-
公开(公告)号：US09098926B2
公开(公告)日：2015-08-04
申请号：US12692155
申请日：2010-01-22
申请人： Long Quan , Jianxiong Xiao , Tian Fang , Peng Zhao
发明人： Long Quan , Jianxiong Xiao , Tian Fang , Peng Zhao
CPC分类号： G06T17/00 , G06K9/00704 , G06T15/04
摘要： The subject disclosure relates to generating three-dimensional façade models from images. In one aspect, a systematic decomposition schema is disclosed for a façade structured into a Direct Acyclic Graph and implemented as a top-down recursive subdivision and bottom-up merging. In a further aspect, optimization of façade depth operating in a façade surface and in the super-pixel level of a whole subdivision region is described.
摘要翻译： 本公开涉及从图像生成三维立面模型。 在一个方面，公开了一种系统分解模式，用于构造为直接非循环图的外观，并实现为自上而下的递归细分和自下而上的合并。 在另一方面，描述了在整个细分区域的外观表面和超像素级中操作的外墙深度的优化。
-
公开(公告)号：US08406564B2
公开(公告)日：2013-03-26
申请号：US12237126
申请日：2008-09-24
申请人： Jian Sun , Heung-Yeung Shum , Lu Yuan , Long Quan
发明人： Jian Sun , Heung-Yeung Shum , Lu Yuan , Long Quan
CPC分类号： G06T5/003 , G06T2207/20016 , G06T2207/20028
摘要： Embodiments related to the removal of blur from an image are disclosed. One disclosed embodiment provides a method of performing an iterative non-blind deconvolution of a blurred image to form an updated image. The method comprises downsampling the blurred image to form a blurred image pyramid comprising images of two or more different resolution scales, downsampling a blur kernel to form a blur kernel pyramid comprising kernels of two or more different sizes, and deconvoluting a selected image in the blurred image pyramid according to a Richardson-Lucy deconvolution process in which a bilateral range/spatial filter is employed.
摘要翻译： 公开了从图像中去除模糊的实施例。 一个公开的实施例提供了一种执行模糊图像的迭代非盲去卷积以形成更新图像的方法。 该方法包括对模糊图像进行下采样以形成包含两个或多个不同分辨率尺度的图像的模糊图像金字塔，对模糊核心进行下采样以形成包含两个或更多个不同大小的粒子的模糊核心金字塔，并且对模糊的所选图像进行解卷积 图像金字塔根据理查森 - 露西反卷积过程，其中采用双边范围/空间滤波器。
-
公开(公告)号：US20110181589A1
公开(公告)日：2011-07-28
申请号：US13010193
申请日：2011-01-20
申请人： Long QUAN , Peng ZHAO , Tian FANG , Honghui ZHANG
发明人： Long QUAN , Peng ZHAO , Tian FANG , Honghui ZHANG
IPC分类号： G06T17/00
CPC分类号： G06T17/05 , G06T2210/04
摘要： Systems and methods are provided to facilitate architectural modeling. In one aspect, a modeling system is provided. This includes a processor configured to generate remodeled images associated with one or more architectural structures. A procedural model is configured to integrate an approximate model from aerial images of the architectural structures and a three-dimensional (3D) reconstruction model from ground-level images of the architectural structures.
摘要翻译： 提供系统和方法以便于架构建模。 在一个方面，提供了建模系统。 这包括被配置为生成与一个或多个架构结构相关联的改造图像的处理器。 程序模型被配置为将来自建筑结构的空中图像的近似模型与来自建筑结构的地面图像的三维（3D）重建模型相集成。
-
公开(公告)号：US09129432B2
公开(公告)日：2015-09-08
申请号：US13010193
申请日：2011-01-20
申请人： Long Quan , Peng Zhao , Tian Fang , Honghui Zhang
发明人： Long Quan , Peng Zhao , Tian Fang , Honghui Zhang
IPC分类号： G06T17/05
CPC分类号： G06T17/05 , G06T2210/04
摘要： Systems and methods are provided to facilitate architectural modeling. In one aspect, a modeling system is provided. This includes a processor configured to generate remodeled images associated with one or more architectural structures. A procedural model is configured to integrate an approximate model from aerial images of the architectural structures and a three-dimensional (3D) reconstruction model from ground-level images of the architectural structures.
摘要翻译： 提供系统和方法以便于架构建模。 在一个方面，提供了建模系统。 这包括被配置为生成与一个或多个架构结构相关联的改造图像的处理器。 程序模型被配置为将来自建筑结构的空中图像的近似模型与来自建筑结构的地面图像的三维（3D）重建模型相集成。
-
公开(公告)号：US09036915B2
公开(公告)日：2015-05-19
申请号：US13575868
申请日：2011-01-27
CPC分类号： G06F17/30247 , G06K9/00704
摘要： Systems and methods are provided to facilitate architectural modeling. In one aspect, repetitive patterns are automatically detected and analyzed to generate modeled structural images such as building facades. In another aspect, structural symmetry is analyzed to facilitate architectural modeling and enhanced image generation.
摘要翻译： 提供系统和方法以便于架构建模。 在一个方面，自动检测和分析重复图案以产生建模立面等建模结构图像。 在另一方面，分析结构对称性以便于建筑建模和增强的图像生成。
-
公开(公告)号：US20110289777A1
公开(公告)日：2011-12-01
申请号：US12790107
申请日：2010-05-28
申请人： Long Quan , Chan Wing Hong
发明人： Long Quan , Chan Wing Hong
IPC分类号： B26B19/02
CPC分类号： B26B19/06
摘要： A blade head assembly for a hand-held hair cutting appliance includes a blade clamping device urging a cutting edge margin of a second blade in sliding engagement with a cutting edge margin of a first blade. The blade clamping device includes a clamping head operable for pivoting generally toward and generally away from the second blade about a pivot axis. The clamping head is resiliently biased generally toward the second cutting blade about the pivot axis into sliding engagement with the second blade. The second blade is slidable relative to the clamping head during reciprocating movement of the second blade relative to the first blade.
