340 results about "Projection model" patented technology

The invention discloses a parallax optimization algorithm-based binocular stereo vision automatic measurement method. The method comprises the steps of 1, obtaining a corrected binocular view; 2, matching by using a stereo matching algorithm and taking a left view as a base map to obtain a preliminary disparity map; 3, for the corrected left view, enabling a target object area to be a colorized master map and other non-target areas to be wholly black; 4, acquiring a complete disparity map of the target object area according to the target object area; 5, for the complete disparity map, obtaining a three-dimensional point cloud according to a projection model; 6, performing coordinate reprojection on the three-dimensional point cloud to compound a coordinate related pixel map; 7, using a morphology method to automatically measure the length and width of a target object. By adopting the method, a binocular measuring operation process is simplified, the influence of specular reflection, foreshortening, perspective distortion, low textures and repeated textures on a smooth surface is reduced, automatic and intelligent measuring is realized, the application range of binocular measuring is widened, and technical support is provided for subsequent robot binocular vision.

The invention belongs to crossing field of computer vision and intelligent robots and discloses a variational mechanism-based large-area indoor scene reconstruction method. The method comprises the following steps: step 1, acquiring calibration parameters of a camera, and building an aberration correcting model; step 2, building a camera position and gesture depiction and camera projection model; step 3, utilizing an SFM-based monocular SFM (Space Frequency Modulation) algorithm to realize camera position and gesture estimation; step 4, building a variational mechanism-based depth map estimation model, and performing solving on the model; and step 5, building a key frame selection mechanism to realize three-dimensional scene renewal. According to the invention, an RGB (Red Green Blue) camera is adopted to acquire environmental data, and a variational mechanism-based depth map generation method is proposed through utilizing a high-precision monocular positioning algorithm, so that quick large-area indoor three-dimensional scene reconstruction is realized, and problems of three-dimensional reconstruction algorithm cost and real-time performance are effectively solved.

The present invention is a method for exploring the viewpoint and focal length of a fisheye lens camera (FELC). It employs the characteristic of the central symmetry of the distortion of the fisheye lens (FEL) to set its optic axis by means of a calibration target with a plurality of symmetrically homocentric figures. Once the optic axis is fixed, further disclose the viewpoint (VP) of the FELC along the optic axis through a trail-and-error procedure and calculate its effective focal length and classify it to the primitive projection mode. Because the invention is capable of finding out both the internal and external parameters of the FELC and the calibration method is easy, low-cost, suitable to any projection model, and has greater sensitivity corresponding to an increasing in image distortion, the distortive images can be transformed easily to normal ones which fit in with a central perspective mechanism. Furthermore, the invention is also practicable and excellent in its applications in the fields of quality identification of the FEL and wide-view 3-D metering.

The present invention relates to a high precision method, model and apparatus for calibrating, determining the rotation of the lens scope around its symmetry axis, updating the projection model accordingly, and correcting the image radial distortion in real-time using parallel processing for best image quality.

The solution provided herein relies on a complete geometric calibration of optical devices, such as cameras commonly used in medicine and in industry in general, and subsequent rendering of perspective correct image in real-time. The calibration consists on the determination of the parameters of a suitable mapping function that assigns each pixel to the 3D direction of the corresponding incident light. The practical implementation of such solution is very straightforward, requiring the camera to capture only a single view of a readily available calibration target, that may be assembled inside a specially designed calibration apparatus, and a computer implemented processing pipeline that runs in real time using the parallel execution capabilities of the computational platform.

The present invention provides a reconstruction method of human posture based on the geometrical skeleton, including:determining human skeleton pattern; obtaining 3D human skeleton pattern, pre-processing image; obtaining bianry image of separation of the background and the human; acquiring human geometrical skeleton; obtaining linear geometrical skeleton; labelling articulare of the start frame; bonding the manual labelling articulare on the geometrical skeleton, shortening the initial error; tracing the articulare by light stream method; obtaining the new position by the light stream method; processing error judgement and position correction to the new articulare obtained by the trace with the combined geometrical skeleton; processing line correction calculated by the light stream method; re-constructing the human posture; converting the two-dimensinal coordinate of the articulare to the 3D skeleton pattern by the parameter evaluating method of the proportion orthogonal projection model. The invention improves accuracy of the posture reconstruction, obtaining a high processing efficiency, capable of processing stable and effect human posture reconstruction in the intelligent video monitor system.

