公开(公告)号：US08805004B2

公开(公告)日：2014-08-12

申请号：US13138091

申请日：2010-01-05

Applicant: Yu Huang ,  Joan Llach

Inventor： Yu Huang ,  Joan Llach

IPC: G06K9/00

CPC classification number: G06K9/00718 ,  G06K9/00724 ,  G06K9/00744

Abstract: Substantial elimination of errors in the detection and location of overlapping human objects in an image of a playfield is achieved, in accordance with at least one aspect of the invention, by performing a predominately shape-based analysis of one or more characteristics obtained from a specified portion of the candidate non-playfield object, by positioning a human object model substantially over the specified portion of the candidate non-playfield object in accordance with information based at least in part on information from the shape-based analysis, and removing an overlapping human object from the portion of the candidate non-playfield object identified by the human object model. In one exemplary embodiment, the human object model is an ellipse whose major and minor axes are variable in relation to one or more characteristics identified from the specified portion of the candidate non-playfield object.

Abstract translation: 根据本发明的至少一个方面，通过基于形状的分析来实现从指定的图像中获得的一个或多个特征，从而实现了重叠的人类对象在场景图像中的检测和定位中的错误的显着消除 通过至少部分地基于来自基于形状的分析的信息的信息，基于基于形状的分析的信息的信息将人体对象模型基本上定位在候选非播放对象的指定部分上，并且去除重叠的人 来自由人类对象模型识别的候选非玩游戏对象的部分的对象。 在一个示例性实施例中，人体对象模型是椭圆，其主轴和短轴相对于从候选非播放对象的指定部分识别的一个或多个特征是可变的。

公开(公告)号：US08391547B2

公开(公告)日：2013-03-05

申请号：US12450410

申请日：2007-11-06

Applicant: Yu Huang ,  Joan Llach ,  Sitaram Bhagavathy

Inventor： Yu Huang ,  Joan Llach ,  Sitaram Bhagavathy

IPC: G06K9/00 ,  G06K9/34

CPC classification number: G06K9/00711 ,  G06K9/44 ,  G06K9/4652

Abstract: A method is disclosed for detecting and locating players in soccer video frames without errors caused by artifacts by a shape analysis-based approach to identify the players and the ball from roughly extracted foregrounds obtained by color segmentation and connected component analysis, by performing a Euclidean distance transform to extract skeletons for every foreground blob, by performing a shape analysis to remove false alarms (non-players and non-ball), and then by performing skeleton pruning and a reverse Euclidean distance transform to cut-off the artifacts primarily caused by playing field lines.

Abstract translation: 公开了一种用于通过基于形状分析的方法来检测和定位足球视频帧中的玩家而产生错误的方法，以通过执行欧几里德距离从颜色分割和连接分量分析获得的粗略提取的前景识别玩家和球， 通过执行形状分析来消除假警报（非玩家和非球），然后通过执行骨架修剪和反向欧几里得距离变换来截取主要由玩耍造成的伪影，从而转换为每个前景斑点提取骨架 现场线。

公开(公告)号：US20110268320A1

公开(公告)日：2011-11-03

申请号：US13138091

申请日：2010-01-05

Applicant: Yu Huang ,  Joan Llach

Inventor： Yu Huang ,  Joan Llach

IPC: G06K9/46

CPC classification number: G06K9/00718 ,  G06K9/00724 ,  G06K9/00744

Abstract: Substantial elimination of errors in the detection and location of overlapping human objects in an image of a playfield is achieved, in accordance with at least one aspect of the invention, by performing a predominately shape-based analysis of one or more characteristics obtained from a specified portion of the candidate non-playfield object, by positioning a human object model substantially over the specified portion of the candidate non-playfield object in accordance with information based at least in part on information from the shape-based analysis, and removing an overlapping human object from the portion of the candidate non-playfield object identified by the human object model. In one exemplary embodiment, the human object model is an ellipse whose major and minor axes are variable in relation to one or more characteristics identified from the specified portion of the candidate non-playfield object.

