135 results about "Essential matrix" patented technology

The invention discloses a monocular vision/inertia autonomous navigation method for an indoor environment, belonging to the field of vision navigation and inertia navigation. The method comprises the following steps: acquiring feature point information based on local invariant features of images, solving a basis matrix by using an epipolar geometry formed by a parallax generated by camera movements, solving an essential matrix by using calibrated camera internal parameters, acquiring camera position information according to the essential matrix, finally combining the vision navigation information with the inertia navigation information to obtain accurate and reliable navigation information, and carrying out 3D reconstruction on space feature points to obtain an environment information mapto complete the autonomous navigation of a carrier. According to the invention, the autonomous navigation of the carrier in a strange indoor environment is realized with independent of a cooperative target, and the method has the advantages of high reliability and low cost of implementation.

The invention relates to a dynamic target position and attitude measurement method based on monocular vision at the tail end of a mechanical arm and belongs to the field of vision measurement. The method comprises the following steps: firstly calibrating with a video camera and calibrating with hands and eyes; then shooting two pictures with the video camera, extracting spatial feature points in target areas in the pictures by utilizing a scale-invariant feature extraction method and matching the feature points; resolving a fundamental matrix between the two pictures by utilizing an epipolar geometry constraint method to obtain an essential matrix, and further resolving a rotation transformation matrix and a displacement transformation matrix of the video camera; then performing three-dimensional reconstruction and scale correction on the feature points; and finally constructing a target coordinate system by utilizing the feature points after reconstruction so as to obtain the position and the attitude of a target relative to the video camera. According to the method provided by the invention, the monocular vision is adopted, the calculation process is simplified, the calibration with the hands and the eyes is used, and the elimination of error solutions in the measurement process of the position and the attitude of the video camera can be simplified. The method is suitable for measuring the relative positions and attitudes of stationery targets and low-dynamic targets.

The invention discloses a method for multi-input multi-output transmission for precoding. The method comprises the following steps: a fundamental matrix is selected, a column vector is selected from the fundamental matrix according to the dimension of a precoding matrix under each rank, the precoding matrixes are combined into codebooks, and the codebooks are respectively stored into the transmitting end and the receiving end of a multi-input multi-output transmission system; the receiving end selects precoding matrixes from the codebooks, and feeds back the indexes thereof to the transmitting end; the transmitting end uses the precoding matrixes corresponding to the indexes when the next transmission is performed, performs linear transformation in spatial domain to signals to be transmitted and then transmits the signals. The invention also discloses a method for multi-input multi-output codebook coding for precoding. The method enables the system to meet the feedback expenses and obtains good performance gain.

The invention provides a multi-camera system calibrating method based on an optical imaging test head and a visual graph structure. The method comprises the following steps: independently calibrating each camera by the optical imaging test head to obtain the initial values of the internal parameter and aberration parameter of each camera; calibrating the multiple cameras two by two, and obtaining the fundamental matrix, polar constraint, rotation matrix and translation vector between every two cameras with a plurality of overlapped regions at a view field by means of linear estimation; building the connection relationship among the multiple cameras according to the graph theory and the visual graph structure, and estimating the rotation vector quantity initial value and translation vector quantity initial value of each camera relative to the referred cameras by a shortest path method; and optimally estimating all the internal parameters and external parameters of the all cameras and the acquired three-dimensional sign point set of the optical imaging test head by a sparse bundling and adjusting algorithm to obtain a high-precision calibrating result. The multi-camera system calibrating method is simple in a calibrating process from the partial situation to the overall situation and from the robust to the precise, ensures high-precise and robust calibration, and is applied to calibrating multi-camera systems with different measurement ranges and different distribution structures.

The invention discloses a random trihedron-based radar-camera system external parameter calibration method. According to the method, an external parameter of a system can be solved with only two frames of data by using a trihedron scene a natural environment. The method comprises the following steps of: stipulating a world coordinate system by using a trihedron; performing planar fitting on the trihedron observed in a radar system to obtain a parameter of each plane and solving conversion relation of the world coordinate system and the radar coordinate system and relative motion between the two frames of data under the radar coordinate system; and in a camera system, solving an essential matrix by using matching characteristic points extracted by front and rear frames, then solving relation motion under the camera coordinate system, solving the plane parameter under the camera coordinate system by using the parameter under the radar coordinate system, finally solving an external parameter of a radar-camera, and performing final optimization by using coplanarity of points on corresponding planes under the two coordinate systems. A scene required by the method is simpler; and the method has the characteristics of high anti-interference performance, simple experimental equipment and high flexibility.

