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

WO2012142483A1 ROBUST FEATURE MATCHING FOR VISUAL SEARCH 审中-公开
标题翻译：强大的功能匹配视觉搜索
公开(公告)号：WO2012142483A1
公开(公告)日：2012-10-18
申请号：PCT/US2012/033620
申请日：2012-04-13
申请人： QUALCOMM Incorporated , VADDADI, Sundeep , HAMSICI, Onur C. , REZNIK, Yuriy , HONG, John H. , LEE, Chong U.
发明人： VADDADI, Sundeep , HAMSICI, Onur C. , REZNIK, Yuriy , HONG, John H. , LEE, Chong U.
IPC分类号： G06F17/30 , G06K9/62
CPC分类号： G06F17/30247 , G06K9/62 , G06K9/627
摘要： Techniques are disclosed for performing robust feature matching for visual search. An apparatus comprising an interface and a feature matching unit may implement these techniques. The interface receives a query feature descriptor. The feature matching unit then computes a distance between a query feature descriptor and reference feature descriptors and determines a first group of the computed distances and a second group of the computed distances in accordance with a clustering algorithm, where this second group of computed distances comprises two or more of the computed distances. The feature matching unit then determines whether the query feature descriptor matches one of the reference feature descriptors associated with a smallest one of the computed distances based on the determined first group and second group of the computed distances.
摘要翻译：公开了用于执行用于视觉搜索的鲁棒特征匹配的技术。包括接口和特征匹配单元的装置可以实现这些技术。接口接收查询特征描述符。特征匹配单元然后计算查询特征描述符和参考特征描述符之间的距离，并且根据聚类算法确定计算出的距离的第一组和所计算的距离的第二组，其中该第二组计算距离包括两个或更多的计算距离。特征匹配单元然后基于所确定的计算出的距离的第一组和第二组来确定查询特征描述符是否与与计算出的距离中的最小一个相关联的参考特征描述符之一匹配。

2. 发明申请

WO2010141899A3 4X4 TRANSFORM FOR MEDIA CODING 审中-公开
标题翻译： 4X4变换媒体编码
公开(公告)号：WO2010141899A3
公开(公告)日：2012-05-18
申请号：PCT/US2010037513
申请日：2010-06-04
申请人： QUALCOMM INC , REZNIK YURIY
发明人： REZNIK YURIY
IPC分类号： G06F17/14 , H04N7/26
CPC分类号： H04N19/625 , G06F17/147 , H04N19/124 , H04N19/42 , H04N19/45 , H04N19/51 , H04N19/61 , H04N19/91
摘要： In general, techniques are described that provide for 4x4 transforms for media coding. A number of different 4x4 transforms are described that adhere to these techniques. As one example, an apparatus includes a 4x4 discrete cosine transform (DCT) hardware unit. The DCT hardware unit implements an orthogonal 4x4 DCT having an odd portion that applies first and second internal factors (C, S) that are related to a scaled factor (?) such that the scaled factor equals a square root of a sum of a square of the first internal factor (C) plus a square of the second internal factor (S). The 4x4 DCT hardware unit applies the 4x4 DCT implementation to media data to transform the media data from a spatial domain to a frequency domain. As another example, an apparatus implements a non-orthogonal 4x4 DCT to improve coding gain.
摘要翻译：一般而言，描述了为媒体编码提供4×4变换的技术。描述了许多不同的4x4变换符合这些技术。作为一个例子，装置包括4×4离散余弦变换（DCT）硬件单元。 DCT硬件单元实现具有奇数部分的正交4×4DCT，所述奇数部分应用与缩放因子（α）有关的第一和第二内部因子（C，S），使得缩放因子等于平方和第一个内部因素（C）加上第二个内部因素（S）的平方。 4x4 DCT硬件单元将4x4 DCT实现应用于媒体数据，以将媒体数据从空间域转换到频域。作为另一个例子，装置实现非正交的4×4DCT以改善编码增益。

