公开(公告)号：US20110299783A1

公开(公告)日：2011-12-08

申请号：US13100081

申请日：2011-05-03

Applicant: Ludovic Chotard ,  Michel Sanches ,  Vitor Schwambach ,  Mahesh Chandra

Inventor： Ludovic Chotard ,  Michel Sanches ,  Vitor Schwambach ,  Mahesh Chandra

IPC: G06K9/64

CPC classification number: G06K9/00228 ,  G06K9/6257

Abstract: The invention concerns a method of performing, by an image processing device, object detection in an image comprising: performing one or more tests of a test sequence for detection of a first object on pixels values of a plurality of at least partially overlapping sub-regions (310, 312, 314) of a first search window (108); generating a cumulative score based on results of said one or more tests on said plurality of sub-regions; comparing said cumulative score with a threshold value; and based on said comparison, selectively performing one or more of said tests of said test sequence on at least one further sub-region of said first search window, said at least one further sub-region at least partially overlapping each of said plurality of sub-regions.

Abstract translation: 本发明涉及一种通过图像处理设备执行图像中的对象检测的方法，包括：对多个至少部分重叠的子区域的像素值执行用于检测第一对象的测试序列的一个或多个测试 （108,312）的第一搜索窗口（310,312,314）; 基于对所述多个子区域的所述一个或多个测试的结果生成累积分数; 将所述累积分数与阈值进行比较; 并且基于所述比较，在所述第一搜索窗口的至少一个另外的子区域上选择性地执行所述测试序列的所述测试中的一个或多个，所述至少一个另外的子区域至少部分地与所述多个子区域 区域。

公开(公告)号：US07848570B2

公开(公告)日：2010-12-07

申请号：US11638320

申请日：2006-12-13

Applicant: Amit Taneja ,  Mahesh Chandra

Inventor： Amit Taneja ,  Mahesh Chandra

IPC: G06K9/00

CPC classification number: G06T1/60

Abstract: To provide a memory efficient method and system for statistical data accumulation and processing, data is divided into multiple data zones and divided into subgroups of memories. A separate memory bin is assigned for each of the subgroups, and this memory bin is shared between various two data zones in each subgroup for processing and accumulation. In this scheme, the histogram data in each location of the separate memory bin for the previously accumulated data zones is processed before updating the stored value for the data zone requiring data accumulation.

Abstract translation: 为了提供用于统计数据累积和处理的存储器有效的方法和系统，数据被分成多个数据区并被划分成存储器的子组。 为每个子组分配一个单独的内存箱，并且该内存仓在每个子组中的各个两个数据区域之间进行共享以进行处理和累加。 在该方案中，在更新需要数据累积的数据区的存储值之前，处理用于先前累积的数据区的单独存储器仓的每个位置中的直方图数据。

公开(公告)号：US20060072840A1

公开(公告)日：2006-04-06

申请号：US11155391

申请日：2005-06-17

Applicant: Antoine Gautier ,  Mahesh Chandra

Inventor： Antoine Gautier ,  Mahesh Chandra

IPC: G06K9/36

CPC classification number: H04N19/60 ,  H04N19/85 ,  H04N2201/33378

Abstract: The conversion device includes an input for receiving data corresponding to an image to be displayed. The received data is in a JPEG decoder output data format A processor is included for reconstructing and writing the image to be displayed into the image memory, in a display module expected input data format. The bandwidth of the image memory is greater than one byte. The processor is fully hardwired and includes a first logic stage for writing the received data byte by byte into an intermediate memory at chosen addresses such that the written data form a sequence of data in the display module expected input data format, and a second logic stage for reading the written data in the intermediate memory, forming successive packets of read data having a size corresponding to the bandwidth, and successively writing the packets into the image memory at chosen addresses such that the written packets together form all the lines of the image.

Abstract translation: 转换装置包括用于接收与要显示的图像相对应的数据的输入。 接收到的数据是JPEG解码器输出数据格式。 包括处理器，用于以显示模块期望的输入数据格式重建和写入要显示的图像到图像存储器中。 图像存储器的带宽大于一个字节。 处理器是完全硬连线的，并且包括用于逐字地将所接收的数据逐字地写入到所选地址的中间存储器中的第一逻辑级，使得写入的数据形成显示模块预期输入数据格式的数据序列，以及第二逻辑级 用于读取中间存储器中的写入数据，形成具有与带宽相对应的大小的连续的读取数据分组，并且以选定的地址将分组顺序地写入图像存储器，使得所写入的分组一起形成图像的所有行。

公开(公告)号：US08605098B2

公开(公告)日：2013-12-10

申请号：US11648125

申请日：2006-12-29

Applicant: Mahesh Chandra

Inventor： Mahesh Chandra

IPC: G06T1/60

CPC classification number: G06T1/60

Abstract: A memory architecture for image processing comprising a memory array having multiple multi-byte memory data paths of equal multi-byte data width, and a multiplexing structure connected to the output of the multiple multi-byte data paths, capable of selectively providing a multi-byte data path of a desired width containing a desired permutation of bytes chosen from one or more of the multiple data paths.

