-
公开(公告)号：US08842163B2
公开(公告)日：2014-09-23
申请号：US13154843
申请日：2011-06-07
申请人： Ankur Datta , Rogerio S. Feris , Yun Zhai
发明人： Ankur Datta , Rogerio S. Feris , Yun Zhai
CPC分类号： G06T17/10 , G06K9/00711 , G06K9/00771 , G06K9/46 , G06K9/4604 , G06K9/52 , G06K2009/4666 , G06T3/20 , G06T3/40 , G06T7/20 , G06T7/251 , G06T7/62 , G06T7/75 , G06T15/205 , G06T19/20 , G06T2200/24 , G06T2207/10016 , G06T2207/30232 , G06T2207/30236 , G06T2219/2004 , G06T2219/2016 , H04N13/264 , H04N13/293 , H04N2013/0088
摘要： Objects within two-dimensional (2D) video data are modeled by three-dimensional (3D) models as a function of object type and motion through manually calibrating a 2D image to the three spatial dimensions of a 3D modeling cube. Calibrated 3D locations of an object in motion in the 2D image field of view of a video data input are computed and used to determine a heading direction of the object as a function of the camera calibration and determined movement between the computed 3D locations. The 2D object image is replaced in the video data input with an object-type 3D polygonal model having a projected bounding box that best matches a bounding box of an image blob, the model oriented in the determined heading direction. The bounding box of the replacing model is then scaled to fit the object image blob bounding box, and rendered with extracted image features.
摘要翻译： 二维（2D）视频数据中的对象通过三维（3D）模型建模，作为对象类型和运动的函数，通过手动校准2D图像到3D建模立方体的三个空间维度。 计算视频数据输入的2D图像视场中的运动对象的校准3D位置，并用于根据相机校准和所计算的3D位置之间确定的运动来确定对象的航向方向。 2D对象图像被替换为具有对象型3D多边形模型的视频数据输入，该模型具有最佳匹配图像斑点的边界框的投影边界框，该模型在确定的方位方向上定向。 然后将替换模型的边界框缩放以适合对象图像Blob边界框，并使用提取的图像特征进行渲染。
-
公开(公告)号：US20120314030A1
公开(公告)日：2012-12-13
申请号：US13154843
申请日：2011-06-07
申请人： Ankur Datta , Rogerio S. Feris , Yun Zhai
发明人： Ankur Datta , Rogerio S. Feris , Yun Zhai
IPC分类号： H04N13/00
CPC分类号： G06T17/10 , G06K9/00711 , G06K9/00771 , G06K9/46 , G06K9/4604 , G06K9/52 , G06K2009/4666 , G06T3/20 , G06T3/40 , G06T7/20 , G06T7/251 , G06T7/62 , G06T7/75 , G06T15/205 , G06T19/20 , G06T2200/24 , G06T2207/10016 , G06T2207/30232 , G06T2207/30236 , G06T2219/2004 , G06T2219/2016 , H04N13/264 , H04N13/293 , H04N2013/0088
摘要： Objects within two-dimensional (2D) video data are modeled by three-dimensional (3D) models as a function of object type and motion through manually calibrating a 2D image to the three spatial dimensions of a 3D modeling cube. Calibrated 3D locations of an object in motion in the 2D image field of view of a video data input are computed and used to determine a heading direction of the object as a function of the camera calibration and determined movement between the computed 3D locations. The 2D object image is replaced in the video data input with an object-type 3D polygonal model having a projected bounding box that best matches a bounding box of an image blob, the model oriented in the determined heading direction. The bounding box of the replacing model is then scaled to fit the object image blob bounding box, and rendered with extracted image features.
