131 results about "Projection mapping" patented technology

A system and method for measuring vehicle speeds using video sensing. The system comprises a tracking camera that generates accurately time-stamped video sequences of the monitored road at high frame rates and a processing unit that analyzes the video sequences in real time to detect moving vehicles and calculate their speeds using the time-over-distance method. The system automatically detects moving vehicles in each image frame and derives vehicle positions from a projective mapping established from reference markers on the road. Time information is obtained from the date and time stamp associated with each image frame. In one example, the system also allows a user of the system to set a trigger speed, and the system automatically saves a video clip of the vehicle whose speed exceeds the trigger speed, recording the speeding vehicle passing through the monitored traffic zone defined by the reference markers.

The invention provides a 3D (three-dimensional) visualization method for a coverage range based on the quick estimation of the attitude of a camera, which comprises the following steps: carrying out 3D scene modeling so as to obtain a 3D scene model, carrying out enhancement on the 3D scene model, and in the process of 3D scene modeling, restoring a depth image from each frame of a video; according to the 3D scene model and the installation position of the camera, registering the camera to the 3D scene model, obtaining camera parameters through estimation according to the attitude of the camera, and determining a projection mapping relation between the video and the 3D scene model; and carrying out displaying in the 3D scene model according to a depth shadow texture principle, interactively picking up a target in the 3D scene model, and according to the projection mapping target, calculating an imaging area of the target in the current camera parameter mode.

The invention discloses an image splicing method by means of a blocking operation. The method comprises the following steps of acquiring an original image which is photographed by multiple cameras, and a preset coordinate mapping table; based on the preset coordinate mapping table, determining a correspondence between a panoramic image and pixel coordinates of the original image, and dividing the original image into a plurality of small blocks with the same size by means of blocking operation; performing projection mapping on the pixel values of the pixels in each small block in the original block after blocking interpolation, and obtaining a final panoramic image according to a mapping result. According to the image splicing method, an operation is performed on the divided source image blocks and a correspondence is found through using each block as a unit. The pixel values of the source pixels are projected into target pixels according to the positions of the target pixels, thereby obtaining a panoramic picture which corresponds with a to-be-processed picture. The blocking operation based on a genetic algorithm reduces redundancy rate of the small blocks so that the processing speed of the panoramic image splicing method based on the blocking operation is greatly improved on an FPGA.

The invention relates to a multi-line laser radar-based 2D data processing method for 3D point clouds. The method comprises the following steps of: S1, taking original data output by a multi-line laser radar as input, receiving 3D point cloud data and screening an interested data area; S2, taking point cloud data which exceeds a set threshold value in the screened data area as outliers and filtering the outliers by adoption of a statistical outlier filter algorithm; S3, taking the filtered point cloud data as input, and carrying out reduced sampling by adoption of a voxel grid filter so as todecrease the data size of point clouds; and S4, taking the reduced sampled point clouds as input, and carrying out projection mapping and regular screening on a plane to carry out plane 2D processing.According to the method, the defects that the data sizes in 3D processing methods are too large and information in 2D methods is incomprehensive are overcome, 3D obstacles can be projected on 2D images so as to reduce the hardware requirements, and obstacle detection and navigation map establishment can be carried out by users in the process running processes of low-speed unmanned intelligent vehicles.

An apparatus and method for providing projection mapping-based augmented reality (AR). According to an exemplary embodiment, the apparatus includes an input to acquire real space information and user information; and a processor to recognize a real environment by using the acquired real space information and the acquired user information, map the recognized real environment to a virtual environment, generate augmented content that changes corresponding to a change in space or a user's movement, and project and visualize the generated augmented content through a projector.

The invention provides a virtual reality projection imaging method and system. The method mainly includes the steps that a projector is installed in a set distance range of 3D glasses, wherein the projection direction of the projector is consistent with the visual direction of the 3D glasses; the projector is connected with a computer processing system through an information transmission system, a virtual reaction scene video transmitted by the computer processing system is received by the information transmission system, and the received virtual reality scene video is projected on a display space. Images can be projected at any projection angle in a projection area in any shape without deformation or distortion. Definition is improved, image granular sensation is reduced, the weight is low, an experiencer feels more comfortable and natural, and the imaging effect is good.

