专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20120170804A1 Method and apparatus for tracking target object 有权
标题翻译：跟踪目标物体的方法和装置
公开(公告)号：US20120170804A1
公开(公告)日：2012-07-05
申请号：US13066515
申请日：2011-04-15
申请人： Shang-Yi Lin , Chia-Chen Chen , Wen-Shiou Luo
发明人： Shang-Yi Lin , Chia-Chen Chen , Wen-Shiou Luo
IPC分类号： G06K9/00
CPC分类号： G06T7/90 , G06T7/248 , G06T2207/10024 , G06T2207/20021 , G06T2207/30196
摘要： A method and apparatus for tracking a target object are provided. A plurality of images is received, and one of the images is selected as a current image. A specific color of the current image is extracted. And the current image is compared with a template image to search a target object in the current image. If the target object is not found in the current image, a previous image with the target object is searched in the images received before the current image. And the target object is searched in the current image according to an object feature of the previous image. The object feature and an object location are updated into a storage unit when the target object is found.
摘要翻译：提供了一种跟踪目标对象的方法和装置。接收多个图像，并且选择一个图像作为当前图像。提取当前图像的特定颜色。并将当前图像与模板图像进行比较，以搜索当前图像中的目标对象。如果当前图像中没有找到目标对象，则在当前图像之前接收的图像中搜索与目标对象的先前图像。并根据先前图像的对象特征在当前图像中搜索目标对象。当找到目标对象时，对象特征和对象位置被更新为存储单元。

2. 发明授权

US09030529B2 Depth image acquiring device, system and method 有权
标题翻译：深度图像采集装置，系统和方法
公开(公告)号：US09030529B2
公开(公告)日：2015-05-12
申请号：US13442886
申请日：2012-04-10
申请人： Chia-Chen Chen , Wen-Shiou Luo , Tung-Fa Liou , Yu-Tang Li , Chang-Sheng Chu , Shuang-Chao Chung
发明人： Chia-Chen Chen , Wen-Shiou Luo , Tung-Fa Liou , Yu-Tang Li , Chang-Sheng Chu , Shuang-Chao Chung
IPC分类号： H04N13/02 , G01B11/25 , H04N13/00
CPC分类号： G01B11/25 , G06T7/521 , G06T7/593 , H04N13/111 , H04N13/239 , H04N13/254
摘要： A depth image acquiring device is provided, which includes at least one projecting device and at least one image sensing device. The projecting device projects a projection pattern to an object. The image sensing device senses a real image. In addition, the projecting device also serves as a virtual image sensing device. The depth image acquiring device generates a disparity image by matching three sets of dual-images formed by two real images and one virtual image, and generates a depth image according to the disparity image. In addition, the depth image acquiring device also generates a depth image by matching two real images, or a virtual image and a real image without verification.
摘要翻译：提供一种深度图像获取装置，其包括至少一个投影装置和至少一个图像感测装置。投影装置将投影图案投射到物体。图像感测装置感测真实图像。此外，投影装置还用作虚像摄像装置。深度图像获取装置通过匹配由两个真实图像和一个虚拟图像形成的三组双重图像来生成视差图像，并且根据视差图像生成深度图像。此外，深度图像获取装置还通过匹配两个真实图像或虚拟图像和实际图像而不进行验证来生成深度图像。

3. 发明申请

US20120262553A1 DEPTH IMAGE ACQUIRING DEVICE, SYSTEM AND METHOD 有权
标题翻译：深度图像获取装置，系统和方法
公开(公告)号：US20120262553A1
公开(公告)日：2012-10-18
申请号：US13442886
申请日：2012-04-10
申请人： Chia-Chen Chen , Wen-Shiou Luo , Tung-Fa Liou , Yu-Tang Li , Chang-Sheng Chu , Shuang-Chao Chung
发明人： Chia-Chen Chen , Wen-Shiou Luo , Tung-Fa Liou , Yu-Tang Li , Chang-Sheng Chu , Shuang-Chao Chung
IPC分类号： H04N13/02
CPC分类号： G01B11/25 , G06T7/521 , G06T7/593 , H04N13/111 , H04N13/239 , H04N13/254
摘要： A depth image acquiring device is provided, which includes at least one projecting device and at least one image sensing device. The projecting device projects a projection pattern to an object. The image sensing device senses a real image. In addition, the projecting device also serves as a virtual image sensing device. The depth image acquiring device generates a disparity image by matching three sets of dual-images formed by two real images and one virtual image, and generates a depth image according to the disparity image. In addition, the depth image acquiring device also generates a depth image by matching two real images, or a virtual image and a real image without verification.
摘要翻译：提供一种深度图像获取装置，其包括至少一个投影装置和至少一个图像感测装置。投影装置将投影图案投射到物体。图像感测装置感测真实图像。此外，投影装置还用作虚像摄像装置。深度图像获取装置通过匹配由两个真实图像和一个虚拟图像形成的三组双重图像来生成视差图像，并且根据视差图像生成深度图像。此外，深度图像获取装置还通过匹配两个真实图像或虚拟图像和实际图像而不进行验证来生成深度图像。

