1012 results about "3D reconstruction" patented technology

A system and process for generating, and then rendering and displaying, an interactive viewpoint video in which a user can watch a dynamic scene while manipulating (freezing, slowing down, or reversing) time and changing the viewpoint at will. In general, the interactive viewpoint video is generated using a small number of cameras to capture multiple video streams. A multi-view 3D reconstruction and matting technique is employed to create a layered representation of the video frames that enables both efficient compression and interactive playback of the captured dynamic scene, while at the same time allowing for real-time rendering.

Miniaturized, five and six degrees-of-freedom magnetic sensors, responsive to pulsed DC magnetic fields waveforms generated by multiple transmitter options, provide an improved and cost-effective means of guiding medical instruments to targets inside the human body. The end result is achieved by integrating DC tracking, 3D reconstructions of pre-acquired patient scans and imaging software into a system enabling a physician to internally guide an instrument with real-time 3D vision for diagnostic and interventional purposes. The integration allows physicians to navigate within the human body by following 3D sensor tip locations superimposed on anatomical images reconstructed into 3D volumetric computer models. Sensor data can also be integrated with real-time imaging modalities, such as endoscopes, for intrabody navigation of instruments with instantaneous feedback through critical anatomy to locate and remove tissue. To meet stringent medical requirements, the system generates and senses pulsed DC magnetic fields embodied in an assemblage of miniaturized, disposable and reposable sensors functional with both dipole and co-planar transmitters.

The present invention provides systems, methods, and devices for electroporation-based therapies (EBTs). Embodiments provide patient-specific treatment protocols derived by the numerical modeling of 3D reconstructions of target tissue from images taken of the tissue, and optionally accounting for one or more of physical constraints or dynamic tissue properties. The present invention further relates to systems, methods, and devices for delivering bipolar electric pulses for irreversible electroporation exhibiting reduced or no damage to tissue typically associated with an EBT-induced excessive charge delivered to the tissue.

A method for measuring three-dimensional devices in a wafer comprises the step of obtaining a plurality of cross-sectional images of a corresponding plurality of three-dimensional devices in the wafer. The plurality of three-dimensional devices have essentially identical geometries. Each cross-sectional image is obtained from a plane in the corresponding three-dimensional device at a predetermined distance from a fiducial mark thereof. The predetermined distance is different for each of the plurality of cross-sectional images. The method further comprises the step of determining the geometries of the plurality of three-dimensional devices based on the cross-sectional images thereof.

A scanning method for scanning samples of biological cells using optical tomography includes preparing, acquiring, reconstructing and viewing three-dimensional images of cell samples. Concentration and enrichment of the cell sample follows. The cell sample is stained. Cells are isolated from the cell sample and purified. A cell/solvent mixture is injected into a gel by centrifugation. A cell/gel mixture is injected into a capillary tube until a cell appears centered in a field of view using a step flow method. An optical imaging system, such as a fixed or variable motion optical tomography system acquires a projection image. The sample is rotated about a tube axis to generate additional projections. Once image acquisition is completed, the acquired shawdowgrams or image projections are corrected for errors. A computer or other equivalent processor is used to compute filtered backprojection information for 3D reconstruction.

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

In a method and apparatus for the three-dimensional presentation of an examination region of a patient in the form of a 3D reconstruction image, a preoperatively acquired 3D image dataset of the examination region is employed in a medical procedure, datasets representing a number of 2D ultrasound images of the examination region are acquired, the preoperative 3D image dataset is updated using the datasets representing 2D ultrasound images, and the 3D reconstruction image is generated on the basis of the updated 3D image dataset.

A method for 3D reconstruction of the positions of a catheter as it is moved within a region of the human body, comprising: (a) ascertaining the 3D position of a point on a catheter for insertion in the body region; (b) acquiring a fixed angle, single-plane fluoroscopic image of the body region and of the catheter; (c) transferring the image data and catheter-point position to a computer; (d) determining the 2D image coordinates of the point on the catheter; (e) changing the length of catheter insertion by a measured amount; (f) thereafter acquiring a further single-plane fluoroscopic image of the body region and the catheter from the same angle, transferring the length change and additional image data to the computer, and determining the 2D image coordinates of the point on the catheter; (g) computing the 3D position of the catheter point; and (h) repeating steps e-g plural times. A 3D model is constructed by assembling the plural 3D positions of the point within the body region into a 3D model of the region.

