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

WO2011084279A3 ALGORITHMS FOR ESTIMATING PRECISE AND RELATIVE OBJECT DISTANCES IN A SCENE 审中-公开
标题翻译：评估场景中精度和相对对象距离的算法
公开(公告)号：WO2011084279A3
公开(公告)日：2011-09-29
申请号：PCT/US2010058711
申请日：2010-12-02
申请人： SONY ELECTRONICS INC , SONY CORP , WONG EARL , LI PINGSHAN , SUGIURA MAMORU , NAKAMURA MAIKIBI , KUSHIDA HIDENORI , MURAKAMI YOSHIHIRO , TRITEYAPRASERT SOROJ
发明人： WONG EARL , LI PINGSHAN , SUGIURA MAMORU , NAKAMURA MAIKIBI , KUSHIDA HIDENORI , MURAKAMI YOSHIHIRO , TRITEYAPRASERT SOROJ
IPC分类号： G06T15/10
CPC分类号： G06T7/571 , G06T2207/10016 , G06T2207/10148
摘要： A two picture matching curve information is able to be used to determine precise object distance or relative object distance in a scene. Acquiring two images with different blur information in addition to the curve information enables a device to determine distance information of objects in a scene. The distance information is able to be used in image processing including generating a depth map which is then able to be used in many imaging applications.
摘要翻译：可以使用两幅图像匹配曲线信息来确定场景中的精确物体距离或相对物体距离。除了曲线信息之外，获取具有不同模糊信息的两个图像使得设备能够确定场景中物体的距离信息。距离信息能够用于图像处理，包括生成深度图，然后能够在许多成像应用中使用。

2. 发明申请

WO2007100701A3 SYSTEM AND METHOD FOR PERFORMING WAVELET-BASED TEXTURE FEATURE EXTRACTION AND CLASSIFICATION 审中-公开
标题翻译：用于执行基于水印的纹理特征提取和分类的系统和方法
公开(公告)号：WO2007100701A3
公开(公告)日：2008-04-24
申请号：PCT/US2007004801
申请日：2007-02-23
申请人： SONY CORP , SONY ELECTRONICS INC , LI PINGSHAN
发明人： LI PINGSHAN
IPC分类号： G06K9/68
CPC分类号： G06K9/522 , G06F17/30262 , G06K9/525 , G06K9/527
摘要： A system and method are disclosed for performing wavelet-based local texture feature extraction and classification procedures. Image data is initially provided to include a query image and a series of test images. A feature detector calculates image parameters corresponding to the image data. The image parameters include mean absolute values, variance values, and texture angles. The feature detector utilizes the image parameters to calculate distance values that represent texture similarity characteristics between the query image and each of the test images. The feature detector then evaluates the distance values to determine one or more matching images from among the test images.
摘要翻译：公开了一种用于执行基于小波的局部纹理特征提取和分类程序的系统和方法。最初提供图像数据以包括查询图像和一系列测试图像。特征检测器计算与图像数据对应的图像参数。图像参数包括平均绝对值，方差值和纹理角度。特征检测器利用图像参数来计算表示查询图像和每个测试图像之间的纹理相似性特征的距离值。然后，特征检测器评估距离值以确定来自测试图像中的一个或多个匹配图像。

3. 发明申请

WO2007120558A3 IMAGE CLASSIFICATION BASED ON A MIXTURE OF ELLIPTICAL COLOR MODELS 审中-公开
标题翻译：基于ELLIPTICAL颜色混合模型的图像分类
公开(公告)号：WO2007120558A3
公开(公告)日：2008-04-03
申请号：PCT/US2007008446
申请日：2007-04-02
申请人： SONY CORP , SONY ELECTRONICS INC , LI PINGSHAN
发明人： LI PINGSHAN
IPC分类号： G06K9/00
CPC分类号： H04N1/628 , G06F17/3025 , G06K9/4652 , G06T7/90
摘要： A method of classifying images based on elliptical color models is utilized in a number of applications. One or more color models are generated from a set of images with a region of interest. Then, sets of images are utilized for training. One set of images has regions of interest, and the other set of images is without regions of interest. By utilizing the two sets of images, a maximum difference between the sets is achieved, so that a color model is most representative of the object desired. Then using the optimal color model, a collection of images are able to be searched, and images are retrieved based on the probability that the images contain the desired object.
摘要翻译：在许多应用中使用基于椭圆色模型的图像分类方法。从具有感兴趣区域的一组图像生成一个或多个颜色模型。然后，将图像组用于训练。一组图像具有感兴趣的区域，而另一组图像没有感兴趣的区域。通过利用两组图像，可以实现两组之间的最大差异，使得颜色模型最能代表所需的对象。然后使用最佳颜色模型，可以搜索图像集合，并且基于图像包含所需对象的概率来检索图像。

