100 results about "Vanishing point" patented technology

The invention discloses a building outer wall falling risk detection method and system based on deep learning, and the method comprises the steps: obtaining an original surface image, extracting vertical face geometric features, constructing a homography matrix based on vanishing points, carrying out the geometric correction, and reconstructing an orthographic projection image; performing enhancement processing on the orthographic projection image, extracting an effective detection area and intercepting a detection image; inputting the detection image into a deep learning segmentation model into which edge weight constraint is introduced, and performing semantic segmentation, binaryzation and optimization to obtain a falling region; a mapping relation is established according to the actual physical size of the building outer wall, and pixel information of the falling area is converted into multi-dimensional parameters such as the actual physical area, the elevation, the width and the height; and combining the defect intensity input quantification risk assessment model to calculate a comprehensive risk index, determining a risk level and outputting a result. Automatic identification and quantitative evaluation can be realized, distortion and background interference are eliminated, accurate conversion from pixels to a multi-dimensional physical space is realized, and a scientific basis is provided for safety investigation.

The invention relates to a visual inertial positioning method and device for a railway train fused with scene information, and the method comprises the steps: building four geometric constraint models through combining a visual inertial odometer with the geometric features of a railway environment; the constraint models are respectively a sleeper advancing distance constraint model, a camera-rail surface absolute height constraint model, a rail vanishing point constraint model and a non-integrity constraint model. And the scene prior information is deeply fused with the visual inertial odometer. In a sliding window optimization framework, an IMU pre-integration residual error, a visual reprojection residual error and a geometric constraint residual error are jointly optimized through a dynamic marginalization strategy, multi-source information collaborative pose estimation is realized, high-precision visual inertial positioning of a train is realized, and particularly, excellent robustness is shown in an environment in which GNSS signals are shielded.

An information processing apparatus acquires an image taken by a camera and estimates a vanishing point by inputting the image to a trained model, the trained model being generated by subjecting a learning model for pose estimation to machine learning using a heatmap indicative of a true value for the vanishing point as training data.

The invention discloses a non-motor vehicle road network construction method based on streetscape images. The non-motor vehicle road network construction method comprises the following steps of S1, obtaining a plurality of streetscape images and metadata and track sequence data of the streetscape images; s2, extracting a motor vehicle lane area and a non-motor vehicle lane area from each streetscape image, identifying road infrastructures and states related to non-motor vehicle lanes, and classifying tracks; s3, fusing the obtained road area, road infrastructure and state and track sequence data to obtain non-motor vehicle geometric road section information, and constructing a topological relation between non-motor vehicle road sections; s4, determining the actual width of the non-motor vehicle lane according to the vanishing points in the directions of the motor vehicle lane and the non-motor vehicle lane and the vanishing points in the horizontal direction; and S5, attaching the attributes of the non-motor vehicle lanes to the road network geometric data to form a non-motor vehicle road network. According to the method, the non-motor vehicle road network containing geometric road section information, a road section topological relation and lane attribute information is constructed.

The invention relates to the technical field of tunnel image data processing, in particular to a tunnel smoke image recognition method and system based on multi-scale feature fusion. The method comprises the following steps: obtaining the spatial weight of each pixel point, wherein the spatial weight is in negative correlation with the distance from the pixel point to a vanishing point; obtaining an enhanced gradient of each pixel point, wherein the enhanced gradient is in positive correlation with the closeness degree between the second characteristic value and the first characteristic value of the pixel point, the first-order gradient module value and the spatial weight; taking the enhanced gradient greater than a gradient threshold as a seed point to perform connected domain analysis to obtain a candidate cluster in the tunnel image; according to the method, the extinction coefficient of the candidate cluster where the seed point is located is obtained, the pixel point corresponding to the candidate cluster is obtained from the historical image sequence of the current tunnel image, time domain accumulation is carried out on the enhancement gradient and the extinction coefficient of the pixel point, the smoke judgment score of the current tunnel image is obtained, tunnel smoke is recognized, and the accuracy of the recognition result is effectively improved.