3. 发明申请

WO2012016168A2 OBJECT RECOGNITION USING INCREMENTAL FEATURE EXTRACTION 审中-公开
标题翻译：使用增量特征提取的对象识别
公开(公告)号：WO2012016168A2
公开(公告)日：2012-02-02
申请号：PCT/US2011045942
申请日：2011-07-29
申请人： QUALCOMM INC , BAHETI PAWAN KUMAR , VADDADI SUNDEEP , SWAMINATHAN ASHWIN , REZNIK YURIY , HAMSICI ONUR C , CHARI MURALI RAMASWAMY , HONG JOHN H , LEE CHONG UK
发明人： BAHETI PAWAN KUMAR , VADDADI SUNDEEP , SWAMINATHAN ASHWIN , REZNIK YURIY , HAMSICI ONUR C , CHARI MURALI RAMASWAMY , HONG JOHN H , LEE CHONG UK
IPC分类号： G06K9/46
CPC分类号： G06K9/6857 , G06K9/4671
摘要： In one example, an apparatus includes a processor configured to extract a first set of one or more keypoints from a first set of blurred images of a first octave of a received image, calculate a first set of one or more descriptors for the first set of keypoints, receive a confidence value for a result produced by querying a feature descriptor database with the first set of descriptors, wherein the result comprises information describing an identity of an object in the received image, and extract a second set of one or more keypoints from a second set of blurred images of a second octave of the received image when the confidence value does not exceed a confidence threshold. In this manner, the processor may perform incremental feature descriptor extraction, which may improve computational efficiency of object recognition in digital images.
摘要翻译：在一个示例中，一种装置包括处理器，该处理器被配置为从接收到的图像的第一八度的第一组模糊图像中提取第一组一个或多个关键点，计算第一组的一个或多个描述符接收关于通过用第一组描述符查询特征描述符数据库产生的结果的置信度值，其中所述结果包括描述所接收的图像中的对象的身份的信息，并且从第二组关键点提取一个或多个关键点当置信度值不超过置信度阈值时，所接收图像的第二八度音阶的第二组模糊图像。以这种方式，处理器可以执行递增特征描述符提取，这可以提高数字图像中对象识别的计算效率。

4. 发明申请

WO2012009237A1 VARIABLE LOCALIZED BIT DEPTH INCREASE FOR FIXED-POINT TRANSFORMS IN VIDEO CODING 审中-公开
标题翻译：视频编码中固定点变换的可变本地化位深度增加
公开(公告)号：WO2012009237A1
公开(公告)日：2012-01-19
申请号：PCT/US2011/043462
申请日：2011-07-08
申请人： QUALCOMM INCORPORATED , JOSHI, Rajan, L. , CHIEN, Wei-Jung , KARCZEWICZ, Marta , REZNIK, Yuriy , CHEN, Peisong , CHUANG, Hsiao-Chiang
发明人： JOSHI, Rajan, L. , CHIEN, Wei-Jung , KARCZEWICZ, Marta , REZNIK, Yuriy , CHEN, Peisong , CHUANG, Hsiao-Chiang
IPC分类号： H04N7/26 , H04N7/30 , H04N7/50
CPC分类号： H04N19/42 , H04N19/122 , H04N19/157 , H04N19/176 , H04N19/184 , H04N19/196 , H04N19/46 , H04N19/60 , H04N19/61
摘要： This disclosure describes techniques for mitigating rounding errors in a fixed- point transform associated with video coding by applying a variable localized bit-depth increase at the transform. More specifically, the techniques include selecting a constant value based on a size of a fixed-point transform in a video coding device and applying a variable localized bit-depth increase at the transform with a value equal to the constant value. Applying the variable localized bit-depth increase includes left-shifting a transform input signal by a number of bits equal to the constant value before the fixed- point transform, and right-shifting a transform output signal by a number of bits equal to the constant value after the fixed-point transform. The constant value is selected from a plurality of constant values stored on the video coding device. Each of the constant values is pre-calculated for one of a plurality of different transform sizes supported by the video coding.
摘要翻译：本公开描述了通过在变换处应用可变局部位深增加来减轻与视频编码相关联的定点变换中的舍入误差的技术。更具体地，这些技术包括基于视频编码装置中的定点变换的大小来选择常数值，并且在变换时以等于常数值的值应用可变的局部位深增加。应用可变局部位置深度增加包括将变换输入信号左移到等于定点变换之前的常数值的位数，并且将变换输出信号右移到等于常数的位数定点变换后的值。从存储在视频编码装置上的多个常数值中选择常数值。对于由视频编码支持的多个不同的变换大小之一，预先计算每个常数值。

