公开(公告)号：US07724984B2

公开(公告)日：2010-05-25

申请号：US11463979

申请日：2006-08-11

申请人： Kengo Terada ,  Eiji Otomura ,  Kouji Nakajima ,  Akira Sakamoto

发明人： Kengo Terada ,  Eiji Otomura ,  Kouji Nakajima ,  Akira Sakamoto

IPC分类号： G06K9/40

CPC分类号： G06F9/5027 ,  G06F9/52 ,  G06F9/522 ,  G06F2209/5017 ,  G06T1/20 ,  H04N19/42

摘要： An image processing apparatus of the invention includes: a plurality of processing units which share image processing; a parameter memory unit which holds a parameter specifying an operation of each of the processing units; and a control unit which controls the plurality of processing units, and the control unit includes: a sequence management unit which activates each of the processing units according to a sequence indicating a sequence of activation of and completion of processing by each of the processing units, and confirms completion of the processing; and a parameter setting unit which, in advance of activation of each of the processing units by the sequence management unit, reads a parameter for each processing unit to be activated, from the parameter memory unit according to a memory map indicating an address of the parameter for the processing unit, and sets the parameter to the processing unit according to the read result.

摘要翻译： 本发明的图像处理装置包括：共享图像处理的多个处理单元; 参数存储单元，其保存指定每个处理单元的操作的参数; 以及控制单元，其控制多个处理单元，并且所述控制单元包括：序列管理单元，其根据指示每个所述处理单元的激活和完成处理的顺序来激活每个处理单元， 并确认完成处理; 以及参数设定单元，其在由所述顺序管理单元激活每个所述处理单元之前，根据指示所述参数的地址的存储器映射从所述参数存储单元读取要激活的每个处理单元的参数 用于处理单元，并根据读取结果将参数设置到处理单元。

公开(公告)号：US20050138326A1

公开(公告)日：2005-06-23

申请号：US11009056

申请日：2004-12-13

申请人： Kengo Terada ,  Takeshi Tanaka ,  Hideshi Nishida

发明人： Kengo Terada ,  Takeshi Tanaka ,  Hideshi Nishida

IPC分类号： G06F12/02 ,  G06F12/00 ,  G06F15/00 ,  G06F15/80 ,  G06T1/20

CPC分类号： G06T1/20 ,  G06F9/30181 ,  G06F9/345 ,  G06F9/3885 ,  G06F9/3887

摘要： A parallel operation apparatus of a SIMD type comprises a processor element group of the SIMD type including a plurality of processor elements, wherein the respective processor elements simultaneously execute an identical operation, a data memory accessible from the respective processor elements in the processor element group, and an address conversion unit for converting an address with respect to the data memory accessed by the processor elements in accordance with a control signal by changing bit positions of the address. The address conversion unit preferably rearranges a first bit, a second bit, and a third bit from a lower order of address data into the second bit, the third bit, and the first bit from the lower order in the change of the bit positions.

摘要翻译： SIMD类型的并行操作装置包括包括多个处理器元件的SIMD类型的处理器元件组，其中相应的处理器元件同时执行相同的操作，可从处理器元件组中的相应处理器元件访问的数据存储器， 以及地址转换单元，用于通过改变地址的位位置来根据控制信号转换相对于由处理器单元访问的数据存储器的地址。 地址转换单元优选地从比特位置的改变中的低阶地址将第一比特，第二比特和第三比特从地址数据的较低阶重新排列成第二比特，第三比特和第一比特。

公开(公告)号：US08971406B2

公开(公告)日：2015-03-03

申请号：US13605043

申请日：2012-09-06

申请人： Viktor Wahadaniah ,  Chong Soon Lim ,  Sue Mon Thet Naing ,  Hai Wei Sun ,  Takahiro Nishi ,  Hisao Sasai ,  Youji Shibahara ,  Toshiyasu Sugio ,  Kyoko Tanikawa ,  Toru Matsunobu ,  Kengo Terada

发明人： Viktor Wahadaniah ,  Chong Soon Lim ,  Sue Mon Thet Naing ,  Hai Wei Sun ,  Takahiro Nishi ,  Hisao Sasai ,  Youji Shibahara ,  Toshiyasu Sugio ,  Kyoko Tanikawa ,  Toru Matsunobu ,  Kengo Terada

IPC分类号： H04N7/26 ,  H04N19/58 ,  H04N19/70 ,  H04N19/174

CPC分类号： H04N19/50 ,  H04N19/105 ,  H04N19/15 ,  H04N19/172 ,  H04N19/174 ,  H04N19/184 ,  H04N19/30 ,  H04N19/58 ,  H04N19/70

摘要： An image coding method includes: writing, into a sequence parameter set, buffer description defining information for defining a plurality of buffer descriptions; selecting one of the buffer descriptions for each processing unit that is a picture or a slice, and writing buffer description selecting information for specifying the selected buffer description, into a first header of the processing unit which is included in the coded bitstream; and coding the processing unit using the selected buffer description, and the buffer description defining information includes long-term information for identifying, among a plurality of reference pictures indicated in the buffer descriptions, a reference picture to be assigned as a long-term reference picture.