An infinity homography for an image pair within an image sequence is transferred to other image pairs within the image sequence utilizing point matches for the subject image pairs. An image set including the image pair for which the infinity homography is known and a third image are selected. Then intermediate parameters for homography transfer for one image pair overlapping the known infinity homography image pair is computed from the known infinity homography and epipoles and fundamental matrices of the overlapping image pairs, to derive the infinity homography for the selected overlapping image pair. The process may then be repeated until infinity homographies for all image pairs of interest within the image sequence have been derived.

The invention provides a mobile augmented reality registration method of an outdoor wide-range natural scene. The mobile augmented reality registration method comprises the steps that three-dimensional reconstruction of feature points is accomplished through an Euclidean reconstruction method on the basis of combination between an essential matrix and triangulation, the initial external reference of a camera is calculated by using the essential matrix, a coordinate system of a virtual three-dimensional object and a coordinate system of the scene plane are built, feature detection and tracking are carried out by using a BRISK operator, tracking is only carried out on an image which is successfully recognized, and the speed of real-time updating of registration information is further increased. Tracking is carried out on the detected scene feature points through a light stream tracking method, scene feature information can be updated in real time, and real-time performance of augmented reality registration is further improved.

An object recognition apparatus that processes images, as acquired by an imaging means (10) mounted on a moving object, in a first image plane and a second image plane of different points of view, and recognizes an object in the vicinity of the moving object. The object recognition apparatus comprises: a feature point detection means (42) that detects feature points in first and second image planes of an object image; a fundamental matrix determination means (43a) that determines, based on calculation of an epipole through the auto-epipolar property, a fundamental matrix that expresses a geometrically corresponding relationship based on translational camera movement, with not less than two pairs of feature points corresponding between the first and second image planes; and a three-dimensional position calculation means (43b) that calculates a three-dimensional position of an object based on the coordinates of the object in the first and second image planes and the determined fundamental matrix.

The large part three-dimensional reconstruction method based on the image sequence comprises the following steps that S1, an unmanned aerial vehicle carrying a camera flies around a target part, and ato-be-reconstructed image sequence is obtained; s2, adopting an SIFT algorithm and an SURF algorithm to jointly extract image feature points; s3, estimating camera motion by calculating an essentialmatrix and a basic matrix based on the sparse feature points obtained by the SIFT corner points and the SURF corner points, and registering three-dimensional space points to obtain sparse point cloudof a three-dimensional scene; s4, judging whether the optimized sparse point cloud has a symmetrical repeated structure or not; and S5, taking the sparse point cloud as seed point and reference imageinput, and performing dense reconstruction based on a dense three-dimensional point construction method of multiple views to obtain a low-resolution depth map. The three-dimensional point recovery andcorrection method based on the image sequence has the advantages that the three-dimensional point recovery and correction method based on the image sequence is provided, and construction from the image sequence to the space sparse three-dimensional points is achieved.

A 3D reconstruction method based on scattered photo sets of the same scene is divided into three stages: the first stage: every pairwsie image feature matching and relative camera motion are estimated; and the stage is divided into 4 steps: (1) every two images are subject to the bidirectional nearest neighbor search and feature domain constraint to obtain a candidate correspondence; (2) the candidate correspondence is subject to parallax domain correspondence constraint to obtain a hypothesis correspondence; (3) the image coordinates of the hypothesis correspondence are standardized to solve an essential matrix estimation meeting the hypothesis correspondence; (4) the essential matrix is decomposed to obtain four groups of possible solutions of the camera motion, and the final solution is determined by the fault-tolerant forward depth constraint; the second stage: the optimized initial reconstruction camera pair is selected according to the results of the first stage, the standard sparse reconstruction method is applied, and the camera pose and the sparse geometric information of the scene are restored; the third stage: selective accurate and dense matching is carried out based on the results of second stage, and an accurate and dense 3D scene point cloud model is reconstructed by the triangulation method. The method has the advantages of obtaining reliable camera pose and high-density scene geometric information, greatly shortening the reconstruction time, having relatively high reconstruction efficiency, and is applicable to processing the scattered photo set with large data size.

The invention discloses a monocular vision inertia SLAM method for a dynamic scene. The method comprises the following steps: firstly, extracting ORB feature points by a visual front end, performing target identification by using a YOLO-v3 neural network, further extracting a potential static feature point set, removing RANSAC outer points of an essential matrix, screening out final static featurepoints, and tracking the final static feature points; meanwhile, in order to improve the data processing efficiency, carrying out pre-integration on IMU measurement values; initializing, and calculating initial values including attitude, speed, gravity vector and gyroscope offset; then, carrying out nonlinear optimization of visual inertia tight coupling, and establishing a map; meanwhile, carrying out loopback detection and repositioning, and finally carrying out global pose graph optimization. According to the method, deep learning and visual inertia SLAM are fused, the influence of a dynamic object on SLAM positioning and mapping can be eliminated to a certain extent, and the stability of long-time work of the system is improved.