Abstract translation: 根据本发明的至少一个方面，通过基于形状的分析来实现从指定的图像中获得的一个或多个特征，从而实现了重叠的人类对象在场景图像中的检测和定位中的错误的显着消除 通过至少部分地基于来自基于形状的分析的信息的信息，基于基于形状的分析的信息的信息将人体对象模型基本上定位在候选非播放对象的指定部分上，并且去除重叠的人 来自由人类对象模型识别的候选非玩游戏对象的部分的对象。 在一个示例性实施例中，人体对象模型是椭圆，其主轴和短轴相对于从候选非播放对象的指定部分识别的一个或多个特征是可变的。

公开(公告)号：US20110026607A1

公开(公告)日：2011-02-03

申请号：US12736496

申请日：2009-04-07

Applicant: Sitaram Bhagavathy ,  Joan Llach ,  Yu Huang

Inventor： Sitaram Bhagavathy ,  Joan Llach ,  Yu Huang

IPC: H04N7/26 ,  G06K9/40 ,  H04N5/21

CPC classification number: G06T5/002 ,  G06T5/003 ,  G06T5/20 ,  G06T2207/10016 ,  H04N19/119 ,  H04N19/124 ,  H04N19/162 ,  H04N19/167 ,  H04N19/17 ,  H04N19/20 ,  H04N19/46 ,  H04N19/80 ,  H04N19/85

Abstract: The visibility of an object in a digital picture is enhanced by comparing an input video of the digital picture with stored information representative of the nature and characteristics of the object to develop object localization information that identifies and locates the object. The input video and the object localization information are encoded and transmitted to a receiver where the input video and the object localization information are decoded and the decoded input video is enhanced by the decoded object localization information

Abstract translation: 通过将数字图像的输入视频与表示对象的性质和特征的存储信息进行比较，以开发识别和定位对象的对象定位信息来增强数字图像中对象的可视性。 输入视频和对象定位信息被编码并发送到接收机，其中输入视频和对象定位信息被解码，并且解码的输入视频被解码的对象定位信息增强

公开(公告)号：US20100098307A1

公开(公告)日：2010-04-22

申请号：US12450410

申请日：2007-11-06

Applicant: Yu Huang ,  Joan Llach ,  Sitaram Bhagavathy

Inventor： Yu Huang ,  Joan Llach ,  Sitaram Bhagavathy

IPC: G06K9/62

CPC classification number: G06K9/00711 ,  G06K9/44 ,  G06K9/4652

Abstract: A method is disclosed for detecting and locating players in soccer video frames without errors caused by artifacts by a shape analysis-based approach to identify the players and the ball from roughly extracted foregrounds obtained by color segmentation and connected component analysis, by performing a Euclidean distance transform to extract skeletons for every foreground blob, by performing a shape analysis to remove false alarms (non-players and non-ball), and then by performing skeleton pruning and a reverse Euclidean distance transform to cut-off the artifacts primarily caused by playing field lines.

Abstract translation: 公开了一种用于通过基于形状分析的方法来检测和定位足球视频帧中的玩家而产生错误的方法，以通过执行欧几里德距离从颜色分割和连接分量分析获得的大致提取的前景识别玩家和球， 通过执行形状分析来消除假警报（非玩家和非球），然后通过执行骨架修剪和反向欧几里得距离变换来截取主要由玩耍造成的伪影，从而转换为每个前景斑点提取骨架 现场线。

公开(公告)号：US20100067802A1

公开(公告)日：2010-03-18

申请号：US12312743

申请日：2007-11-30

Applicant: Yu Huang ,  Joan Llach

Inventor： Yu Huang ,  Joan Llach

IPC: G06K9/46

CPC classification number: G06K9/32 ,  G06K2009/3291 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/30224 ,  G06T2207/30241

Abstract: An implementation provides a method for estimating a location for an object in a particular image of a sequence of images. The location is estimated using a particle-based framework, such as a particle filter. It is determined that the estimated location for the object in the particular image is occluded. A trajectory is estimated for the object based on one or more previous locations of the object in one or more previous images in the sequence of images. The estimated location of the object is changed based on the estimated trajectory.

Abstract translation: 实现提供了一种用于估计图像序列的特定图像中的对象的位置的方法。 使用基于粒子的框架（如粒子滤波器）来估计位置。 确定特定图像中对象的估计位置被遮挡。 基于图像序列中的一个或多个先前图像中的物体的一个或多个先前位置来估计对象的轨迹。 基于估计的轨迹改变对象的估计位置。

公开(公告)号：US09214030B2

公开(公告)日：2015-12-15

申请号：US12451264

申请日：2008-04-25

Applicant: Joel Sole ,  Yu Huang ,  Joan Llach

Inventor： Joel Sole ,  Yu Huang ,  Joan Llach

IPC: H04N7/30 ,  H04N7/26 ,  H04N7/64 ,  G06T7/20 ,  G06T5/00

CPC classification number: G06T7/2006 ,  G06T5/005 ,  G06T7/194 ,  G06T7/215 ,  G06T2207/10016

Abstract: A method for processing a video sequence having a plurality of frames includes the steps of: extracting features from each of the frames, determining correspondences between the extracted features from two of the frames, estimating motion in the video sequence based on the determined correspondences, generating a background mosaic for the video sequence based on the estimated motion, and performing foreground-background segmentation on each of the frames based on the background mosaic.