An information processing apparatus estimates a plurality of vanishing points and an intrinsic parameter of a camera by inputting an image to a learning model trained by machine learning in advance for estimating a vanishing point and an intrinsic parameter of the camera; projects the estimated vanishing points onto a unit sphere in a world coordinate system on the basis of the intrinsic parameter; and calculates a rotation angle indicative of a posture of the camera on the basis of errors between the projected vanishing points and a plurality of reference vanishing points projected onto the unit sphere in advance.

The invention provides a point and line feature-based pose estimation method and electronic equipment. The method comprises the following steps of extracting point features and line features from an environment image; calculating one or more vanishing points in the environment image based on the extracted line features; according to the geometrical relationship between each line feature and the vanishing point, grouping the line features into different dominant direction sets, and removing the line features which do not belong to any dominant direction set to obtain an optimized line feature set; and fusing the point features and the optimized line feature set, taking the fused point features and the optimized line feature set as input together, performing pose estimation through a visual SLAM algorithm, and outputting pose information of the camera. According to the method, the weak texture environment is effectively dealt with, the point features and the line features are fused, and the line features are optimized by using the vanishing points, so that the key problems that the traditional visual SLAM which only depends on the point features is rare in features and easy to fail in tracking in the low-texture structured environment are solved, and stable and high-precision positioning in the severe environment is realized.

The invention provides a vehicle-mounted camera external parameter calibration method, electronic equipment and a program product, and relates to the technical field of vehicles. The method comprises the following steps: when a camera external parameter dynamic calibration starting condition is satisfied, acquiring a road image sequence corresponding to each camera of a vehicle; each group of road image sequence comprises at least one image of a structured road and a corresponding acquisition moment; determining vanishing point positions and horizon line positions corresponding to the cameras by utilizing an end-to-end vanishing point / horizon line detection model based on each group of road image sequences; wherein the end-to-end vanishing point / horizon line detection model is used for outputting the vanishing point position in the road image sequence, or outputting the vanishing point position and the horizon line position in the road image sequence; and according to the vanishing point position and the horizon line position corresponding to each camera, external parameters of each camera are determined. According to the invention, an efficient and simple solution is provided for external parameter calibration of the vehicle-mounted camera.

This invention proposes a camera focal length and attitude calibration method based on camera position and dual vanishing points, belonging to the fields of computer vision, SLAM, and photogrammetry. This invention only requires knowledge of two sets of parallel lines in space, measuring the camera position and the unit direction vectors of the parallel lines, capturing feature images of the parallel lines, obtaining the imaging relationship in the camera, and extracting the corresponding vanishing points. Utilizing the important geometric phenomenon that the angle between two straight lines in the camera coordinate system is equal to the angle between the unit direction vectors of the two sets of parallel lines, a method for quickly solving the camera focal length is established. Finally, the correspondence of unit direction vectors is converted into the correspondence of spatial points between two coordinate systems with the same origin to solve for the camera attitude. This invention reduces the number of vanishing points required for camera calibration, shortens the calibration time, provides a unique solution, and can simultaneously solve for focal length and attitude, among other advantages.

The invention discloses a camera / laser radar joint calibration method based on vanishing point constraint, and belongs to the technical field of robot perception and computer vision, and the method comprises the following steps: S1, obtaining a circle center coordinate and an orthogonal vanishing point in a camera coordinate system, and a circle center coordinate and a direction vector of an orthogonal straight line in a laser radar coordinate system; s2, determining a rotation matrix from a camera coordinate system to a laser radar coordinate system; and S3, estimating a translation vector from the camera coordinate system to the laser radar coordinate system. According to the camera / laser radar joint calibration method based on vanishing point constraint, through a rotation-translation decoupling form, direction information of strong constraint is provided by using an orthogonal groove and an outer frame, and rotation is preferentially locked through vanishing point and straight line fitting, so that the influence of a circle center error on rotation is significantly weakened, and the calibration precision is improved. And the overall precision and stability are improved.

