1699 results about "Linear fitting" patented technology

The invention belongs to the field of intelligent automobile road detection and relates to a method for detecting road information and identifying forward vehicles based on vision. The method comprises image preprocessing, lane line characteristic parameter extraction, region-of-interest segmentation and vehicle outline identification. According to the method for detecting the road information and identifying the forward vehicles based on vision, the complexity of computation is simplified by extracting the regions of interest, filtering out background regions and reducing the processing scope; the processing result of each frame of image is obtained through fixed computation times by use of a line-by-line retrieval method, and differing from the characteristic, namely linear fitting on each bright spot, of Hough conversion, the method has outstanding advantages in algorithm instantaneity; the instantaneity of the Robinson direction model operator is improved, and an intermediate variable is set to reduce the computation times of each pixel point. The regions of interest are screened and judged by use of an information entropy and a vehicle tail symmetry characteristic in the target region, and therefore, the omission factor and the false drop rate of the algorithm are reduced.

Embodiments of the present invention provide methods for optimizing a lithographic projection apparatus including optimizing projection optics therein, and preferably including optimizing a source, a mask, and the projection optics. The projection optics is sometimes broadly referred to as “lens”, and therefore the joint optimization process may be termed source mask lens optimization (SMLO). SMLO is desirable over existing source mask optimization process (SMO), partially because including the projection optics in the optimization can lead to a larger process window by introducing a plurality of adjustable characteristics of the projection optics. The projection optics can be used to shape wavefront in the lithographic projection apparatus, enabling aberration control of the overall imaging process. According to the embodiments herein, the optimization can be accelerated by iteratively using linear fitting algorithm or using Taylor series expansion using partial derivatives of transmission cross coefficients (TCCs).

The invention provides an image processing method based on sparse sampling magnetic resonance imaging. Multiple phase-control coils are utilized, simultaneously data in an K space central area is collected in a high-density mode, Gaussian distribution is utilized to conduct random downsampling K space data of the periphery of the K space central area, the K space data which is collected by each coil conducts Fourier transform and is transformed into an image space, according to sensitive information of each coil, signals of the image space conduct linear fitting, a reconstructed spinning density image p is formed, and a frequency domain signal after postero-medial rotatory instability (PMRI) downsampling is utilized to obtain a reference image. Therefore, information which is based on local noise variance conducts ration and calculating for a regular bound term to achieve precise image reconstruction.

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 present invention discloses a lithium battery SOC estimation method based on a BP neural network. The method comprises the steps of (1) establishing a neuron model; (2) establishing a BP neural network model; (3) constructing a BP neural network algorithm; (4) obtaining the network sample data; (5) carrying out the sample SOC calculation. The neural network algorithm has the stronger non-linear fitting capability, and the relation between input and output can be obtained by training a lot of input and output samples on the condition of not needing to consider the internal structure of a lithium battery and for the external excitation, thereby being able to fitting the dynamic characteristics of the lithium battery very well to estimate the SOC of the battery. The method is high in estimation precision and can obtain higher precision on the condition of enough battery data samples, and the neural network SOC estimation has the very good applicability and is suitable for various power batteries.

The invention discloses a lane line detection method based on feature point piecewise linear fitting. The method mainly includes the following steps that image reading is conducted; region-of-interest region reading is conducted on a read image; edge extraction is conducted on an extracted region-of-interest region image; binaryzation is conducted on an edge image of an interest road; feature points are extracted from the binarized edge image, and a candidate feature point vector set is obtained; filtering is conducted on the candidate feature point vector set, and filtered feature point vectors are obtained; piecewise linear fitting is conducted on the filtered feature point vectors by using the least square method, and candidate lane line equations are obtained; the candidate lane line equations are recognized; according to features of video frames, recognized lane lines are tracked, and a final lane line is output. According to the method, lane lines of lanes can be effectively detected, and the method has good anti-jamming capability and good fault tolerance. Meanwhile, the method is small in computation amount, simple to achieve and high in practicability.

The invention relates to a motion compensation method based on motion state identification in real-time electronic image stabilization, which comprises the steps that: (1) the likelihood function of a motion type is trained; (2) a motion compensation model is built; (3) the offset of a current frame image with correspondence to the center point of a window is calculated; (4) a component motion is filtered, and an ideal motion parameter and a linear fitting parameter are calculated; (5) the motion state of the current frame image is identified, and a motion compensation parameter is set up; (6) according to the motion compensation quantity of three stages, the output position of the current frame image is determined. The method divides motion compensation into the three parts of jitter compensation, smooth motion compensation and deviation compensation; camera motion is divided into staring shoot and scanning shoot; by identifying the current motion state of a scene, the proportion of the three motion compensation parameters are adaptively adjusted, therefore the 'too smooth' and the 'lack of smooth' problems during the motion compensation solving process is solved. The motion compensation method has the advantages that, the image stabilization problems in various complicated motion states and during free shooting mode conversion are effectively solved, and the objective to real-timely output stable video is achieved.