5. 发明申请

WO2011069023A2 FAST SUBSPACE PROJECTION OF DESCRIPTOR PATCHES FOR IMAGE RECOGNITION 审中-公开
标题翻译：用于图像识别的描述符的快速替代预测
公开(公告)号：WO2011069023A2
公开(公告)日：2011-06-09
申请号：PCT/US2010/058807
申请日：2010-12-02
申请人： QUALCOMM INCORPORATED , HAMSICI, Onur C. , REZNIK, Yuriy , HONG, John H. , VADDADI, Sundeep , LEE, Chong U.
发明人： HAMSICI, Onur C. , REZNIK, Yuriy , HONG, John H. , VADDADI, Sundeep , LEE, Chong U.
IPC分类号： G06K9/46
CPC分类号： G06K9/4671
摘要： A method for generating a feature descriptor is provided. A set of pre-generated sparse projection vectors is obtained. A scale space for an image is also obtained, where the scale space having a plurality scale levels. A descriptor for a keypoint in the scale space is then generated based on a combination of the sparse projection vectors and sparsely sampled pixel information for a plurality of pixels across the plurality of scale levels.
摘要翻译：提供了一种生成特征描述符的方法。获得一组预先生成的稀疏投影向量。也可以获得图像的标度空间，其中刻度空间具有多个刻度级别。然后，基于稀疏投影矢量和跨越多个比例级别的多个像素的稀疏采样的像素信息的组合来生成缩放空间中的关键点的描述符。

6. 发明申请

WO2011005573A2 8-POINT TRANSFORM FOR MEDIA DATA CODING 审中-公开
标题翻译：用于媒体数据编码的8点变换
公开(公告)号：WO2011005573A2
公开(公告)日：2011-01-13
申请号：PCT/US2010/039660
申请日：2010-06-23
申请人： QUALCOMM Incorporated , REZNIK, Yuriy , JOSHI, Rajan, L. , KARCZEWICZ, Marta
发明人： REZNIK, Yuriy , JOSHI, Rajan, L. , KARCZEWICZ, Marta
IPC分类号： G06F17/14
CPC分类号： H04N19/00812 , G06F17/147 , H04N19/42 , H04N19/45 , H04N19/61 , H04N19/625
摘要： In general, techniques are described for implementing an 8-point discrete cosine transform (DCT). An apparatus comprising an 8-point discrete cosine transform (DCT) hardware unit may implement these techniques to transform media data from a spatial domain to a frequency domain. The 8-point DCT hardware unit includes an even portion comprising factors A, B that are related to a first scaled factor (μ) in accordance with a first relationship. The 8-point DCT hardware unit also includes an odd portion comprising third, fourth, fifth and sixth internal factors (G, D, E, Z) that are related to a second scaled factor (η) in accordance with a second relationship. The first relationship relates the first scaled factor to the first and second internal factors. The second relationship relates the second scaled factor to the third internal factor and a fourth internal factor, as well as, the fifth internal factor and a sixth internal factor.
摘要翻译：通常，描述了用于实现8点离散余弦变换（DCT）的技术。包括8点离散余弦变换（DCT）硬件单元的装置可以实施这些技术以将媒体数据从空间域转换到频域。 8点DCT硬件单元包括与根据第一关系的第一缩放因子（μ）相关的因子A，B的偶数部分。 8点DCT硬件单元还包括与根据第二关系的第二比例因子（α）相关的第三，第四，第五和第六内部因素（G，D，E，Z）的奇数部分。第一个关系将第一个缩放因子与第一个和第二个内部因素相关联。第二个关系将第二个缩放因子与第三个内在因素和第四个内在因素以及第五个内在因素和第六个内在因素联系起来。