The invention discloses an indoor scene 3D reconstruction method based on Kinect and solves the technical problem of the real-time reconstruction of an indoor scene 3D model and avoidance of excessive redundant points. The method comprises steps of: obtaining the depth data of an object by using Kinect and de-nosing and down-sampling the depth data; obtaining the point cloud data of a current frame and calculating the vector normal of each point in the frame; using a TSDF algorithm to establish a global data cube, and using a ray casting algorithm to calculate predicted point cloud data; calculating a point cloud registration matrix by using an ICP algorithm and the predicted point cloud data, fusing the obtained point cloud data of each frame into the global data cube, and fusing the point cloud data frame by frame until a good fusion effect is obtained; rendering the point cloud data with an isosurface extraction algorithm and constructing the 3D model of the object. The method improves the registration speed and the registration precision, is fast in fusion speed and few in redundancy points, and can be used for real-time reconstruction of the indoor scene.

An image processing system and method reconstructs 3D image information corresponding to a scene from a plurality of 2D images of the scene. The method receives a plurality of image features corresponded between different 2D views of the scene, the corresponded image features deviating between different views as a result of camera relative motion. The method determines image features of the received plurality of image features that are occluded views, determines image features of the received plurality of image features that are confident seeds associated with 3D depth information, and propagates 3D depth information from the confident seeds to neighboring image features, while avoiding image features that have been determined to be occluded views. The 3D image information can be rendered and displayed such as for a virtual walkthrough of the scene.

In an image post-processing method and apparatus for 3D visualization of 2D/3D fused image data for use in catheter angiography in an endovascular interventional procedure, upon forward movement of a micro-catheter through blood vessel in the interventional procedure, x-ray images are acquired from different projection directions and are subjected to a pattern recognition algorithm for edge-based segmentation of the image regions filled by the micro-catheter, with all remaining image regions being masked out. The segmented projection exposures are prepared by a 3D reconstruction algorithm to obtain an image data set for (pseudo-) three-dimensional representation of the micro-catheter. This image data set are intraoperatively registered and fused with an image data set acquired from an angiographic pre-examination for three-dimensional visualization of the vessel topography. The reconstructed 3D representation of the catheter is mixed into the three-dimensionally prepared representation of endovascular blood vessel sections to be treated.

A system and method for planning surgical procedure including importing CT image data of a patient; generating a 3D reconstruction from the CT image data; presenting a slice of the 3D reconstruction; selecting a target anatomical feature from the slice of the 3D reconstruction; setting a treatment zone including presenting at least one slice of the 3D reconstruction including the target anatomical feature, and presenting a treatment zone marker defining a location and a size of the treatment zone on the presented at least one slice of the 3D reconstruction; setting an access route to the treatment zone; and presenting a three-dimensional model including the treatment zone and the access route.

The invention discloses a visual sense simultaneous localization and mapping method based on dot and line integrated features. The method comprehensively utilizes the line features and the dot features extracted and obtained from a binocular camera image and is able to be used for the positioning and the attitude estimation of a robot in both an external environment and an internal environment. As the dot features and the line features are integrated for use, the system becomes more robust and more accurate. For the parameterization of linear features, the Pluck coordinates are used for straight line calculations, including geometric transformations, 3D reconstructions, and etc. In the back-end optimization, the orthogonal representation of the straight line is used to minimize the number of the parameters of the straight line. The off-line established visual dictionary for the dot and line integrated features is used for closed loop detections; and through the method of adding zone bits, the dot characteristics and the line characteristics are treated differently in the visual dictionary and when an image database is created and image similarity is calculated. The invention can be applied to the construction of a scene image both indoors and outdoors. The constructed map integrates the feature dots and the feature lines, therefore, able to provide even richer information.

A method for reconstructing 3D blood vessels belongs to the field of medical detection technology for solving the accuracy problem in blood vessel reconstruction. The technical scheme is that the method can accurately reconstruct the anatomic structure of a blood vessel by combining cross section information of the blood vessel acquired by an IVUS image sequence and ultrasonic duct spatial geometrical information obtained by 3D reconstruction based on X-ray angiographic images. Compared with the reconstruction result obtained by using two single images, the method can completely and accurately reflect the actual shapes of blood vessels and possibly-existing plaques, thus providing more reliable basis for clinical treatment of coronary heart diseases and other angiopathies.

The present invention provides a method for generating a three-dimensional (3D) building model based on photographed house type image identification. The method is used for solving the problem conventional house-type-image-based 3D reconstruction methods are not suitable for photographing-version house type images. Aiming at characteristics of a photographing- version house type image, correction treatment is first carried out on the photographing- version house type image, thus to enable the quality of the corrected image to be similar to that of an electronic-version house type image, thereby bringing convenience for follow-up house type image identification; carrying out wall body identification according to the characteristics of the photographing-version house type image, and carrying out size correction and closing of wall bodies, and generating a cross-platform JSON file; and ultimately using wall body information of the JSON file by Unity3D to carry out 3D reconstruction. With adoption of the method provided by the present invention, identification of photographed house type images is realized, the 3D building model is generated, the problem that the photographed house type image is inclined can be effectively solved, a wall body calculating method based on wall body intersecting anchor points is provided, and thus the following generated 3D wall bodies can be conveniently freely pulled and stretched based on the anchor points.