A method and apparatus for determining a position and attitude of at least one camera by calculating and extracting estimated rotation and translation values from an estimated fundamental matrix based on information from at least a first and second 2D image. Variable substitution is utilized to strengthen derivatives and provide a more rapid convergence. A solution is provided for solving position and orientation from correlated point features in images using a method that solves for both rotation and translation simultaneously.

The invention discloses an omni-directional stereo vision three-dimensional reconstruction method based on Taylor series models. The method comprises the following: a step of calibrating a camera, which is to utilize a Taylor series model to calibrate an omni-directional vision sensor so as to obtain internal parameters of the camera; a step of obtaining epipolar geometric relation, which comprises the steps of calculating an essential matrix between binocular omni-directional cameras and extracting the rotation and translation component of the cameras; a step of correcting an outer polar line, which is to correct the outer polar line of a shot omni-directional stereo image so as to allow a corrected polar quadratic curve to coincide with an image scan line; and a step of three-dimensional reconstruction, which is to carry out feature point matching to the corrected stereo image and calculate the three-dimensional coordinates of points according to matching results. The method can be applicable to various omni-directional vision sensors, has the characteristics of wide application range and high precision, and can carry out effective three-dimensional reconstruction under the condition that the parameters of the omni-directional vision sensors are unknown.

The invention discloses a visual positioning method and device. The method comprises the following steps of firstly determining continuous frames of images collected by an image sensor according to the two frames of images and inertia data, determining pose change data of the image sensor; determining an essential matrix of the two frames of images; respectively determining each feature point in the two frames of images; matching feature points to obtain each feature point pair; for each feature point pair, determining the matching degree of two feature points in the feature point pair according to the determined essential matrix, finally determining the feature point pair of which the matching degree is within the preset threshold interval from the feature point pairs according to the preset threshold interval, and performing visual positioning according to the screened feature point pairs. The matching degree of each feature point pair is determined through the essential matrix, so that the feature points with higher matching degree are screened out and sent to the rear end, the rear end performs visual positioning according to the feature points with higher matching degree, thepositioning is more accurate, and the map construction precision is higher.

Point matches between images within an image sequence are identified by sparse optical flow computation and employed to compute a fundamental matrix for the epipolar geometry, which in turn is employed to derive an epipolar geometry constraint for computing dense optical flow for the image sequence. The epipolar geometry constraint may further be combined with local, heuristic constraints or robust statistical methods. Improvements in both accuracy and performance in computing optical flow are achieved utilizing the epipolar geometry constraint.

The present invention provides a method for fast, robust and efficient BA pipeline (SfM) for wide area motion imagery (WAMI). The invention can, without applying direct outliers filtering (e.g. RANSAC) or re-estimation of the camera parameters (e.g. essential matrix estimation) efficiently refine noisy camera parameters in very short amounts of time. The method is highly robust owing to its adaptivity with the persistency factor of each track. The present invention highly suitable for sequential aerial imagery, particularly for WAMI, where camera parameters are available from onboard sensors.

The invention discloses a method for estimating the attitude of a carrier aircraft in the landing process based on vision guidance. Feature points of two successive frames of images acquired by a carrier aircraft are first extracted and matched. According to matching point pairs and pixel coordinates thereof, the epipolar geometrical relationship of the two frames of images are calculated to obtain a basis matrix. An essential matrix is determined by the correspondence between the basis matrix and an intrinsic matrix. After the singular value decomposition of the essential matrix, a rotation matrix is solved. The obtained rotation matrix is converted into Euler angles, so as to estimate attitude information of the carrier aircraft during the descent. The method of the invention can estimate the attitude information of the carrier aircraft simply with two or more frames of observation images, and has more flexibility. Based on the visual guidance mode, the method of the invention has the advantages of low cost, high precision, and strong anti-interference ability.

The invention relates to a visual inertial ranging method and system of tightly coupled vehicle wheel coder data. The visual inertial ranging method comprises the steps of: (1), setting the initialization state of the visual inertial ranging method to be unfinished, and obtaining a camera image, an inertial measurement unit IMU measurement value and a wheel coder reading in real time in initialization and measurement processes; (2), calculating an essential matrix between a current image and a previous-frame image, and adding the essential matrix and the corresponding IMU measurement value andwheel coder reading into a first sliding window and a second sliding window at the same time; (3), performing IMU-wheel coder pre-integration on the IMU measurement value and wheel coder reading corresponding to a last-frame image; judging whether the initialization state is finished or not, if so, executing the step (5), and otherwise, executing the step (4); (4), initializing parameters by utilizing a pre-integration result; (5), obtaining parameters corresponding to each image in the first sliding window; and (6), performing visual inertial ranging of the tightly coupled vehicle wheel coder data according to the parameters.