The invention discloses a pointer instrument reading identification method. The method comprises the steps of extracting a dial plate, removing interference, and correcting the dial plate by using affine transformation; performing circle detection and straight line detection on the dial plate to obtain predicted circle center and pointer angle; based on features of a scale connected domain on thedial plate, screening out the scale connected domain, performing linear fitting on the scale connected domain, calculating an intersection point of every two fitting straight lines, and performing screening verification on a to-be-selected circle center by utilizing the predicted circle center and pointer angle to obtain the circle center of the dial plate, wherein a distance from the centroid ofthe scale connected domain to the circle center on the dial plate is the radius of the dial plate; and according to information such as the circle center of the dial plate, the radius of the dial plate, the straight lines of a pointer, extracting an arc scale bar of the dial plate, expanding the arc scale bar in a rectangular shape, then according to horizontal coordinate distribution of scale onthe rectangular scale bar, performing minimum and maximum scale detection, noisy point removal and scale insertion, and finally in combination with the pointer angle, calculating reading of the dial plate. The method is high in universality and high in timeliness; and the reading has relatively high accuracy.

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.

According to an angular point positioning method and apparatus which are provided by the present invention, firstly, an interest area on a target image is subjected to edge detection to acquire a plurality of edge pixel points, then the plurality of edge pixel points are partitioned into two fit areas according to preset rules, coordinates of each edge pixel point in each fit area is subjected to linear fitting to obtain two fitting straight lines and finally, angular point coordinates can be obtained by calculating a point of intersection of two fitting straight lines, and thus, in the image matching process, the required angular point position can be accurately positioned without manually presetting an offset and not only the manual operation is reduced, but also accuacy of angular point positioning and image matching is greatly promoted, so that system accuracy of a mechanism is promoted.

The invention discloses a network-connected vehicle positioning method based on a 3D laser radar and V2X. The method comprises the following steps of using a laser radar installed on a network-connected vehicle to scan an environment around a network-connected vehicle so as to obtain radar data; preprocessing the radar data, acquiring preprocessed laser point cloud data, converting the point clouddata to a network-connected vehicle coordinate system, and then, according to the density change characteristic of a radar point in the point cloud data, using a raster map to carry out point cloud segmentation so as to realize the separation of a pavement and barriers; carrying out the clustering of the barriers, acquiring a radar point set corresponding to each barrier, and then obtaining the contour of the barrier, then carrying out linear fitting to obtain the shape of the barrier, and combining the size of the barrier to realize barrier identification; and finally, realizing the exchangeof barrier information among other network-connected vehicles through a V2X module. In the invention, a problem that an existing vehicle positioning method has low accuracy and poor reliability is solved, and simultaneously problems that a requirement to the speed of a mobile communication network is high and cost is high are alleviated.

The invention discloses a residual error posterior-based abnormal value online detection and confidence degree assessment method. The method comprises the steps of collecting data, establishing time series data, performing linear fitting on the time series data to obtain a linear combination formula of data at a current moment and p pieces of previous data, and predicting a data value of subsequent time; comparing the predicted data value with an actually detected data value to obtain a predicted residual error series; determining a probability density function of the predicted residual error series by adopting a KDE (Kernel Density Estimation) method; performing posterior ratio check on the predicted residual error series, and judging whether the data at the current moment is an abnormal point or not; and by taking the time series data as an input, building an SOM state model, obtaining state series and state transition probability matrixes, defining an abnormal scoring function, and outputting an abnormal score. By comparing the probability that the data is the abnormal point with the probability that the data is a normal point, the abnormal value in the pollutant discharge concentration time series data is identified online, so that the accuracy and reliability of abnormal value judgment are improved.

The invention discloses a method for horizontal tilt correction of a number plate image. Due to the reasons of a shooting angle and the like of the number plate image, a number plate is tilted so that character segmentation is not facilitated, and the number plate needs to be corrected. After a series of image enhancement operations, obtained number plate edge images are good in quality; based on the edge images, the character law is utilized to search a legal character connected domain of the edge images, linear fitting is performed on an upper endpoint and a lower endpoint of the connected domain so as to find out the upper boundary and the lower boundary of a character zone, the slope is obtained, the tilt correction rotation angle is calculated, and the number plate is rotated. A removing method of a pseudo connected domain and a connected domain searching method are improved, and the robustness of the tilt correction method is greatly improved.

