公开(公告)号：US20160133027A1

公开(公告)日：2016-05-12

申请号：US14930009

申请日：2015-11-02

申请人： Ying ZHAO ,  Gang WANG ,  Liyan LIU

发明人： Ying ZHAO ,  Gang WANG ,  Liyan LIU

IPC分类号： G06T7/00 ,  G06K9/46 ,  G06K9/52 ,  G06T7/40

CPC分类号： G06T7/11 ,  G06K9/0014 ,  G06K9/3233 ,  G06T7/194 ,  G06T2207/10004 ,  G06T2207/10028

摘要： A method and an apparatus for separating a foreground image are disclosed. The method includes obtaining an input image, and color information and depth information of the input image; roughly dividing, based on the depth information of the input image, the input image to obtain an initial three-color image; reducing or expanding, based on the color information of the input image, an unknown region in the initial three-color image to obtain an optimized three-color image; and separating the foreground image from the optimized three-color image. According to the method, the initial three-color image can be optimized based on the color information of the input image, so that a more accurate three-color image can be obtained; thus the foreground image can be accurately separated from the three-color image.

摘要翻译： 公开了一种用于分离前景图像的方法和装置。 该方法包括获得输入图像，输入图像的颜色信息和深度信息; 基于输入图像的深度信息粗略地划分输入图像以获得初始三色图像; 基于输入图像的颜色信息，减少或扩大初始三色图像中的未知区域以获得优化的三色图像; 并且将前景图像与优化的三色图像分离。 根据该方法，可以基于输入图像的颜色信息优化初始三色图像，从而可以获得更准确的三色图像; 因此可以将前景图像与三色图像精确地分离。

公开(公告)号：US20180106707A1

公开(公告)日：2018-04-19

申请号：US15784290

申请日：2017-10-16

申请人： Zhiguo XING ,  Haidou WANG ,  Gang WANG

发明人： Zhiguo XING ,  Haidou WANG ,  Gang WANG

IPC分类号： G01N3/16

CPC分类号： G01N3/165 ,  G01N2203/0037 ,  G01N2203/0073

摘要： An impeller high-precision static performance simulation device, a testing machine, and an impeller performance simulation testing method are provided. In the device, a centrifugal force acting on a blade is simulated by an upper damper, a lower damper and a tension sensor. In the process of carrying out a simulation test to the performance of the impeller, a centrifugal force effect of an air compressor impeller is simulated by a static pulling force, to accurately simulate and evaluate the service condition of the impeller under the action of a high-precision static force.

公开(公告)号：US20180099327A1

公开(公告)日：2018-04-12

申请号：US15730957

申请日：2017-10-12

申请人： Gang WANG ,  Zhiguo XING ,  Haidou WANG

发明人： Gang WANG ,  Zhiguo XING ,  Haidou WANG

IPC分类号： B21D43/04 ,  B21D22/02 ,  B21D43/00

CPC分类号： B21D43/04 ,  B21D3/16 ,  B21D22/02 ,  B21D43/003 ,  C21D7/04 ,  C21D9/32 ,  F16H57/00 ,  F16H2057/0062

摘要： A device for performing strengthening treatment on a tooth root of a gear, a punch driver, a tooth root strengthening treatment device and a punch moving device are provided according to the present application. The device for performing the strengthening treatment on the tooth root of the gear according to the present application can impact a tooth root of a gear to be processed continuously under the action of the punch driver, and has a high efficiency while having a stable effect. The device in the present application is not limited by a complicated geometrical shape and a narrow space of the tooth root. Thus, it may be known that the devices according to the present application can address the issue of a low efficiency and poor effect in a current shot peening technique during performing the strengthening treatment on the tooth root.

公开(公告)号：US20170024874A1

公开(公告)日：2017-01-26

申请号：US15143718

申请日：2016-05-02

申请人： Bo PANG ,  Shengyin FAN ,  Xin WANG ,  Qian WANG ,  Gang WANG

发明人： Bo PANG ,  Shengyin FAN ,  Xin WANG ,  Qian WANG ,  Gang WANG

IPC分类号： G06T7/00 ,  G06K9/00

CPC分类号： G06K9/00771 ,  G06K9/00389

摘要： A method and an apparatus for detecting an abnormal situation are disclosed. The method includes recognizing whether a detection target exists in a captured image; generating, based on the captured image, a three-dimensional point cloud of the detection target in the captured image, when the detection target exists; obtaining, based on the generated three-dimensional point cloud, one or more current posture features of the detection target; and determining, based on the current posture features and one or more predetermined posture feature standards, whether the abnormal situation exists, the posture feature standards being previously determined based on one or more common features when the detection target performs a plurality of abnormal actions.

