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

WO2007087405A3 CAPTURING SCENE IMAGES AND DEPTH GEOMETRY AND GENERATING A COMPENSATION IMAGE 审中-公开
标题翻译：捕获场景图像和深度几何并产生补偿图像
公开(公告)号：WO2007087405A3
公开(公告)日：2008-07-24
申请号：PCT/US2007002056
申请日：2007-01-24
申请人： UNIV COLUMBIA , NAYAR SHREE K , ZHANG LI
发明人： NAYAR SHREE K , ZHANG LI
IPC分类号： G06T15/50
CPC分类号： G06K9/2036 , G06K2209/401
摘要： In some embodiments, systems for capturing scene images and depth geometry are provided, comprising a projector, an optical sensor, and a digital processing device. The projector is capable of being defocused with respect to a scene and projects light having a shifting periodic illumination pattern on the scene. The optical sensor has a plurality of pixels and detects a portion of the radiance of at least one image of the scene at each of the pixels. The digital processing device is capable of being coupled to the optical sensor and obtains a temporal radiance profile from the radiance over a time period for each of the pixels, determines an amount of projection defocus at each of the of pixels using the temporal radiance profile, and, at each of the pixels, computes a depth to the scene at the pixel using the amount of projection defocus at the pixel.
摘要翻译：在一些实施例中，提供了用于捕获场景图像和深度几何的系统，包括投影仪，光学传感器和数字处理装置。投影机能够相对于场景散焦，并且投射在场景上具有移动的周期性照明图案的光。光学传感器具有多个像素并且检测每个像素处的场景的至少一个图像的一部分的辐射度。数字处理装置能够耦合到光学传感器并且从每个像素的时间周期的辐射中获得时间辐射轮廓，使用时间辐射轮廓确定每个像素处的投影散焦量，并且在每个像素处，使用像素处的投影散焦量来计算像素处的场景的深度。

2. 发明申请

WO2019027505A1 FACE DETECTION, POSE ESTIMATION, AND DISTANCE FROM A CAMERA ESTIMATION USING A SINGLE NETWORK 审中-公开
公开(公告)号：WO2019027505A1
公开(公告)日：2019-02-07
申请号：PCT/US2018/015592
申请日：2018-01-26
申请人： APPLE INC.
发明人： KUMAR, Atulit , FASEL, Ian R. , GERNOTH, Thorsten , GUO, Haitao , HAMSICI, Onur C.
IPC分类号： G06K9/00 , G06K9/20 , G06K9/62
CPC分类号： G06K9/00288 , G06K9/00221 , G06K9/00255 , G06K9/00302 , G06K9/2036 , G06K9/6273 , G06K2209/401 , G06T7/521
摘要： A single network encodes and decodes an image captured using a camera on a device. The single network detects if a face is in the image. If a face is detected in the image, the single network determines properties of the face in the image and outputs the properties along with the face detection output. Properties of the face may be determined by sharing the task for face detection. Properties of the face that are output along with the face detection output include the location of the face, the pose of the face, and/or the distance of the face from the camera.

3. 发明申请

WO2018226579A1 SCANNED BEAM DISPLAY WITH MULTIPLE DETECTOR RANGEFINDING 审中-公开
公开(公告)号：WO2018226579A1
公开(公告)日：2018-12-13
申请号：PCT/US2018/035842
申请日：2018-06-04
申请人： MICROVISION, INC.
发明人： XUE, Bin , VISWANATHAN, P. Selvan , JACKSON, Robert James , VALLIATH, George Thomas
IPC分类号： G01S7/486 , G01S7/481 , G01S17/10
CPC分类号： G01S7/4865 , G01S7/4808 , G01S7/4817 , G01S17/003 , G01S17/10 , G01S17/42 , G06K2209/401
摘要： A scanning display system includes two detectors (310, 320) for rangefinding. Round trip times-of-flight are measured for reflections of laser pulses received at the detectors. A proportional correction factor is determined based at least in part on the geometry of the scanning display system. The proportional correction factor is applied to the measured times-of-flight to create estimates of more accurate times-of-flight.