The invention relates to an estimating method of the main curvature and the main direction of point cloud data, which comprises the following steps of: preprocessing, estimating a normal transversal curvature, fitting a Weingarten matrix, computing the characteristic value and the characteristic vector of the Weingarten matrix and computing the main curvature and the main direction. In the method, the main curvature and the main direction faithful to an original object are obtained only by utilizing the scanning data and the estimated normal vector of a laser scanner. The main curvature and the main direction are computed by the method through least square linear fitting and the characteristic value and the characteristic vector of the matrix, the algorithm is simple, the computing result is accurate, and the time complexity is highly effective. The method is called as a normal transversal fitting method, and the computing result thereof has important application value in the fields of virtual reality, computer games, natural scene simulation, urban landscape design, data compression, characteristic extraction, object 3D reconstruction and the like.

The invention discloses a drivable region detection method based on a laser radar. The method includes the steps that the laser radar is used for scanning an actual traffic scene, and flat and rugged conditions of a current scene are obtained; scanning data returned by the laser radar are divided into a plurality of fragments through the height variation condition, an iterative linear fitting algorithm is used for extracting appropriate linear features from all the segments, flat regions are found out from the fragments which meet constraint conditions, and drivable regions are determined from the flat regions according to the requirements of the vehicle width; if a multi-line laser exists, corresponding drivable regions can be determined from the flat regions reflected by the line data on the basis of a drivable region of former line data from the near to the distant. According to the method, detection of the drivable regions in the actual traffic scene can be effectively completed, safe passage regions of an automobile are described accurately, and the method has good real-time performance, usability and robustness.

The invention discloses a designated-driving order predicting method and a designated-driving transport capacity scheduling method which can be used for airports. The designated-driving order predicting method comprises the steps of: establishing a history order database of each airport; carrying out area clustering on the airports according to order change similarity; carrying out time interval clustering on a plurality of basic time intervals according to order numbers in the basic time intervals of each area type so as to form different order prediction basic time intervals of each area type; extracting a corresponding order number and change factors in each order prediction basic time interval of each area type, adopting a BP nerve network to carry out non-linear fitting, and enabling each order prediction basic time interval of each area type to obtain a different order prediction model; and when an order prediction request is received, according to the request area type and order prediction basic time interval, selecting the corresponding order prediction model, and by combined with the change factors, predicting an order number. By adopting the designated-driving transport capacity scheduling method, a reasonable driver distribution scheme is generated according to the order prediction result.

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.

Provided are a method which permits complete training data and data with added errors, and enables the early and accurate discovery of errors in facilities such as a plant, and a system thereof. To achieve the objectives, (1) the behavior of temporal data is observed over time, and the trace is divided into clusters; (2) the divided cluster groups are modeled in sub spaces, and the discrepancy values are calculated as errors candidates; (3) the training data are used (compare, reference, etc.) for reference to determine the state transitions caused by the changes over time, the environmental changes, the maintenance (parts replacement), and the operation states; and (4) the modeling is a sub space method such as regression analysis or projection distance method of every N data removing N data items, (N=0, 1, 2, . . . ) (for example, when N=1, one error data item is considered to have been added, this data is removed, then the modeling is performed), or a local sub space method. Linear fitting in regression analysis is equivalent to the lowest order regression analysis.

The invention discloses a method for estimating the modulation frequency and starting frequency of a linear frequency-modulated signal. The method comprises the following steps of: I, acquiring a data sequence x(n), wherein n=0, 1, 2, ellipsis , N-1; II, initializing parameters; III, calculating the power spectrum Yi(12) of a data sequence xi(m) in an ith short time window; IV, estimating the instant frequency estimated value fi of the data sequence in the short time window by adopting a Rife interpolation algorithm; V, judging whether the data sequences of all short time windows are processed, if not, returning to the step III, otherwise, turning to a step VI; VI, calculating a kth iteration weight; VII, judging whether an iteration weight least square linear fitting stop condition is met, if not, returning to the step VI, otherwise, turning to a step VIII; and VIII, calculating modulation frequency and starting frequency parameters. Due to the adoption of the method, the accuracy ofparameter estimation can be increased on the premise of ensuring rapid estimation without performing complex calculation and parameter search.

