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

US20100173269A1 FOOD RECOGNITION USING VISUAL ANALYSIS AND SPEECH RECOGNITION 有权
标题翻译：食品识别使用视觉分析和语音识别
公开(公告)号：US20100173269A1
公开(公告)日：2010-07-08
申请号：US12683124
申请日：2010-01-06
申请人： Manika Puri , Zhiwei Zhu , Jeffrey Lubin , Tom Pschar , Ajay Divakaran , Harpreet S. Sawhney
发明人： Manika Puri , Zhiwei Zhu , Jeffrey Lubin , Tom Pschar , Ajay Divakaran , Harpreet S. Sawhney
IPC分类号： G09B19/00
CPC分类号： G09B19/0092
摘要： A method and system for analyzing at least one food item on a food plate is disclosed. A plurality of images of the food plate is received by an image capturing device. A description of the at least one food item on the food plate is received by a recognition device. The description is at least one of a voice description and a text description. At least one processor extracts a list of food items from the description; classifies and segments the at least one food item from the list using color and texture features derived from the plurality of images; and estimates the volume of the classified and segmented at least one food item. The processor is also configured to estimate the caloric content of the at least one food item.
摘要翻译：公开了一种用于分析食品板上的至少一种食品的方法和系统。食品牌的多个图像由图像捕获装置接收。对食品牌上的至少一种食品的描述由识别装置接收。描述是语音描述和文本描述中的至少一个。至少一个处理器从描述中提取食物列表; 使用从多个图像导出的颜色和纹理特征来对列表中的至少一个食物项进行分类和分割; 并估计分类和分段的至少一种食品的体积。处理器还被配置为估计至少一个食物的热量含量。

2. 发明授权

US08439683B2 Food recognition using visual analysis and speech recognition 有权
标题翻译：食物识别使用视觉分析和语音识别
公开(公告)号：US08439683B2
公开(公告)日：2013-05-14
申请号：US12683124
申请日：2010-01-06
申请人： Manika Puri , Zhiwei Zhu , Jeffrey Lubin , Tom Pschar , Ajay Divakaran , Harpreet S. Sawhney
发明人： Manika Puri , Zhiwei Zhu , Jeffrey Lubin , Tom Pschar , Ajay Divakaran , Harpreet S. Sawhney
IPC分类号： G09B19/00
CPC分类号： G09B19/0092
摘要： A method and system for analyzing at least one food item on a food plate is disclosed. A plurality of images of the food plate is received by an image capturing device. A description of the at least one food item on the food plate is received by a recognition device. The description is at least one of a voice description and a text description. At least one processor extracts a list of food items from the description; classifies and segments the at least one food item from the list using color and texture features derived from the plurality of images; and estimates the volume of the classified and segmented at least one food item. The processor is also configured to estimate the caloric content of the at least one food item.
摘要翻译：公开了一种用于分析食品板上的至少一种食品的方法和系统。食品牌的多个图像由图像捕获装置接收。对食品牌上的至少一种食品的描述由识别装置接收。描述是语音描述和文本描述中的至少一个。至少一个处理器从描述中提取食物列表; 使用从多个图像导出的颜色和纹理特征来对列表中的至少一个食物项进行分类和分割; 并估计分类和分段的至少一种食品的体积。处理器还被配置为估计至少一个食物的热量含量。

3. 发明授权

US09600067B2 System and method for generating a mixed reality environment 有权
公开(公告)号：US09600067B2
公开(公告)日：2017-03-21
申请号：US12606581
申请日：2009-10-27
申请人： Rakesh Kumar , Targay Oskiper , Oleg Naroditsky , Supun Samarasekera , Zhiwei Zhu , Janet Kim
发明人： Rakesh Kumar , Targay Oskiper , Oleg Naroditsky , Supun Samarasekera , Zhiwei Zhu , Janet Kim
IPC分类号： G09G5/00 , G06F3/01
CPC分类号： G06T19/006 , G06F3/012 , G06F3/0346
摘要： A system and method for generating a mixed-reality environment is provided. The system and method provides a user-worn sub-system communicatively connected to a synthetic object computer module. The user-worn sub-system may utilize a plurality of user-worn sensors to capture and process data regarding a user's pose and location. The synthetic object computer module may generate and provide to the user-worn sub-system synthetic objects based information defining a user's real world life scene or environment indicating a user's pose and location. The synthetic objects may then be rendered on a user-worn display, thereby inserting the synthetic objects into a user's field of view. Rendering the synthetic objects on the user-worn display creates the virtual effect for the user that the synthetic objects are present in the real world.

