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. 发明授权

US09811946B1 High resolution (HR) panorama generation without ghosting artifacts using multiple HR images mapped to a low resolution 360-degree image 有权
公开(公告)号：US09811946B1
公开(公告)日：2017-11-07
申请号：US15168156
申请日：2016-05-30
申请人： Kwok Wai Hung , Luhong Liang , Xuejiao Liu
发明人： Kwok Wai Hung , Luhong Liang , Xuejiao Liu
IPC分类号： G06T3/40 , G06T19/00 , H04N5/232
CPC分类号： G06T3/4038 , H04N5/2258 , H04N5/23238
摘要： A hybrid-resolution panoramic VR generator places High-Resolution (HR) patches from a ring of HR cameras onto a 360-degree Low-Resolution (LR) image from a LR camera pointing upward from the ring into a panoramic mirror that captures the combined field of view of all the multiple HR cameras, but at a lower resolution. Ghosting artifacts caused by parallax errors between adjacent HR cameras are eliminated because object placement is determined by the 360-degree LR image. Each HR image is homographicly projected into 3 projections by grouping objects of different depths to obtain homographic matrixes. The 360-degree LR image is upscaled to HR and a query patch is searched in search windows in the three projections for up to two adjacent HR images. Best-matching patches are weighted by similarity with the query patch and blended to generate a reconstructed patch placed at the query patch location in a reconstructed HR panorama image.

2. 发明申请

US20090010261A1 Signal Transition Feature Based Coding For Serial Link 失效
标题翻译：用于串行链路的信号转换特征编码
公开(公告)号：US20090010261A1
公开(公告)日：2009-01-08
申请号：US10577677
申请日：2005-11-22
申请人： Xiaoying He , Luhong Liang , Ying Jia
发明人： Xiaoying He , Luhong Liang , Ying Jia
IPC分类号： H04L12/56
CPC分类号： G11B20/10 , H04L25/4906
摘要： Signal transition feature based coding for serial link is described herein. According to one embodiment, in response to a data stream transmitted onto a serial communication link, one or more bits of the data stream are encoded according to bit order determined based on a frequency of signal transitions of the data stream. As a result, a sequence of encoded data stream having a lower number of bit transitions with respect to the frequency of signal transitions of the data stream prior to the encoding is generated. Thereafter, the encoded data sequence is transmitted onto the serial communication link. Other methods and apparatuses are also described.
摘要翻译：本文描述了用于串行链路的基于信号转换特征的编码。根据一个实施例，响应于发送到串行通信链路的数据流，数据流的一个或多个比特根据基于数据流的信号转换频率确定的比特顺序进行编码。结果，产生具有相对于编码之前的数据流的信号转换频率的较低数量位转换的编码数据流序列。此后，将编码数据序列发送到串行通信链路。还描述了其它方法和装置。

3. 发明申请

US20050027530A1 Audio-visual speaker identification using coupled hidden markov models 审中-公开
标题翻译：使用耦合的隐马尔可夫模型的视听扬声器识别
公开(公告)号：US20050027530A1
公开(公告)日：2005-02-03
申请号：US10631424
申请日：2003-07-31
申请人： Tieyan Fu , Xiaoxing Liu , Luhong Liang , Xiaobo Pi , Ara Nefian
发明人： Tieyan Fu , Xiaoxing Liu , Luhong Liang , Xiaobo Pi , Ara Nefian
IPC分类号： G06K9/62 , G06K9/68 , G10L15/24 , G10L17/00 , G10L15/14
CPC分类号： G06K9/6293 , G06K9/6297 , G10L15/24 , G10L17/10 , G10L17/16
摘要： A phoneme and a viseme of a person may be modeled using a coupled hidden Markov model. The coupled hidden Markov model and a second model may be compared to identify the person.
摘要翻译：可以使用耦合的隐马尔可夫模型来模拟人的音素和视力。可以将耦合的隐马尔科夫模型和第二模型进行比较以识别人。

