81results about "Geometric image transformation" patented technology

The embodiments of the invention relate to a method for projecting virtual reality panoramic video stream to a user, comprising the steps of dividing the panoramic video stream into multiple spherical subareas, providing different video qualities for the spherical subareas related to a user perspective and the spherical subareas unrelated to the user perspective according to user perspective information tracked in real time, and moving user observation points, thus realizing an optimal video reproduction effect and reducing the transmission bandwidth. The invention further relates to equipment for projecting virtual reality panoramic video stream to a user.

The invention relates to a method of quickly beautifying a facial image in conjunction with skin roughness; the method comprises: converting the facial image from RGB space into YCbCr chrominance space, and extracting brightness component, blue chrominance component and red chrominance component graphs; solving an ellipse center and long and short radiuses of a skin color elliptical model in conjunction with blue chrominance component and red chrominance component histograms, and calculating a skin color soft threshold graph according to skin color similarity; processing brightness component to obtain a local skin color variance graph in conjunction with the skin color soft threshold graph, using the local skin color variance graph as a smoothing parameter and smoothing brightness component graph to perform Gaussian blurring on the soothing brightness component graph, and linearly mixing to obtain a smooth graph in conjunction with the brightness component graph; using the skin color soft threshold graph as a weight to fuse the brightness component graph and a smooth graph to obtain a fused graph, and subjecting the fused graph to curve whitening to obtain a finally beautified graph. The method uses skin color similarity and roughness to remove skin color defects while retaining the skin nature, and has significant overall beautifying effect.

A method, apparatus, user interface and computer program product include the ability to determine a brightness characteristic of a display, use the brightness characteristic to determine a minimum and optimum font size for information displayed on the display, and automatically adjust the displayed information such that a size of a smallest font of the information is not smaller than the minimum font size and that a size of a main font of the information is not smaller that the optimum font size.

The invention relates to a graph interactive realization method, in particular to a method for multiplexing CIM documents and geographic or plant-station SVG graphs which are outputted by an EMS system in the power industry and based on the IEC61970 standard in a DMIS/OMS system and converting the CIM documents and the geographic or plant-station SVG graphs into SVG graphs which meet the interactive demand of the DMIS/OMS system. The method is characterized by comprising the following steps: firstly, models of the DMIS/OMS and an EMS are synchronized with graphic information and associated with equipment; secondly, SVG graph documents undergo normalizing processing so that the interaction of the SVG graphs outputted by the EMS system is improved, so as to make the SVG graphs directly multiplexed in the application scene of the DMIS/OMS system; and thirdly, the SVG graph documents are compressed. The graph interactive realization method can guarantee synchronous update of the models of the DMIS/OMS and the EMS and the graphic information, and changes the condition that the related models and the related graphic information are required to be manually synchronized in the prior art.

The invention provides a method and a device for an integrating two-dimensional code with an image. The method of the invention comprises steps of adjusting the attributes of part of points in the two-dimensional code to enable the attributes of part of the points to be close to the attributes of the corresponding areas in the first image according to attribute information of a first image and attribute information of the points in the two-dimensional code of the first image, wherein the two-dimensional identification result of color lumps to which part of the points the attributes of which are not adjusted belong to is different from the two-dimensional recognition result of the area in the first image corresponding to the part of the points, and integrating the two-dimensional code with the first image to obtain a second image, wherein the attributes of points of the two-dimensional code are adjusted. The invention enables the two-dimensional code to be more matched with the environment color.

The invention discloses a real-time identification method of the live panoramic traffic signs. Aiming at the real-timely acquired large-resolution panoramic traffic images, a proposed data processingmethod is used to extract a training set, and a proposed TSNet network is trained and fine-tuned. In the detection stage, after the image is scaled based on an image pyramid, the sliding window processing method and a DS-NMS algorithm are used to ensure the real-time target identification and improve the accuracy, so that the traffic signs can be identified quickly and accurately in the panoramicstate.

Embodiments are directed towards a system for enabling a user to view an image on a surface. The system may include projector(s), sensor, projection surface or screen, and processor. The projectors may project light for an image onto the surface. The sensor may detect light reflected off the surface. The surface may include multiple types of surface elements, such as multiple first elements positioned as border of a display area on the surface to provide feedback regarding the surface and multiple second elements positioned within the border of the display area to reflect the image to the user. The processor may determine characteristics of the border of the display area based on light reflected to the sensor from first elements. And it may modify parameters of the image based on the characteristics of the border of the display area.

Disclosed is a high resolution image obtaining apparatus and method. The high resolution image obtaining apparatus may divide an input image frame into a background region and foreground region and apply an optimized resolution enhancement algorithm to each region, thereby effectively obtaining a high resolution image frame with respect to the input image frame.

