17 results about "Image warping" patented technology

Methods and systems are disclosed for performing real-time deforming operations. The system receives an image that includes a depiction of a real-world object. The system applies a machine learning model to the image to generate a warping field and segmentation mask, the machine learning model trained to establish a relationship between a plurality of training images depicting real-world objects and corresponding ground-truth warping fields and segmentation masks associated with a target shape. The system applies the generated warping field and segmentation mask to the image to warp the real-world object depicted in the image to the target shape.

Methods and systems are disclosed for performing real-time deforming operations. The system receives an image that includes a depiction of a real-world object. The system applies a machine learning model to the image to generate a warping field and segmentation mask, the machine learning model trained to establish a relationship between a plurality of training images depicting real-world objects and corresponding ground-truth warping fields and segmentation masks associated with a target shape. The system applies the generated warping field and segmentation mask to the image to warp the real-world object depicted in the image to the target shape.

The embodiment of the invention provides an image processing method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a reverse mapping tensor; in the on-chip storage space of the calculation unit, a buffer area used for image distortion transformation is distributed; writing forward mapping information of a group of pixels corresponding to a first sliding window into the buffer area based on the first sliding window on the reverse mapping tensor; moving one first unit block in response to the first sliding window, writing forward mapping information in a first area in the buffer area into an off-chip storage space of the computing unit, and moving forward mapping information in a second area in the buffer area to the first area; and determining a forward mapping tensor for the reverse mapping tensor based on the forward mapping information written in the off-chip storage space to perform image warping transformation on the input image. In this way, the image distortion transformation efficiency can be improved.

The invention provides an X-ray back scattering image deformation correction method, device and system, and the method comprises the steps: obtaining the six-degree-of-freedom pose change during the scanning of a device in real time through an environment pose sensing system fixed on the device, replacing the conventional error-prone inertial measurement or contact track recording, and employing the high-precision pose data to achieve the correction of the deformation of an X-ray back scattering image. And calculating the accurate position of each pixel of the original image on an ideal imaging plane through space-time synchronization and an affine transformation model, and finally generating a distortionless image through interpolation resampling. According to the image deformation correction method provided by the invention, high-precision and non-contact full-scene image correction independent of external marks is realized, and the problem of image distortion caused by jitter in handheld scanning is effectively solved.

A method morphs an input image depicting a face to an output image depicting a face that is a blend of characteristics of a plurality of input entities. The method comprises: training a face-morphing model comprising: a shared set of parameters shared between the input identities; and, for each of the input entities, an identity-specific set of parameters. The method also comprises: receiving an input image depicting a face of one of the plurality of input identities; receiving a set of interpolation parameters; combining the identity-specific sets of trained neural-network parameters for the plurality input identities based on the interpolation parameters, to thereby obtain a blended set of neural-network parameters; and inferring an output image depicting a face that is a blend of characteristics of the input entities using the shared set of trained neural-network parameters, the blended set of neural-network parameters and the input image.

The present invention provides an image warping processing system, an image warping processing method, an image display device, a computer-readable storage medium, and a computer program product. The image warping processing system comprises a pre-rotation unit and a warping unit. The pre-rotation unit is used for performing at least one pre-rotation on a first image to be warped, to obtain a second image. The warping unit is used for performing a warping operation on the second image to obtain a third image conforming to a warping target. The warping target at least indicates a target rotation angle of the third image relative to the first image. By configuring a pre-rotation unit to perform at least one pre-rotation on an image to be warped, the present invention achieves the effect of realizing large-angle image rotation with a small amount of storage resources, and improves display real-time performance.

A method and system for performing image warping of images having missing pixel data. The method includes obtaining, by a first imaging assembly having a first field of view, a first image of one or more objects in the first field of view. The first image has one or more pixels with missing data pixel values. A processor determines a mapped pixel location for each pixel of the first image. The processor then identifies a pixel neighborhood having a pixel neighborhood configuration for each mapped pixel location. The processor further determines a mapped pixel value for each mapped pixel, each mapped pixel value based on the pixel neighborhood configuration. The warped image of mapped pixels and mapped pixel values is then presented to a user.

A method for generating a training dataset (500) for training a machine learning model for the recognition of morphed images, wherein the method comprises: Repeatedly performing the following steps: Receiving (101) an image (130, 150) of an object (134, 154); Identifying (103) a set of landmarks (134, 154) in accordance with a landmark pattern; Determining (105) the positions of the set of reference points with respect to a coordinate system (131, 151) defined relative to the object (134, 154); Adding an entry (501.1-n) to the training dataset (500), where the entry specifies the set of positions and a label, where the label indicates whether the received image (130, 150) is a real image or a morphed image.

Efficient image warping systems and methods for optimized processing and memory management are disclosed herein. A method for transforming digital images using coordinate transformations and Double Data Rate (DDR) memory optimizes processing and memory usage. The method receives an input image and a warp specification, fetches estimated source blocks from DDR memory based on the specification, and processes these blocks in cache memory optimized for random access. It addresses out-of-bounds pixel issues by adjusting the range of source blocks, ensuring accurate assembly of the warped image. This approach improves efficiency in digital image warping, particularly in real-time applications.

