会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 12. 发明申请
    • METHOD AND A SYSTEM FOR IDENTIFYING REFLECTIVE SURFACES IN A SCENE
    • 用于识别场景中的反射表面的方法和系统
    • WO2017056089A3
    • 2017-07-27
    • PCT/IL2016051062
    • 2016-09-27
    • INFINITY AUGMENTED REALITY ISRAEL LTD
    • PROTTER MATANKUSHNIR MOTTIGOLDBERG FELIX
    • G06T15/06
    • G06K9/6267G06K9/00201G06K9/4661G06K9/52G06T7/0004G06T7/0075G06T7/593G06T19/00G06T2200/04G06T2207/30108
    • Methods and a system for identifying reflective surfaces in a scene are provided herein. The system may include a sensing device configured to capture a scene. The system may further include a storage device configured to store three-dimensional positions of at least some of the objects in the scene. The system may further include a computer processor configured to attempt to obtain a reflective surface representation for one or more candidate surfaces selected from the surfaces in the scene. In a case that the attempted obtaining is successful, computer processor is further configured to determine that the candidate reflective surface is indeed a reflective surface defined by the obtained surface representation. According to some embodiments of the present invention, in a case the attempted calculation is unsuccessful, determining that the recognized portion of the object is an object that is independent of the stored objects.
    • 本文提供了用于识别场景中的反射表面的方法和系统。 该系统可以包括被配置为捕捉场景的感测装置。 该系统还可以包括存储设备,该存储设备被配置为存储场景中的至少一些对象的三维位置。 该系统还可以包括计算机处理器,该计算机处理器被配置为尝试获得从场景中的表面中选择的一个或多个候选表面的反射表面表示。 在尝试获得成功的情况下,计算机处理器进一步被配置为确定候选反射表面确实是由所获得的表面表示限定的反射表面。 根据本发明的一些实施例,在尝试计算不成功的情况下,确定对象的识别部分是独立于所存储对象的对象。
    • 15. 发明申请
    • RANGE IMAGE GENERATION
    • 范围图像生成
    • WO2017039844A1
    • 2017-03-09
    • PCT/US2016/042295
    • 2016-07-14
    • INTEL CORPORATION
    • MILLER, BrettWOODFILL, John
    • H04N13/02G06T7/00
    • G06K9/6215G06K9/52G06K2209/40G06T7/593G06T2207/10012G06T2207/20028
    • Techniques are provided for range image generation. An input image and a reference image are used to compute raw and optimized disparity-space correlation disparity results for each pixel in the reference image. A bilateral filter is applied to both the raw and optimized disparity space correlation disparity results within a neighborhood of a given pixel. For each pixel in the neighborhood, a mean of sub-pixel disparity estimates includes the raw disparity-space correlation disparity result, and another mean of sub-pixel disparity estimates is computed using optimized disparity-space correlation disparity results. The output of the bilateral filter is a weighted sum of the means, with the weights being proportional to the ratio of valid, non-optimized sub-pixel correlation disparity results to optimized sub-pixel correlation disparity results, thereby favoring non-optimized estimates. A sub-pixel range image is generated based at least in part on the sub-pixel disparity estimate for each pixel in the reference image.
    • 为范围图像生成提供了技术。 输入图像和参考图像用于计算参考图像中每个像素的原始和优化的视差空间相关差异结果。 双向滤波器应用于给定像素的邻域内的原始和优化的视差空间相关差异结果。 对于邻域中的每个像素,子像素差异估计的平均值包括原始视差 - 空间相关视差结果,并且使用优化的视差 - 空间相关差异结果来计算子像素差异估计的另一平均值。 双边滤波器的输出是均值的加权和,权重与有效非优化子像素相关差异结果与优化子像素相关差异结果的比例成比例,从而有利于非优化估计。 至少部分地基于参考图像中的每个像素的子像素差异估计来生成子像素范围图像。
    • 16. 发明申请
    • 3D HAND POSE RECOVERY FROM BINOCULAR IMAGING SYSTEM
    • 从双向成像系统的3D手柄恢复
    • WO2016145625A1
    • 2016-09-22
    • PCT/CN2015/074447
    • 2015-03-18
    • TANG, Xiaoou
    • TANG, XiaoouQIAN, ChenHUI, Tak WaiLOY, Chen Change
    • G06T7/00
    • G06T7/593G06T2207/30196
    • Disclosed is an apparatus, a method and a system for constructing a 3D hand model from a binocular imaging system. The apparatus may comprise a retrieving device configured to retrieve a hand region from a stereo frame comprising at least a first image and a second image; a segmenting device in electrical communication with the retrieving device and configured to segment at least one hand part each having feature points from the retrieved hand region; an acquiring device electrically coupled with the segmenting device and configured to, for each segmented hand part, acquire a plurality of matched feature point pairs in which the feature points in the first image are matched with corresponding feature points in the second image; and a generating device in electrical communication with the acquiring device and configured to generate a 3D model of each hand part based on the matched feature point pairs of the hand part to construct the 3D hand model.
    • 公开了一种用于从双目成像系统构建3D手模型的装置,方法和系统。 该装置可以包括被配置为从包括至少第一图像和第二图像的立体声帧中检索手区域的检索装置; 与所述检索装置电通信并且被配置为将至少一个手部部分分割成具有来自所检索的手区域的特征点的分割装置; 与所述分割装置电耦合并且被配置为对于每个分割的手部分获取多个匹配的特征点对的获取装置,其中所述第一图像中的特征点与所述第二图像中的相应特征点匹配; 以及生成装置,其与所述获取装置进行电通信,并且被配置为基于所述手部的匹配的特征点对来生成每个手部的3D模型,以构建所述3D手模型。
    • 18. 发明申请
    • A METHOD FOR DETERMINING DEPTH FOR STEREOSCOPIC RECONSTRUCTION OF THREE DIMENSIONAL IMAGES
    • 用于确定三维图像的立体重建的深度的方法
    • WO2016092532A1
    • 2016-06-16
    • PCT/IL2015/000049
    • 2015-12-06
    • INUITIVE LTD.
    • SHMUELI, NivLIFSCHES, Samuel
    • G06T7/00
    • G06T7/593G06F17/10G06T1/60G06T7/97G06T2207/10012
    • A method is provided for obtaining a disparity map for reconstructing a three dimensional image. The map is based upon a large range of disparities and is obtained by using a hardware provided with a buffer capable of storing data that relates to substantially less disparities than a data associated with the large disparities' range. The method comprises the steps of: providing a pair of stereoscopic images captured by two image capturing devices; dividing the large disparities' range into N disparity ranges; executing a stereo matching algorithm for a plurality of times, using data retrieved from a pair of captured images, wherein the algorithm is executed each time while using a different disparity range out of the N disparity ranges, thereby obtaining a plurality of individual disparity maps, each corresponding to a different disparity range; and merging the individual disparity maps to generate a map of the large disparities' range.
    • 提供了一种用于获得用于重建三维图像的视差图的方法。 该映射基于大范围的差异,并且通过使用提供有能够存储与与大差异范围相关联的数据相比差异少的数据的缓冲器来获得。 该方法包括以下步骤:提供由两个图像捕获装置捕获的一对立体图像; 将大差距范围划分为N个差异范围; 使用从一对拍摄图像获取的数据执行多次的立体匹配算法,其中每次在N个视差范围内使用不同的视差范围时执行算法,从而获得多个个体视差图, 每个对应于不同的视差范围; 并且合并各个差异图以产生大差异范围的图。