This invention discloses a method for extrinsic parameter calibration between a camera and a lidar based on the vanishing point method, comprising the following steps: S1, acquiring an optical image of a target reference object using a camera, and acquiring laser point cloud data of the target reference object using a lidar; S2, determining the principal point and focal length of the camera based on the optical image; S3, processing the laser point cloud data based on the determined principal point and focal length of the camera to obtain a lidar projection image; S4, calibrating the extrinsic parameters between the camera and the lidar using the vanishing points of the optical image and the lidar projection image, and obtaining the extrinsic parameter calibration results; S5, further optimizing the camera's principal point, focal length, and extrinsic parameter calibration results using an iterative optimization method to obtain optimized extrinsic parameter calibration results. This invention utilizes vanishing points to solve the extrinsic parameter calibration problem between a camera and a lidar in scenarios without a calibration board, improving the efficiency and accuracy of extrinsic parameter calibration between lidar and camera.

The application relates to the technical field of lane line detection, and discloses a lane line detection method, device, computer equipment and storage medium, the method comprising the following steps: acquiring a lane image, detecting the lane image, and generating vanishing point coordinates; based on the vanishing point coordinates, a lane line detection model is used to generate a first lane line category and a second lane line category; lane line fusion is carried out based on the first lane line category and the second lane line category, and a lane line detection result is generated. The application improves the detection precision and accuracy of the lane line and reduces the safety hidden danger of automatic driving.

The application discloses a lane line detection method based on vanishing points and color filters, comprising the following steps: S1, acquiring continuous multiple frames of images from a driving video for pretreatment, acquiring the vanishing point position of the lane line under the driving environment, and then adaptively extracting a region of interest (ROI); S2, filtering the ROI according to the color features of the lane line to obtain a binary image, acquiring all the connected regions, their centroids and inclination angles in the binary image, and screening the connected regions meeting the lane line features based on the vanishing point features and angle constraints; S3, further acquiring the centroid points meeting the lane line features from the remaining connected regions, fitting the acquired centroid points using a least square method, and identifying the lane line. The lane line detection can be completed under complex conditions such as lane line damage, lane marking interference and lane line occlusion, has certain robustness, and improves the accuracy and real-time performance of the lane line detection method.

The application discloses a kind of line feature-based visual SLAM positioning precision promotion method, including extracting line feature on input image and short line segment is merged;Line feature is grouped according to angle to improve line feature matching speed;Angle and length threshold are set to screen line feature;The distance of candidate point and other line features is calculated, remove the outlier greater than threshold, calculate the center point as vanishing point to make the variance of in-point minimum;According to the coordinate variation of vanishing point, judge whether the motion of camera occurs rotation;Angle threshold is set, and the line feature with the included angle less than threshold is filtered out;Line feature is grouped according to angle to speed up the matching process of line feature after filtering;Normalize parameter is calculated by line feature endpoint;The camera pose is calculated by iteration to minimize the reprojection error.The application filters out the degenerate line feature by setting angle threshold, avoids the influence of degenerate line feature on pose calculation, and improves the accuracy of camera pose calculation by solving camera pose iteratively.

The application provides a fish-eye camera calibration method and a readable storage medium. The calibration method comprises the following steps: acquiring a calibration pattern; calibrating a first parameter in a manner of solving a vanishing point based on the calibration pattern; and calibrating a second parameter based on the calibration pattern and the first parameter. The first parameter comprises a focal length of the fish-eye camera and a translation parameter from an image plane coordinate system to an image coordinate system; and the second parameter comprises a distortion coefficient of the fish-eye camera. In this way, the parameters to be calibrated are solved in two steps, thereby avoiding the phenomenon that a large amount of data is required, a long calculation time is needed, a calibration result is unstable, and robustness is poor due to the calibration of a large number of parameters at one time. The calibration method can complete calibration only by using one calibration image under certain conditions, thereby solving the problem that the time, cost and robustness are not ideal in the prior art.