An image processing circuit for performing local tone mapping (LTM) after image warping. The image processing circuit includes a warping circuit that warps an input image to generate a warped image, and a LTM circuit coupled to the warping circuit. The LTM circuit determines an input color component value for a color component of a pixel in a version of the warped image, determines an output color component value for the color component of the pixel, based on mapping of coordinates of pixels in the warped image to coordinates of pixels in the input image, determines a gain value for the pixel as a ratio of the output color component value relative to the input color component value, and adjusts color component values for color components of the pixel using the gain value to generate adjusted color component values for the color components of the pixel in an output image.

This invention provides a 720-degree VR LED dome screen combining a disc-shaped ground screen, relating to the field of immersive image display technology. It includes: a dome LED screen, which is a half-rotation curved surface formed by splicing a first circular LED module at the top and multiple first curved-edge LED modules on the sides; a disc-shaped ground screen, which is a cylinder formed by splicing a second circular LED screen in the central area and multiple second curved-edge LED modules; and a central LED screen, which is a hyperboloid formed by splicing multiple third curved-edge LED modules, with the upper edge of the hyperboloid coinciding with the lower edge of the dome LED screen, and the lower edge of the hyperboloid coinciding with the outer edge of the disc-shaped ground screen. The beneficial effect is that through the three-screen curved splicing structure, a smooth and seamless splicing of the dome LED screen and the disc-shaped ground screen is achieved, resulting in complete spherical spatial image coverage. This effectively solves the problems of visual obstruction, restricted movement, and image distortion in the splicing area, enhancing the immersive viewing experience.

The application provides a finished product camera video real-time splicing method and system based on heterogeneous computing, which comprises the following steps: processing double-channel fisheye video streams through offline calibration to achieve global coarse alignment, and obtaining double-channel equirectangular projection video images containing target video images and reference video images; performing feature matching and inter-frame jitter suppression processing based on optical flow estimation on the target video images and the reference video images to obtain a pixel set matching point set; sequentially performing local homography matrix solving based on grid division and image warping processing on the pixel set matching point set to obtain a warped image; performing image fusion on the warped image and the reference video image through brightness matching and distance weight processing to obtain a fused image; and obtaining a fused video stream through the fused image. The application realizes pixel-level weighted fusion by defining the range through an overlapping area mask, correcting color brightness deviation through histogram matching, and generating dynamic weight coefficients based on distance transformation.

An automatic processing method for adjusting base maps based on AutoCAD topographic maps. This invention relates to the field of geographic information technology. First, it determines the map sheet boundaries of the base map through contour recognition; then, it obtains the minimum envelope rectangle through relevant algorithms, thereby determining the maximum range of the corrected image; subsequently, image correction is performed to "restore" the base map with image distortion to be as close as possible to the original base topographic map, laying a good foundation for subsequent overlay and synthesis. Second, considering the original information in the base map, the basic coordinate data is identified to determine the insertion position of the base map. Then, based on calculations, the corrected positioning position and magnification ratio are determined, achieving accurate overlay of the corrected image onto the AutoCAD map sheet. This invention automatically realizes the "overlay" of the electronic base map and the AutoCAD map sheet, providing a more accurate basis for subsequent feature addition and supplementation labeling.

The disclosed system and method relate to automatically detecting empty spaces on retail store shelves, identifying the missing product(s) and causing the space to be replenished or restocked. For example, stores may use shelf-mounted imaging devices to capture images of shelves across the aisle from the imaging devices. The images captured by the imaging devices may be pre-processed to de-warp, de-skew images and stitch together multiple images in order to retrieve an image that captures a full width of a shelf. The pre-processed images can then be used to detect products on the shelf, identify the detected products. An iterative projection algorithm or product fingerprint matching algorithm can be used to identify the products. When an incorrect product listing or an empty shelf space is encountered, a message may be sent to the store employee to remedy the issue.

The application provides a filter screen detection method and device, a computer readable storage medium and an air conditioning system. The detection method comprises: acquiring a target image, which is an image of a filter screen to be detected; extracting a plurality of frame contour lines, which are edges of a frame contour of the filter screen to be detected in the target image; analyzing the target image by using an image warping algorithm to obtain a warping degree of the filter screen to be detected, the warping degree being used to represent a deformation degree of a grid in the filter screen to be detected; and determining that the filter screen to be detected is unqualified in a case where any one of the frame contour lines is not a straight line and / or the warping degree of the filter screen to be detected is greater than a warping degree threshold. Compared with manual measurement of deformation, the image detection greatly improves the efficiency and solves the problem of low efficiency of manual detection of whether an air conditioner filter screen is qualified in the prior art. In addition, manual detection may be inaccurate due to errors, and therefore the image detection can also improve the accuracy of detection.