The invention discloses a visual line tracking method based on projection mapping correction and ocular fixation point compensation under natural lights; the method comprises the following steps: extracting double-eye iris center and eye inner and outer angle point and mouth corner point characteristics; calculating a projection mapping relation between a rectangle formed by the eye inner and outer angle points and mouth corner points and the rectangle information when the head is in a calibrated position, thus carrying out projection mapping correction for iris center positions and eye inner and outer angle point positions, and eliminating influences caused by head motions; using corrected left and right eye iris centers to respectively form 4 vectors with the left and right eye inner and outer angle points, and a polynomial mapping model is combined to obtain a real time ocular fixation point; finally using a support vector regression model to carry out ocular fixation point compensation. The visual line tracking method is high in precision, can reduce head motion influences, and can realize visual line tracking under natural lights.

A projective body is aligned with a surface to generate texture coordinates for the surface. The present invention includes selecting an appropriate projective body for a given surface, orienting and positioning the surface with respect to the projective body, projecting the surface onto the projective body, and then mapping the projective body onto the texture rectangle. An inertial ellipsoid is used to orient the surface and the projective body. The inertial ellipsoid can also be used as the projective body. Ellipsoidal coordinates are preferably used to project the surface onto the projective body.

The invention discloses a three-dimensional perspective transforming method of two-dimensional graphics, which comprises the following steps of: skeleton drawing; node mapping: mapping nodes on a two-dimensional molding graphic onto a skeleton according to the corresponding relation between the two-dimensional molding graphic and the skeleton as well as distances and orientation; skeleton adjustment: carrying out the three-shaft rotation of the skeleton by respectively passing around a rotating point and a rotating shaft, and carrying out three-dimensional adjustment; node back-projection: back-projecting the nodes into a three-dimensional space according to the orientation parameters of the nodes projected onto the skeleton by adopting a reverse calculating method, so as to obtain an adjusted three-dimensional modeling graphic object; and projection mapping of a three-dimensional modeling graphic: projecting the three-dimensional molding graphic of the three-dimensional space onto an appointed plane according to the position of a view point to obtain a two-dimensional perspective effect graphic. Through the mode, by adopting the three-dimensional perspective transforming method of the two-dimensional graphics provided by the invention, the efficiency of perspective adjustment in the producing process of two-dimensional cartoons is effectively improved, and the quality of the cartoons is effectively ensured while the cost is saved.

Disclosed herein is a real-time dynamic non-planar projection apparatus and method, which can reduce visual errors, such as distortion of a screen image or deviation from a border area, upon projecting screen images from a projector onto the surface of a non-planar object that is moved in real time. The presented real-time dynamic non-planar projection apparatus includes a preprocessing unit for preprocessing data related to a static part of a screen image to be projected onto a non-planar surface. A real-time projection unit classifies non-planar objects in the screen image to be projected onto the non-planar surface into a rigid body and a non-rigid body using data output from the preprocessing unit, respectively renders the rigid body and the non-rigid body depending on a viewer's current viewpoint, and projects rendered results onto the non-planar surface via projection mapping.

The invention relates to a system and method for automatic alignment and projection mapping. A system and method for automatic alignment and projection mapping are provided. A projector and at least two cameras are mounted with fields of view that overlap a projection area on a three-dimensional environment. A computing device: controls the projector to project structured light patterns that uniquely illuminate portions of the environment; acquires images of the patterns from the cameras; generates a two-dimensional mapping of the portions between projector and camera space and by processing the images and correlated patterns; generates a cloud of points representing the environment using the mapping and camera positions; determines a projector location, orientation and lens characteristics from the cloud; positions a virtual camera relative to a virtual three-dimensional environment, corresponding to the environment, parameters of the virtual camera respectively matching parameters of the projector; and, controls the projector to project based on a virtual location, orientation and characteristics of the virtual camera.

The embodiment of the invention discloses an interactive video projection method and device, equipment and a storage medium. The method comprises the steps of determining the initial position postureof the camera in the virtual scene according to the video frame shot by the camera; rendering the three-dimensional map based on the initial position posture; obtaining a two-dimensional picture corresponding to the shooting range of the camera in the initial position posture; performing feature matching on the two-dimensional picture and a video frame shot by a camera; determining three-dimensional feature points, corresponding to the two-dimensional feature points on the video frame, in the three-dimensional map after matching is completed; determining a camera pose matrix, focal length information and / or distortion parameters through a pose solving algorithm; and setting a camera in the virtual scene according to the above information, and adding the video frame into the rendering pipeline for video projection, thereby realizing semi-automatic interactive rapid video projection mapping without manually and accurately configuring camera parameters by a worker, and improving video projection efficiency.

