-
1.发明申请公开(公告)号：US20120275702A1
公开(公告)日：2012-11-01
申请号：US13097551
申请日：2011-04-29
IPC分类号： G06K9/34
CPC分类号： G06T7/162 , G06T7/11 , G06T2207/10004
摘要： An image is segmented into superpixels by constructing a graph with vertices connected by edges, wherein each vertex corresponds to a pixel in the image, and each edge is associated with a weight indicating a similarity of the corresponding pixels, A subset of edges in the graph are selected to segment the graph into subgraphs, wherein the selecting maximizes an objective function based on an entropy rate and a balancing term. The edges with maximum gains are added to the graph until a number of subgraphs is equal to some threshold.
摘要翻译： 通过构造具有由边缘连接的顶点的图形将图像分割成超像素，其中每个顶点对应于图像中的像素，并且每个边缘与指示相应像素的相似度的权重相关联。图中的边缘子集 被选择为将图形分割为子图，其中所述选择基于熵速率和平衡项来最大化目标函数。 具有最大增益的边缘被添加到图形中，直到一些子图等于某个阈值。
-
2.发明授权公开(公告)号：US08428363B2
公开(公告)日：2013-04-23
申请号：US13097551
申请日：2011-04-29
IPC分类号： G06K9/48
CPC分类号： G06T7/162 , G06T7/11 , G06T2207/10004
摘要： An image is segmented into superpixels by constructing a graph with vertices connected by edges, wherein each vertex corresponds to a pixel in the image, and each edge is associated with a weight indicating a similarity of the corresponding pixels, A subset of edges in the graph are selected to segment the graph into subgraphs, wherein the selecting maximizes an objective function based on an entropy rate and a balancing term. The edges with maximum gains are added to the graph until a number of subgraphs is equal to some threshold.
摘要翻译： 通过构造具有由边缘连接的顶点的图形将图像分割成超像素，其中每个顶点对应于图像中的像素，并且每个边缘与指示相应像素的相似度的权重相关联。图中的边缘的子集 被选择为将图形分割为子图，其中所述选择基于熵速率和平衡项来最大化目标函数。 具有最大增益的边缘被添加到图形中，直到一些子图等于某个阈值。
-
公开(公告)号：US08165403B1
公开(公告)日：2012-04-24
申请号：US12950357
申请日：2010-11-19
申请人： Srikumar Ramalingam , Ashok Veeraraghavan , Yuichi Taguchi , Cuneyt Oncel Tuzel , Nitesh Shroff
发明人： Srikumar Ramalingam , Ashok Veeraraghavan , Yuichi Taguchi , Cuneyt Oncel Tuzel , Nitesh Shroff
CPC分类号： G06T7/75 , G06T2207/10152 , G06T2207/30164
摘要： A pose of an object is determine by acquiring sets of images of the object by a camera, wherein the object has a thread arranged on a surface such that a local region of the object appears substantially spherical, wherein the camera is at a different point of view for each set, and wherein each image in each set is acquired while the scene is illuminated from a different direction. A set of features is extracted from each image, wherein the features correspond to points on the surface having normals towards the camera. A parametric line is fitted to the points for each image, wherein the line lies on a plane joining a center of the camera and an axis of the object. Then, geometric constraints are applied to lines to determine the pose of the object.
摘要翻译： 通过摄像机获取物体的图像来确定物体的姿态，其中物体具有布置在表面上的线，使得物体的局部区域基本上呈球形，其中照相机处于不同点 并且其中当从不同方向照亮场景时获取每组中的每个图像。 从每个图像提取一组特征，其中特征对应于具有朝向相机的法线的表面上的点。 参数线适合于每个图像的点，其中线位于连接照相机的中心和物体轴线的平面上。 然后，将几何约束应用于线以确定对象的姿态。
-
公开(公告)号：US11282180B1
公开(公告)日：2022-03-22
申请号：US16857221
申请日：2020-04-24
摘要： A method includes determining a detection output that represents an object in a two-dimensional image using a detection model, wherein the detection output includes a shape definition that describes a shape and size of the object; defining a three-dimensional representation based on the shape definition, wherein the three-dimensional representation includes a three-dimensional model that represents the object that is placed in three-dimensional space according to a position and a rotation; determining a three-dimensional detection loss that describes a difference between the three-dimensional representation and three-dimensional sensor information; and updating the detection model based on the three-dimensional detection loss.
-
公开(公告)号：US10984272B1
公开(公告)日：2021-04-20
申请号：US16241011
申请日：2019-01-07
摘要： A neural network is trained to defend against adversarial attacks, such as by preparing an input image for classification by a neural network where the input image includes a noise-based perturbation. The input image is divided into source patches. Replacement patches are selected for the source patches by searching a patch library for candidate patches available for replacing ones of those source patches, such as based on sizes of those source patches. A denoised image reconstructed from a number of replacement patches is then output to the neural network for classification. The denoised image may be produced based on reconstruction errors determined for individual candidate patches identified from the patch library. Alternatively, the denoised image may be selected from amongst a number of candidate denoised images. A set of training images is used to construct the patch library, such as based on salient data within patches of those training images.
