detected simultaneously and accurately from distance data including measurement noises.

The invention discloses a method for tracking extended targets by means of extracting feature points by the aid of frameworks. The method includes preprocessing to-be-processed images by means of Gaussian smooth filtering so as to remove influence of noise on follow-up algorithms; dividing the smoothened images by an FCM (fuzzy C-means cluster) algorithm to acquire binary images; performing Hough transformation on the binary target images acquired by means of dividing the smoothened images, detecting first certain portions on the targets, extracting the feature points of second certain portions on the targets by the aid of the frameworks, linearly fitting the feature points on the frameworks to acquire axes of the targets, and utilizing intersection points of straight lines of the axes as final tracking points. Linear features of the first certain portions on the targets are obvious. Linear features of the second certain portions on the targets are unobvious. The method has the advantage that the targets can be stably tracked under the condition of violent posture change.

The invention discloses an anti-jamming sub pixel straight line fitting method. The method comprises the following steps that: carrying out ROI (Region of Interest) setting on an image, and detectingthe edge points of a straight line in the ROI; then, using a neighborhood weighting way to carry out subpixel refinement on the edge points, and calculating the subpixel gradient values of the edge points; through the synthetic judgment of a gradient threshold and a polarity direction, carrying out secondary curve fitting and smooth filtering on the point which conforms to a condition, and recording as a candidate straight line edge point; and then, using a straight line fitting algorithm based on an edge point distance weight to carry out multi-time iterative fitting on the candidate straightline edge point to obtain a straight line parameter, and calculating the point of intersection of the fit straight line and the ROI to obtain two end points of a final target straight line. The invention puts forward a high-accuracy straight line fitting algorithm based on the edge point distance weight, a multi-time iterative fitting strategy is used for greatly lowering the interference of an outlier and a noise pint for target straight line fitting, and therefore, the method has the advantages of high robustness, high accuracy and high anti-jamming ability.