The invention discloses a method for calibrating external parameters of a monitoring camera by adopting reference height, which comprises the following steps of: far vanishing point and lower vanishing point-based vision model description and related coordinate system establishment; projected coordinate calculation of reference plumb information-based far vanishing points and lower vanishing points in an image plane; reference height calibration-based camera height, overhead view angle and amplification factor calculation; design of a reference plumb direction-based horizon inclination angle calibration tool; and design and use of perspective projection model-based three-dimensional measurement software and three tools for three-dimensional measurement, namely an equal height change scale, a ground level distance measurement scale and a field depth reconstruction framework. The calibrating method is simple and convenient in operation, quick in calculation and high in measurement precision. The reference can be a pedestrian, furniture or an automobile; and a special ground mark line is not needed. The method allows the camera to be arranged at a low place, and the shooting overhead view angle is slightly upward as long as the bottom of the reference can be seen clearly in the video and the ground level coordinate system is definite.

The invention relates to a fish eye lens calibration and fish eye image distortion correction method which belongs to the field of digital image processing and is very suitable for occasions of vision navigation, mobile monitoring and so on. Since imaging using a large wide angle will cause serious distortion, generally, imaging correction is needed to facilitate human eye observation. The method provided by the invention is mainly technically characterized by establishing a space coordinate system 1 and employing a least square curve-fitting method to calibrate a fish eye image to determine the center andthe radius of a fish eye lens, establishing a cylindrical projection model in a space coordinate system UV, and setting one-to-one relationships among an image point q2 of the fish eye image, a point q1 on object sphere and a point q projected on a cylinder, wherein q1 is in vertical projection relation with a bottom plane on which q2 is located and line q1q parallels to line oq2, thus achieving the purpose of fish eye image correction.

The invention discloses a method for recognizing faces shaded by eyeglasses, which comprises the following steps of: inputting an image of an eyeglass-free face and a general face model to acquire corresponding points on a face image and the face model, and performing coordinate transformation on all peaks to adjust the peaks under the same coordinate system; processing the model to acquire a facade head model of which the posture is corrected; adding an eyeglass model on the head model and pasting textures; performing fuzzy processing and light reflecting processing on the lenses of the eyeglasses; and generating virtual samples in which the eyeglasses are worn under different conditions by using a projection model. The invention also provides a corresponding face recognition system. The method and the system have the advantages of wide simulation range, high generality, greatly improved recognition effect, real-time property, high practicability, high recognition rate and the like, can comprise more changes of the eyeglasses, are quick and are easy to operate.

The invention discloses a monocular vision range finding method based on geometric relation, and the method comprises the following steps: S1, calculating the distance between a section straight line of a target object and a camera lens in a horizontal plane; S2, calculating the distance between a target object and the optical axis of a monocular lens through the triangle similarity principle. According to the projection model of a camera, the method obtains the relation between a road surface coordinate system and an image coordinate system through geometric derivation, is simple in calculation process, is low in calculation complexity, and is lower in requirements for hardware. Meanwhile, the method can reach higher precision, and the error of the method is less than 0.5m. The method can effectively calculate the distance between the front vehicles or other obstacles under the conditions that the hardware configuration condition is very simple and almost no additional load and electric quantity is added, thereby achieving the effective avoidance. The method and device are good in application prospect, such as the technical field of automobile automatic driving or intelligent robot walking.