4. 发明申请

WO2016172856A1 用于识别人脸的装置、系统、方法和计算机程序产品审中-公开
公开(公告)号：WO2016172856A1
公开(公告)日：2016-11-03
申请号：PCT/CN2015/077692
申请日：2015-04-28
申请人：北京旷视科技有限公司 , 北京小孔科技有限公司
发明人：范浩强
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/00288 , G06K9/00255 , G06K9/00281 , G06K9/2027 , G06K9/2036 , G06K9/4661 , G06K2209/401 , H04N13/254
摘要：公开了一种用于识别人脸的装置、系统、方法和计算机程序产品，所述方法包括：对被测的人脸依次发射至少一组有结构的光线；采集所述人脸在依次经受所述至少一组有结构的光线中的每一组光线的照射时的有光源图像集；基于所述有光源图像集，提取由所述人脸的被测点集中的每个被测点的特征所组成的第一特征集；获取由人脸模板的测定点集中的每个测定点的特征所组成的第二特征集；基于所述第一特征集和所述第二特征集，计算所述人脸与所述人脸模板之间的相似度；以及如果所述相似度大于阈值，则将所述人脸识别为与所述人脸模板相一致。

5. 发明申请

WO2007087389A3 KEY DUPLICATION MACHINE 审中-公开
标题翻译：关键复印机
公开(公告)号：WO2007087389A3
公开(公告)日：2007-11-29
申请号：PCT/US2007002015
申请日：2007-01-23
申请人： HY KO PRODUCTS CO
发明人： BASS MICHAEL A , MUTCH WILLIAM R , RYAI RICHARD W SR , THOMPSON CHESTER O D , DRAKE ROBERT E , PORRAS RANDALL A
IPC分类号： B23C1/16
CPC分类号： B23C3/35 , B23B2270/32 , B23C2235/08 , B23C2235/12 , B23C2235/32 , B23C2235/41 , G06K9/20 , G06K9/2036 , G06K9/4661 , G06K9/48 , G06K2209/401 , Y10T409/300952 , Y10T409/301008 , Y10T409/303808
摘要： Apparatus, methods, and other embodiments associated with a key duplication machine are described. In one embodiment, an assembly for duplicating a master key includes an optical imaging device, a logic, a clamping assembly, and a cutting member. The optical imaging device is capable of capturing an optical image of at least a portion of the master key. The logic is capable of determining a key pattern of the master key from the optical image of the master key. The clamping assembly is capable of clamping a key blank and the cutting member is capable of cutting a key pattern into said key blank.
摘要翻译：描述与密钥复制机相关联的装置，方法和其他实施例。在一个实施例中，用于复制主密钥的组件包括光学成像设备，逻辑，夹紧组件和切割构件。光学成像装置能够捕获至少一部分主密钥的光学图像。该逻辑能够从主密钥的光学图像确定主密钥的关键图形。夹紧组件能够夹紧钥匙坯件，并且切割构件能够将钥匙图案切割到所述钥匙坯件中。