摘要翻译： 公开了一种用于检测异常情况的方法和装置。 该方法包括识别捕获图像中是否存在检测目标; 当所述检测目标存在时，基于所捕获的图像生成所述捕获图像中的所述检测目标的三维点云; 基于生成的三维点云获得检测对象的一个​​或多个当前姿态特征; 以及基于当前姿态特征和一个或多个预定姿势特征标准，确定是否存在异常情况，当检测目标执行多个异常动作时，基于一个或多个共同特征预先确定姿势特征标准。

公开(公告)号：US20120138972A1

公开(公告)日：2012-06-07

申请号：US13308752

申请日：2011-12-01

申请人： Wenbo LI ,  Gang WANG ,  Zhuo ZHANG

发明人： Wenbo LI ,  Gang WANG ,  Zhuo ZHANG

IPC分类号： H01L33/62

CPC分类号： H01L29/78633 ,  G02F1/136227 ,  H01L29/78666 ,  H01L29/7869

摘要： The present disclosure discloses a method for fabricating an array substrate comprising: depositing a source/drain metallic film on a first base substrate, and forming a source electrode, a drain electrode and a data line; sequentially depositing a semiconductor layer film, a gate insulating layer film and a gate metallic film on the first base substrate, and forming a semiconductor layer, a gate insulating layer, a gate electrode and a gate line; depositing a gate protection layer film on the first base substrate, and forming a gate protection layer and a through hole, wherein the through hole is formed on the gate protection layer corresponding to the drain electrode to expose a portion of the drain electrode; and depositing a pixel electrode film on the first base substrate, and forming a pixel electrode, wherein the pixel electrode is connected to the drain electrode via the through hole.

摘要翻译： 本公开公开了一种制造阵列基板的方法，包括：在第一基底基板上沉积源极/漏极金属膜，以及形成源电极，漏电极和数据线; 在第一基底基板上依次沉积半导体层膜，栅极绝缘层膜和栅极金属膜，以及形成半导体层，栅极绝缘层，栅电极和栅极线; 在所述第一基板上沉积栅极保护层膜，形成栅极保护层和通孔，其中所述通孔形成在与所述漏电极相对应的所述栅极保护层上以暴露所述漏极电极的一部分; 以及在所述第一基板上沉积像素电极膜，并且形成像素电极，其中所述像素电极经由所述通孔连接到所述漏电极。

公开(公告)号：US20150206004A1

公开(公告)日：2015-07-23

申请号：US14600402

申请日：2015-01-20

申请人： Lingyan LIANG ,  Gang WANG

发明人： Lingyan LIANG ,  Gang WANG

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/46

CPC分类号： G06T7/204 ,  G06K9/00355 ,  G06K9/6212 ,  G06T7/248 ,  G06T7/277 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/30196

摘要： Disclosed is an object tracking method comprising steps of obtaining a grayscale image sequence and a depth image sequence; predicting a candidate target region of a tracking object in a current image; determining a depth weight image of the candidate target region; acquiring a target template which is expressed by a probability density distribution of features; expressing, by a probability density distribution of features, a candidate target whose position moves in the candidate target region; calculating, based on a probability density expression of the target template and a probability density expression of the candidate target, a similarity between the target template and the candidate target, so as to get a confidence level image of the candidate target region; and locating, based on the confidence level image of the candidate target region, a position of the tracking object in the current image.

摘要翻译： 公开了一种物体跟踪方法，包括获得灰阶图像序列和深度图像序列的步骤; 预测当前图像中的跟踪对象的候选对象区域; 确定候选目标区域的深度权重图像; 获取由特征的概率密度分布表示的目标模板; 通过特征的概率密度分布来表达位置在候选目标区域中移动的候选目标; 基于目标模板的概率密度表达式和候选目标的概率密度表达式计算目标模板和候选目标之间的相似度，以获得候选目标区域的置信水平图像; 以及基于候选目标区域的置信度图像来定位跟踪对象在当前图像中的位置。

公开(公告)号：US20150169956A1

公开(公告)日：2015-06-18

申请号：US14568223

申请日：2014-12-12

申请人： Ganmei YOU ,  Yaojie LU ,  Zhongchao SHI ,  Chao CHEN ,  Gang WANG

发明人： Ganmei YOU ,  Yaojie LU ,  Zhongchao SHI ,  Chao CHEN ,  Gang WANG

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06K9/52

CPC分类号： G06K9/00624 ,  G06K9/00805 ,  G06K9/4604 ,  G06K9/52 ,  G06K9/6215 ,  G06T7/246 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/20068 ,  G06T2207/20076 ,  G06T2207/30252

摘要： Disclosed is an object tracking method. The method includes steps of obtaining a first boundary region of a waiting-for-recognition object in the disparity map related to the current frame; calculating a probability of each valid pixel in the first boundary region so as to get a pixel probability map of the waiting-for-recognition object; obtaining historic tracking data of each tracked object, which includes identifier information of the tracked object and a pixel probability map related to each of one or more prior frame related disparity maps prior to the disparity map related to the current frame; determining identifier information of the waiting-for-recognition object, and updating the pixel probability map of the waiting-for-recognition object; and updating, based on the updated pixel probability map of the waiting-for-recognition object, the first boundary region of the waiting-for-recognition object, so as to get a second boundary region of the waiting-for-recognition object.