7. 发明申请

WO2011005572A2 8-POINT TRANSFORM FOR MEDIA DATA CODING 审中-公开
标题翻译：用于媒体数据编码的8点变换
公开(公告)号：WO2011005572A2
公开(公告)日：2011-01-13
申请号：PCT/US2010/039657
申请日：2010-06-23
申请人： QUALCOMM Incorporated , REZNIK, Yuriy , JOSHI, Rajan L. , KARCZEWICZ, Marta
发明人： REZNIK, Yuriy , JOSHI, Rajan L. , KARCZEWICZ, Marta
IPC分类号： G06F17/14
CPC分类号： H04N19/625 , G06F17/147 , H04N19/60
摘要： In general, techniques are described for implementing an 8-point inverse discrete cosine transform (IDCT). An apparatus comprising an 8-point inverse discrete cosine transform (IDCT) hardware unit may implement these techniques to transform media data from a frequency domain to a spatial domain. The 8-point IDCT hardware unit includes an even portion comprising factors A, B that are related to a first scaled factor (μ) in accordance with a first relationship. The 8-point IDCT hardware unit also includes an odd portion comprising third, fourth, fifth and sixth internal factors (G, D, E, Z) that are related to a second scaled factor (η) in accordance with a second relationship. The first relationship relates the first scaled factor to the first and second internal factors. The second relationship relates the second scaled factor to the third, fourth, fifth and sixth internal factors.
摘要翻译：通常，描述了用于实现8点逆离散余弦变换（IDCT）的技术。包括8点逆离散余弦变换（IDCT）硬件单元的装置可以实现这些技术以将媒体数据从频域转换为空间域。 8点IDCT硬件单元包括与根据第一关系的第一缩放因子（μ）相关的因子A，B的偶数部分。 8点IDCT硬件单元还包括与根据第二关系的第二缩放因子（α）相关的第三，第四，第五和第六内部因素（G，D，E，Z）的奇数部分。第一个关系将第一个缩放因子与第一个和第二个内部因素相关联。第二个关系将第二个比例因素与第三个，第四个，第五个和第六个内部因素相关联。

8. 发明申请

WO2010141474A1 EFFICIENT CODING OF PROBABILITY DISTRIBUTIONS FOR IMAGE FEATURE DESCRIPTORS 审中-公开
标题翻译：图像特征描述符的概率分布的有效编码
公开(公告)号：WO2010141474A1
公开(公告)日：2010-12-09
申请号：PCT/US2010/036908
申请日：2010-06-01
申请人： QUALCOMM INCORPORATED , REZNIK, Yuriy A.
发明人： REZNIK, Yuriy A.
IPC分类号： G06K9/46 , G06F17/30 , G06T9/00 , H03M7/30
CPC分类号： G06K9/4642 , G06K9/4671 , H03M7/40 , H04N19/30 , H04N19/90
摘要： A method for encoding or compressing probability distributions is disclosed. A first mapping of probability distribution of samples to the types from the predefined set of types is generated. A second mapping of the types in the predefined set of types to lexicographic indexes from the index space is generated. A probability distribution is quantized as a type from the predefined set of types. The type is then mapped to a lexicographic index from the index space that spans the predefined set of types. A code for the lexicographic index is then transmitted and / or stored as part of a feature descriptor.
摘要翻译：公开了一种编码或压缩概率分布的方法。生成样本的概率分布与来自预定类型类型的类型的第一映射。生成从索引空间将预定义的一组类型中的类型与词典索引的第二映射。概率分布被量化为来自预定义类型集合的类型。然后，该类型将从跨越预定义类型集的索引空间映射到词典索引。然后将词典索引的代码作为特征描述符的一部分被发送和/或存储。