The invention discloses a caching method for a vector diagram converted bitmap and a special image processing device. The caching method comprises the steps of: storing a vector diagram into a vector diagram storage module based on different demands; drawing a corresponding vector diagram; carrying out optimization in the aspect of display for the vector diagram by a vector diagram-to-bitmap conversion module; handing in the well converted bitmap to a bitmap caching module by the vector diagram-to-bitmap conversion module; deleting unnecessary bitmaps from an internal memory; and obtaining necessary images from the bitmap caching module by the bitmap display module. The special image processing device comprises a vector diagram storage module, a vector diagram-to-bitmap conversion module, a bitmap caching module and a bitmap display module, wherein the output end of the vector diagram storage module is connected to the input end of the vector diagram-to-bitmap conversion module; the output end of the vector diagram-to-bitmap conversion module is connected to the input end of the bitmap caching module; and the output end of the bitmap caching module is connected to the input end of the bitmap display module. According to the invention, the size of the application is reduced to a relatively great extent.

The invention discloses a dynamic multi-picture typesetting method and apparatus. The method comprises the following steps: determining an N-dimensional initial space vector, wherein an element of the N-dimensional initial space vector is a length-width ratio of each picture to be typesetted, and N is the number of the pictures to be typesetted; according to the pictures to be typesetted and the size of an area to be typesetted, obtaining all typesetting combinations, obtaining a new N-dimensional space vector corresponding to each typesetting combination, wherein each element of the N-dimensional space vectors is the length-width ratio of each picture in the corresponding typesetting combinations; establishing a distance model between the N-dimensional initial space vector and the new N-dimensional space vectors, wherein the distance model is used for calculating a distance between the N-dimensional initial space vector and the new N-dimensional space vectors; solving the distance model, and obtaining a new N-dimensional space vector with the smallest distance; and taking a typesetting combination corresponding to the new N-dimensional space vector with the smallest distance as a final typesetting combination.

The invention discloses a full-automatic rapid generating and completing method for new view in manufacturing of 3D film. The method comprise the steps of performing 3D back projection and surface triangulation for the original view image and the depth image according to the camera parameters of the original view; performing 3D space projection rendering for the gridded image surface structure according to the camera parameters of the new view so as to generate the image of the new view and the depth image; expanding the color and depth of a non-empty area in the new view image and the depth image to fill tan empty area by the flooding filling method until the color and depth of all pixels in the empty area are completely filled. With the adoption of the method, the view image and depth of the 3D new view can be efficiently and rapidly synthesized; in addition, the empty area produced by shielding in the new view can be fully automatically rapidly repaired so as to obtain the realistic new view image synthesizing result.

The invention discloses an image compression method based on multi-scale feature coding. The image compression method comprises the steps: obtaining a selection vector through the averaging of the absolute values of gradient spectrums of image features of a training set, and guiding different channel features to select the coding resolution through the selection vector; meanwhile, recovering the features of low-resolution coding at a decoding end through a super-resolution network; and finally recombining the features of low-resolution coding with the features of high-resolution coding to forma complete feature spectrum, and mapping the complete feature spectrum back to an original image. According to the image compression method, difference processing is carried out according to the characteristics of the image characteristics, and the characteristics easy to recover from the context information are transmitted at low resolution, so that the code rate is saved; and for complex fine features, high-resolution transmission is adopted, so that the loss degree is reduced.

The invention provides an image super-resolution reconstruction method. The method comprises the following steps: obtaining a to-be-reconstructed low-resolution image; inputting the low-resolution image into a generation model in a trained generative adversarial network, and obtaining a super-resolution image corresponding to the low-resolution image output by the generation model, wherein the generation model has a preset first loss function, and the first loss function comprises a pixel difference loss function and a perception loss function. According to the invention, super-resolution reconstruction is carried out on the low-resolution image by using the trained generation model in the generative adversarial network; the loss function of the generation model comprises the pixel difference loss function and the perception loss function, so that the super-resolution image output by the trained generation model is infinitely close to a high-resolution image in detail, texture and semantics, and the human eye perception quality of the super-resolution image is improved. The invention further provides an image super-resolution reconstruction device.

Slicing and scaling figures. An example method includes generating one or more slice lines for a figure. The one or more slice lines result in a plurality of regions including a central region and one or more corner regions for the figure. Further, the one or more corner regions are scaled while maintaining aspect ratio of the one or more corner regions.