A portable intelligent electronic nose for recognizing gas and its preparing method feature use of 4-8 sensor arrays whose signal output is serially sent to a regulator circuit, a pattern recognizer and a computer. The pattern recognition and non-linear fitting of nerve cell network, the artificial nerve network model with forward transfer, and the training algorithm with backward transfer of error are used. The electronic nose can detect one or several gases in the range of selected sensors and further possess the function of quantitative analysis.

The utility model discloses a beam hardening correction method of cone beam CT based on registration model simulation, which acquires multi-color projection data through circle locus cone beam CT scanning to a spare part. After acquiring CT images of sequence slices by cone beam CT reconstitution to the multi-color projection, the contour of certain pieces of the images are extracted so that a measurement point formed a plurality of closed contour lines is acquired. Projection simulation is processed after the registration of the measurement point and the CAD model of the part, and then the length of the part passing through the part at every imaging point is acquired. A hardening curve that passes through the original point is acquired by nonlinear fitting and a straight line that passes through the original point is acquired by linear fitting. The beam hardening constructed defect of the cone beam CT is corrected according to the hardening curve and the rectifying straight line. The utility model is flexible in application, and can approximately corrected through multi-color projection to unique color projection, and the beam hardening artifacts is reduced obviously after correction.

The invention relates to an identification and deviation-detection method for a lane, which comprises the following steps: (1) acquiring a lane image and carrying out pretreatment on the lane image; (2) carrying out Canny operator edge detection on the lane image which is subjected to the pretreatment to obtain lane edge images; (3) determining the position of a lane mark according to the obtained lane edge images and a Kalman predictor-based lane tracking method, selecting Kalman prediction areas, filtering out a set of effective points by using a distance discrimination method, and extracting lane parameters on the basis of optimizing the set of effective points; (4) extracting the lane mark by using the Hough conversion with linear fitting according to the obtained lane parameters; and (5) counting the number of background points and lane mark points in the Kalman prediction areas by using the starting point position and the dynamic prediction of a lane which are determined in the step (3), and solving the ratio of the background points to the lane mark points. With the adoption of the identification and deviation-detection method for the lane provided by the invention, the monitoring for lane condition can be rapidly and stably realized.

The invention discloses a method for automatically identifying pavement diseases. The method comprises the following steps of 1, converting an input pavement grey image into a binary image; 2, using a digital filter template for performing expansion processing and corrosion processing on the binary image obtained in the step 1; performing eight-communication mark on the image obtained in the step 2, obtaining the height and width of each communication area, and setting the communication area with the maximum value of the height and width smaller than the first preset threshold value to be black; 4, performing linear fitting on each communication area of the image obtained in the step 3, obtaining the length and direction vectors of a fitting line segment, obtaining the communication areas where the fitting segments with the length larger than the second preset threshold value are located, and taking the communication areas as seed areas; 5, obtaining confidence coefficients of all extended seed areas, if the maximum confidence coefficient is smaller than the confidence coefficient threshold value, judging that the diseases are not found in the pavement grey image, and if the maximum confidence coefficient is larger than a confidence coefficient threshold value, judging that the diseases are found in the pavement grey image.

The invention discloses a soil and stone mixed filling roadbed compaction degree detecting method, which comprises the steps of: randomly selecting a soil and stone mixed filling roadbed test site, and obtaining the site compaction degree by a single-point douche or a sand cone method; carrying out fast static test in a preset position near the test site and obtaining a curve between the penetration power P and the penetration depth w; calculating the average density Rhom of the soil and stone mixed filling roadbed and calculating the initial void ratio n0 in the preset position; carrying out linear fitting according to the curve between the penetration power P and the penetration depth w and obtaining the value of the initial intermediate quantity a0 and b0; calculating the void-free deformation modulus E0 of stone particles of the soil and stone mixed filling roadbed; and calculating the compaction degree of other positions, i.e. the compaction degree in the ordinary positions. The method can be used for fast, stably and accurately detecting the compaction degree of the soil and stone mixed filling roadbed and is suitable for any compaction process and roadbeds compacted by compaction machinery.

The present invention relates to a laser differential confocal tomography focusing method and device, and relates to the technical field of optical imaging and detection. The method uses a rear pupilto block half of a measurement beam, uses a spectroscopic differential confocal detection system to detect the unblocked measurement beam, and uses an absolute zero point of a differential confocal response curve to achieve high precision tomographic focusing. The method organically combines a laser differential confocal technique and a ray tracing technique to establish a ray tracing and compensation model to eliminate influence among each fixed focal surface parameters, and achieves fast trigger of focus through data near a linearly fitting absolute zero point. The method can obtain the differential confocal response curve by using only one detector, and realizes the tomographic focusing through the absolute zero point of the differential confocal response curve, greatly simplifies system structure, in the same time, avoids error introduced by adjustment inaccuracy, and greatly improves precision of focusing. The method will provide a new technical approach to the field of confocal imaging / detection.