The invention particularly relates to a covariance matrix and projection mapping-based point cloud characteristic curve extraction method, and mainly overcomes the shortcomings that an existing feature line extraction method is insensitive to fine features of a model and is high in time cost and relatively poor in noise resistance. The method comprises the steps of firstly clustering features into a plurality of band-shaped clusters by using eigenvalues of a covariance matrix as the features; then extracting key feature points according to a main direction in each cluster; and projecting the key feature points to local curved surfaces obtained by fitting through a moving least square method and taking the key points as centers, thereby forming a smooth feature line. The method is suitable for extraction of the feature line of the surface of a three-dimensional point cloud model, is used for describing geometric characteristics of the model, is a basic operation of processing a geometric model, and can be widely applied to the fields of geometric model visualization, optimization and simplification, curved surface reconstruction, mode recognition, reverse engineering and the like.

The invention discloses a stadium marker line-based method for determining camera exterior parameters, which comprises the following steps of: selecting the marker line from the shot stadium image; acquiring the first coordinate of the mark line on the actual plane of the stadium and the second coordinate of the marker line on the shot stadium image; generating the projection mapping relationship between the marker line on the actual plane of the stadium and the marker line on the stadium image according to the first and second coordinates; calculating the projection mapping relationship between the point on the actual plane of the stadium and the point on the stadium image according to the projection mapping relationship of the marker lines; calculating the initial value of the current camera exterior parameter matrix according to the projection mapping relationship of the points and the camera interior parameters acquired in advance; and optimizing the initial value of the current camera exterior parameter matrix to acquire the final camera exterior parameter matrix. According to the method and system, the problem that a point cannot be selected actually can be solved and the accuracy of camera exterior parameter calibration can be guaranteed.

A steel pipe contour online measurement method comprises a first step of installing four laser displacement sensors capable of moving up and down synchronously at two sides, whose distance is greater than the diameter of a steel pipe, to an end of the steel pipe, dividing the laser displacement sensors into two groups by taking one laser displacement sensor at one side and one corresponding laser displacement sensor at the other side as a group; a second step of using the two groups of laser displacement sensors for respectively measuring two groups of contour data of the steel pipe; a third step of calculating an included angle between a connecting line of the laser displacement sensors in one group and a radial cross section of the steel pipe based on the two groups of contour data; and a fourth step of performing projection mapping of the above included angle so as to obtain contour data of the radial cross section of the steel pipe. The invention has the advantage of eliminating errors due to axis deviation of the steel pipe.

The invention discloses a real-time three-dimensional reconstruction method and system based on Kinect V2. The system comprises a constant-speed stepping motor electric rotating platform capable of timing, a Kinect V2 camera fixed to a tripod and a computer. According to the invention, based on a classical KinectFusion three-dimensional reconstruction algorithm, the filtering and denoising of thedepth image are improved, so that the reconstruction quality is improved; An objective function in an ICP algorithm is optimized, the robustness of a system is enhanced, RGB data and a point cloud model are added into a fusion algorithm of a model for splicing fusion, the model is endowed with colors to improve the visual visual visual effect, and finally a more accurate and specific three-dimensional point cloud model is obtained through a projection mapping algorithm. According to the system, the GPU is used for parallel acceleration processing of data, so that the reconstruction speed reaches about 25 frames per second, an object can be accurately reconstructed in real time, and the system can be widely applied to low-cost rapid three-dimensional reconstruction. Finally, the computer processing process is converted into the ARM microprocessor, a wifi transmission module is added, and a simple three-dimensional reconstruction device is obtained through integration.