The application relates to the technical field of image processing, and discloses a claim settlement data anti-fake detection method, device, equipment and medium, belongs to the technical field of image processing, is applied to a financial technology scene, and comprises the following steps: performing shooting posture recognition on a shooting device to obtain a real shooting posture; performing edge line segment detection and vanishing point recognition on an original image obtained by the shooting device to perform shooting posture inference according to the recognized object vanishing point position, and obtain an inferred shooting posture; and performing anomaly detection on the original image according to the inferred shooting posture and the real shooting posture to obtain an image category obtained by whether the shooting device truly shoots a damaged object. In the application, the real shooting posture at the shooting moment of the shooting device is obtained, and the inferred shooting posture is inversely deduced according to the object vanishing point position detected from the original image, so that the authenticity of the claim settlement image is detected according to the inferred shooting posture and the real shooting posture, and the accuracy of the claim settlement anti-fraud detection is improved.

The invention provides a relative pose measurement method based on a sequence frame image, and the method comprises the steps: collecting an infrared image of a target in real time through an infrared camera, and collecting the inertial pose information of an aircraft in real time through an inertial navigation system in the process of measuring the relative position pose of the aircraft; grouping the acquired images in the form of a sliding window; obtaining a first homography matrix and a second homography matrix; determining a final homography matrix; obtaining a final point line feature on the current frame image; acquiring vanishing points of the target left line and the target right line intersected on the image coordinate system and vanishing points of the target starting line on the image coordinate system; establishing a pose resolving equation; and performing pose calculation on the pose calculation equation to obtain a pitch angle, a course angle and a roll angle of the aircraft and lateral displacement, forward displacement and vertical displacement of the aircraft relative to the target.

This invention relates to the field of vehicle assisted driving technology, and discloses a method, system, and electronic device for three-dimensional matching of wheel trajectories. The method includes: acquiring a first image and a second image with a fixed spatial positional relationship, which are synchronously acquired by an image acquisition device; acquiring a current frame image from the first image or the second image; estimating an initial wheel trajectory based on the vanishing point in the current frame image and the vehicle's inherent parameters; iteratively updating the trajectory parameters by combining real-time steering wheel angle and vehicle speed; determining the region of interest and performing feature extraction and matching on the image within the region; optimizing through cost aggregation and extracting a single disparity value along the trajectory path. This method solves the problems of high computational cost, difficult deployment, and difficulty in adapting to dynamic changes in vehicles with fixed regions of interest in large-scale deep learning networks, thereby improving the accuracy and real-time performance of wheel trajectory tracking and providing a more reliable perception basis for trajectory prediction and active control of vehicle assisted driving systems.

A method of performing a camera to ground alignment for a camera system on a vehicle. The method includes determining if enabling conditions have occurred and estimating a location of a vanishing point in a source image. Ground lines are selected based on a source image. A lane line detection is performed based on clustering of the ground lines to determine lane lines in the source image. At least one of pitch, yaw, or roll of the vehicle are estimated from the source image. A cost function based on estimates of pitch, yaw, and roll is minimized to obtain an optimal pitch value, an optimal yaw value, an optimal roll value, and lane lines from the source image. A sliding window-based refinement is performed on source images. Alignment results are broadcast to a downstream application or it is determined if the camera system on the vehicle is misaligned.