4. 发明申请

US20140093185A1 APPARATUS, SYSTEM, AND METHOD FOR MULTI-PATCH BASED SUPER-RESOLUTION FROM AN IMAGE 有权
标题翻译：装置，系统和方法，用于基于图像的多分辨率超分辨率
公开(公告)号：US20140093185A1
公开(公告)日：2014-04-03
申请号：US13630803
申请日：2012-09-28
申请人： Luhong Liang , King Hung Chiu , Edmund Y. Lam
发明人： Luhong Liang , King Hung Chiu , Edmund Y. Lam
IPC分类号： G06K9/36
CPC分类号： G06T3/4053
摘要： Embodiments of the present invention include apparatuses, systems and methods for multi-patch based super-resolution from a single video frame. Such embodiments include a scale-invariant self-similarity (SiSS) based super-resolution method. Instead of searching HR examples in a database or in LR image, the present embodiments may select the patches according to the SiSS characteristics of the patch itself, so that the computational complexity of the method may be reduced because there is not any search involved. To solve the problem of lack of relevant examples in natural images, the present embodiments may employ multi-shaped and multi-sized patches in HR image reconstruction. Additionally, embodiments may include steps for a hybrid weighing method for suppressing artifacts. Advantageously, certain embodiments of the method may be 10˜1,000 times faster than the example based SR approaches using patch searching and can achieve comparable HR image quality.
摘要翻译：本发明的实施例包括用于来自单个视频帧的用于基于多贴片的超分辨率的装置，系统和方法。这样的实施例包括基于尺度不变自相似性（SiSS）的超分辨率方法。代替在数据库或LR图像中搜索HR示例，本实施例可以根据补丁本身的SiSS特性来选择补丁，使得可以减少该方法的计算复杂度，因为没有涉及任何搜索。为了解决自然图像中缺少相关示例的问题，本实施例可以在HR图像重建中采用多形和多尺寸的贴片。另外，实施例可以包括用于抑制伪像的混合称重方法的步骤。有利地，该方法的某些实施例可以比使用补丁搜索的基于示例的SR方法快10〜1000倍，并且可以实现可比较的HR图像质量。

5. 发明授权

US08675999B1 Apparatus, system, and method for multi-patch based super-resolution from an image 有权
标题翻译：用于基于图像的基于多贴片的超分辨率的装置，系统和方法
公开(公告)号：US08675999B1
公开(公告)日：2014-03-18
申请号：US13630803
申请日：2012-09-28
申请人： Luhong Liang , King Hung Chiu , Edmund Y. Lam
发明人： Luhong Liang , King Hung Chiu , Edmund Y. Lam
IPC分类号： G06K9/32
CPC分类号： G06T3/4053
摘要： Embodiments of the present invention include apparatuses, systems and methods for multi-patch based super-resolution from a single video frame. Such embodiments include a scale-invariant self-similarity (SiSS) based super-resolution method. Instead of searching HR examples in a database or in LR image, the present embodiments may select the patches according to the SiSS characteristics of the patch itself, so that the computational complexity of the method may be reduced because there is not any search involved. To solve the problem of lack of relevant examples in natural images, the present embodiments may employ multi-shaped and multi-sized patches in HR image reconstruction. Additionally, embodiments may include steps for a hybrid weighing method for suppressing artifacts. Advantageously, certain embodiments of the method may be 10˜1,000 times faster than the example based SR approaches using patch searching and can achieve comparable HR image quality.
摘要翻译：本发明的实施例包括用于来自单个视频帧的用于基于多贴片的超分辨率的装置，系统和方法。这样的实施例包括基于尺度不变自相似性（SiSS）的超分辨率方法。代替在数据库或LR图像中搜索HR示例，本实施例可以根据补丁本身的SiSS特性来选择补丁，使得可以减少该方法的计算复杂度，因为没有涉及任何搜索。为了解决自然图像中缺少相关示例的问题，本实施例可以在HR图像重建中采用多形和多尺寸的贴片。另外，实施例可以包括用于抑制伪像的混合称重方法的步骤。有利地，该方法的某些实施例可以是使用补丁搜索的基于示例的SR方法的10〜1000倍，并且可以实现可比较的HR图像质量。

6. 发明授权

US07961936B2 Non-overlap region based automatic global alignment for ring camera image mosaic 有权
标题翻译：基于非重叠区域的自动全局对准环形摄像机图像拼接
公开(公告)号：US07961936B2
公开(公告)日：2011-06-14
申请号：US11694778
申请日：2007-03-30
申请人： Luhong Liang , Xiao Xiao , Ying Jia , Steve W. Deutsch
发明人： Luhong Liang , Xiao Xiao , Ying Jia , Steve W. Deutsch
IPC分类号： G06K9/80 , G06T15/00
CPC分类号： G06T7/85 , G06T2207/10021 , G06T2207/30208
摘要： Various embodiments are directed to non-overlap region based automatic global alignment for ring camera image mosaic. The non-overlap region based homography calculation may be based on feature points of a planar target appearing in a non-overlap region among images captured by a multi-camera based video capture device. Other embodiments are described and claimed.
摘要翻译：各种实施例涉及用于环形摄像机图像拼接的基于非重叠区域的自动全局对准。基于非重叠区域的单应性计算可以基于出现在由基于多摄像机的视频捕获设备捕获的图像之中的非重叠区域中的平面目标的特征点。描述和要求保护其他实施例。

7. 发明授权

US07472063B2 Audio-visual feature fusion and support vector machine useful for continuous speech recognition 有权
标题翻译：视听特征融合和支持向量机，可用于连续语音识别
公开(公告)号：US07472063B2
公开(公告)日：2008-12-30
申请号：US10326368
申请日：2002-12-19
申请人： Ara V. Nefian , Xiaobo Pi , Luhong Liang , Xiaoxing Liu , Yibao Zhao
发明人： Ara V. Nefian , Xiaobo Pi , Luhong Liang , Xiaoxing Liu , Yibao Zhao
IPC分类号： G10L15/14 , G06K9/70
CPC分类号： G06K9/6293 , G10L15/25
摘要： A speech recognition method includes several embodiments describing application of support vector machine analysis to a mouth region. Lip position can be accurately determined and used in conjunction with synchronous or asynchronous audio data to enhance speech recognition probabilities.
摘要翻译：语音识别方法包括描述向口区域应用支持向量机分析的几个实施例。可以准确地确定唇部位置并将其与同步或异步音频数据结合使用，以增强语音识别概率。