摘要翻译： 公开了一种物体跟踪方法。 该方法包括以下步骤：获得与当前帧相关的视差图中等待识别对象的第一边界区域; 计算第一边界区域中的每个有效像素的概率，以获得等待识别对象的像素概率图; 获得每个跟踪对象的历史跟踪数据，其包括跟踪对象的标识符信息和与在与当前帧相关的视差图之前的一个或多个先前帧相关视差图中的每一个相关的像素概率图; 确定等待识别对象的标识符信息，以及更新等待识别对象的像素概率图; 以及基于等待识别对象的更新的像素概率图来更新等待识别对象的第一边界区域，以获得等待识别对象的第二边界区域。

公开(公告)号：US20100200856A1

公开(公告)日：2010-08-12

申请号：US12628878

申请日：2009-12-01

申请人： Wenjie HU ,  Zenghui SUN ,  Hongyu LIU ,  Gang WANG ,  Xibin SHAO

发明人： Wenjie HU ,  Zenghui SUN ,  Hongyu LIU ,  Gang WANG ,  Xibin SHAO

IPC分类号： H01L33/00 ,  H01L21/28

CPC分类号： H01L27/1288 ,  H01L21/28 ,  H01L27/1214 ,  H01L33/00

摘要： A method for manufacturing E-paper array substrate and an E-paper array substrate are provided. The method for manufacturing E-paper array substrate uses two masks. Steps on a surface of the array substrate structure are eliminated, so as to facilitate a subsequent coating process of E-ink and enable a uniform distribution of a drain electric field. An E-paper array substrate is further provided.

摘要翻译： 提供了一种用于制造电子纸阵列基板和电子纸阵列基板的方法。 电子纸阵列基板的制造方法使用两个掩模。 消除阵列基板结构表面上的步骤，以便于随后的电子墨水涂布工艺，并且能够均匀分布漏极电场。 还提供了一种电子纸阵列基板。

公开(公告)号：US20160019683A1

公开(公告)日：2016-01-21

申请号：US14797667

申请日：2015-07-13

申请人： Ganmei YOU ,  Yuan LIU ,  Zhongchao SHI ,  Yaojie LU ,  Gang WANG

发明人： Ganmei YOU ,  Yuan LIU ,  Zhongchao SHI ,  Yaojie LU ,  Gang WANG

IPC分类号： G06T7/00

CPC分类号： G06T7/74 ,  G06T2207/10021 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/30261

摘要： Disclosed is an object detection method used to detect an object in an image pair corresponding to a current frame. The image pair includes an original image of the current frame and a disparity map of the same current frame. The original image of the current frame includes at least one of a grayscale image and a color image of the current frame. The object detection method comprises steps of obtaining a first detection object detected in the disparity map of the current frame; acquiring an original detection object detected in the original image of the current frame; correcting, based on the original detection object, the first detection object so as to obtain a second detection object; and outputting the second detection object.

摘要翻译： 公开了一种用于检测对应于当前帧的图像对中的对象的对象检测方法。 图像对包括当前帧的原始图像和相同当前帧的视差图。 当前帧的原始图像包括灰度图像和当前帧的彩色图像中的至少一个。 对象检测方法包括以下步骤：获得在当前帧的视差图中检测到的第一检测对象; 获取在当前帧的原始图像中检测到的原始检测对象; 基于原始检测对象来校正第一检测对象，以获得第二检测对象; 并输出第二检测对象。

公开(公告)号：US20140205566A1

公开(公告)日：2014-07-24

申请号：US14086271

申请日：2013-11-21

申请人： Lv LIAO ,  Fumiaki YOKOKAWA ,  Gang WANG

发明人： Lv LIAO ,  Fumiaki YOKOKAWA ,  Gang WANG

IPC分类号： C07H19/20 ,  A61K45/06 ,  A61K31/7076

CPC分类号： C07H19/20 ,  A61K31/7076 ,  A61K45/06 ,  C07H19/16

摘要： A compound of Formula (I) is provided that has been shown to be useful for treating a disease caused by a viral infection: wherein R1, R2 and R3 are as defined herein.

摘要翻译： 提供式（I）的化合物，其已被证明可用于治疗由病毒感染引起的疾病：其中R1，R2和R3如本文所定义。