An embodiment of the present application provides an image mosaic method that acquires a first fisheye image and a second fisheye image collected by a fisheye camera and constructs a logical sphere according to a radius parameter of an imaging model of the fisheye camera, wherein the first fisheye image and the second fisheye image are respectively acquired by a first fisheye lens and a second fisheye lens whose optical axes are located on the same straight line and arranged opposite to each other in the fisheye camera. A projection mapping relationship between each of the first fish eye imageand the second fish eye image and the imaging model is determined. The first fisheye image and the second fisheye image are inversely mapped to the logical sphere based on the projection mapping relationship between the first fisheye image and the imaging model and the projection mapping relationship between the second fisheye image and the imaging model to obtain a spherical mosaic image. The spherical mosaic image is subjected to spherical expansion processing to obtain a 360-degree panoramic image. The invention can be applied to panoramic image mosaic of any image content.

The invention discloses a fraud detection method based on face color space and metric analysis. The method is an identification model designed by aiming at a printed photo as a fraud means, wherein the original image is an RGB three-channel color image, and the method is characterized by converting the original image into a plurality of color spaces through color space conversion, and then extracting the LBP local texture features to obtain a texture map of each color space. All the feature maps are subjected to a metric analysis training algorithm to obtain a projection mapping matrix, the feature maps can be mapped and projected to a more discriminative feature space through calculation, and finally, all the statistic features are merged and sent to the convolutional neural network to calculate a classification result. The method solves the common problems that an existing fraud detection technology is not high in recognition efficiency and prone to noise interference and the like.

There is provided a system and method for multiple sided video projection mapping on arbitrarily shaped objects. By using the same shape data to manufacture the object and to configure the projection mapping onto the object, stray light, reflections, and other distortions can be reduced or eliminated. By constructing the object using a non-opaque layer and a projection coating layer, video content projected onto the object can be seen on multiple sides. Thus, the number of projectors required for multi-sided viewing can be reduced, simplifying deployment and reducing costs. The invention may be of particular use for retail spaces or other public venues where display of image or video content for information, entertainment, or atmosphere enhancement is desirable.

The invention provides an intelligent projection mapping method and system based on blockchain storage. The method comprises: a control center receiving information sent by a user terminal, extracts information contained by the information, and binds the information to a data writing-in blockchain database; the control center generates a private key and encrypts data and controls a clothing numberreceiver to receive clothing number information in real time and analyzes whether information is received; if so, information included by the received clothing number information is extracted and private key acquisition information is sent to a user terminal; the control center obtains private key information returned by the user terminal, and carries out decryption to read data of the blockchaindatabase; the control center extracts information included by the data read by decryption and compares the extracted information with the received clothing number information to obtain a comparison result; if the extracted information is consistent with the received clothing number information, the consistent clothing number and a bound clothing mapping image are sent to a projection device; andthe projection device receives the number and image and projects the clothing mapping image onto a corresponding projection mapping clothing surface.

The invention provides an automatic teaching projection system based on artificial intelligence. The automatic teaching projection system comprises an intelligent classroom, a projection device, a telescopic device, a display device, a closing device, an identification device, a wireless device and a processing device. The intelligent classroom comprises intelligent desks, a blackboard frame and atouchable display screen. The projection device comprises teaching projection channels, teaching projection hydraulic pumps, teaching projection hydraulic rods and teaching projection mapping devices. The telescopic device comprises telescopic channels, telescopic hydraulic pumps, telescopic hydraulic rods and teaching eye trackers. The display device comprises display channels, display tracks, teaching display screens, display motors and display rollers. The closing device comprises projection closing motors, projection closing plates, telescopic closing motors and telescopic closing plates.The identification device comprises first cameras, second cameras, a teacher display screen and warning lights. The wireless device is disposed at an internal position of the processing device, and the processing device is disposed at an internal position of the intelligent classroom.

The invention provides a projector apparatus with a distance image acquisition device and a projection mapping method that can project an image focused on the entire projection object even in a case in which there is a difference in distance to the projection object and the projection object moves. Two projector apparatuses with a TOF camera, that is, a first projector apparatus with a TOF camera including a first projector apparatus for a far distance and a first TOF camera that acquires a distance image of a far projection object and a second projector apparatus with a TOF camera including a second projector apparatus for a near distance and a second TOF camera that acquires a distance image of a near projection object can project a projection image for a far distance and a projection image for a near distance which are focused on the entire projection object even in a case in which there is a difference in distance to the projection object and the projection object moves. In addition, a first light source and a second light source of the projector apparatuses are pulse-driven to function as light sources of the first and second TOF cameras.