6. 发明申请

WO2007087405A2 SYSTEMS, METHODS, AND MEDIA FOR CAPTURING SCENE IMAGES AND DEPTH GEOMETRY AND GENERATING A COMPENSATION IMAGE 审中-公开
标题翻译：用于捕获场景图像和深度几何并产生补偿图像的系统，方法和媒体
公开(公告)号：WO2007087405A2
公开(公告)日：2007-08-02
申请号：PCT/US2007/002056
申请日：2007-01-24
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , NAYAR, Shree, K. , ZHANG, Li
发明人： NAYAR, Shree, K. , ZHANG, Li
IPC分类号： G06K9/40
CPC分类号： G06K9/2036 , G06K2209/401
摘要： In some embodiments, systems for capturing scene images and depth geometry are provided, comprising a projector, an optical sensor, and a digital processing device. The projector is capable of being defocused with respect to a scene and projects light having a shifting periodic illumination pattern on the scene. The optical sensor has a plurality of pixels and detects a portion of the radiance of at least one image of the scene at each of the pixels. The digital processing device is capable of being coupled to the optical sensor and obtains a temporal radiance profile from the radiance over a time period for each of the pixels, determines an amount of projection defocus at each of the of pixels using the temporal radiance profile, and, at each of the pixels, computes a depth to the scene at the pixel using the amount of projection defocus at the pixel.
摘要翻译：在一些实施例中，提供了用于捕获场景图像和深度几何的系统，包括投影仪，光学传感器和数字处理装置。该投影机能够相对于场景散焦，并投射场景上具有移动的周期性照明图案的光。光学传感器具有多个像素并且检测每个像素处的场景的至少一个图像的一部分的辐射度。数字处理装置能够耦合到光学传感器并且从每个像素的时间周期的辐射度获得时间辐射轮廓，使用时间辐射轮廓确定每个像素处的投影散焦量，并且在每个像素处，使用像素处的投影散焦量来计算像素处的场景的深度。

7. 发明申请

WO2007087389A2 KEY DUPLICATION MACHINE 审中-公开
标题翻译：关键多用机
公开(公告)号：WO2007087389A2
公开(公告)日：2007-08-02
申请号：PCT/US2007/002015
申请日：2007-01-23
申请人： HY-KO PRODUCTS COMPANY
发明人： BASS, Michael, A. , MUTCH, William, R. , RYAI, Richard, W., Sr. , THOMPSON, Chester, O. D. , DRAKE, Robert, E. , PORRAS, Randall, A.
IPC分类号： B23C1/16
CPC分类号： B23C3/35 , B23B2270/32 , B23C2235/08 , B23C2235/12 , B23C2235/32 , B23C2235/41 , G06K9/20 , G06K9/2036 , G06K9/4661 , G06K9/48 , G06K2209/401 , Y10T409/300952 , Y10T409/301008 , Y10T409/303808
摘要： Apparatus, methods, and other embodiments associated with a key duplication machine are described. In one embodiment, an assembly for duplicating a master key includes an optical imaging device, a logic, a clamping assembly, and a cutting member. The optical imaging device is capable of capturing an optical image of at least a portion of the master key. The logic is capable of determining a key pattern of the master key from the optical image of the master key. The clamping assembly is capable of clamping a key blank and the cutting member is capable of cutting a key pattern into said key blank.
摘要翻译：描述了与密钥复制机关联的设备，方法和其他实施例。在一个实施例中，用于复制主钥匙的组件包括光学成像装置，逻辑，夹持组件和切割构件。该光学成像设备能够捕捉主密钥的至少一部分的光学图像。该逻辑能够从主密钥的光学图像确定主密钥的密钥模式。夹持组件能够夹持钥匙坯，并且切割构件能够将钥匙图案切割成所述钥匙坯。

8. 发明申请

WO2016018550A1 OVERLAPPING PATTERN PROJECTOR 审中-公开
标题翻译：重叠图案投影机
公开(公告)号：WO2016018550A1
公开(公告)日：2016-02-04
申请号：PCT/US2015/038228
申请日：2015-06-29
申请人： APPLE INC.
发明人： MOR, Zafrir , MORGENSTEIN, Boris
IPC分类号： G01B11/25 , G02B27/09
CPC分类号： G02B27/4205 , F21V5/048 , F21Y2105/00 , F21Y2115/10 , F21Y2115/30 , G01B11/2513 , G02B27/1093 , G02B27/20 , G06K9/2036 , G06K2209/401 , G06T7/521 , H01S5/005 , H01S5/423
摘要： An optoelectronic device (30) includes a semiconductor substrate (132), an array (120) of optical emitters arranged on the substrate in a two-dimensional pattern, a projection lens (146) and a diffractive optical element (DOE - 144). The projection lens is mounted on the semiconductor substrate and is configured to collect and focus light emitted by the optical emitters so as to project optical beams containing a light pattern corresponding to the two- dimensional pattern of the optical emitters on the substrate. The DOE is mounted on the substrate and is configured to produce and project multiple overlapping replicas (152, 154, 156) of the pattern.
摘要翻译：光电子器件（30）包括半导体衬底（132），以二维图案布置在衬底上的光发射体的阵列（120），投影透镜（146）和衍射光学元件（DOE-144）。投影透镜安装在半导体基板上并且被配置为收集和聚焦由光发射器发射的光，以便将包含与光发射器的二维图案相对应的光图案的光束投射到基板上。 DOE安装在基板上并且被配置为产生并投影图案的多个重叠副本（152,154,156）。