4. 发明授权

US08269722B2 Gesture recognition system and method thereof 有权
标题翻译：手势识别系统及其方法
公开(公告)号：US08269722B2
公开(公告)日：2012-09-18
申请号：US12545340
申请日：2009-08-21
申请人： Jun-Mein Wu , Wen-Shiou Luo , Wei-Yih Ho , Chia-Chen Chen , Cheng-Yuan Tang
发明人： Jun-Mein Wu , Wen-Shiou Luo , Wei-Yih Ho , Chia-Chen Chen , Cheng-Yuan Tang
IPC分类号： G09G5/00 , G06K9/62 , G06K9/64
CPC分类号： G06K9/00375
摘要： A gesture recognition system includes an image pick-up device, a processor, an operation engine, an optimal template selection means, and a display terminal. The image pick-up device is for capturing an image containing a natural gesture. The processor is for finding out a skin edge of a skin part from the image, and then classifying the skin edge into multiple edge parts at different angles. The operation engine has multiple parallel operation units and multiple gesture template libraries of different angle classes. These parallel operation units respectively find out gesture templates most resembling the edge parts in the gesture template libraries of different angle classes. The optimal template selection means selects an optimal gesture template from the resembling gesture templates found out by the parallel operation units. The display terminal is for displaying an image of the optimal gesture template. Thereby, marker-less and real-time gesture recognition is achieved.
摘要翻译：手势识别系统包括图像拾取装置，处理器，操作引擎，最佳模板选择装置和显示终端。图像拾取装置用于捕获包含自然手势的图像。处理器用于从图像中发现皮肤部分的皮肤边缘，然后将皮肤边缘分成不同角度的多个边缘部分。操作引擎具有多个并行操作单元和多个不同角度类的多个手势模板库。这些并行操作单元分别找出最类似于不同角度类的手势模板库中的边缘部分的手势模板。最佳模板选择装置从由并行操作单元发现的类似手势模板中选择最佳手势模板。显示终端用于显示最佳手势模板的图像。从而实现无标记和实时手势识别。

5. 发明授权

US08442269B2 Method and apparatus for tracking target object 有权
标题翻译：跟踪目标物体的方法和装置
公开(公告)号：US08442269B2
公开(公告)日：2013-05-14
申请号：US13066515
申请日：2011-04-15
申请人： Shang-Yi Lin , Chia-Chen Chen , Wen-Shiou Luo
发明人： Shang-Yi Lin , Chia-Chen Chen , Wen-Shiou Luo
IPC分类号： G06K9/00
CPC分类号： G06T7/90 , G06T7/248 , G06T2207/10024 , G06T2207/20021 , G06T2207/30196
摘要： A method and apparatus for tracking a target object are provided. A plurality of images is received, and one of the images is selected as a current image. A specific color of the current image is extracted. And the current image is compared with a template image to search a target object in the current image. If the target object is not found in the current image, a previous image with the target object is searched in the images received before the current image. And the target object is searched in the current image according to an object feature of the previous image. The object feature and an object location are updated into a storage unit when the target object is found.
摘要翻译：提供了一种跟踪目标对象的方法和装置。接收多个图像，并且选择一个图像作为当前图像。提取当前图像的特定颜色。并将当前图像与模板图像进行比较，以搜索当前图像中的目标对象。如果当前图像中没有找到目标对象，则在当前图像之前接收的图像中搜索与目标对象的先前图像。并根据先前图像的对象特征在当前图像中搜索目标对象。当找到目标对象时，对象特征和对象位置被更新为存储单元。