9. 发明申请

WO2009059333A1 TECHNIQUE FOR ENCODING/DECODING OF CODEBOOK INDICES FOR QUANTIZED MDCT SPECTRUM IN SCALABLE SPEECH AND AUDIO CODECS 审中-公开
标题翻译：用于编码/解码可扩展语音和音频编解码器中定量MDCT频谱的代码指标的技术
公开(公告)号：WO2009059333A1
公开(公告)日：2009-05-07
申请号：PCT/US2008/082376
申请日：2008-11-04
申请人： QUALCOMM INCORPORATED , REZNIK, Yuriy , HUANG, Pengjun , SRINIVASAMURTHY, Naveen B. , CHIVUKULA, Ravi Kiran
发明人： REZNIK, Yuriy , HUANG, Pengjun , SRINIVASAMURTHY, Naveen B. , CHIVUKULA, Ravi Kiran
IPC分类号： G10L19/14
CPC分类号： G10L19/24
摘要： Codebook indices for a scalable speech and audio codec may be efficiently encoded based on anticipated probability distributions for such codebook indices. A residual signal from a Code Excited Linear Prediction (CELP)-based encoding layer may be obtained, where the residual signal is a difference between an original audio signal and a reconstructed version of the original audio signal. The residual signal may be transformed at a Discrete Cosine Transform (DCT)-type transform layer to obtain a corresponding transform spectrum. The transform spectrum is divided into a plurality of spectral bands, where each spectral band having a plurality of spectral lines. A plurality of different codebooks are then selected for encoding the spectral bands, where each codebook is associated with a codebook index. A plurality of codebook indices associated with the selected codebooks are then encoded together to obtain a descriptor code that more compactly represents the codebook indices.
摘要翻译：用于可扩展语音和音频编解码器的码本索引可以基于这种码本索引的预期概率分布而被有效地编码。可以获得来自基于码激励线性预测（CELP）的编码层的残留信号，其中残留信号是原始音频信号和原始音频信号的重建版本之间的差。可以在离散余弦变换（DCT）型变换层处变换残差信号，以获得相应的变换频谱。变换频谱被分成多个频谱带，其中每个频谱带具有多个谱线。然后选择多个不同的码本来编码频谱带，其中每个码本与码本索引相关联。然后将与所选码本相关联的多个码本索引编码在一起以获得更紧凑地表示码本索引的描述符码。

10. 发明申请

WO2008112550A2 DATA COMPRESSION USING VARIABLE-TO-FIXED LENGTH CODES 审中-公开
标题翻译：使用可变固定长度代码的数据压缩
公开(公告)号：WO2008112550A2
公开(公告)日：2008-09-18
申请号：PCT/US2008/056225
申请日：2008-03-07
申请人： QUALCOMM Incorporated , REZNIK, Yuriy
发明人： REZNIK, Yuriy
CPC分类号： H03M7/40 , H04N19/61 , H04N19/91
摘要： This disclosure is directed to techniques for memory efficient variable to fixed length (VF) coding techniques for a variety of applications, such as media coding. For example, such techniques may be applied to code digital video, image, audio, or speech data. The techniques described in this disclosure may utilize algebraic properties of VF coding trees constructed using Tunstall or Khodak algorithms, and employ combinatorial enumeration techniques for construction, encoding and decoding of codewords. For some applications, the VF coding techniques may be implemented within media encoders, decoders, or combined encoder-decoders (CODECs). Also, in some aspects, various attributes defining a VF coding tree constructed according to this disclosure may be provided in a memory efficient data structure stored in memory associated with a coding device.
摘要翻译：本公开涉及用于诸如媒体编码的各种应用的用于存储器有效的可变长度（FW）编码技术的技术。例如，这样的技术可以应用于对数字视频，图像，音频或语音数据进行编码。本公开中描述的技术可以利用使用Tunstall或Khodak算法构建的VF编码树的代数特性，并且采用组合枚举技术来构造，编码和解码码字。对于一些应用，VF编码技术可以在媒体编码器，解码器或组合编码器解码器（CODEC）中实现。此外，在一些方面，可以在与编码装置相关联的存储器中存储的存储器有效数据结构中提供定义根据本公开的VF编码树的各种属性。

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