9. 发明申请

WO2015197026A1 一种获取目标物体体征数据的方法、装置及终端审中-公开
公开(公告)号：WO2015197026A1
公开(公告)日：2015-12-30
申请号：PCT/CN2015/082539
申请日：2015-06-26
申请人：华为技术有限公司
发明人：唐卫东
IPC分类号： G06T19/00
CPC分类号： G06T7/0012 , G06K9/00208 , G06K9/00214 , G06K9/00369 , G06K9/2036 , G06K9/209 , G06K9/346 , G06K9/40 , G06K9/4661 , G06K9/4671 , G06K9/469 , G06K9/48 , G06K9/522 , G06K2209/401 , G06T7/13 , G06T7/62 , G06T19/00 , G06T2207/10028 , G06T2207/20072 , G06T2207/30196
摘要：本发明实施例提供一种获取目标物体体征数据的方法，包括：获取目标物体的3D深度图像；所述3D深度图像为带有距离信息的二维图像，所述距离信息包括所述目标物体到成像设备之间的距离；根据所述目标物体的3D深度图像中像素的深度值获取所述目标物体的图形轮廓和骨架参数；所述深度值为根据所述距离信息获取的所述目标物体上某一点到所述成像设备之间的距离；在3D模型库中检索与所述目标物体的图形轮廓及骨架参数相匹配的3D模型，获取所述3D模型的参数比例；获取所述目标物体的至少一个真实尺寸；根据所述3D模型的参数比例和所述的至少一个真实尺寸获取所述目标物体的体征数据。从而为广大用户实现"所见即所得"的体验。

10. 发明申请

WO2006074310A2 CREATING 3D IMAGES OF OBJECTS BY ILLUMINATING WITH INFRARED PATTERNS 审中-公开
标题翻译：通过与红外图案照相来创建物体的3D图像
公开(公告)号：WO2006074310A2
公开(公告)日：2006-07-13
申请号：PCT/US2006000345
申请日：2006-01-09
申请人： GESTURETEK INC , GU JIN
发明人： GU JIN
CPC分类号： G01B11/2513 , G01B11/25 , G01B11/2545 , G06K9/2018 , G06K9/2036 , G06K2209/401 , G06T7/521 , G06T7/55 , G06T2200/08 , H04N2013/0081
摘要： According to a general aspect, processing images includes projecting an infra-red pattern onto a 3D object and producing a first image, a second image, and a third image of the 3D object while the pattern is projected on the 3D object. The first image and the second image include the 3D object and the pattern. The first image and the second image are produced by capturing at a first camera and a second camera, respectively, light filtered through an infrared filter. The third image includes the 3D object but not the pattern. Processing the images also includes establishing a first-pair correspondence between a portion of pixels in the first image and a portion of pixels in the second image. Processing the images further includes constructing, based on the first-pair correspondence and the third image, a 2D image that depicts a 3D construction of the 3D object.
摘要翻译：根据一般方面，处理图像包括将红外图案投影到3D对象上，并且在图案投影到3D对象上时产生3D对象的第一图像，第二图像和第三图像。第一图像和第二图像包括3D对象和图案。第一图像和第二图像分别通过在第一相机和第二相机上捕获通过红外滤光器过滤的光而产生。第三个图像包括3D对象，但不包括模式。处理图像还包括建立第一图像中的一部分像素与第二图像中的像素部分之间的第一对对应关系。处理图像还包括基于第一对对应和第三图像构建描绘3D对象的3D构造的2D图像。

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