3111 results about "Projection image" patented technology

Methods and systems are described which allow a classification of first and second objects in an X-ray projection image. A respective representation and localization of both objects are determined by applying the models to match the objects in the X-ray image and a spatial relation of the classified objects is obtained. Such methods and systems take advantage of artificial intelligence.

The invention relates to the technical field of quality monitoring, and discloses a diamond high-strength micro-powder quality detection method and system based on artificial intelligence. The method comprises the steps of obtaining a two-dimensional projection image sequence of diamond micro-powder particles, calculating a projection matrix based on camera calibration parameters and geometric constraints, obtaining a multi-view image data set of the particles, establishing a pixel-level corresponding relation, extracting three-dimensional space coordinates of the surfaces of the particles, and reconstructing dense point cloud data of the particles. Establishing a local coordinate system based on the dense point cloud data, determining attitude parameters of particles in a three-dimensional space, if the attitude parameters deviate from a normal range, performing attitude compensation processing to obtain standardized point cloud data, and performing three-dimensional grid model construction on the standardized point cloud data; and calculating geometrical characteristic parameters of the particles based on the three-dimensional grid model, performing defect detection on the surfaces of the particles, and generating a crystal integrity evaluation report of the particles. The quality detection accuracy of the diamond high-strength micro-powder particles is improved.

The invention provides a multi-angle photographing and three-dimensional reconstruction method and system for soft tissue, and relates to the technical field of soft tissue three-dimensional reconstruction, and the method comprises the steps: analyzing soft tissue features based on deep learning, generating a bulb tube motion track and sampling interval data, and controlling a mechanical arm to drive a bulb tube to collect projection images at multiple angles; screening an optimal image sequence by using an image quality evaluation network, and performing preprocessing such as material decomposition, feature extraction, space registration and image optimization; and inputting the optimized image and the material features into a reconstruction model, performing iterative calculation in combination with an anatomical structure template to generate density distribution data, performing curved surface reconstruction and intelligent tissue segmentation based on graph convolution based on the density distribution data, and finally generating a three-dimensional model containing tissue layering information.

The invention provides a distortion correction method and system for image projection, and relates to the technical field of image processing, and the method comprises the steps: generating a geometric deformation parameter matrix and a light field attenuation vector of a projection surface through a constructed bidirectional distortion detection model, carrying out the regional analysis of the geometric deformation parameter matrix, and obtaining a curvature feature, dividing a priority correction level through curvature features, and determining a nonlinear compensation factor according to the priority correction level and a light field attenuation vector; constructing a self-adaptive projection network based on the distortion sensitive features of the projection image and the nonlinear compensation factor, and performing reverse coordinate mapping on the projection image through the self-adaptive projection network to obtain an initial correction image; determining an artifact suppression weight map through the high-frequency detail threshold value and the low-frequency smooth threshold value of the initial correction image; according to the invention, geometric deformation parameter optimization and light field attenuation compensation of image projection can be realized, so that the distortion correction precision and the anti-artifact capability are improved.

The invention relates to the technical field of image recognition, in particular to a circuit board micropore copper plating quality inspection method based on image recognition. The method comprises the following steps: setting an annular polarized light source array; performing dynamic depth-of-field fusion shooting on the circuit board micropore based on the annular polarized light source array to obtain a two-dimensional projection drawing of the circuit board micropore; performing sub-pixel edge enhancement on the circuit board micropore two-dimensional projection drawing to generate a circuit board micropore enhanced projection drawing; and segmenting the interest boundary of the circuit board micropore enhanced projection drawing to obtain the hole wall region-of-interest boundary. Advanced image recognition, deformation analysis and self-learning technologies are introduced, efficient, accurate and automatic circuit board micropore copper plating quality intelligent inspection is achieved, and the defects of a traditional method in the aspects of detection precision, efficiency and comprehensive evaluation capacity are overcome.

The invention relates to the technical field of panoramic video processing, in particular to a multi-modal fusion panoramic video intelligent content analysis method, which comprises the following steps of: acquiring a panoramic video frame and a synchronous audio thereof; performing spherical projection transformation on the panoramic image data, and converting the equidistant projection image into a spherical image; generating a plurality of plane images based on the spherical image; performing candidate target position detection based on the plurality of plane images; based on a candidate target position detection result, an image target detection model is utilized to realize instance segmentation of a target, and target features are extracted to generate a target embedded description vector sequence; based on the synchronous audio, an audio recognition processing module is used for carrying out time sequence information extraction, and an acoustic attention sequence is formed; a spectrum sensor is adopted to realize association fusion of the target embedded description vector sequence and the acoustic attention sequence, and an audio and video collaborative attention sequence is generated; and based on the audio and video collaborative attention sequence, establishing an audio and visual event identification model, and obtaining event content described by the panoramic content.