摘要翻译： 图像编码方法包括：向序列参数集写入定义用于定义多个缓冲器描述的信息的缓冲器描述; 选择作为图像或切片的每个处理单元的缓冲器描述之一，以及将用于指定所选择的缓冲器描述的缓冲器描述选择信息写入被包括在编码比特流中的处理单元的第一标题; 以及使用所选择的缓冲器描述对处理单元进行编码，并且缓冲器描述定义信息包括用于在缓冲器描述中指示的多个参考图像之中识别要被分配为长期参考图像的参考图像的长期信息 。

公开(公告)号：US08805099B2

公开(公告)日：2014-08-12

申请号：US13529246

申请日：2012-06-21

申请人： Hisao Sasai ,  Takahiro Nishi ,  Youji Shibahara ,  Toshiyasu Sugio ,  Kyoko Tanikawa ,  Toru Matsunobu ,  Kengo Terada

发明人： Hisao Sasai ,  Takahiro Nishi ,  Youji Shibahara ,  Toshiyasu Sugio ,  Kyoko Tanikawa ,  Toru Matsunobu ,  Kengo Terada

IPC分类号： G06K9/36 ,  H04N7/26 ,  H04N7/50

CPC分类号： H04N19/91 ,  H04N19/103 ,  H04N19/13 ,  H04N19/136 ,  H04N19/17 ,  H04N19/61

摘要： An image decoding method is an image decoding method of decoding coded image data, including selecting, based on a type of a decoding target signal, an arithmetic decoding method that is used to decode the decoding target signal, from among a plurality of arithmetic decoding methods that include: a first arithmetic decoding method which is performed based on a symbol occurrence probability obtained according to a context, and which involves update of the symbol occurrence probability according to a decoding symbol; and a second arithmetic decoding method which is performed based on a symbol occurrence probability obtained according to a context, and which maintains the symbol occurrence probability that is other than 50%.

摘要翻译： 图像解码方法是对编码图像数据进行解码的图像解码方法，包括从多个算术解码方法中选择基于解码对象信号的类型的解码对象信号的解码方法， 包括：基于根据上下文获得的符号发生概率执行并且涉及根据解码符号更新符号发生概率的第一算术解码方法; 以及第二算术解码方法，其基于根据上下文获得的符号发生概率进行，并且维持不到50％的符号发生概率。

公开(公告)号：US20130058408A1

公开(公告)日：2013-03-07

申请号：US13605043

申请日：2012-09-06

申请人： Viktor Wahadaniah ,  Chong Soon Lim ,  Sue Mon Thet Naing ,  Hai Wei Sun ,  Takahiro Nishi ,  Hisao Sasai ,  Youji Shibahara ,  Toshiyasu Sugio ,  Kyoko Tanikawa ,  Toru Matsunobu ,  Kengo Terada

发明人： Viktor Wahadaniah ,  Chong Soon Lim ,  Sue Mon Thet Naing ,  Hai Wei Sun ,  Takahiro Nishi ,  Hisao Sasai ,  Youji Shibahara ,  Toshiyasu Sugio ,  Kyoko Tanikawa ,  Toru Matsunobu ,  Kengo Terada

IPC分类号： H04N7/32

CPC分类号： H04N19/50 ,  H04N19/105 ,  H04N19/15 ,  H04N19/172 ,  H04N19/174 ,  H04N19/184 ,  H04N19/30 ,  H04N19/58 ,  H04N19/70

摘要： An image coding method includes: writing, into a sequence parameter set, buffer description defining information for defining a plurality of buffer descriptions; selecting one of the buffer descriptions for each processing unit that is a picture or a slice, and writing buffer description selecting information for specifying the selected buffer description, into a first header of the processing unit which is included in the coded bitstream; and coding the processing unit using the selected buffer description, and the buffer description defining information includes long-term information for identifying, among a plurality of reference pictures indicated in the buffer descriptions, a reference picture to be assigned as a long-term reference picture.

公开(公告)号：US20120328207A1

公开(公告)日：2012-12-27

申请号：US13529246

申请日：2012-06-21

申请人： Hisao Sasai ,  Takahiro Nishi ,  Youji Shibahara ,  Toshiyasu Sugio ,  Kyoko Tanikawa ,  Toru Matsunobu ,  Kengo Terada

发明人： Hisao Sasai ,  Takahiro Nishi ,  Youji Shibahara ,  Toshiyasu Sugio ,  Kyoko Tanikawa ,  Toru Matsunobu ,  Kengo Terada

IPC分类号： G06K9/36

CPC分类号： H04N19/91 ,  H04N19/103 ,  H04N19/13 ,  H04N19/136 ,  H04N19/17 ,  H04N19/61

摘要： An image decoding method is an image decoding method of decoding coded image data, including selecting, based on a type of a decoding target signal, an arithmetic decoding method that is used to decode the decoding target signal, from among a plurality of arithmetic decoding methods that include: a first arithmetic decoding method which is performed based on a symbol occurrence probability obtained according to a context, and which involves update of the symbol occurrence probability according to a decoding symbol; and a second arithmetic decoding method which is performed based on a symbol occurrence probability obtained according to a context, and which maintains the symbol occurrence probability that is other than 50%.

摘要翻译： 图像解码方法是对编码图像数据进行解码的图像解码方法，包括从多个算术解码方法中选择基于解码对象信号的类型的解码对象信号的解码方法， 包括：基于根据上下文获得的符号发生概率执行并且涉及根据解码符号更新符号发生概率的第一算术解码方法; 以及第二算术解码方法，其基于根据上下文获得的符号发生概率进行，并且维持不到50％的符号发生概率。