-
公开(公告)号：US20190244050A1
公开(公告)日：2019-08-08
申请号：US16386143
申请日：2019-04-16
发明人： Xiangkai LIN , Linchao BAO , Wei LIU
CPC分类号： G06K9/4609 , G06K9/20 , G06K9/34 , G06K9/46 , G06K9/6211 , G06T3/0006 , G06T5/20 , G06T7/00 , G06T7/246 , G06T7/73
摘要： Embodiments of this application disclose a method for determining camera pose information of a camera of a mobile terminal. The method includes: obtaining a first image, a second image, and a template image; performing feature point detection on a first feature point of the template image and a second feature point of the second image, to obtain a first homography; determining a first target homography according to a first optical flow feature point in the first image and a second optical flow feature point in the second image, and determining a second homography according to the first target homography and a second target homography; and performing complementary filtering processing on the first homography and the second homography, to obtain camera pose information of the camera. In the embodiments of this application, complementary filtering processing may be performed on two homographies obtained in a camera pose tracking process.
-
公开(公告)号：US20190197347A1
公开(公告)日：2019-06-27
申请号：US16312983
申请日：2017-06-30
发明人： Darin T OKUDA , Braeden D NEWTON
CPC分类号： G06K9/6201 , A61B5/055 , G06K9/34 , G06K2209/051 , G06T7/11 , G06T15/08 , G06T17/00 , G06T2207/10088 , G06T2207/30016 , G06T2207/30096 , G06T2210/41 , G16H30/40
摘要： Methods, apparatuses, systems, and implementations for creating 3-dimensional (3D) representations exhibiting geometric and surface characteristics of brain lesions are disclosed. 2D and/or 3D MRI images of the brain may be acquired. Brain lesions and other abnormalities may be identified and isolated with each lesion serving as a region of interest (ROI). Saved ROI may be converted into stereolithography format, maximum intensity projection (MIP) images, and/or orthographic projection images. Data corresponding to these resulting 3D brain lesion images may be used to create 3D printed models of the isolated brain lesions using 3D printing technology. Analysis of the 3D brain lesion images and the 3D printed brain lesion models may enable a more efficient and accurate way of determining brain lesion etiologies.
-
公开(公告)号：US20190051191A1
公开(公告)日：2019-02-14
申请号：US15675591
申请日：2017-08-11
申请人： The Boeing Company
CPC分类号： G08G5/045 , B64C39/024 , B64C2201/123 , B64C2201/127 , B64C2201/141 , G06K9/0063 , G06K9/00805 , G06K9/2018 , G06K9/209 , G06K9/34 , G06K9/6269 , G06K9/6289 , G06K2009/4666 , G08G5/0013 , G08G5/0021 , G08G5/0069
摘要： In general, certain embodiments of the present disclosure provide a detection and avoidance system for a vehicle. According to various embodiments, the detection and avoidance system comprises an imaging unit configured to obtain a first image of a field of view at a first camera channel. The first camera channel filters radiation at a wavelength, where one or more objects in the field of view do not emit radiation at the wavelength. The detection and avoidance system further comprises a processing unit configured to receive the first image from the imaging unit and to detect one or more objects therein, as well as a notifying unit configured to communicate collision hazard information determined based upon the detected one or more objects to a pilot control system of the vehicle. Accordingly, the pilot control maneuvers the vehicle to avoid the detected objects.
-
公开(公告)号：US20190035210A1
公开(公告)日：2019-01-31
申请号：US16150686
申请日：2018-10-03
申请人： ARB LABS INC.
发明人： Adrian BULZACKI , Vlad CAZAN
IPC分类号： G07F17/32 , G06K9/00 , G06K9/78 , G06K9/46 , G06K9/36 , G06K9/34 , G06K9/32 , G06K9/20 , G06K9/62
CPC分类号： G07F17/3227 , A63F3/00157 , A63F2003/00164 , G06K9/00201 , G06K9/0053 , G06K9/00577 , G06K9/00771 , G06K9/2027 , G06K9/2054 , G06K9/209 , G06K9/3233 , G06K9/34 , G06K9/346 , G06K9/36 , G06K9/46 , G06K9/4642 , G06K9/62 , G06K9/6298 , G06K9/78 , G07F17/3211 , G07F17/322
摘要： System, processes and devices for monitoring betting activities using bet recognition devices and a server. Each bet recognition device has an imaging component for capturing image data for a gaming table surface. The bet recognition device receives calibration data for calibrating the bet recognition device. A server processor coupled to a data store processes the image data received from the bet recognition devices over the network to detect, for each betting area, a number of chips and a final bet value for the chips.
-
5.发明申请公开(公告)号：US20180300882A1
公开(公告)日：2018-10-18
申请号：US15487813
申请日：2017-04-14
发明人： Vladimir Kim , Aaron Hertzmann , Mehmet Yumer
CPC分类号： G06T7/143 , G06K9/00201 , G06K9/34 , G06K9/685 , G06T7/11 , G06T2200/04 , G06T2207/10028 , G06T2207/20081
摘要： The present disclosure includes methods and systems for identifying and manipulating a segment of a three-dimensional digital model based on soft classification of the three-dimensional digital model. In particular, one or more embodiments of the disclosed systems and methods identify a soft classification of a digital model and utilize the soft classification to tune segmentation algorithms. For example, the disclosed systems and methods can utilize a soft classification to select a segmentation algorithm from a plurality of segmentation algorithms, to combine segmentation parameters from a plurality of segmentation algorithms, and/or to identify input parameters for a segmentation algorithm. The disclosed systems and methods can utilize the tuned segmentation algorithms to accurately and efficiently identify a segment of a three-dimensional digital model.