4. 发明申请

WO2011119267A3 BLUR FUNCTION MODELING FOR DEPTH OF FIELD RENDERING 审中-公开
标题翻译：用于现场渲染深度的BLUR功能建模
公开(公告)号：WO2011119267A3
公开(公告)日：2011-11-17
申请号：PCT/US2011024832
申请日：2011-02-15
申请人： SONY CORP , LI PINGSHAN , ALI GAZI
发明人： LI PINGSHAN , ALI GAZI
IPC分类号： G06T15/00 , G06T5/00 , H04N5/232
CPC分类号： G06T5/002 , G06T5/20 , G06T2207/20012 , G06T2207/20021 , H04N5/23229 , H04N5/2356 , H04N5/2621
摘要： A method and apparatus of depth of field rendering which simulates larger apertures for images captured at a smaller aperture. The depth of field rendering provides selective simulation of out-of-focus effects which are attainable with cameras having a larger aperture when capturing images at a smaller aperture. A blur function model is created based on the relationship between the blur change and the aperture change. This model is used to determine the blur difference which would arise between two images taken at two different apertures. Then the out-of-focus effect is generated by blurring the image in a rendering process based on the blur difference.
摘要翻译：深度场渲染的方法和设备，其模拟在较小孔径处拍摄的图像的较大孔径。景深渲染提供对离焦效果的选择性模拟，这是通过在较小光圈下拍摄图像时具有较大光圈的照相机可以实现的。基于模糊变化与光圈变化之间的关系创建模糊函数模型。该模型用于确定在两个不同孔径拍摄的两幅图像之间产生的模糊差异。然后通过基于模糊差异在渲染过程中模糊图像来产生离焦效果。

5. 发明专利

BRPI0902791A2 未知
公开(公告)号：BRPI0902791A2
公开(公告)日：2010-05-25
申请号：BRPI0902791
申请日：2009-08-28
申请人： SONY CORP , SONY ELECTRONICS INC
发明人： WONG EARL QUONG , NAKAMURA MAKIBI , KUSHIDA HIDENORI , TRITEYAPRASERT SOROJ , MURAKAMI YOSHIHIRO , LI PINGSHAN , SUGIURA MAMORU
IPC分类号： G03B3/00 , G06F19/00
摘要： A camera auto-focuses using computed blur differences between images of a three-dimensional scene. The camera computes the blur difference between two images of the scene acquired at two different picture numbers. The camera uses the computed blur difference to predict a third picture number, where the camera uses the third picture number to auto-focus a camera lens on the scene.

6. 发明专利

JP2010176128A Two-dimensional polynomial model for depth estimation based on two-picture matching 审中-公开
标题翻译：基于两图匹配的深度估计的二维多项式模型
公开(公告)号：JP2010176128A
公开(公告)日：2010-08-12
申请号：JP2010013551
申请日：2010-01-05
申请人： Sony Corp , Sony Electronics Inc , ソニーエレクトロニクスインク , ソニー株式会社
发明人： LI PINGSHAN , WONG EARL , TRITEYAPRASERT SOROJ
IPC分类号： G02B7/28 , G02B7/36 , G03B13/36 , G06T1/00 , H04N5/232
CPC分类号： H04N5/23212 , G02B7/38 , G02B27/0012 , G06T7/571
摘要： PROBLEM TO BE SOLVED: To provide a method and apparatus for depth estimation based on image capture, particularly on two-picture matching of a camera.
SOLUTION: An apparatus and method for electronically estimating focusing distance between a camera (still and/or video camera) and a subject. Images at different focal positions of a calibration target are collected with distances between subject positions. In one aspect, histogram matching is performed to reduce noise error. A focus matching model is then generated in response to detected blur differences between successive images of the calibration target. The focus matching model is preferably converted to a polynomial equation of a desired order to smooth out image collection noise. The focus matching model is stored for access during operation. In use, the distance to subject is estimated in response to capturing images, detecting blur differences between the images and entering the blur difference information into the matching model.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供一种基于图像捕获的深度估计的方法和装置，特别是在相机的双图像匹配上。解决方案：一种用于电子估计相机（静止和/或摄像机）与被摄体之间的对焦距离的装置和方法。在校准目标的不同焦点位置处的图像以被摄体位置之间的距离被收集。在一个方面，执行直方图匹配以减少噪声误差。然后响应于校准目标的连续图像之间的检测到的模糊差异而产生焦点匹配模型。焦点匹配模型优选地被转换为期望顺序的多项式方程，以平滑图像采集噪声。焦点匹配模型存储在操作期间进行访问。在使用中，响应于拍摄图像估计到被摄体的距离，检测图像之间的模糊差异并将模糊差异信息输入到匹配模型中。版权所有（C）2010，JPO＆INPIT