The invention relates to a visual inertial navigation SLAM method based on ground plane hypothesis. According to the method, feature points are extracted from an image to perform IMU pre-integration,a camera projection model is established, and camera internal parameter calibration and external parameter calibration between an IMU and a camera are performed; a system is initialized, a visually observed point cloud and a camera pose are aligned to the IMU pre-integration, and a ground equation and the camera pose are restored; the ground is initialized to obtain a ground equation, the ground equation under the current camera pose is determined and back projected to an image coordinate system, and a more accurate ground region is acquired; and based on state estimation, all sensor observation models are derived, camera observation, IMU observation and ground feature observation are fused to do state estimation, a graph optimization model is used to do state estimation, and a sparse graph optimization and gradient descent method is used to realize overall optimization. Compared with previous algorithms, the precision of the method is greatly improved, estimation of the camera pose can be limited globally, and therefore accuracy is greatly improved.

A picture composing apparatus designed to combine a plurality of images taken by a plurality of image pickup devices. In the apparatus, a first projecting unit projects the plurality of images taken by the image pickup devices onto a projection section in accordance with an image pickup situation of the image pickup devices to generate a plurality of first projected images, and a second projecting unit projects the plurality of first projected images to a three-dimensional projection model to generate a second projected image. Also included in the apparatus are a virtual image pickup device for virtually picking up the second projected image and an image pickup situation determining unit for determining an image pickup situation of the virtual image pickup device, whereby the second projected image is picked up by the virtual image pickup device in the image pickup situation determined by the pickup situation determining unit to combine the plurality of images taken by the plurality of image pickup devices, thus producing a high-quality composite picture. This apparatus can offer a natural composite picture in which joints among the images taken by the image pickup devices do not stand out. In addition, when mounted on a motor vehicle, this apparatus allows a driver to easily seize the surrounding situations and the positional relationship of the motor vehicle with respect to other objects.

The invention belongs to the field of advanced manufacturing technology, relating to a correction method of fisheye image distortion on the basis of cubic projection. The correction method comprises the following steps: 1. using a fisheye lens to obtain an imaging model, and calibrating the fisheye lens according to the imaging model to obtain a calibration parameter; 2. according to the collected fisheye image, determining a viewpoint, taking the viewpoint as the original point of a coordinate system, and building a cubic perspective projection model to obtain the cubic perspective projection of a spatial point; 3. building a mapping relation between the cubic perspective projection of the spatial point and the fisheye image; and 4. using bilinearity interpolation to realize the distortion correction of the fisheye image. The invention utilizes a cubic projection model to correct distorted fisheye images and can effectively overcome the geometric distortion existing in the original fisheye images, and the corrected image conforms to the intuitional feeling of people and has strong sense of reality.

A system, apparatus and method for determining a 3-D point cloud is presented. First a processor detects feature points in the first 2-D image and feature points in the second 2-D image and so on. This set of feature points is first matched across images using an efficient transitive matching scheme. These matches are pruned to remove outliers by a first pass of s using projection models, such as a planar homography model computed on a grid placed on the images, and a second pass using an epipolar line constraint to result in a set of matches across the images. These set of matches can be used to triangulate and form a 3-D point cloud of the 3-D object. The processor may recreate the 3-D object as a 3-D model from the 3-D point cloud.

The invention discloses a method for detecting a boundary of a lane where a vehicle is, which comprises the steps of: first adaptively extracting edge points for the part below a horizon of a road image according to pixel gradient amplitudes and calculating an edge direction, then searching and positioning a lane boundary by utilizing the particle swarm optimization in a parameter vector space ofa lane boundary projection model according to the extracted edge points, the edge direction and the lane boundary projection model; finally, calculating a plane geometric structure of the lane wherein the vehicle is, a position of the vehicle in the lane and an angle of deviation according to the searched lane boundary projection model parameter values and a parameter calculation method. The method can reflect an actual lane boundary curve more accurately, has better environment self-adaption capability, enhances the robustness of the lane detection, and has high reliability and strong antijamming capability.