-
公开(公告)号：US20180285640A1
公开(公告)日：2018-10-04
申请号：US15476562
申请日：2017-03-31
申请人： THE BOEING COMPANY
发明人： Timothy E. Brown , Robert J. Klein
CPC分类号： G06K9/00637 , G01J3/2823 , G01J3/42 , G06K9/00657 , G06K9/34 , G06K9/4661 , G06K9/6201 , G06K2009/00644 , G06K2009/4657
摘要： A method of identifying a target material in a spectral image includes acquiring a spectral image of a scene. The method also includes performing image segmentation to partition the spectral image into a plurality of segments. The method includes accessing a database of spectral models of a plurality of materials to determine a material whose spectral model is most similar to the spectral data for the segment, a difference between the spectral model of the material and the spectral data for the segment including measurable reflectance or radiance at characteristic frequencies or wavelengths. The method also includes analyzing a database of spectral data for a plurality of target materials to identify a target material whose spectral data also has measurable reflectance or radiance at the characteristic frequencies or wavelengths. And the method includes outputting an identifier of the target material for display with the spectral image.
-
公开(公告)号：US20180260668A1
公开(公告)日：2018-09-13
申请号：US15456367
申请日：2017-03-10
发明人： Xiaohui Shen , Zhe Lin , Yi-Hsuan Tsai , Xin Lu , Kalyan K. Sunkavalli
CPC分类号： H04N1/387 , G06K9/34 , G06K9/4628 , G06K9/4652 , G06K9/6256 , G06K9/627 , G06N3/02 , G06N3/0454 , G06N3/08 , G06N3/084 , G06T11/00 , H04N1/6066
摘要： Methods and systems are provided for generating harmonized images for input composite images. A neural network system can be trained, where the training includes training a neural network that generates harmonized images for input composite images. This training is performed based on a comparison of a training harmonized image and a reference image, where the reference image is modified to generate a training input composite image used to generate the training harmonized image. In addition, a mask of a region can be input to limit the area of the input image that is to be modified. Such a trained neural network system can be used to input a composite image and mask pair for which the trained system will output a harmonized image.
-
8.发明申请公开(公告)号：US20180192910A1
公开(公告)日：2018-07-12
申请号：US15802293
申请日：2017-11-02
申请人： Nocimed, Inc.
IPC分类号： A61B5/055 , G06K9/34 , A61B5/00 , G01R33/485 , G01R33/483 , G01R33/54 , G06T7/11 , G06T7/12 , G06T7/62
CPC分类号： A61B5/055 , A61B5/4566 , G01R33/4835 , G01R33/485 , G01R33/543 , G06K9/34 , G06T7/11 , G06T7/12 , G06T7/62 , G06T2207/10088 , G06T2207/30012
摘要： A system and method for automating an appropriate voxel prescription in a uniquely definable region of interest (ROI) in a tissue of a patient is provided, such as for purpose of conducting magnetic resonance spectroscopy (MRS) in the ROI. The dimensions and coordinates of a single three dimensional rectilinear volume (voxel) within a single region of interest (ROI) are automatically identified. This is done, in some embodiments by: (1) applying statistically identified ROI search areas within a field of view (FOV); (2) image processing an MRI image to smooth the background and enhance a particular structure useful to define the ROI; (3) identifying a population of pixels that define the particular structure; (4) performing a statistical analysis of the pixel population to fit a 2D model such as an ellipsoid to the population and subsequently fit a rectilinear shape within the model; (5) repetiting elements (1) through (4) using multiple images that encompass the 3D ROI to create a 3D rectilinear shape; (6) a repetition of elements (1) through (5) for multiple ROIs with a common FOV. A manual interface may also be provided, allowing for override to replace by manual prescription, assistance to identify structures (e.g. clicking on disc levels), or modifying the automated voxel (e.g. modify location, shape, or one or more dimensions).
-
9.发明申请公开(公告)号：US20180173936A1
公开(公告)日：2018-06-21
申请号：US15736146
申请日：2016-06-15
申请人： NEC Corporation
发明人： Masanori MIZOGUCHI
CPC分类号： G06K9/00114 , G06F21/32 , G06K9/00087 , G06K9/0012 , G06K9/34 , G06K9/4652 , G06T7/00
摘要： A dermal image information processing device includes: a dermal image information acquisition unit that acquires image information indicating an image of a papillary layer; and a singular region detection unit that detects a singular region indicating damage of the papillary layer, based on the acquired image information.
-
10.发明授权公开(公告)号：US10002313B2
公开(公告)日：2018-06-19
申请号：US15379277
申请日：2016-12-14
申请人： Sighthound, Inc.
CPC分类号： G06K9/6814 , G06K9/3233 , G06K9/34 , G06K9/4628 , G06K9/4671 , G06K9/6286 , G06N3/0454 , G06N3/0481 , G06N3/082 , G06T7/00 , G06T7/136 , G06T7/74 , G06T2207/10004 , G06T2207/10016 , G06T2207/20004 , G06T2207/20016 , G06T2207/20024 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084
摘要： A Convolutional Neural Network (CNN) includes an initial set of convolutional layers and max pooling units, in which any input is convoluted with the learned image filters and the output is a stack of the different filter responses. Max pooling produces a scaled version of the output. The process can be repeated several times, resulting in a stack of space invariant-scaled images. Since the operation is space invariant, the computations of these layers not need to be recomputed if interested just in certain regions of the image. A Region Of Interest (ROI) Pooling layer is used to select regions to be processed by the set of fully connected layers, which uses the response of the multiple convolutional layers of the network to determine the regions where the objects (of different scales) could be located. This object proposal method is implemented as a Region Of Interest (ROI) Selector.
-
-
-
-
-
-
-
-
-
搜索结果
1024 条记录 (耗时 0.032 秒)