4. 发明授权

US07925049B2 Stereo-based visual odometry method and system 有权
标题翻译：立体视觉测距法和系统
公开(公告)号：US07925049B2
公开(公告)日：2011-04-12
申请号：US11833498
申请日：2007-08-03
申请人： Zhiwei Zhu , Taragay Oskiper , Oleg Naroditsky , Supun Samarasekera , Harpreet Singh Sawhney , Rakesh Kumar
发明人： Zhiwei Zhu , Taragay Oskiper , Oleg Naroditsky , Supun Samarasekera , Harpreet Singh Sawhney , Rakesh Kumar
IPC分类号： G06F9/00
CPC分类号： G06K9/32 , G06K2209/40 , G06T7/248 , G06T7/593 , G06T7/74 , G06T2207/10021 , G06T2207/20164 , G06T2207/30212 , G06T2207/30252
摘要： A method for estimating pose from a sequence of images, which includes the steps of detecting at least three feature points in both the left image and right image of a first pair of stereo images at a first point in time; matching the at least three feature points in the left image to the at least three feature points in the right image to obtain at least three two-dimensional feature correspondences; calculating the three-dimensional coordinates of the at least three two-dimensional feature correspondences to obtain at least three three-dimensional reference feature points; tracking the at least three feature points in one of the left image and right image of a second pair of stereo images at a second point in time different from the first point in time to obtain at least three two-dimensional reference feature points; and calculating a pose based on the at least three three-dimensional reference feature points and its corresponding two-dimensional reference feature points in the stereo images. The pose is found by minimizing projection residuals of a set of three-dimensional reference feature points in an image plane.
摘要翻译：一种用于从图像序列估计姿态的方法，其包括以下步骤：在第一时间点检测第一对立体图像的左图像和右图像中的至少三个特征点; 将左图像中的至少三个特征点与右图像中的至少三个特征点匹配以获得至少三个二维特征对应; 计算所述至少三个二维特征对应的三维坐标以获得至少三个三维参考特征点; 在与第一时间点不同的第二时间点跟踪第二对立体图像的左图像和右图像之一中的至少三个特征点，以获得至少三个二维参考特征点; 以及基于立体图像中的至少三个三维参考特征点及其对应的二维参考特征点来计算姿势。通过使图像平面中的一组三维参考特征点的投影残差最小化来发现该姿势。

5. 发明申请

US20080167814A1 UNIFIED FRAMEWORK FOR PRECISE VISION-AIDED NAVIGATION 有权
标题翻译：用于精准视觉辅助导航的统一框架
公开(公告)号：US20080167814A1
公开(公告)日：2008-07-10
申请号：US11949433
申请日：2007-12-03
申请人： Supun Samarasekera , Rakesh Kumar , Taragay Oskiper , Zhiwei Zhu , Oleg Naroditsky , Harpreet Sawhney
发明人： Supun Samarasekera , Rakesh Kumar , Taragay Oskiper , Zhiwei Zhu , Oleg Naroditsky , Harpreet Sawhney
IPC分类号： G01C21/00
CPC分类号： G06K9/00791 , B60R1/00 , G01C21/005 , G01C21/165 , G06K9/3216 , G06K9/4642 , G06K9/52 , G06K9/6215 , G06T7/74 , H04N13/239 , H04N2013/0081
摘要： A system and method for efficiently locating in 3D an object of interest in a target scene using video information captured by a plurality of cameras. The system and method provide for multi-camera visual odometry wherein pose estimates are generated for each camera by all of the cameras in the multi-camera configuration. Furthermore, the system and method can locate and identify salient landmarks in the target scene using any of the cameras in the multi-camera configuration and compare the identified landmark against a database of previously identified landmarks. In addition, the system and method provide for the integration of video-based pose estimations with position measurement data captured by one or more secondary measurement sensors, such as, for example, Inertial Measurement Units (IMUs) and Global Positioning System (GPS) units.
摘要翻译：一种用于使用由多个摄像机捕获的视频信息有效地定位目标场景中的感兴趣对象的系统和方法。该系统和方法提供多摄像机视觉测距，其中由多摄像机配置中的所有摄像机为每个摄像机生成姿态估计。此外，系统和方法可以使用多摄像机配置中的任何摄像机来定位和识别目标场景中的突出地标，并将识别的地标与先前识别的地标的数据库进行比较。另外，该系统和方法提供了基于视频的姿势估计与由一个或多个二次测量传感器捕获的位置测量数据的集成，例如惯性测量单元（IMU）和全球定位系统（GPS）单元。