Systems and methods are provided for image guided surgery. Such systems and methods receive a model of an anatomical structure as well as a model of an object, and process a projection image generated by an imaging device from an imaging direction, wherein the projection image includes at least a part of the anatomical structure and at least a part of the object. Based on (i) the projection image, (ii) the imaging direction, (iii) the model of the object, and (iv) the model of the anatomical structure, the systems and methods determine a spatial position and orientation of the object relative to a space of movement. The space of movement may be defined in relation to the anatomical structure.

The invention relates to the technical field of human body health assessment, in particular to a health assessment method and system based on a 3D human body posture image model. The method comprises the following steps: acquiring human body annular scanning data; extracting a dynamic posture sequence of a vertical position, a forward bending position and a lateral bending position of the human body annular scanning data, and performing phase shift fringe projection on the human body annular scanning data according to the dynamic posture sequence to obtain human body three-dimensional point cloud data; a sagittal plane, a coronal plane and a cross section of the human body three-dimensional point cloud data are analyzed for orthogonal projection, and a human body multi-angle projection image group is generated; and identifying skeleton contour features of the human body multi-angle projection image group so as to establish a dynamic marking system of the anatomical mark points. Through high-precision dynamic acquisition and multi-dimensional space analysis, precision, standardization and individuation of 3D human body posture health assessment are realized, and the accuracy and comprehensiveness of human body posture health assessment are improved.

The invention relates to the technical field of projection display, and discloses a projection curtain light field display gain method and system used under ambient light. According to the method, environment light data, projection curtain data and original output signals of projection equipment are collected in real time, and a dynamic light field distribution model is established after fusion processing. And based on the dynamic light field distribution model, adopting an adaptive genetic algorithm to optimize a compensation weight, generating a light field compensation parameter set, performing reverse compensation processing of brightness gain, contrast and chromaticity offset on an original output signal, and generating an enhanced projection signal. The system comprises a multi-source data acquisition module, a light field feature extraction module, a dynamic compensation calculation module, a signal enhancement processing module and a closed-loop feedback control module, ensures that the projection image keeps an optimal display effect under different ambient light conditions, and remarkably improves the watching experience of audiences.

An electronic device includes: a projector; a camera; one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the electronic device to: control the projector to display a projected image on a screen, wherein the screen includes surfaces; control the camera to obtain a captured image including the surfaces and the projected image; identify, based on the captured image, shapes of the surfaces and areas of the projected image projected onto the surfaces; and correct the projected image, based on the shapes of the surfaces and the areas of the projected image, by transforming the projected image into one from among a three-dimensional image and a flat image.

The present invention proposes a 3D semantic segmentation method for performing 3D semantic segmentation on the basis of fusion data obtained through sensor fusion of cameras and LiDAR. The method may include the steps of: receiving an image photographed by a camera and point cloud data acquired from LiDAR, by a learning data generation device; generating a projection image expressing the point cloud data in polar coordinates of a size the same as those of the image, by the learning data generation device; and inputting the image and the projection image into an artificial intelligence (AI) machine-learned in advance to estimate a 2D segment map and a 3D segment map having dimensions as high as the number of types of classes to be predicted, by the learning data generation device.

The invention relates to a three-dimensional point cloud registration method and system based on a two-dimensional visual large model. A source point cloud and a target point cloud are decoupled into two-dimensional projection representation; constructing a structure consistency restoration domain, restoring geometric structure fracture and semantic deficiency in the projection image, and generating a dense and continuous restoration image; inputting the repaired image into a pre-trained visual geometry large model, carrying out cross-modal feature matching and pose resolving, and synchronously outputting a pixel-level matching confidence map; and inversely mapping a two-dimensional pose calculation result to a three-dimensional space to complete coarse registration, constructing a high-credibility anchor point set in the three-dimensional space by using a confidence map, and guiding a point cloud fine registration algorithm to converge to global optimum. According to the method, the registration large model for natural image training can be seamlessly migrated to the point cloud data, and retraining is not needed; in a weak texture and partially overlapped point cloud scene, a robust rough registration initial value can still be provided; the convergence speed and the anti-noise performance of fine registration are remarkably improved, and adaptive improvement from coarse to fine is achieved.

