-
公开(公告)号:US08472718B2
公开(公告)日:2013-06-25
申请号:US13204574
申请日:2011-08-05
申请人: Xutao Lv , Su Wang , Shengyang Dai , Xun Xu , Akira Nakamura
发明人: Xutao Lv , Su Wang , Shengyang Dai , Xun Xu , Akira Nakamura
CPC分类号: G06T3/4053
摘要: Systems and methods for implementing a superpixel image segmentation technique using a boundary preserving distance metric are disclosed. The disclosed technique segments a digital image into superpixels comprising contiguous pixel regions sharing similar characteristics. Superpixel image segmentation techniques presented herein utilize a boundary preserving distance metric. A boundary preserving distance metric presented herein measures the similarity between two pixels of a digital image at least partially based on a boundary probability values of the two pixels and surrounding pixels.
摘要翻译: 公开了使用边界保留距离度量来实现超像素图像分割技术的系统和方法。 所公开的技术将数字图像分割成包含具有相似特征的相邻像素区域的超像素。 本文提出的超像素图像分割技术利用边界保留距离度量。 这里给出的边界保持距离度量至少部分地基于两个像素和周围像素的边界概率值来测量数字图像的两个像素之间的相似度。
-
公开(公告)号:US20120275703A1
公开(公告)日:2012-11-01
申请号:US13204574
申请日:2011-08-05
申请人: Xutao Lv , Su Wang , Shengyang Dai , Xun Xu , Akira Nakamura
发明人: Xutao Lv , Su Wang , Shengyang Dai , Xun Xu , Akira Nakamura
IPC分类号: G06K9/34
CPC分类号: G06T3/4053
摘要: Systems and methods for implementing a superpixel image segmentation technique using a boundary preserving distance metric are disclosed. The disclosed technique segments a digital image into superpixels comprising contiguous pixel regions sharing similar characteristics. Superpixel image segmentation techniques presented herein utilize a boundary preserving distance metric. A boundary preserving distance metric presented herein measures the similarity between two pixels of a digital image at least partially based on a boundary probability values of the two pixels and surrounding pixels.
摘要翻译: 公开了使用边界保留距离度量来实现超像素图像分割技术的系统和方法。 所公开的技术将数字图像分割成包含具有相似特征的相邻像素区域的超像素。 本文提出的超像素图像分割技术利用边界保留距离度量。 这里给出的边界保持距离度量至少部分地基于两个像素和周围像素的边界概率值来测量数字图像的两个像素之间的相似度。
-
公开(公告)号:US20120102154A1
公开(公告)日:2012-04-26
申请号:US13277067
申请日:2011-10-19
申请人: Yu Huang , Xutao Lv , Yue Chen , Hong Heather Yu
发明人: Yu Huang , Xutao Lv , Yue Chen , Hong Heather Yu
IPC分类号: G06F15/16
CPC分类号: H04L67/06 , H04L65/4084 , H04L65/605
摘要: Methods and systems for transcoding in a cloud computing platform are disclosed. According to an embodiment, a receiver receives an uploading file by one data block at a time, and stores the received data blocks in various storage modules. Small segment files are then generated when the size of the received data blocks is larger than a threshold. A transcoder transcodes the small segment files from one format such as a bit rate or a frame size to another while the receiver is still receiving a new data block. The transcoded small segment files may be stitched together to form a stitched file, which may be stored in a storage module to be downloaded through a content distribution network (CDN). The transcoded small segment files may be passed to streaming servers for streaming over a network while the receiver is still receiving a new data block of the uploading file.
摘要翻译: 公开了用于云计算平台中的代码转换的方法和系统。 根据实施例,接收机一次由一个数据块接收上传文件,并将接收到的数据块存储在各种存储模块中。 然后当接收的数据块的大小大于阈值时,生成小段文件。 当接收器仍然接收到新的数据块时,代码转换器将小段文件从诸如比特率或帧大小的格式转码为另一种格式。 代码转换的小段文件可以被缝合在一起以形成缝合文件,其可以存储在存储模块中以通过内容分发网络(CDN)下载。 代码转换的小段文件可以被传递到流服务器,用于通过网络进行流传输,同时接收器仍然接收上传文件的新数据块。
-
公开(公告)号:US20180107866A1
公开(公告)日:2018-04-19
申请号:US15297789
申请日:2016-10-19
申请人: Jia Li , Xutao Lv , Xiaoyu Xiaoyu , Xuehan Xiong , Jianchao Yang
发明人: Jia Li , Xutao Lv , Xiaoyu Xiaoyu , Xuehan Xiong , Jianchao Yang
CPC分类号: G06K9/00288 , G06K9/00281 , G06T7/11 , G06T2207/20076 , G06T2207/20112
摘要: Systems, devices, media, and methods are presented for modeling facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial features within the portion of the face. The systems and methods generate a descriptor function representing the set of facial features, fit object functions of the descriptor function, identify an identification probability for each facial feature, and assign an identification to each facial feature.
-
-
-