6. 发明申请

US20080144925A1 Stereo-Based Visual Odometry Method and System 有权
标题翻译：立体声视觉测距法和系统
公开(公告)号：US20080144925A1
公开(公告)日：2008-06-19
申请号：US11833498
申请日：2007-08-03
申请人： Zhiwei Zhu , Taragay Oskiper , Oleg Naroditsky , Supun Samarasekera , Harpreet Singh Sawhney , Rakesh Kumar
发明人： Zhiwei Zhu , Taragay Oskiper , Oleg Naroditsky , Supun Samarasekera , Harpreet Singh Sawhney , Rakesh Kumar
IPC分类号： G06K9/00
CPC分类号： G06K9/32 , G06K2209/40 , G06T7/248 , G06T7/593 , G06T7/74 , G06T2207/10021 , G06T2207/20164 , G06T2207/30212 , G06T2207/30252
摘要： A method for estimating pose from a sequence of images, which includes the steps of detecting at least three feature points in both the left image and right image of a first pair of stereo images at a first point in time; matching the at least three feature points in the left image to the at least three feature points in the right image to obtain at least three two-dimensional feature correspondences; calculating the three-dimensional coordinates of the at least three two-dimensional feature correspondences to obtain at least three three-dimensional reference feature points; tracking the at least three feature points in one of the left image and right image of a second pair of stereo images at a second point in time different from the first point in time to obtain at least three two-dimensional reference feature points; and calculating a pose based on the at least three three-dimensional reference feature points and its corresponding two-dimensional reference feature points in the stereo images. The pose is found by minimizing projection residuals of a set of three-dimensional reference feature points in an image plane.
摘要翻译：一种用于从图像序列估计姿态的方法，其包括以下步骤：在第一时间点检测第一对立体图像的左图像和右图像中的至少三个特征点; 将左图像中的至少三个特征点与右图像中的至少三个特征点匹配以获得至少三个二维特征对应; 计算所述至少三个二维特征对应的三维坐标以获得至少三个三维参考特征点; 在与第一时间点不同的第二时间点跟踪第二对立体图像的左图像和右图像之一中的至少三个特征点，以获得至少三个二维参考特征点; 以及基于立体图像中的至少三个三维参考特征点及其对应的二维参考特征点来计算姿势。通过使图像平面中的一组三维参考特征点的投影残差最小化来发现该姿势。