The invention relates to a method and device for quickly measuring a building material emission key parameter, belonging to the field of indoor environmental tests. The method comprises the following steps: building an effect model for concentration in the measuring device in the building material VOC (volatile organic compounds) emission process; controlling the temperature of the measuring device to be always kept at a set value by a temperature controlling device (such as a constant-temperature water bath); putting a building material to be measured into the measuring device, and sealing the measuring device; in the building material emission process, measuring the concentration of target VOC in the measuring device for several times; finally, taking the average value of the concentration results of the last 2-3 times as a balanced concentration, and taking other concentration results as a hourly concentration; tidying into the mode of logarithm; and then, carrying out linear fit for emission time to obtain a slope and an intercept so as to obtain three key parameters, i.e. initial concentration, diffusion coefficient and distribution coefficient in the building material emission process. The environmental chamber system and the measuring method are simple, have the advantages of short test time and higher precision and are convenient for engineering application.

The invention provides a method for calibrating a Coriolis mass flowmeter. The method comprises the following steps of: firstly, performing estimated calibration on the meter, measuring an estimated zero point of the meter at zero flow of a full pipe, and setting the estimated zero point into the meter; selecting a larger flow point, measuring an estimated meter coefficient and setting the estimated meter coefficient into the meter; secondly, performing correction calibration on the meter, executing three flow accumulation experiments under each flow point, calculating an error of the accumulated mass flow under each flow point, obtaining a corrected coefficient of the estimated meter coefficient and a corrected coefficient of the estimated zero point by a linear fitting method according to the error so as to obtain a corrected meter coefficient and a corrected zero point, and setting the corrected meter coefficient and the corrected zero point into the meter; and finally, performing validation calibration on the meter, namely taking five flow points within a full measurement range of the meter, executing three flow accumulation experiments under each flow point, and calculating the error of the meter and the repetitiveness so as to determine a precision level of the meter. By the method, the precision level of the meter can be increased effectively.

The invention provides a target-free automatic measuring device and method for axis pose of a tubular part and aims to improve the measurement accuracy of the pose of the tubular part on the premise of automation, non-contact and no target. The method comprises implementation steps as follows: establishing a measurement coordinate system according to the measuring device; controlling a computer toacquire multiple section profiles of the tubular part located on a parallel section through a laser profile sensor; controlling the computer to calculate fitting points of axis of the tubular part and fitting points of busbars on each section; controlling the computer to calculate the pitch angle and the deflection angle of the axis of the tubular part; controlling the computer to calculate comprehensive fitting points of the axis of the tubular part, performing spatial linear fitting on these comprehensive fitting points to obtain pose parameters of the axis of the tubular part. The measuring device and method can be applied to precise measurement of the axis poses of tubular parts in an automatic tubular part assembly process to facilitate adjustment by a pose adjusting mechanism.

The invention discloses a method for measuring tree-crown volume fractal dimension by applying a three-dimensional laser image-scanning system. The method comprises the steps of utilizing the three-dimensional laser scanning system to scan a tree-crown, obtaining the three-dimensional space lattice data of the tree-crown, establishing the tree-crown three-dimensional space model and calculating the surface area and volume of the tree-crown; and then linear fitting by taking the logarithm value of the tree-crown volume as an independent variable and taking the logarithm value of leaf biomass as an induced variable so as to determine that the measured tree-crown volume fractal dimension is three times of the linear fitting slope. The method avoids felling stumpage and protects the forests; and simultaneously, the adoption of the fractal dimension as the new parameter representing the tree-crown pattern structure is a beneficial supplement for the forest-measurement and significant for further studying the growth of trees.

The invention discloses a lane line detection method which comprises the following steps: firstly, acquiring a lane line image through a camera, and calibrating a lane line width; secondly, performing lane line modeling to obtain a detection area; thirdly, detecting edge point pairs to obtain a lane line edge point pair picture; and finally, performing least square linear fitting on the two biggest connected regions in the lane line edge point pair picture to obtain a lane line. According to the method, accurate lane line detection can be completed under a complicated background, the interference resistance is high, the calculation process is simple, the calculated quantity is small, the algorithm is quick, the real-time performance is strong, and the popularization and application values are high.