6. 发明申请

US20100194679A1 GESTURE RECOGNITION SYSTEM AND METHOD THEREOF 有权
标题翻译：识别识别系统及其方法
公开(公告)号：US20100194679A1
公开(公告)日：2010-08-05
申请号：US12545340
申请日：2009-08-21
申请人： Jun Mein Wu , Wen Shiou Luo , Wei Yih Ho , Chia Chen Chen , Cheng Yuan Tang
发明人： Jun Mein Wu , Wen Shiou Luo , Wei Yih Ho , Chia Chen Chen , Cheng Yuan Tang
IPC分类号： G06K9/64 , G09G5/00 , G06T7/00
CPC分类号： G06K9/00375
摘要： A gesture recognition system includes an image pick-up device, a processor, an operation engine, an optimal template selection means, and a display terminal. The image pick-up device is for capturing an image containing a natural gesture. The processor is for finding out a skin edge of a skin part from the image, and then classifying the skin edge into multiple edge parts at different angles. The operation engine has multiple parallel operation units and multiple gesture template libraries of different angle classes. These parallel operation units respectively find out gesture templates most resembling the edge parts in the gesture template libraries of different angle classes. The optimal template selection means selects an optimal gesture template from the resembling gesture templates found out by the parallel operation units. The display terminal is for displaying an image of the optimal gesture template. Thereby, marker-less and real-time gesture recognition is achieved.
摘要翻译：手势识别系统包括图像拾取装置，处理器，操作引擎，最佳模板选择装置和显示终端。图像拾取装置用于捕获包含自然手势的图像。处理器用于从图像中发现皮肤部分的皮肤边缘，然后将皮肤边缘分成不同角度的多个边缘部分。操作引擎具有多个并行操作单元和多个不同角度类的多个手势模板库。这些并行操作单元分别找出最类似于不同角度类的手势模板库中的边缘部分的手势模板。最佳模板选择装置从由并行操作单元发现的类似手势模板中选择最佳手势模板。显示终端用于显示最佳手势模板的图像。从而实现无标记和实时手势识别。

7. 发明申请

US20110161061A1 COLLISION SIMULATION METHOD OF THREE DIMENSIONAL OBJECT 审中-公开
标题翻译：三维对象的碰撞模拟方法
公开(公告)号：US20110161061A1
公开(公告)日：2011-06-30
申请号：US12775479
申请日：2010-05-07
申请人： Jun-Mein Wu , Chia-Chen Chen , Wen-Shiou Luo
发明人： Jun-Mein Wu , Chia-Chen Chen , Wen-Shiou Luo
IPC分类号： G06F17/10
CPC分类号： G06T17/20 , G06T2210/21
摘要： A collision simulation method of a three dimensional (3D) object is provided, wherein the 3D object is composed of a plurality of polygonal meshes. First, a collision between the polygonal meshes and an object is detected. When one of the polygonal meshes is collided by the object, at least one virtual vertex is generated at a first position where the polygonal mesh is collided by the object, wherein the polygonal mesh includes a plurality of vertexes. Then, the virtual vertex is connected to the vertexes to form a plurality of sub meshes. Next, a force between the object and the virtual vertex is calculated to update the first position of the virtual vertex into a second position. After that, forces between the virtual vertex and the vertexes are calculated according to the second position of the virtual vertex so as to update the positions of the vertexes.
摘要翻译：提供了三维（3D）对象的碰撞模拟方法，其中3D对象由多个多边形网格组成。首先，检测多边形网格和对象之间的碰撞。当所述多边形网格中的一个被所述对象冲突时，在所述多边形网格与所述对象相冲突的第一位置处生成至少一个虚拟顶点，其中所述多边形网格包括多个顶点。然后，虚拟顶点连接到顶点以形成多个子网格。接下来，计算对象和虚拟顶点之间的力，以将虚拟顶点的第一位置更新为第二位置。之后，根据虚拟顶点的第二位置计算虚拟顶点和顶点之间的力，以便更新顶点的位置。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式