7. 发明授权

US09121713B2 Unified framework for precise vision-aided navigation 有权
标题翻译：精准视觉辅助导航的统一框架
公开(公告)号：US09121713B2
公开(公告)日：2015-09-01
申请号：US13451037
申请日：2012-04-19
申请人： Supun Samarasekera , Rakesh Kumar , Taragay Oskiper , Zhiwei Zhu , Oleg Naroditsky , Harpreet Sawhney
发明人： Supun Samarasekera , Rakesh Kumar , Taragay Oskiper , Zhiwei Zhu , Oleg Naroditsky , Harpreet Sawhney
IPC分类号： H04N7/18 , G01C21/16 , G01C21/00 , G06K9/32 , G06T7/00
CPC分类号： G06K9/00791 , B60R1/00 , G01C21/005 , G01C21/165 , G06K9/3216 , G06K9/4642 , G06K9/52 , G06K9/6215 , G06T7/74 , H04N13/239 , H04N2013/0081
摘要： A system and method for efficiently locating in 3D an object of interest in a target scene using video information captured by a plurality of cameras. The system and method provide for multi-camera visual odometry wherein pose estimates are generated for each camera by all of the cameras in the multi-camera configuration. Furthermore, the system and method can locate and identify salient landmarks in the target scene using any of the cameras in the multi-camera configuration and compare the identified landmark against a database of previously identified landmarks. In addition, the system and method provide for the integration of video-based pose estimations with position measurement data captured by one or more secondary measurement sensors, such as, for example, Inertial Measurement Units (IMUs) and Global Positioning System (GPS) units.
摘要翻译：一种用于使用由多个摄像机捕获的视频信息有效地定位目标场景中的感兴趣对象的系统和方法。该系统和方法提供多摄像机视觉测距，其中由多摄像机配置中的所有摄像机为每个摄像机生成姿态估计。此外，系统和方法可以使用多摄像机配置中的任何摄像机来定位和识别目标场景中的突出地标，并将识别的地标与先前识别的地标的数据库进行比较。另外，该系统和方法提供了基于视频的姿势估计与由一个或多个二次测量传感器捕获的位置测量数据的集成，例如惯性测量单元（IMU）和全球定位系统（GPS）单元。

8. 发明授权

US08697529B2 Schottky junction source/drain transistor and method of making 失效
标题翻译：肖特基结源极/漏极晶体管及其制造方法
公开(公告)号：US08697529B2
公开(公告)日：2014-04-15
申请号：US13508731
申请日：2011-09-28
申请人： Dongping Wu , Jun Luo , Yinghua Piao , Zhiwei Zhu , Shili Zhang , Wei Zhang
发明人： Dongping Wu , Jun Luo , Yinghua Piao , Zhiwei Zhu , Shili Zhang , Wei Zhang
IPC分类号： H01L21/336 , H01L21/338
CPC分类号： H01L29/7839 , H01L29/6653 , H01L29/66848
摘要： A method of making a transistor, comprising: providing a semiconductor substrate; forming a gate stack over the semiconductor substrate; forming an insulating layer over the semiconductor substrate; forming a depleting layer over the insulating layer; etching the depleting layer and the insulating layer; forming a metal layer over the semiconductor substrate; performing thermal annealing; and removing the metal layer. As advantages of the present invention, an upper outside part of each of the sidewalls include a material that can react with the metal layer, so that metal on two sides of the sidewalls is absorbed during the annealing process, preventing the metal from diffusing toward the semiconductor layer, and ensuring that the formed Schottky junctions can be ultra-thin and uniform, and have controllable and suppressed lateral growth.
摘要翻译：一种制造晶体管的方法，包括：提供半导体衬底; 在所述半导体衬底上形成栅叠层; 在半导体衬底上形成绝缘层; 在绝缘层上形成耗尽层; 蚀刻耗尽层和绝缘层; 在所述半导体衬底上形成金属层; 进行热退火; 并去除金属层。作为本发明的优点，每个侧壁的上部外侧部分包括能够与金属层反应的材料，从而在退火过程中吸收侧壁两侧的金属，从而防止金属朝向半导体层，并且确保形成的肖特基结可以是超薄和均匀的，并且具有可控和抑制的横向生长。