Techniques are described for identifying correspondences between images to generate a fundamental matrix for the camera positions related to the images. The resultant fundamental matrix enables epipolar geometry to correlate common features among the images. Correspondences are identified by confirming feature matches across images by applying a homography to data representing features across images. Further techniques are described herein for generating a representation of a boundary of a feature of a structure based on a digital image. In one or more embodiments, generating a representation of a boundary of a particular feature in a digital image comprises determining a portion of the image that corresponds to the structure, and determining a portion of the image that corresponds to the particular feature. One more vanishing points are associated with the portion of the image corresponding to the particular feature. The one or more vanishing points are used to generate a set of bounding lines for the particular feature, based on which the boundary indicator for the feature is generated.

The application discloses a kind of inland river ship freeboard measurement method based on monocular vision.First, the internal parameter calibration of monocular camera is carried out using checkerboard by Zhang Zhengyou calibration method, and the internal parameter of camera is obtained;The camera shoots the side view of the ship, and the Deeplabv3+ model is used to segment the part between the ship deck line and the waterline according to the side view of the ship;Further, the ship deck line and the waterline are detected to determine the position of the ship freeboard and calculate the pixel height of the ship freeboard;The conversion from pixel height to actual height is realized by the camera internal parameter obtained by calibration, and the real value of the ship freeboard is calculated.The application models the parameters of the camera itself, does not rely on vanishing point and vanishing line for ship freeboard measurement, and provides assistance for the safety navigation of inland river ships on water as the basis for ship overload detection.

A method for adjusting a region of interest (ROI) in a dynamic image is implemented by an in-vehicle electronic device installed on a vehicle. The method includes: for each of a first predetermined number of successive image frames, detecting a pair of lane line segments and an intersection point; using the first predetermined number of pairs of lane line segments and the first predetermined number of intersection points, determining a first vanishing point and a temporary ROI; for each of a second predetermined number of successive image frames, calculating a pair of slopes associated with the pair of lane line segments within the temporary ROI; obtaining a second vanishing point based on the second predetermined number of pairs of slopes; and in a case where the second vanishing point and the first vanishing point correspond with one another, storing the temporary ROI as an updated ROI.

The invention discloses a building height estimation method based on a single image of a smart phone, and the method comprises the steps: extracting vanishing points and feature lines, and fusing the broken feature lines; the feature lines are grouped according to the corresponding relation with the vanishing points, at least one candidate building boundary line is screened out for each building edge, and intersection points of the candidate building boundary lines are defined as candidate corner points; according to the effective length of the candidate building boundary line and the geometric length of the building edge, calculating the confidence degree of the candidate corner point, and selecting the candidate corner point with the highest confidence degree as a final building corner point; constructing three-dimensional building angular points and projecting the three-dimensional building angular points to an image plane; and constructing an optimization cost function based on a confidence weighted reprojection error between the projection coordinates and the building corner coordinates with confidence, optimizing the to-be-optimized parameters by minimizing the confidence weighted reprojection error, and finally obtaining a building height estimation value. On the basis, high-precision building height measurement can be carried out only by using the smart phone.

The embodiment of the invention provides a camera calibration method and system, and relates to the technical field of vision. The camera calibration method comprises: based on a line segment set associated with a terminal device, obtaining an orthogonal vanishing point pair corresponding to the type of the terminal device and a line segment group corresponding to the orthogonal vanishing point pair, the line segment set associated with the terminal device comprising line segments identified based on an image shot by the terminal device; and according to the orthogonal vanishing point pairs and the corresponding line segment groups corresponding to the terminal devices of the same model, generating the camera internal reference of the terminal devices of the model. According to the technical scheme, special personnel do not need to collect images for calibration, the calibration efficiency can be obviously improved, and the model coverage rate of the calibrated terminal equipment can be maintained at a high level.

This invention discloses a method and apparatus for determining the open / closed state of a door. The method includes: acquiring at least one current image containing environmental objects using an image acquisition unit fixed to the door; wherein the environmental objects include at least one set of parallel contour lines in three-dimensional space; extracting at least one current vanishing point formed by the projection of the contour lines onto an image plane from the current image; comparing the current vanishing point with pre-stored reference vanishing points; and determining the state of the door based on the comparison result. This invention utilizes vanishing points generated by the inherent parallel line structure in the environment to determine the door state. Because the line structure is stable and highly tolerant to changes in illumination, its robustness to changes in light and noise in the environment is greatly enhanced.