A radiation suite includes a room having a floor, a ceiling, and one or more walls, a radiation system including a gantry enclosing a radiation source and a couch, and an image projection system operable to project an image on a projection surface on at least a portion of the gantry and / or the couch, providing a calming environment for a patient to relax. The image projection system comprises a computer and one or more projectors operably controlled by the computer. The computer comprises a mapping software operable to map an image file to the projection surface. The one or more projectors are operable to project the mapped image file on the projection surface.

The invention provides a method, equipment and system for generating a lightscribe projection content. The method comprises: after a position change of lightscribe projection equipment is obtained, the lightscribe projection equipment is used for shooting an image of a projected material object; all profile points, corresponding to the profile of the projected material object, in a mask layer of an original lightscribe projection content before the position change are determined; on the basis of stereoscopic vision matching, corresponding points of all profile points in the obtained image of the projected material object are determined, and a new mask layer is formed based on the set of the corresponding points; and with the new mask layer, a new lightscribe projection content after the position change of the lightscribe projection equipment is generated. On the basis of the lightscribe projection content generation technology, the new mask layer can be formed automatically by using the stereoscopic vision technology when the position of the projection equipment changes, so that the new lightscribe projection content can be generated rapidly and conveniently. Therefore, problems of lightscribe projection content offset and light leak can be solved.

The invention relates to a novel photon probability mapping method based on terrace forming, which belongs to the technical field of mapping method. The method comprises the following steps: matchingaccording to channel conditions and generating an optimal Gaussian beam by a laser; performing probability matching by a probability matcher, and changing the shape of the Gaussian beam by a spatial phase array to obtain a novel beam formed in terrace; performing the 64QAM projection mapping on the data by the novel beam; concentrating and converging the 64 constellation point optical signals; performing pre-emphasis; amplifying the optical signals after passing through a channel, detecting by a photodetector, performing low-pass filter, orthogonalizing and normalizing, and performing data convergence and equalization; matching probabilistic solutions, removing step noise by wavelet transform analysis, performing constellation demapping; estimating channel conditions according to the received data, feeding back channel state information to the probability matcher, and performing real-time dynamic regulation on the probability matcher. The novel photon probability mapping method based on the terrace forming can effectively reduce the signal transmission power, reduces the bit error rate, improves the frequency band utilization, and lengthens the transmission distance.

A projection system includes a projection apparatus embodied in a housing secured to a user. The projection apparatus has a processor in data communication with a networking device, at least one input / output device, and computer memory. The computer memory includes a program with machine readable instructions that, when effected by processor, perform the following steps: (a) determine an edge of a surface to be measured; (b) project an initial image onto the surface, the initial image being based on a predetermined set of conditions; (c) determine a substantially perpendicular distance D1 between the projection apparatus and the surface; (d) determine a distance D2 between the projection apparatus and the edge of the surface; (e) calibrate the initial image based on the distances D1 and D2 determined in steps (c) and (d); and (f) project an updated image onto the surface.

A light homogenization method for multi-source large-scale surface exposure 3D printing, comprising the following steps: projecting pure-color images of a first color and a second color having identical attributes, capturing an image of an overlapping portion and calculating height and width information of the overlapping portion; splitting a pre-processed slice and respectively recording width and height information of two slices resulting from the splitting and generating two grayscale images having identical attributes thereto; counting power values of identical positions of slices in different grayscale values, performing a further calculation to obtain a projection mapping function, using the projection mapping function as a basis for performing optimization on grayscale interpolation of the generated images; and fusing the processed grayscale images and the originally split two slices to obtain a surface exposure 3D printing slice having a uniform brightness in final shaping.

The present invention relates to a method of utilizing a projection matrix of a Veronese mapping checkerboard to calibrate a central catadioptric camera. The method comprises the steps of using the central catadioptric camera to shoot a target image, and extracting the image points corresponding to the checkerboard in the space; utilizing the Veronese mapping to expand the coordinates, and using a DLT-similarity method to estimate the projection matrix linearly; utilizing the projection matrix to solve the parameters in the camera. By utilizing the method of the present invention, no physical scale requirement is required, the points are easy to select, the point sources are abundant, the calibration errors caused by the data errors during a calibration process are reduced, and the one-to-one correspondence of the image points and the angular points of the space checkerboard can be controlled, thereby improving the calibration precision of the camera.