9. 发明申请

US20140048875A1 Asymmetrical Gate MOS Device and Method of Making 有权
标题翻译：非对称门MOS器件及制作方法
公开(公告)号：US20140048875A1
公开(公告)日：2014-02-20
申请号：US14113705
申请日：2011-12-28
申请人： Dongping Wu , Cheng Hu , Lun Zhu , Zhiwei Zhu , Shili Zhang , Wei Zhang
发明人： Dongping Wu , Cheng Hu , Lun Zhu , Zhiwei Zhu , Shili Zhang , Wei Zhang
IPC分类号： H01L29/66 , H01L29/78
CPC分类号： H01L21/28008 , H01L21/26586 , H01L21/28097 , H01L21/28105 , H01L21/2815 , H01L21/28518 , H01L29/04 , H01L29/4975 , H01L29/66575 , H01L29/6659 , H01L29/66659 , H01L29/7835
摘要： An asymetric gate MOS device is disclosed. The gate is a metal gate, and the metal gate has a different work function on the source side from that on the drain side of the MOS device, so that the overall performance parameters of the MOS device are more optimized. A method of making an asymetric gate MOS device is also disclosed. In the method, dopant ions are implanted into the gate of the MOS device, so as to cause the gate to have a different work function on the source side from that on the drain side of the MOS device. As a result, the overall performance parameters of the MOS device are more optimized. The method can be easily implemented.
摘要翻译：公开了一种非对称门MOS器件。栅极是金属栅极，金属栅极在源极侧与MOS器件的漏极侧具有不同的功函，使得MOS器件的整体性能参数更加优化。还公开了制造不对称栅极MOS器件的方法。在该方法中，将掺杂剂离子注入到MOS器件的栅极中，以使栅极在源极侧与MOS器件的漏极侧上具有不同的功函数。结果，MOS器件的整体性能参数更加优化。该方法可以很容易地实现。

10. 发明申请

US20140034955A1 Nano-MOS Devices and Method of Making 审中-公开
标题翻译：纳米MOS器件及其制造方法
公开(公告)号：US20140034955A1
公开(公告)日：2014-02-06
申请号：US13519315
申请日：2011-10-31
申请人： Dongping Wu , Cheng Hu , Luo Zhu , Zhiwei Zhu , Shili Zhang , Wei Zhang
发明人： Dongping Wu , Cheng Hu , Luo Zhu , Zhiwei Zhu , Shili Zhang , Wei Zhang
IPC分类号： H01L21/285 , H01L29/04 , H01L29/423 , H01L29/66 , H01L29/78 , H01L29/41
CPC分类号： H01L21/28518 , H01L21/28097 , H01L21/2815 , H01L21/28255 , H01L21/28264 , H01L21/32053 , H01L29/04 , H01L29/413 , H01L29/41758 , H01L29/42376 , H01L29/4238 , H01L29/4975 , H01L29/66477 , H01L29/66575 , H01L29/78
摘要： The present invention discloses a method of making nano-MOS devices having a metal gate, thereby avoiding the poly depletion effect, and enhancing the MOS device's performance. The method forms metal gates by depositing a metal film over sidewall surfaces on two sides of a polycrystalline semiconductor layer. The metal in the metal film diffuses toward the sidewall surfaces of the polycrystalline semiconductor layer and forms, after annealing, metal-semiconductor compound nanowires (i.e., metal gates) on the sidewall surfaces of the polycrystalline semiconductor layer. Thus, high-resolution lithography is not required to form metal compound semiconductor nanowires, resulting in significant cost saving. At the same time, a nano-MOS device is also disclosed, which includes a metal gate, thereby avoiding the poly depletion effect, and resulting in enhanced MOS device performance.
摘要翻译：本发明公开了一种制造具有金属栅极的纳米MOS器件的方法，从而避免多晶硅耗尽效应，并提高MOS器件的性能。该方法通过在多晶半导体层的两侧上的侧壁表面上沉积金属膜来形成金属栅极。金属膜中的金属向多晶半导体层的侧壁表面扩散，并且在多晶半导体层的侧壁表面上退火后形成金属 - 半导体化合物纳米线（即，金属栅极）。因此，不需要高分辨率光刻来形成金属化合物半导体纳米线，导致显着的成本节省。同时，还公开了一种纳米MOS器件，其包括金属栅极，从而避免多晶硅耗尽效应，并且导致增强的MOS器件性能。

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