摘要翻译： 二维（2D）视频数据中的对象通过三维（3D）模型建模，作为对象类型和运动的函数，通过手动校准2D图像到3D建模立方体的三个空间维度。 计算视频数据输入的2D图像视场中的运动对象的校准3D位置，并用于根据相机校准和所计算的3D位置之间的确定的运动来确定对象的方位方向。 2D对象图像被替换为具有对象型3D多边形模型的视频数据输入，该模型具有最佳匹配图像斑点的边界框的投影边界框，该模型在确定的方位方向上定向。 然后将替换模型的边界框缩放以适合对象图像Blob边界框，并使用提取的图像特征进行渲染。
-
公开(公告)号：US08620026B2
公开(公告)日：2013-12-31
申请号：US13085547
申请日：2011-04-13
IPC分类号： G06K9/00
CPC分类号： G06K9/4604 , G06K9/00751
摘要： Training data object images are clustered as a function of motion direction attributes and resized from respective original into same aspect ratios. Motionlet detectors are learned for each of the sets from features extracted from the resized object blobs. A deformable sliding window is applied to detect an object blob in input by varying window size, shape or aspect ratio to conform to a shape of the detected input video object blob. A motion direction of an underlying image patch of the detected input video object blob is extracted and motionlet detectors selected and applied that have similar motion directions. An object is thus detected within the detected blob and semantic attributes of an underlying image patch extracted if a motionlet detectors fires, the extracted semantic attributes available for use for searching for the detected object.
摘要翻译： 训练数据对象图像作为运动方向属性的函数进行聚类，并从相应的原始尺寸变为相同的宽高比。 通过从调整大小的对象斑点中提取的特征，为每个集合学习运动检测器。 应用可变形滑动窗口通过改变窗口尺寸，形状或宽高比来检测输入中的对象斑点，以符合检测到的输入视频对象斑点的形状。 提取检测到的输入视频对象斑点的底层图像块的运动方向，并选择并应用具有相似运动方向的运动检测器。 因此，如果移动检测器触发，则所提取的底层图像块的检测到的blob和语义属性中的对象被检测到，所提取的语义属性可用于搜索检测到的对象。
-
公开(公告)号：US20120263346A1
公开(公告)日：2012-10-18
申请号：US13085547
申请日：2011-04-13
IPC分类号： G06K9/00
CPC分类号： G06K9/4604 , G06K9/00751
摘要： Training data object images are clustered as a function of motion direction attributes and resized from respective original into same aspect ratios. Motionlet detectors are learned for each of the sets from features extracted from the resized object blobs. A deformable sliding window is applied to detect an object blob in input by varying window size, shape or aspect ratio to conform to a shape of the detected input video object blob. A motion direction of an underlying image patch of the detected input video object blob is extracted and motionlet detectors selected and applied that have similar motion directions. An object is thus detected within the detected blob and semantic attributes of an underlying image patch extracted if a motionlet detectors fires, the extracted semantic attributes available for use for searching for the detected object.
摘要翻译： 训练数据对象图像作为运动方向属性的函数进行聚类，并从相应的原始尺寸变为相同的宽高比。 通过从调整大小的对象斑点中提取的特征，为每个集合学习运动检测器。 应用可变形滑动窗口通过改变窗口尺寸，形状或宽高比来检测输入中的对象斑点，以符合检测到的输入视频对象斑点的形状。 提取检测到的输入视频对象斑点的底层图像块的运动方向，并选择并应用具有相似运动方向的运动检测器。 因此，如果移动检测器触发，则所提取的底层图像块的检测到的blob和语义属性中的对象被检测到，所提取的语义属性可用于搜索检测到的对象。
-
公开(公告)号：US20140098989A1
公开(公告)日：2014-04-10
申请号：US13645831
申请日：2012-10-05
IPC分类号： G06K9/00
CPC分类号： G06K9/00778 , G06K9/38 , G06K2209/23 , G06T7/248 , G06T2207/10016 , G06T2207/30236
摘要： Multiple discrete objects within a scene image captured by a single camera track are distinguished as un-labeled from a background model within a first frame of a video data input. Object position and object appearance and/or object size attributes are determined for each of the blobs, and costs determined to assign to existing blobs of existing object tracks as a function of the determined attributes and combined to generate respective combination costs. The un-labeled object blob that has a lowest combined cost of association with any of the existing object tracks is labeled with the label of that track having the lowest combined cost, said track is removed from consideration for labeling remaining un-labeled object blobs, and the process iteratively repeated until each of the track labels have been used to label one of the un-labeled blobs.