The application discloses a low-complexity unmanned aerial base road anomaly identification method and belongs to the field of computer vision; specifically, firstly, road images with parallel line structures are collected according to continuous time sequences, edge features of each frame of image are extracted, and then edge straight lines are extracted, and the intersection point coordinate median of all non-collinear straight lines is the vanishing point coordinate; then, the estimated attitude angle of the unmanned aerial vehicle is derived, compared with the attitude angle measured by the sensor to eliminate the error of unmanned aerial vehicle jitter, and then the attitude angle deviation is calculated; the detection time is segmented, and the road detection unit is corresponded; elements with the attitude angle deviation exceeding a threshold value are marked as abnormal; a road detection unit with the number of abnormal elements exceeding a threshold value is found out, and the difference between each pair of adjacent attitude angle deviations and the time difference of the unit are calculated; when the deviation mean or the time difference mean is greater than or equal to a threshold value, the road detection unit has an anomaly, an alarm is given, and output is performed. The application saves the time of the unmanned aerial vehicle for executing a road anomaly detection task.

The application discloses a kind of computer vision and image processing technical field's based on target interception and vanishing point hybrid calculation image rectification method and system, to solve the problem that cannot quickly find vanishing point in the image rectification of prior art, and it is more complex to remove pseudo vanishing point etc., it includes collecting image data, intercepting target image, positioning and linear fitting to target image edge to obtain vanishing point vector data, by vanishing point hybrid calculation model processing to obtain the final predicted vanishing point coordinate, finally carries out image rectification.The application first uses target detection model to detect the position where main target is located, then intercepts, reduces the interference of background information, then the vanishing point hybrid calculation model is fused and calculated to the vanishing point obtained by fitting, to obtain real vanishing point coordinate, reduce vanishing point screening complexity.

The invention discloses an automatic image distortion removing method and system based on lane line and single vanishing point constraint, and the method comprises the steps: obtaining a to-be-corrected original distortion image, carrying out the preprocessing of the original distortion image through a Canny edge detection algorithm, and extracting and screening all lane line edge contours; optimizing the edge contours of the screened lane lines to obtain distortion coordinates of each contour; on the basis of the distortion coordinate of each contour, obtaining a coordinate set containing a reference point of a group of curve segments by using the constructed transformation model from the ideal coordinate to the distortion coordinate; obtaining a distortion parameter based on straight line fitting based on the parameter-containing point coordinate set; single vanishing point constraint is introduced, and distortion parameters are optimized; and on the basis of the optimized distortion parameters, carrying out inverse operation through a transformation model to obtain a distorted image. According to the method, the distortion parameter of the camera can be automatically, accurately and robustly estimated only by using a single image containing the lane line, and image distortion removal is completed.

The invention discloses a deep learning-based thunder vision information fusion recognition method and system, and the method comprises the steps: carrying out the target detection and pixel-level segmentation of a video stream of a camera, obtaining a fine vehicle pixel mask, extracting line segments in an image region corresponding to the vehicle pixel mask, determining the vanishing points of a vehicle in three main directions through the vanishing point clustering, and carrying out the recognition of the thunder vision information. And recovering a vehicle three-dimensional pixel surrounding frame based on the vanishing point and the vehicle pixel mask, taking the vertex of the surrounding frame as a temporary calibration plate, estimating and optimizing internal and external parameters of the camera online, fusing radar speed measurement and visual attitude information, and outputting the six-degree-of-freedom pose of each target. According to the method, high-precision and high-robustness vehicle three-dimensional position information and attitude parameters are obtained, and low-cost and high-reliability high-quality traffic data are continuously and stably provided for an intelligent traffic system.