-
6.发明授权Method for clustering samples with weakly supervised kernel mean shift matrices 有权用弱监督核平均移位矩阵聚类样本的方法公开(公告)号：US08296248B2
公开(公告)日：2012-10-23
申请号：US12495614
申请日：2009-06-30
申请人： Cuneyt Oncel Tuzel , Fatih Porikli
发明人： Cuneyt Oncel Tuzel , Fatih Porikli
IPC分类号： G06F15/18
CPC分类号： G06K9/6226 , G06N99/005
摘要： A method clusters samples using a mean shift procedure. A kernel matrix is determined from the samples in a first dimension. A constraint matrix and a scaling matrix are determined from a constraint set. The kernel matrix is projected to a feature space having a second dimension using the constraint matrix, wherein the second dimension is higher than the first dimension. Then, the samples are clustered according to the kernel matrix.
摘要翻译： 方法使用平均偏移程序聚类样本。 从第一维度的样本确定核心矩阵。 从约束集确定约束矩阵和缩放矩阵。 使用约束矩阵将核心矩阵投影到具有第二维度的特征空间，其中第二维度高于第一维度。 然后，根据核心矩阵对样本进行聚类。
-
公开(公告)号：US20120053944A1
公开(公告)日：2012-03-01
申请号：US12872054
申请日：2010-08-31
CPC分类号： G10L15/14 , G06K9/00429 , G06K9/6297
摘要： A compressed state sequence s is determined directly from the input sequence of data x. A deterministic function ƒ(x) only tracks unique state transitions, and not the dwell times in each state. A polynomial time compressed state sequence inference method outperforms conventional compressed state sequence inference techniques.
摘要翻译： 直接从数据x的输入序列确定压缩状态序列。 确定性函数ƒ（x）仅跟踪唯一的状态转换，而不是每个状态下的停留时间。 多项式时间压缩状态序列推理方法优于传统的压缩状态序列推理技术。
-
公开(公告)号：US11080562B1
公开(公告)日：2021-08-03
申请号：US16441167
申请日：2019-06-14
申请人： Shreyas Saxena , Wenda Wang , Guanhang Wu , Nitish Srivastava , Dimitrios Kottas , Cuneyt Oncel Tuzel , Luciano Spinello , Ricardo da Silveira Cabral
发明人： Shreyas Saxena , Wenda Wang , Guanhang Wu , Nitish Srivastava , Dimitrios Kottas , Cuneyt Oncel Tuzel , Luciano Spinello , Ricardo da Silveira Cabral
摘要： A method includes obtaining training samples that include images that depict objects and annotations of annotated key point locations for the objects. The method also includes training a machine learning model to determine estimated key point locations for the objects and key point uncertainty values for the estimated key point locations by minimizing a loss function that is based in part on a key point localization loss value that represents a difference between the annotated key point locations and the estimated key point locations values and is weighted by the key point uncertainty values.
-
公开(公告)号：US08306314B2
公开(公告)日：2012-11-06
申请号：US12648190
申请日：2009-12-28
CPC分类号： G06T1/00 , G06T7/586 , G06T7/74 , G06T15/20 , G06T2207/10152 , G06T2207/30164
摘要： A pose for an object in a scene is determined by first rendering sets of virtual images of a model of the object using a virtual camera. Each set of virtual images is for a different known pose the model, and constructing virtual depth edge map from each virtual image, which are stored in a database. A set of real images of the object at an unknown pose are acquired by a real camera, and constructing real depth edge map for each real image. The real depth edge maps are compared with the virtual depth edge maps using a cost function to determine the known pose that best matches the unknown pose, wherein the matching is based on locations and orientations of pixels in the depth edge maps.
摘要翻译： 通过使用虚拟相机首先渲染对象的模型的虚拟图像集来确定场景中的对象的姿势。 每组虚拟图像是针对不同的已知姿态的模型，并且构建存储在数据库中的每个虚拟图像的虚拟深度边缘图。 通过真实摄像机获取未知姿态的对象的一组真实图像，并为每个真实图像构建真实的深度边缘图。 使用成本函数将真实深度边缘图与虚拟深度边缘图进行比较，以确定与未知姿势最佳匹配的已知姿势，其中匹配基于深度边缘图中的像素的位置和取向。
-
公开(公告)号：US08405531B2
公开(公告)日：2013-03-26
申请号：US12872054
申请日：2010-08-31
CPC分类号： G10L15/14 , G06K9/00429 , G06K9/6297
摘要： A compressed state sequence s is determined directly from the input sequence of data x. A deterministic function ƒ(x) only tracks unique state transitions, and not the dwell times in each state. A polynomial time compressed state sequence inference method outperforms conventional compressed state sequence inference techniques.
摘要翻译： 直接从数据x的输入序列确定压缩状态序列。 确定性函数ƒ（x）仅跟踪唯一的状态转换，而不是每个状态下的停留时间。 多项式时间压缩状态序列推理方法优于传统的压缩状态序列推理技术。
-
-
-
-
-
-
-
-
-
搜索结果
18 条记录 (耗时 0.021 秒)