摘要翻译： 由单个摄像机轨道拍摄的场景图像内的多个离散对象被区分为视频数据输入的第一帧内的背景模型的未标记。 确定每个斑点的对象位置和对象外观和/或对象大小属性，以及确定为根据所确定的属性分配给现有对象轨道的现有块的成本并组合以生成相应的组合成本。 与任何现有对象轨道具有最低组合成本的未标记对象斑点用具有最低组合成本的该轨道的标签进行标记，所述轨道被从考虑中去除以标记剩余的未标记对象斑点， 并且迭代地重复该过程，直到每个轨道标签已被用于标记未标记的一个斑点。
-
公开(公告)号：US09002060B2
公开(公告)日：2015-04-07
申请号：US13535409
申请日：2012-06-28
CPC分类号： G06K9/00771 , G06K9/00718 , G06K9/00758 , G06K9/6215 , G06K9/6218 , G06K9/6256 , G06K9/6262 , G06K2009/00738
摘要： Automatic object retrieval from input video is based on learned, complementary detectors created for each of a plurality of different motionlet clusters. The motionlet clusters are partitioned from a dataset of training vehicle images as a function of determining that vehicles within each of the scenes of the images in each cluster share similar two-dimensional motion direction attributes within their scenes. To train the complementary detectors, a first detector is trained on motion blobs of vehicle objects detected and collected within each of the training dataset vehicle images within the motionlet cluster via a background modeling process; a second detector is trained on each of the training dataset vehicle images within the motionlet cluster that have motion blobs of the vehicle objects but are misclassified by the first detector; and the training repeats until all of the training dataset vehicle images have been eliminated as false positives or correctly classified.
摘要翻译： 从输入视频自动对象检索是基于为多个不同的运动集群中的每一个创建的学习的互补检测器。 作为确定每个群集中的图像的每个场景内的车辆在其场景内共享类似的二维运动方向属性的函数的函数，将运动群集从训练车辆图像的数据集分割。 训练互补检测器，对第一检测器进行训练，以通过背景建模过程在运动组内的每个训练数据集车辆图像内检测和收集的车辆物体的运动斑点进行训练; 对具有车辆对象的运动斑点但由第一检测器错误分类的运动集群内的训练数据集车辆图像上的每一个训练第二检测器; 并且训练重复，直到所有训练数据集车辆图像已被消除为假阳性或正确分类为止。
-
公开(公告)号：US20140003708A1
公开(公告)日：2014-01-02
申请号：US13535409
申请日：2012-06-28
IPC分类号： G06K9/62
CPC分类号： G06K9/00771 , G06K9/00718 , G06K9/00758 , G06K9/6215 , G06K9/6218 , G06K9/6256 , G06K9/6262 , G06K2009/00738
摘要： Automatic object retrieval from input video is based on learned, complementary detectors created for each of a plurality of different motionlet clusters. The motionlet clusters are partitioned from a dataset of training vehicle images as a function of determining that vehicles within each of the scenes of the images in each cluster share similar two-dimensional motion direction attributes within their scenes. To train the complementary detectors, a first detector is trained on motion blobs of vehicle objects detected and collected within each of the training dataset vehicle images within the motionlet cluster via a background modeling process; a second detector is trained on each of the training dataset vehicle images within the motionlet cluster that have motion blobs of the vehicle objects but are misclassified by the first detector; and the training repeats until all of the training dataset vehicle images have been eliminated as false positives or correctly classified.
摘要翻译： 从输入视频自动对象检索是基于为多个不同的运动集群中的每一个创建的学习的互补检测器。 作为确定每个群集中的图像的每个场景内的车辆在其场景内共享类似的二维运动方向属性的函数的函数，将运动群集从训练车辆图像的数据集分割。 训练互补检测器，对第一检测器进行训练，以通过背景建模过程在运动组内的每个训练数据集车辆图像内检测和收集的车辆物体的运动斑点进行训练; 对具有车辆对象的运动斑点但由第一检测器错误分类的运动集群内的训练数据集车辆图像上的每一个训练第二检测器; 并且训练重复，直到所有训练数据集车辆图像已被消除为假阳性或正确分类为止。
-
公开(公告)号：US08917934B2
公开(公告)日：2014-12-23
申请号：US13523074
申请日：2012-06-14
CPC分类号： G06T7/11 , G06K9/00536 , G06K9/00785 , G06K9/3241 , G06K9/38 , G06K9/4642 , G06T7/13 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20021 , G06T2207/30236
摘要： Foreground objects of interest are distinguished from a background model by dividing a region of interest of a video data image into a grid array of individual cells that are each smaller than that a foreground object of interest. More particularly, image data of the foreground object of interest spans a contiguous plurality of the cells. Each of the cells are labeled as foreground if accumulated edge energy within the cell meets an edge energy threshold, if color intensities for different colors within each cell differ by a color intensity differential threshold, or as a function of combinations of said determinations in view of one or more combination rules.