The invention provides a face symmetry plane obtaining method based on iterative mirroring and registration, and belongs to the field of computer vision. The face symmetry plane obtaining method comprises the following steps that (1) face data are acquired through 3D scanning, and a point cloud is smoothly scanned by a Gaussian filter; (2) the longitudinal axis is roughly estimated through PCA, the face is axially segmented to acquire slice contour, and the most symmetrical points are determined and the symmetry plane is solved; and (3) a new point cloud is generated by the symmetry plane point cloud, the point cloud and mirroring data are registered through ICP and registration iteration is performed and the symmetry plane is solved. The novel face symmetry plane obtaining method is put forward on the basis of the iterative mirroring and registration method so that the influence of the local asymmetry of the symmetrical object and the asymmetry caused in the scanning process can be effectively avoided and the obtained symmetry plane is enabled to be more accurate.

The invention discloses a point cloud acquisition method, device and system and a storage medium. A six-axis robot carries a single line laser three-dimensional camera to move back and forth on the sliding chute, different rows of the whole scanning area are scanned, large-view-field panoramic scanning is realized; structure is very simple, correspondingly, installation and control are very simple, simplification of the structure and control is achieved, and an overlapped area exists between every two adjacent scans, so that after rough splicing is conducted, the rotation matrix and the translation matrix can be calculated only based on the point cloud of the overlapped area, the number of the point clouds is greatly reduced, the fine splicing time is shortened, and the splicing precisionis improved.

An information processing apparatus, method, and program are provided that control display of an image. The information processing apparatus, method, and program designate a first point and a second point on an image, determine a zoom direction based on a position of the first point relative to a position of the second point, and zoom the image in the zoom direction.

The invention provides an image splicing method and system and electronic equipment, and relates to the technical field of image recognition, and the method comprises the steps: obtaining a pluralityof to-be-spliced original images; performing feature positioning on the original image by using a feature extraction algorithm to obtain target feature points; obtaining descriptors corresponding to the target feature points by using a local difference binary algorithm; matching the local feature points of different original images based on the descriptor to obtain a matching result; and splicingthe plurality of original images according to a matching result. According to the method, multi-feature-point simultaneous matching is carried out through the local structure information to replace single feature point matching in the prior art, the image matching accuracy is improved, the final image splicing success rate is improved, and therefore the problem that in the prior art, the pipelinewelding seam image splicing effect is poor is solved.

The invention aims at providing a measurement support device, an endoscope system, and a processor for an endoscope system capable of displaying an accurate indicator with a simple configuration. In a measurement support device related to one aspect of the invention, the coordinates of a spot, and coordinates of points indicating an actual size of a measurement target in a subject and indicating a circular marker distorted in accordance with distortion aberration of an imaging optical system are stored in association with each other in a storage unit, the coordinates of the points indicating the circular marker are acquired with reference to the storage unit on the basis of the measured coordinates of the spot, and the circular marker is displayed on the basis of the acquired coordinates. Thus, the distance measurement is unnecessary, the configuration is simple, and the processing load is low. Additionally, since the circular marker is displayed in the vicinity of the spot (for example, centering on a spot position), there is little deviation between the spot position and a marker position, the circular marker is accurate as an indicator. Additionally, since the indicator is not widely displayed, there is little processing load.

The invention belongs to the technical field of composite stress and strain measurement, and provides an out-of-surface strain measuring method based on digital image correlation. The out-of-surface strain measuring method comprises the steps of: firstly, conducting a text according to an experimental scheme, correlating a camera with a force sensor in order to ensure that a distance between a lens and a test piece remains unchanged, driving the camera and force sensor to move simultaneously, slowly loading the test piece, and pressing down a camera shutter at the same time, wherein the camerashutter is not loosened during the test process until the end of loading, and images and test data before and after deformation are obtained after the test ends; secondly, writing an algorithm for calculating and searching a position of a point after deformation, so as to obtain deformation information (displacement and strain) of the test piece, and performing bilinear interpolation to obtain astrain value of an arbitrary point of the test piece through dividing regions; and finally, acquiring a strain cloud chart of the test piece through setting shades of colors according to whether the strain value is plus or minus and the magnitude of the strain value. The out-of-surface strain measuring method is convenient to operate, can be applied to deformation measurement of complicated structures, improves the calculation efficiency and expands the applicable range.

A terminal apparatus provides a highly convenient user interface. The terminal apparatus includes a designated direction detection unit and a display control unit. The designated direction detection unit detects a designated direction, which is a direction in which the terminal apparatus is directed, with respect to a reference direction as a reference of the direction of the terminal apparatus on the basis of a signal from a sensor that outputs a signal indicating the attitude of the terminal apparatus. The display control unit displays an image, in which the direction in which the object is directed with respect to the reference direction is maintained and the object is disposed at the end of a direction corresponding to the designated direction, on a display device.