Abstract translation: 一种用于处理具有多个帧的视频序列的方法包括以下步骤：从每个帧中提取特征，确定来自两帧中提取的特征之间的对应关系，基于所确定的对应度估计视频序列中的运动，产生 基于估计运动的视频序列的背景马赛克，以及基于背景马赛克对每个帧执行前景背景分割。

公开(公告)号：US20110026606A1

公开(公告)日：2011-02-03

申请号：US12736408

申请日：2009-04-07

Applicant: Sitaram Bhagavathy ,  Joan Llach ,  Yu Huang

Inventor： Sitaram Bhagavathy ,  Joan Llach ,  Yu Huang

IPC: H04N7/12

CPC classification number: G06T5/20 ,  G06T5/002 ,  G06T5/003 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/20012 ,  G06T2207/20192 ,  G06T2207/30221

Abstract: The visibility of an object in a digital picture is enhanced by comparing an input video of the digital picture with stored information representative of the nature and characteristics of the object to develop object localization information that identifies and locates the object. The visibility of the object and the region in which the object is located is enhanced by image processing and the enhanced input video is encoded.

Abstract translation: 通过将数字图像的输入视频与表示对象的性质和特征的存储信息进行比较，以开发识别和定位对象的对象定位信息来增强数字图像中对象的可视性。 通过图像处理增强对象和对象所在的区域的可视性，并对增强的输入视频进行编码。

公开(公告)号：US20100067803A1

公开(公告)日：2010-03-18

申请号：US12312744

申请日：2007-11-30

Applicant: Yu Huang ,  Joan Llach

Inventor： Yu Huang ,  Joan Llach

IPC: G06K9/46

CPC classification number: G06K9/32 ,  G06K2009/3291 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/30224 ,  G06T2207/30241

Abstract: An implementation provides a method for determining a trajectory of an object in a particular image in a sequence of digital images, the trajectory being based on one or more previous locations of the object in one or more previous images in the sequence. A weight is determined, for a particle in a particle-based framework for tracking the object, based on distance from the trajectory to the particle. A location estimate is determined for the object using the particle-based framework, the location estimate being based on the determined particle weight.

Abstract translation: 实现提供了一种用于确定数字图像序列中的特定图像中的对象的轨迹的方法，该轨迹基于该序列中的一个或多个先前图像中的对象的一个​​或多个先前位置。 基于从轨迹到粒子的距离来确定用于跟踪对象的基于粒子的框架中的粒子的权重。 使用基于粒子的框架为对象确定位置估计，位置估计基于确定的粒子重量。

公开(公告)号：US20090238406A1

公开(公告)日：2009-09-24

申请号：US12311266

申请日：2006-12-19

Applicant: Yu Huang ,  Joan Llach

Inventor： Yu Huang ,  Joan Llach

IPC: G06K9/00

CPC classification number: G06F17/5009 ,  G06F2217/16 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/30221 ,  G06T2207/30224 ,  G06T2207/30241

Abstract: According to an implementation, a set of particles is provided for use in estimating a location of a state of a dynamic system. A local-mode seeking mechanism is applied to move one or more particles in the set of particles, and the number of particles in the set of particles is modified. The location of the state of the dynamic system is estimated using particles in the set of particles. Another implementation provides dynamic state estimation using a particle filter for which the particle locations are modified using a local-mode seeking algorithm based on a mean-shift analysis and for which the number of particles is adjusted using a Kullback-Leibler-distance sampling process. The mean-shift analysis may reduce degeneracy in the particles, and the sampling process may reduce the computational complexity of the particle filter. The implementation may be useful with non-linear and non-Gaussian systems.

Abstract translation: 根据实施方式，提供一组粒子用于估计动态系统状态的位置。 应用本地模式寻找机制来移动该组粒子中的一个或多个粒子，并且修改该组粒子中的粒子的数量。 使用该组粒子中的粒子来估计动态系统状态的位置。 另一个实现方案使用粒子滤波器提供动态状态估计，使用基于平均移位分析的局部模式搜索算法对粒子位置进行修改，并且使用Kullback-Leibler-distance采样过程来调整粒子的数量。 均值分析可以减少粒子的退化，采样过程可能会降低粒子滤波器的计算复杂度。 该实现对于非线性和非高斯系统可能是有用的。