7. 发明公开

EP2005364A4 IMAGE CLASSIFICATION BASED ON A MIXTURE OF ELLIPTICAL COLOR MODELS 有权
标题翻译： ON COLOR椭圆模型基于图像的分类的共混物
公开(公告)号：EP2005364A4
公开(公告)日：2015-03-11
申请号：EP07774732
申请日：2007-04-02
申请人： SONY CORP , SONY ELECTRONICS INC
发明人： LI PINGSHAN
IPC分类号： G06K9/00 , G06F17/30 , G06K9/46 , G06T7/40 , H04N1/62
CPC分类号： H04N1/628 , G06F17/3025 , G06K9/4652 , G06T7/90
摘要： A method of classifying images based on elliptical color models is utilized in a number of applications. One or more color models are generated from a set of images with a region of interest. Then, sets of images are utilized for training. One set of images has regions of interest, and the other set of images is without regions of interest. By utilizing the two sets of images, a maximum difference between the sets is achieved, so that a color model is most representative of the object desired. Then using the optimal color model, a collection of images are able to be searched, and images are retrieved based on the probability that the images contain the desired object.

8. 发明公开

EP2494524A4 ALGORITHMS FOR ESTIMATING PRECISE AND RELATIVE OBJECT DISTANCES IN A SCENE 有权转让
标题翻译： ALGORITHMEN ZUR MESSUNG PRESZISER UND RELATIVER OBJEKTABSTNDE IN EINER SZENE
公开(公告)号：EP2494524A4
公开(公告)日：2017-02-22
申请号：EP10842442
申请日：2010-12-02
申请人： SONY ELECTRONICS INC , SONY CORP
发明人： WONG EARL , LI PINGSHAN , SUGIURA MAMORU , NAKAMURA MAKIBI , KUSHIDA HIDENORI , MURAKAMI YOSHIHIRO , TRITEYAPRASERT SOROJ
IPC分类号： G06T7/571
CPC分类号： G06T7/571 , G06T2207/10016 , G06T2207/10148

9. 发明公开

KR20180026506A 가우시안의 라플라시안 근사에 기초한 단일 이미지로부터의 디포커스 추정 审中-公开
标题翻译：基于高斯拉普拉斯近似估计单幅图像散焦
公开(公告)号：KR20180026506A
公开(公告)日：2018-03-12
申请号：KR20187003331
申请日：2016-08-05
申请人： SONY CORP
发明人： LI PINGSHAN , WEI JIANING
IPC分类号： G06K9/03 , G06K9/62 , G06T5/00
CPC分类号： G06K9/6215 , G06K9/036 , G06T5/00 , G06T5/003 , G06T5/50 , G06T2207/30168 , H04N5/23212
摘要： 디포커스추정알고리즘이본 명세서에기술된다. 디포커스추정알고리즘은단일이미지를이용한다. 가우시안의라플라시안근사는가우시안의차이를계산함으로써결정된다. 디포커스블러는가우시안의차이를사용하여두 이미지들간의블러차이를계산함으로써추정될수 있다.
摘要翻译：这里描述散焦估计算法。散焦估计算法使用单个图像。通过计算高斯差异来确定高斯的拉普拉斯逼近。可以通过使用高斯差异来计算两个图像之间的模糊差来估计散焦模糊。

10. 发明专利

BR102012030034A2 未知
公开(公告)号：BR102012030034A2
公开(公告)日：2013-11-12
申请号：BR102012030034
申请日：2012-11-26
申请人： SONY CORP
发明人： ALI GAZI , LI PINGSHAN , MATSUI AKIRA , MIZUKURA TAKAMI
IPC分类号： G06T7/60
摘要： A system and method for generating robust depth maps includes a depth estimator that creates a depth map pyramid structure that includes a plurality of depth map levels that each have different resolution characteristics. In one embodiment, the depth map levels include a fine-scale depth map, a medium-scale depth map, and a coarse scale depth map. The depth estimator evaluates depth values from the fine-scale depth map by utilizing fine-scale confidence features, and evaluates depth values from the medium-scale depth map and the coarse-scale depth map by utilizing coarse-scale confidence features. The depth estimator then fuses optimal depth values from the different depth map levels into an optimal depth map.

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