Abstract translation: 一种用于图像处理的存储器架构，包括具有多个多字节数据宽度的多个多字节存储器数据路径的存储器阵列，以及连接到多个多字节数据路径的输出的复用结构，能够选择性地提供多字节数据， 包含从多个数据路径中的一个或多个中选择的期望的字节排列的期望宽度的字节数据路径。

公开(公告)号：US07460718B2

公开(公告)日：2008-12-02

申请号：US11155391

申请日：2005-06-17

Applicant: Antoine Gautier ,  Mahesh Chandra

Inventor： Antoine Gautier ,  Mahesh Chandra

IPC: G06K9/36

CPC classification number: H04N19/60 ,  H04N19/85 ,  H04N2201/33378

Abstract: The conversion device includes an input for receiving data corresponding to an image to be displayed. The received data is in a JPEG decoder output data format A processor is included for reconstructing and writing the image to be displayed into the image memory, in a display module expected input data format. The bandwidth of the image memory is greater than one byte. The processor is fully hardwired and includes a first logic stage for writing the received data byte by byte into an intermediate memory at chosen addresses such that the written data form a sequence of data in the display module expected input data format, and a second logic stage for reading the written data in the intermediate memory, forming successive packets of read data having a size corresponding to the bandwidth, and successively writing the packets into the image memory at chosen addresses such that the written packets together form all the lines of the image.

Abstract translation: 转换装置包括用于接收与要显示的图像相对应的数据的输入。 接收到的数据是JPEG解码器输出数据格式。 包括处理器，用于以显示模块期望的输入数据格式重建和写入要显示的图像到图像存储器中。 图像存储器的带宽大于一个字节。 处理器是完全硬连线的，并且包括用于逐字地将所接收的数据逐字地写入到所选地址的中间存储器中的第一逻辑级，使得写入的数据形成显示模块预期输入数据格式的数据序列，以及第二逻辑级 用于读取中间存储器中的写入数据，形成具有与带宽相对应的大小的连续的读取数据分组，并且以选定的地址将分组顺序地写入图像存储器，使得所写入的分组一起形成图像的所有行。

公开(公告)号：US08805081B2

公开(公告)日：2014-08-12

申请号：US13100081

申请日：2011-05-03

Applicant: Ludovic Chotard ,  Michel Sanches ,  Vitor Schwambach ,  Mahesh Chandra

Inventor： Ludovic Chotard ,  Michel Sanches ,  Vitor Schwambach ,  Mahesh Chandra

IPC: G06K9/46

CPC classification number: G06K9/00228 ,  G06K9/6257

Abstract: The invention concerns a method of performing, by an image processing device, object detection in an image comprising: performing one or more tests of a test sequence for detection of a first object on pixels values of a plurality of at least partially overlapping sub-regions (310, 312, 314) of a first search window (108); generating a cumulative score based on results of said one or more tests on said plurality of sub-regions; comparing said cumulative score with a threshold value; and based on said comparison, selectively performing one or more of said tests of said test sequence on at least one further sub-region of said first search window, said at least one further sub-region at least partially overlapping each of said plurality of sub-regions.

Abstract translation: 本发明涉及一种通过图像处理设备执行图像中的对象检测的方法，包括：对多个至少部分重叠的子区域的像素值执行用于检测第一对象的测试序列的一个或多个测试 （108,312）的第一搜索窗口（310,312,314）; 基于对所述多个子区域的所述一个或多个测试的结果生成累积分数; 将所述累积分数与阈值进行比较; 并且基于所述比较，在所述第一搜索窗口的至少一个另外的子区域上选择性地执行所述测试序列的所述测试中的一个或多个，所述至少一个另外的子区域至少部分地与所述多个子区域 区域。

公开(公告)号：US20070204096A1

公开(公告)日：2007-08-30

申请号：US11648125

申请日：2006-12-29

Applicant: Mahesh Chandra

Inventor： Mahesh Chandra

IPC: G06F12/06

CPC classification number: G06T1/60

Abstract: A memory architecture for image processing comprising a memory array having multiple multi-byte memory data paths of equal multi-byte data width, and a multiplexing structure connected to the output of the multiple multi-byte data paths, capable of selectively providing a multi-byte data path of a desired width containing a desired permutation of bytes chosen from one or more of the multiple data paths.

Abstract translation: 一种用于图像处理的存储器架构，包括具有多个多字节数据宽度的多个多字节存储器数据路径的存储器阵列，以及连接到多个多字节数据路径的输出的复用结构，能够选择性地提供多字节数据， 包含从多个数据路径中的一个或多个中选择的期望的字节排列的期望宽度的字节数据路径。

公开(公告)号：US20070168621A1

公开(公告)日：2007-07-19

申请号：US11638320

申请日：2006-12-13

Applicant: Amit Taneja ,  Mahesh Chandra

Inventor： Amit Taneja ,  Mahesh Chandra

IPC: G06F13/28 ,  G06F12/00

CPC classification number: G06T1/60

Abstract: To provide a memory efficient method and system for statistical data accumulation and processing, data is divided into multiple data zones and divided into subgroups of memories. A separate memory bin is assigned for each of the subgroups, and this memory bin is shared between various two data zones in each subgroup for processing and accumulation. In this scheme, the histogram data in each location of the separate memory bin for the previously accumulated data zones is processed before updating the stored value for the data zone requiring data accumulation.

Abstract translation: 为了提供用于统计数据累积和处理的存储器有效的方法和系统，数据被分成多个数据区并被划分成存储器的子组。 为每个子组分配一个单独的内存箱，并且该内存仓在每个子组中的各个两个数据区域之间进行共享以进行处理和累加。 在该方案中，在更新需要数据累积的数据区的存储值之前，处理用于先前累积的数据区的单独存储器仓的每个位置中的直方图数据。