Systems and methods for autonomous robotic surgery are provided to control a movement of a robotic device so as to perform a surgical procedural step, wherein controlling of the movement is based on information including a spatial position and orientation of at least a part of the robotic device. A trigger information may cause the system to pause or stop the surgical procedural step and cause the system to receive a projection image. Further, the projection image may be processed so as to determine a spatial position and orientation of at least the part of the object or of the robotic device.

The present disclosure relates to a cone beam computed tomography (CT) imaging system, an image processing method, and a device therefor. An image processing method performed by a cone beam computed tomography (CT) imaging apparatus including a source and a detector that rotate around an object may include: obtaining a plurality of projection images projected on the detector for the object; obtaining a correction projection matrix; and reconstructing a three-dimensional image by back-projecting the plurality of projection images based on the correction projection matrix.

Methods and systems for assisting a vehicle to park using mixed-domain image data. Image-domain data is generated based on raw image data received from a plurality of cameras mounted on a vehicle. The raw image data is associated with a parking zone outside the vehicle, and the image-domain data is generated by a feature-detection machine learning model. A bird's-eye-view (BEV) image is generated based on the raw image data, wherein the BEV image is a projected image of the parking zone. BEV-domain data associated with the BEV image is generated. The BEV-domain data includes data associated with parking landmarks in the parking zone. A computing system localizes the vehicle within the parking zone based on the BEV-domain data and the image-domain data to generate localization data. The computing system performs mapping of the parking zone based on the BEV-domain data, the image-domain data, and the localization data.

The invention discloses a three-dimensional color modeling method and system based on multi-sensor fusion, and the method comprises the steps: obtaining monocular vision pose information, an RGB image and radar three-dimensional point cloud information, enabling the monocular vision pose information to be used for correcting a radar pose, and generating corrected point cloud information; the corrected point cloud information is screened and then projected to a specific plane; proper feature points are extracted from the projection image and the RGB image, and according to the corresponding relation between the feature points of the projection image and the RGB image, the plane point cloud of the projection image and the pixel coordinate plane of the RGB image are registered; performing fusion modeling on the point cloud and the image data by using an MRF model; according to the method, the radar pose is corrected by using visual pose information, the accumulated error influence of a system is reduced, the corrected point cloud is projected to a plane, and feature points of a projection image and a color image are extracted to establish an MRF model for describing the relationship between a pixel plane and the corresponding point cloud, so that a point cloud image which is uniformly distributed in space and contains color information is obtained.

The invention relates to a skeleton posture prediction method and system, computer equipment and a storage medium. The method comprises the steps that preoperative three-dimensional image data and intra-operative projection data of a target skeleton are acquired; obtaining an initial attitude matrix of the target skeleton according to the three-dimensional image data; obtaining preoperative projection data of the target skeleton according to the initial attitude matrix and the preoperative three-dimensional image data; performing style migration on the preoperative projection data to obtain intra-operative simulation projection data; and obtaining a target attitude matrix of the target skeleton according to the intraoperative simulation projection data and the intraoperative projection data. According to the method, the image style migration is performed on the preoperative projection data to obtain the intraoperative simulation projection data, so that the intraoperative simulation projection data is closer to the real intraoperative projection image to improve the registration precision, prediction is performed in combination with the actually acquired intraoperative projection data, the precision and robustness of bone pose prediction are improved, the iteration process is simplified, and the accuracy and robustness of bone pose prediction are improved. And the bone posture prediction efficiency is greatly improved.

The present invention relates to a compact mobile display device, and more specifically, to a portable display implemented by mounting an ultra-short-throw projection optical module on a transparent, flexible, or hard substrate to project a projection image. In the present invention, when the ultra-short-throw projection optical module is mounted and the substrate that projects the image is made of a flexible and transparent material that can be bent, folded, or rolled, the user can enjoy augmented reality that overlaps reality through a transparent display. In addition to viewing images, it is possible to conveniently carry the display device by bending, folding, or rolling it while viewing the expanded display.