摘要翻译： 将感兴趣的前景物体与背景模型区分开，将视频数据图像的感兴趣区域划分为各自小于感兴趣的前景对象的各个单元格的网格阵列。 更具体地，感兴趣的前景对象的图像数据跨越连续的多个单元。 如果每个单元内的不同颜色的颜色强度与颜色强度差异阈值相差，或者作为所述确定的组合的函数，则单元格内的累积边缘能量满足边缘能量阈值时，每个单元格被标记为前景 一个或多个组合规则。
-
公开(公告)号：US08903198B2
公开(公告)日：2014-12-02
申请号：US13152615
申请日：2011-06-03
CPC分类号： G06F17/30256 , G06F17/30277 , G06F17/3028 , G06F17/3053 , G06K9/00268 , G06K9/481 , G06K9/6263 , G06K9/66 , G06N99/005
摘要： Images are retrieved and ranked according to relevance to attributes of a multi-attribute query through training image attribute detectors for different attributes annotated in a training dataset. Pair-wise correlations are learned between pairs of the annotated attributes from the training dataset of images. Image datasets may then be searched via the trained attribute detectors for images comprising attributes in a multi-attribute query, wherein images are retrieved from the searching that each comprise one or more of the query attributes and also in response to information from the trained attribute detectors corresponding to attributes that are not a part of the query but are relevant to the query attributes as a function of the learned plurality of pair-wise correlations. The retrieved images are ranked as a function of respective total numbers of attributes within the query subset attributes.
摘要翻译： 根据与训练数据集中注释的不同属性的训练图像属性检测器，根据与多属性查询的属性的相关性来检索和排列图像。 在图像训练数据集的注释属性对之间学习成对相关。 然后可以经由经训练的属性检测器搜索包括多属性查询中的属性的图像的图像数据集，其中从搜索中检索每个包括一个或多个查询属性的图像，并且还响应于来自经训练的属性检测器的信息 对应于不是查询的一部分但与所学习的多个成对相关性的函数的查询属性相关的属性。 检索到的图像根据查询子集属性内的各个属性总数的顺序排列。
-
公开(公告)号：US20130336581A1
公开(公告)日：2013-12-19
申请号：US13523074
申请日：2012-06-14
CPC分类号： G06T7/11 , G06K9/00536 , G06K9/00785 , G06K9/3241 , G06K9/38 , G06K9/4642 , G06T7/13 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20021 , G06T2207/30236
摘要： Foreground objects of interest are distinguished from a background model by dividing a region of interest of a video data image into a grid array of individual cells that are each smaller than that a foreground object of interest. More particularly, image data of the foreground object of interest spans a contiguous plurality of the cells. Each of the cells are labeled as foreground if accumulated edge energy within the cell meets an edge energy threshold, if color intensities for different colors within each cell differ by a color intensity differential threshold, or as a function of combinations of said determinations in view of one or more combination rules.
摘要翻译： 将感兴趣的前景物体与背景模型区分开，将视频数据图像的感兴趣区域划分为各自小于感兴趣的前景对象的各个单元格的网格阵列。 更具体地，感兴趣的前景对象的图像数据跨越连续的多个单元。 如果每个单元内的不同颜色的颜色强度与颜色强度差异阈值相差，或者作为所述确定的组合的函数，则单元格内的累积边缘能量满足边缘能量阈值时，每个单元格被标记为前景 一个或多个组合规则。
-
-
-
-
-
-
-
-
-
搜索结果
48 条记录 (耗时 0.021 秒)