A road condition video camera demarcating method under the traffic monitoring condition includes the following demarcating steps: (1) visual model describing and relevant coordinate system creating: according to the requirement of the monitoring system performance, a classical Tsai transmission projection model is used for reference, and according to the feature of the road condition imaging, a new visual model is presented after conducting corresponding amendment on the classical Tsai transmission projection model, and three kinds of coordinates are established. (2) demarcating the main point of a video camera and the extension factor: the image monitoring light stream is used as the demarcating basic element; by the extension movement of the video camera, a reference frame forecast image and the difference value of the light stream field in a real time frame sampling image are used as the restriction, a constraint equation is established by adopting the least square method, the main point coordinate of the video camera and the actual magnification coefficient of the video camera can be distinguished by the powell direction family method. (3) Demarcated object selecting and parameter linearity evaluating. (4) Accuracy making on the internal and external parameters of the video camera: according to all the angle points of the monitored image and the corresponding world coordinate point, the Levenberg-Marguardt optimization algorithm is adopted to make accuracy on the video camera model parameter, and then the video camera demarcating is finished.

The invention is suitable for the digital image processing field and provides a fish-eye lens correction method and device and a portable terminal. The method comprises the following steps: carrying out distortion correction on a fisheye image through an equidistant projection model to obtain an initial correction image, the image content of which is a calibration board; obtaining all angle pointsof the calibration board from the initial correction image, re-projecting angle point coordinates to the fisheye image to obtain rough angle point coordinate values of the calibration board in the fisheye image, and serving the angle points as feature points in the fisheye image; and carrying out iteration on the feature points in the fisheye image to obtain different parameter values within a preset parameter range, carrying out correction on the fish-eye lens through the equidistant projection model, and serving the parameter value obtained when the deviation amount is minimum as an accurate correction value of the fish-eye lens. The fish-eye lens correction method reduces preparation workload in the early stage, and is simple in operation process; a camera does not need to change position and angle; and the fish-eye lens correction method is wide in application range, does not need to set a lot of parameters, is simple to calculate, and meanwhile, realizes an accurate fisheye correction effect.

The invention discloses a multi-camera global calibration method based on high-precision auxiliary cameras and ball targets. According to the method, aiming at a multi-camera system which is arranged complicatedly and free of public view field, a global camera coordinate system serves as the world coordinate system, the three-dimensional coordinates, under local coordinate systems, of the sphere centers of a group (at least three) of ball targets are reconfigured by means of cameras to be calibrated and a global camera at the same time, a transfer matrix between two coordinate systems is solved on this basis, and then the transfer matrixes from all camera coordinate systems to the world coordinate system are obtained. When the three-dimensional coordinates of the sphere centers are reconfigured, a single-view method is adopted, a parameter equation is adopted for presenting a spheric projection model, and therefore sphere center reconfiguration precision can be improved greatly. The method has the advantages that operation is easy and flexibility is high. By the adoption of the method, calibration can be achieved conveniently for the multi-camera system which is arranged complicatedly and free of public view field.

The invention discloses an image processing method and device of iris positioning. The method comprises the steps that a human eye image in an iris area is obtained; the pupil boundary is positioned in the human eye image through a self-adaptation circular arc projection model algorithm; the outer boundary of the iris is positioned in the human eye image through the self-adaptation circular arc projection model algorithm; the eyelid area is removed from the human eye image, and the image of the interested iris area is extracted.

An object of the present invention is to provide a driving assistance system capable of displaying a picked-up image near a vehicle as a less-distorted image on a monitor.

A driving assistance system according to the present invention comprises an imaging means (2) for picking up a surrounding image of a vehicle (1) on a road surface, an image translating means (3) for executing an image translation by using a three-dimensional projection model (300), which is convex toward a road surface side and whose height from the road surface is not changed within a predetermined range from a top end portion of the vehicle (1) in a traveling direction, to translate the image picked up by the imaging means (2) into an image viewed from a virtual camera (2a), and a displaying means (4) for displaying an image translated by the image translating means (3). The three-dimensional projection model (300) is configured by a cylindrical surface model (301) that is convex toward the road surface side, and a spherical surface model (302) connected to an end portion of the cylindrical surface model (301). Accordingly, the straight line on the road surface, which is in parallel with the center axis of the cylindrical surface model (301), is displayed as the straight line, and thus a clear and less-distorted screen can be provided to the driver.