摘要翻译： 一种用于手持式切割器具的刀头组件包括：叶片夹持装置，其推动第二刀片的切割边缘与第一刀片的切割边缘边缘滑动接合。 刀片夹紧装置包括夹紧头，该夹紧头可操作用于围绕枢转轴线大致朝向并大体上远离第二刀片枢转。 夹紧头通常朝着第二切割刀片围绕枢转轴线弹性偏压，与第二刀片滑动接合。 第二刀片在第二刀片相对于第一刀片的往复运动期间可相对于夹紧头滑动。
-
公开(公告)号：US20100201682A1
公开(公告)日：2010-08-12
申请号：US12692155
申请日：2010-01-22
申请人： Long Quan , Jianxiong Xiao , Tian Fang , Peng Zhao
发明人： Long Quan , Jianxiong Xiao , Tian Fang , Peng Zhao
CPC分类号： G06T17/00 , G06K9/00704 , G06T15/04
摘要： The subject disclosure relates to generating three-dimensional façade models from images. In one aspect, a systematic decomposition schema is disclosed for a façade structured into a Direct Acyclic Graph and implemented as a top-down recursive subdivision and bottom-up merging. In a further aspect, optimization of façade depth operating in a façade surface and in the super-pixel level of a whole subdivision region is described.
摘要翻译： 本公开涉及从图像生成三维立面模型。 在一个方面，公开了一种系统分解模式，用于构造为直接非循环图的外观，并实现为自上而下的递归细分和自下而上的合并。 在另一方面，描述了在整个细分区域的外观表面和超像素级中操作的外墙深度的优化。
-
公开(公告)号：US08494285B2
公开(公告)日：2013-07-23
申请号：US13315587
申请日：2011-12-09
申请人： Honghui Zhang , Long Quan
发明人： Honghui Zhang , Long Quan
IPC分类号： G06K9/46
CPC分类号： G06T7/162 , G06T7/11 , G06T2207/10024 , G06T2207/20072 , G06T2207/30252
摘要： Systems, methods, and apparatus are described that that increase computer vision analysis in the field of semantic segmentation. With images accompanied by scan data, both two-dimensional and three-dimensional image information is employed for joint segmentation. Through the established correspondence between image data and scan data, two-dimensional and three-dimensional information respectively associated therewith is integrated. Using trained random forest classifiers, the probability of each pixel in images belonging to different object classes is predicted. With the predicted probability, optimization of the labeling of images and scan data is performed by integrating multiples cues in the markov random field.
摘要翻译： 描述了在语义分割领域增加计算机视觉分析的系统，方法和装置。 对于伴随扫描数据的图像，采用二维和三维图像信息进行联合分割。 通过图像数据和扫描数据之间建立的对应关系，分别与其相关联的二维和三维信息被整合。 使用训练有素的随机森林分类器，预测属于不同对象类的图像中每个像素的概率。 利用预测的概率，通过在马尔可夫随机场中整合多个线索来执行图像标记和扫描数据的优化。
-
公开(公告)号：US20200209898A1
公开(公告)日：2020-07-02
申请号：US16725852
申请日：2019-12-23
申请人： Long QUAN , Bo WANG , Yunxiao HAO , He WANG , Zepeng LI , Lianpeng XIA
发明人： Long QUAN , Bo WANG , Yunxiao HAO , He WANG , Zepeng LI , Lianpeng XIA
摘要： The present invention discloses a load-sensing multi-way valve with a variable differential pressure, where each valve group uses a new element: an electro-hydraulic pressure compensation valve, so as to implement continuous real-time adjustment and control of compensated differential pressure and real-time position feedback and monitoring of a compensation valve trim, and overcome a flow mismatch problem of a conventional LS system in a flow saturation working condition and problems of a fixed shunting proportion of an LUDV system and poor operation coordination of actuators. The load-sensing multi-way valve with a variable differential pressure disclosed in the present invention has advantages such as strong working condition applicability, high flow distribution accuracy, and strong technicality.
-
公开(公告)号：US08798965B2
公开(公告)日：2014-08-05
申请号：US13148173
申请日：2010-02-03
申请人： Long Quan , Jianxiong Xiao , Tian Fang , Peng Zhao
发明人： Long Quan , Jianxiong Xiao , Tian Fang , Peng Zhao
CPC分类号： G06T17/05 , G06T7/174 , G06T7/579 , G06T2207/10016
摘要： The subject disclosure relates to generating models from images. In an aspect, multi-view semantic segmentation is provided to recognize and segment images at the pixel level into semantically meaningful areas, and which can provide labels with a specific object class. In further aspects, a partition scheme is provided that can separate objects into independent blocks using major line structures of a scene. In addition, an inverse patch-based orthographic composition and structure analysis on a block is provided that can regularize noisy and missing reconstructed 3D data to facilitate image-based modeling.
摘要翻译： 本公开涉及从图像生成模型。 在一方面，提供多视图语义分割以识别和将像素级别的图像分割成语义有意义的区域，并且其可以向特定对象类别提供标签。 在另外的方面，提供了一种可以使用场景的主线结构将对象分离为独立块的分区方案。 此外，还提供了一个块的基于逆贴片的正交组合和结构分析，可以使噪声和缺失重建的3D数据规范化，以促进基于图像的建模。
-
-
-
-
-
-
-
-
-
搜索结果
14 条记录 (耗时 0.162 秒)