8. 发明授权

US07728746B2 Signal transition feature based coding for serial link 失效
标题翻译：用于串行链路的基于信号转换特征的编码
公开(公告)号：US07728746B2
公开(公告)日：2010-06-01
申请号：US10577677
申请日：2005-11-22
申请人： Xiaoying He , Luhong Liang , Ying Jia
发明人： Xiaoying He , Luhong Liang , Ying Jia
IPC分类号： H03M9/00
CPC分类号： G11B20/10 , H04L25/4906
摘要： Signal transition feature based coding for serial link is described herein. According to one embodiment, in response to a data stream transmitted onto a serial communication link, one or more bits of the data stream are encoded according to bit order determined based on a frequency of signal transitions of the data stream. As a result, a sequence of encoded data stream having a lower number of bit transitions with respect to the frequency of signal transitions of the data stream prior to the encoding is generated. Thereafter, the encoded data sequence is transmitted onto the serial communication link. Other methods and apparatuses are also described.
摘要翻译：本文描述了用于串行链路的基于信号转换特征的编码。根据一个实施例，响应于发送到串行通信链路的数据流，数据流的一个或多个比特根据基于数据流的信号转换频率确定的比特顺序进行编码。结果，产生具有相对于编码之前的数据流的信号转换频率的较低数量位转换的编码数据流序列。此后，将编码数据序列发送到串行通信链路。还描述了其它方法和装置。

9. 发明授权

US07454342B2 Coupled hidden Markov model (CHMM) for continuous audiovisual speech recognition 有权
标题翻译：耦合隐马尔可夫模型（CHMM）用于连续视听语音识别
公开(公告)号：US07454342B2
公开(公告)日：2008-11-18
申请号：US10392709
申请日：2003-03-19
申请人： Ara Victor Nefian , Xiaoxing Liu , Xiaobo Pi , Luhong Liang , Yibao Zhao
发明人： Ara Victor Nefian , Xiaoxing Liu , Xiaobo Pi , Luhong Liang , Yibao Zhao
IPC分类号： G10L15/14
CPC分类号： G06K9/6293 , G06K9/6297 , G10L15/142 , G10L15/25
摘要： Method and apparatus for an audiovisual continuous speech recognition (AVCSR) system using a coupled hidden Markov model (CHMM) are described herein. In one aspect, an exemplary process includes receiving an audio data stream and a video data stream, and performing continuous speech recognition based on the audio and video data streams using a plurality of hidden Markov models (HMMs), a node of each of the HMMs at a time slot being subject to one or more nodes of related HMMs at a preceding time slot. Other methods and apparatuses are also described.
摘要翻译：本文描述了使用耦合隐马尔可夫模型（CHMM）的视听连续语音识别（AVCSR）系统的方法和装置。在一个方面，示例性过程包括接收音频数据流和视频数据流，以及使用多个隐马尔可夫模型（HMM），基于音频和视频数据流执行连续语音识别，每个HMM的节点在时隙处于前一时隙处的相关HMM的一个或多个节点。还描述了其它方法和装置。

10. 发明申请

US20170345214A1 High Resolution (HR) Panorama Generation Without Ghosting Artifacts Using Multiple HR Images Mapped to a Low-Resolution 360-Degree Image 有权
公开(公告)号：US20170345214A1
公开(公告)日：2017-11-30
申请号：US15168156
申请日：2016-05-30
申请人： Kwok Wai HUNG , Luhong LIANG , Xuejiao LIU
发明人： Kwok Wai HUNG , Luhong LIANG , Xuejiao LIU
IPC分类号： G06T19/00 , G06T3/40 , H04N5/232
CPC分类号： G06T3/4038 , H04N5/2258 , H04N5/23238
摘要： A hybrid-resolution panoramic VR generator places High-Resolution (HR) patches from a ring of HR cameras onto a 360-degree Low-Resolution (LR) image from a LR camera pointing upward from the ring into a panoramic mirror that captures the combined field of view of all the multiple HR cameras, but at a lower resolution. Ghosting artifacts caused by parallax errors between adjacent HR cameras are eliminated because object placement is determined by the 360-degree LR image. Each HR image is homographicly projected into 3 projections by grouping objects of different depths to obtain homographic matrixes. The 360-degree LR image is upscaled to HR and a query patch is searched in search windows in the three projections for up to two adjacent HR images. Best-matching patches are weighted by similarity with the query patch and blended to generate a reconstructed patch placed at the query patch location in a reconstructed HR panorama image.

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