The invention discloses a self-adaptive and rapid correcting method for a fish-eye lens. The self-adaptive and rapid correcting method for the fish-eye lens comprises the steps that an equidistant projection model is constructed and straight lines at different positions are extracted to obtain a point set; camera parameters are initialized and noise filtering is carried out on the point set; the image plane of the straight lines is further optimized according to the rule that the straight line must be projected as straight lines; the optimized image is projected to six faces of a largest inscribed cube of a unit watching ball by unfolding the cube, and the projection is output; secondary correction is carried out on primary calibration of the same equipment, and if the output projection result has deviation, recalibration is carried out. Through the self-adaptive and rapid correcting method for the fish-eye lens, the fish-eye lens can be rapidly corrected, a large amount of calculation is avoided, the result is accurate, and operation is convenient and rapid.

The invention discloses a detection method for a lane boundary and a main vehicle position. The detection method comprises the following steps of: firstly, setting an optimal external vehicle-mounted camera parameter; then self-adaptively setting an edge threshold according to a lane image pixel gradient amplitude, extracting an edge point and calculating an edge point direction; optimally searching and locating the lane boundary by using an ant colony according to a lane boundary projection model, the edge point and the edge point direction; and finally calculating a lane plane linear parameter value and the main vehicle position. According to the detection method, the lane boundary can be searched and located quickly and effectively, and the lane plane linear parameter value and the deviation angle and the position of a main vehicle in a lane can be measured; and the detection method can adapt to linear changes of various lanes and weather and illumination changes.

The invention provides a method for reconstructing target three-dimensional scattering center inverse synthetic aperture radar. The method for reconstructing the target three-dimensional scattering center of the inverse synthetic aperture radar comprises the following steps: conducting continuous image formation on echo data after motion compensation so as to obtain an ISAR two-dimensional image sequence; respectively conducting horizontal scaling and vertical scaling on the information storage and retrieval (ISAR) two-dimensional image sequence so as to obtain a position coordinate of the scattering center; and respectively extracting a position coordinate of the scattering center in an ISAR two-dimensional image of each frame, calculating a displacement velocity field of every two adjacent frames of the scattering center of the ISAR two-dimensional image, combining projection equation and target motion equation of an orthographic projection model so as to obtain estimated values of a third dimension coordinate by combining a projection equation and a target motion equation of an orthographic projection model, and averaging multiple estimated values to obtain the final third dimension coordinate. Therefore, reconstruction of the target three-dimensional scattering center is completed directly. The method for reconstructing the target three-dimensional scattering center of the inverse synthetic aperture radar does not need cost of extra system hardware, can distinguish scattering centers with different heights in the same distance and position resolution unit, does not need to utilize prior information such as observation perspective of the radar, and has relatively small calculating amount.

The invention discloses a method for acquiring a characteristic size of a remote video monitored target on the basis of a depth fingerprint, which comprises the following steps of: acquiring a plurality of slice images of a region of interest of a monitored scene of a target video monitoring system by a gated imaging technique, overlapping the slice images to obtain a depth fingerprint of the region of interest and implanting the depth fingerprint into the target video monitoring system; when the monitored target appears in the region of interest, extracting the monitored target from the background, matching the monitored target with the depth fingerprint, and determining fingerprint lines which are subordinate to foot characteristic lines of the monitored target, wherein space distance information of the fingerprint lines is target distance information; and after acquiring the target distance information, inverting information of the characteristic size of the target from the length of a characteristic segment of the target to be measured, which takes a pixel as the unit, in a monitoring image according to a mopping relation between a three-dimensional space and a two-dimensional image plane under the condition of a perspective projection model. By the method, the problem that a conventional remote video monitoring system is difficult to acquire the information of the characteristic size of the target is solved.