A method and apparatus for recovering a three-dimensional (3D) scene from two-dimensional (2D) images. A sequence of images is divided into a number of smaller segments and a 3D reconstruction is performed on each segment individually. All the reconstructed segments are then combined together through an efficient bundle adjustment to complete the 3D reconstruction. Segmenting may be achieved by dividing the segments based on the number of feature points that are in each frame. The number of frames per segment is reduced by creating virtual key frames. The virtual key frames encode the 3D structure for each segment, but are only a small subset of the original frames in the segment. A final bundle adjustment is performed on the virtual key frames, rather than all of the original frames. Thus, the final bundle adjustment is two orders of magnitude faster than a conventional bundle adjustment.

The present invention relates to an image reconstruction device (12) for an X-ray apparatus and a method for local 3D reconstruction of an object area of an examination object (7) from 2D image data of several 2D X-ray images of the examination object (7) registered in chronological order with different known projection geometries using the X-ray apparatus. With the method a location in the object area under consideration is selected from one of the 2D X-ray images. The positions of the selected location are determined in at least some of the 2D X-ray images and a spatial motion of the selected location between the registrations of the 2D X-ray images is calculated from the positions obtained, taking the known projection geometries into consideration. The calculated motion is then annulled by modifying the 2D image data in the 2D X-ray images and a 3D image dataset of at least the object area is reconstructed from the modified 2D image data. The method and the image reconstruction device enable a 3D image of a moving locally bounded object area to be reconstructed in a simple way without motion artifacts.

The invention relates to a three-dimensional model reconstruction method of tree point cloud data based on partition and automatic growth, comprising the following steps: preprocessing; estimating the main curvature of point cloud; partitioning data according to the main curvature; calculating a framework of a principal branch of branches by the partitioned point cloud belonging to a branch part;leading from the framework of the principal branch of the branches to generate twigs of the branches by the partitioned point cloud belonging to a leaf part; and generating a branch mesh model and adding a leaf model at the ends of the twigs of the branches. In the method, the three-dimensional reconstruction model which is faithful to original entities can be obtained by means of the scanning data of a laser scanner; the reconstruction model of the tree point cloud data can be obtained based on data partition and growth of the twigs of the branches, thus the method has simple algorithm and accurate calculation result; and the calculation result has important application value in the fields such as virtual reality, computer games, natural scene simulation, urban landscape design, film production, three-dimensional reconstruction of trees, agriculture and forestry measurement and the like.

The invention discloses a method for 3D reconstruction and texture generation from single-view face based on multi-task learning, belonging to the computer vision field. The method comprises the following steps of: selecting a special viewpoint for rendering a three-dimensional human face model; generating depth map and texture map as truth value data from special viewpoint; designing an integrated learning and coding network based on feature sharing of depth information and texture information; designing the branch decoding network to recover the depth map from the shared features, and recovering the depth map, designing the mutual information with shared features as latent variables to maximize the generation of antagonistic network, and restoring the texture unwrapping map, adjusting the proportion of each task loss function and training the model; interpolating the depth map and using texture map to reconstruct the 3D face mesh model with texture details. The invention utilizes multi-task learning to carry out single-view face three-dimensional reconstruction, texture generation and style migration, and has the advantages of high speed, low cost and the like.

A C-arm x-ray imaging system enhances reconstructed volumes internal to a patient. Truncation artifacts in reconstructed volume data sets may be reduced by creating an effective x-ray detector of greater size. The x-ray detector may include a movable stage and a detector mount. The movable stage may be movable within the x-ray detector mount. A first partial circular scan may be performed with the movable stage at a first position. The movable stage may be repositioned to a second position before a second partial circular scan is performed. Performing two partial circular scans with the movable stage located at different positions may increase the effective size of the x-ray detector. The associated views acquired with the detector in opposite offset positions are combined and used for 3D reconstruction. A method of calibration may include generating first and second projection matrices associated with first and second transform parameters, respectively.

The invention discloses a human body 3D reconstruction method and device for a complex dynamic scene under a multi-view camera. The method comprises the following steps: photographing a target human body object at multiple views to obtain 2D images at multiple views under the same moment; predicting all the parts of the human body in the video sequence through a model after deep network learning to obtain the human body skeleton information of the human body; matching the movement and rough contour of the character in the images through a virtual 3D human body model according to the skeleton information to obtain the human body contour information of the human body; and carrying out human body 3D modeling through a Virtual Hull method according to the calibrated internal and external parameter information of the camera at multiple views as well as the human body skeleton information and the human body contour information. Through the method, 3D reconstruction of a human body object ina video sequence can be realized through camera calibration and other processes, and therefore, accurate character object segmentation is realized, and the accuracy and reliability of reconstruction are improved.