The invention relates to a glass single-face machining detection method, system and terminal, and relates to the technical field of glass machining.The method comprises the steps that after single-face grinding is completed on the basis of glass, a detection image of the surface of the ground glass is obtained; identifying the detection image based on a preset projection feature to form a projection image; judging whether the projection image is consistent with a preset projection reference image or not; if yes, clamping the glass into a preset qualified area; if not, analyzing a deviation condition between the projection image and the projection reference image and taking the deviation condition as projection deviation information; and processing abnormity early warning information is determined according to the projection deviation information, and the processing abnormity early warning information is output to a terminal held by a manager. The method has the effect of improving the qualified rate of the quality of the finally produced glass product.

A vehicular exterior rearview mirror assembly includes a mirror head accommodating a mirror reflective element and an illumination module, which includes a light source, a first mask, and a second mask. When the light source is powered, emitted light that passes through the first mask is a first color and emitted light that passes through the second mask is a second color. With the mirror assembly mounted at a vehicle, and when the light source is powered to emit light, light emitted by the light source passes through the first mask to project a first projected image onto a ground region and passes through the second mask to project a second projected image onto the ground region. The first projected image includes a first logo portion having the first color, and the second projected image includes a second logo portion having the second color.

The invention relates to the field of X-ray image processing, and discloses an X-ray image reconstruction method based on direction perception tensor modeling. The method comprises the following steps: acquiring a plurality of X-ray projection images with different incident angles, and establishing a projection direction mapping matrix in combination with tissue direction distribution; constructing a high-order direction perception tensor field based on the mapping matrix and the structure prior information, wherein the high-order direction perception tensor field is used for describing the dominant structure direction and anisotropic response characteristics of each image position; a direction enhancement response diagram is generated through tensor-guided gradient calculation, and dynamic enhancement of local edges is achieved; then structure response intensity is extracted to construct a structure sensitive function graph, and the structure sensitive function graph serves as a weighting factor in image reconstruction; based on the weighted graph and the tensor field, an image reconstruction objective function containing direction consistency constraint is constructed, joint optimization is executed, a regularization item is dynamically updated, and high-fidelity reconstruction of the image under the low-dose condition is achieved. According to the method, the image detail keeping and noise suppression capabilities are improved, and the method has relatively high adaptability and robustness.

The invention belongs to the technical field of medical images, and relates to a surgical navigation-oriented multi-dimensional medical image adaptive registration method, which comprises the following steps: acquiring a 3D CT image, performing feature extraction, and performing voxel-by-voxel addition on the 3D CT image and an original 3D CT image to obtain a 3D image to be projected; obtaining current pose estimation and target pose estimation; inputting the 3D image, the current pose estimation and the current pose estimation into a ProST projector to obtain a current projection image and a target projection image; inputting the current projection image and the target projection image into a double-path encoder-decoder, and capturing a global corresponding relation between features by adopting a cross-modal attention module to generate final features; fusing the final features, and inputting the fused final features into a total differential regression iteration model to obtain a registered medical image; the regression module provided by the invention provides a more robust initial pose for the optimization framework, and the probability that the network falls into local minimum during gradient descent optimization is greatly reduced.

The invention discloses a wide-angle camera distorted image correction method and device based on track visual detection. The method comprises the following steps: acquiring a track distorted image; the projection imaging intersection point between the sleeper and the steel rail is adopted to form a mark point; solving the distortion center of the camera by combining a distortion model according to the mapping relation between the three-dimensional world coordinate and the projection coordinate of the three-dimensional world coordinate in the distorted image; solving distortion parameters of a camera by combining a Levenberg-Marquardt algorithm according to the fact that blanking points formed by parallel steel rails in the image must be subjected to collinear constraint; re-projection correction is carried out on the mark points participating in calculation; screening out bad mark points and removing the bad mark points; the distortion center and the distortion parameters are calculated again until all the mark points meet the 3 sigma criterion; and according to the optimal distortion center and the distortion parameters, track image correction is carried out through a distortion model. According to the invention, high-efficiency and accurate distortion correction can be carried out on line without the participation of a special cooperative calibration object.

The invention belongs to the technical field of medical image data processing, and particularly relates to a cardiac coronary plaque simulation method and system based on a digital phantom, and the method comprises the step of generating reconstructed simulation CT projection images with different halo artifact degrees. The method solves the problems that the effectiveness of an artifact removal method cannot be verified and evaluated due to the fact that the algorithm training effect is not generalized enough, and has the beneficial technical effects that the effectiveness of the artifact removal method is fully verified and evaluated, and the generalization of a deep learning halo artifact removal algorithm is improved.

There is provided an image processing apparatus comprising. An obtainment unit obtains a first circular fisheye image accompanied by a first missing region in which no pixel value is present. A generation unit generates a first equidistant cylindrical projection image by performing first equidistant cylindrical transformation processing based on the first circular fisheye image. The generation unit generates the first equidistant cylindrical projection image such that a first corresponding region corresponding to the first missing region has a pixel value in the first equidistant cylindrical projection image.

The invention relates to the technical field of printed circuit board copper embedding, and discloses a method and device for controlling the copper embedding quality of a printed circuit board, computer equipment and a storage medium. The method comprises the following steps: acquiring a projection image of a copper nail grabbed by a mechanical arm and a hole site on a printed circuit board; converting the projection image into a three-dimensional image; extracting information in the three-dimensional image to obtain the diameter of the copper nail and the diameter of the hole site; calculating a difference value between the diameter of the copper nail and the diameter of the hole site to obtain an interference value; judging whether the interference value exceeds a preset threshold value or not; and if the interference value does not exceed the preset threshold value, controlling the mechanical arm to embed the copper nail into the hole site of the printed circuit board so as to complete the copper embedding operation. According to the method, high-precision quantitative detection of the diameter of the copper nail and the diameter of the hole site is achieved, the difference value of the two diameters is calculated in real time, whether the interference magnitude of copper embedding operation is within the design range or not can be accurately judged, the copper embedding yield is increased, and the rework and scrap cost caused by copper embedding defects is reduced.

The invention relates to an image correction technology, and discloses a CBCT (cone beam computed tomography) image osteosclerosis artifact correction method, which comprises the following steps: acquiring a high-energy projection image and a low-energy projection image of a target object, performing image reconstruction, and calculating to obtain a primary artifact-free image; extracting a bone image and a soft tissue image from the primary artifact-free image based on threshold segmentation, calculating a bone weight, taking the artifact image of the target object as training input data, taking the bone image and the soft tissue image as reference data, and training to obtain a dual-channel artifact correction model; and outputting a preprocessed bone image and a preprocessed soft tissue image according to the to-be-processed osteosclerosis artifact image by using a dual-channel artifact correction model, and carrying out weighted fusion on the preprocessed bone image and the preprocessed soft tissue image according to a bone weight to obtain an artifact-free reconstructed image. The invention further provides a CBCT image osteosclerosis artifact correction device, electronic equipment and a storage medium. According to the invention, the image artifact correction effect can be improved.

A method includes generating, using at least one processing device, a ground truth optical flow map for displacement of pixels within a reference image based on a motion model. The motion model determines 3D coordinates of pixels within the reference image based on estimated depths of the pixels within the reference image. The method also includes performing, using the at least one processing device, 3D to 2D reprojection of the pixels within the reference image based on the motion model to generate a reprojected image view corresponding to a shifted camera perspective. The method further includes generating, using the at least one processing device, an occlusion mask for the reference image. The occlusion mask corresponds to occluded pixels within the reprojected image view. In addition, the method includes performing, using the at least one processing device, occlusion region inpainting of the occluded pixels to generate an inpainted reprojected image view.

In various examples, a visualization of an environment may be generated using a Panini projection that is optimized based on detected scene content. For example, image data of an environment may be perspective projected (e.g., using a rectilinear projection) to generate a reference projection image, which may be analyzed to detect the presence of vanishing points and / or horizontal lines (e.g., in a central region). The image data of the environment may be projected using a Panini projection that is optimized based on distances to detected objects, the absence of a detected vanishing point, and / or the presence of a detected horizontal line to generate a Panini projection image. In some embodiments, vertical compression is applied to the Panini projection image to correct for distortion of horizontal lines (e.g., based on the presence of a detected horizontal line).

The invention provides an intelligent adaptive projection lamp and a projection control method, and the method comprises the steps: collecting multi-source environment data which comprises at least one of environment illumination data, projection surface characteristic data and user operation data; performing preprocessing, feature extraction and feature fusion on the multi-source environment data to generate an environment feature vector; performing projection mapping on the environment feature vector through a parameter prediction model based on rate distortion optimization to generate projection parameters; performing image deblurring processing and adaptive k-space sampling reconstruction on the projection parameters to generate an optimized projection image; collecting projection effect feedback data for the optimized projection image; and performing online updating optimization on the parameter prediction model according to the projection effect feedback data. According to the invention, intelligent adaptive adjustment of the projection parameters is realized, and the projection quality is improved.