-
公开(公告)号：US09111349B2
公开(公告)日：2015-08-18
申请号：US13328133
申请日：2011-12-16
申请人： Richard Stephan Szeliski , Edward Hsiao , Sudipta Narayan Sinha , Krishnan Ramnath , Charles Lawrence Zitnick, III , Simon John Baker
发明人： Richard Stephan Szeliski , Edward Hsiao , Sudipta Narayan Sinha , Krishnan Ramnath , Charles Lawrence Zitnick, III , Simon John Baker
CPC分类号： G06K9/00214 , G06K9/00785 , G06T7/564 , G06T2207/30236
摘要： The claimed subject matter provides for systems and/or methods for identification of instances of an object of interest in 2D images by creating a database of 3D curve models of each desired instance and comparing an image of an object of interest against such 3D curve models of instances. The present application describes identifying and verifying the make and model of a car from a possibly single image—after the models have been populated with training data of test images of many makes and models of cars. In one embodiment, an identification system may be constructed by generating a 3D curve model by back-projecting edge points onto a visual hull reconstruction from silhouettes of an instance. The system and methods employ chamfer distance and orientation distance provides reasonable verification performance, as well as an appearance model for the taillights of the car to increase the robustness of the system.
摘要翻译： 所要求保护的主题提供用于通过创建每个期望实例的3D曲线模型的数据库来识别2D图像中感兴趣对象的实例的系统和/或方法，并将感兴趣对象的图像与3D图像的3D曲线模型进行比较 实例。 本申请描述了从可能单个图像中识别和验证汽车的品牌和型号 - 在模型已经填充有许多车型和车型的测试图像的训练数据之后。 在一个实施例中，识别系统可以通过通过将边缘点反向投影到实例的轮廓的视觉船体重建上来生成3D曲线模型来构造。 系统和方法采用倒角距离和取向距离提供合理的验证性能，以及汽车尾灯的外观模型，以提高系统的鲁棒性。
-
公开(公告)号：US20130156329A1
公开(公告)日：2013-06-20
申请号：US13328133
申请日：2011-12-16
申请人： Richard Stephan Szeliski , Edward Hsiao , Sudipta Narayan Sinha , Krishnan Ramnath , Charles Lawrence Zitnick, III , Simon John Baker
发明人： Richard Stephan Szeliski , Edward Hsiao , Sudipta Narayan Sinha , Krishnan Ramnath , Charles Lawrence Zitnick, III , Simon John Baker
CPC分类号： G06K9/00214 , G06K9/00785 , G06T7/564 , G06T2207/30236
摘要： The claimed subject matter provides for systems and/or methods for identification of instances of an object of interest in 2D images by creating a database of 3D curve models of each desired instance and comparing an image of an object of interest against such 3D curve models of instances. The present application describes identifying and verifying the make and model of a car from a possibly single image—after the models have been populated with training data of test images of many makes and models of cars. In one embodiment, an identification system may be constructed by generating a 3D curve model by back-projecting edge points onto a visual hull reconstruction from silhouettes of an instance. The system and methods employ chamfer distance and orientation distance provides reasonable verification performance, as well as an appearance model for the taillights of the car to increase the robustness of the system.
摘要翻译： 所要求保护的主题提供用于通过创建每个期望实例的3D曲线模型的数据库来识别2D图像中感兴趣对象的实例的系统和/或方法，并将感兴趣对象的图像与3D图像的3D曲线模型进行比较 实例。 本申请描述了从可能单个图像中识别和验证汽车的品牌和型号 - 在模型已经填充有许多车型和车型的测试图像的训练数据之后。 在一个实施例中，识别系统可以通过通过将边缘点反向投影到实例的轮廓的视觉船体重建上来生成3D曲线模型来构造。 系统和方法采用倒角距离和取向距离提供合理的验证性能，以及汽车尾灯的外观模型，以提高系统的鲁棒性。
-
公开(公告)号：US08837811B2
公开(公告)日：2014-09-16
申请号：US12817216
申请日：2010-06-17
CPC分类号： G06T7/0042 , G06T7/579 , G06T7/73 , G06T2207/10016
摘要： Described is a linear structure from motion technique that is scalable, parallelizable, treats images equally, and is robust to outliers, without requiring intermediate bundle adjustment. Camera rotations for images are estimated using feature point correspondence and vanishing points matched across the images. The camera rotation data is fed into a linear system for structure and translation estimation that removes outliers and provides output data corresponding to structure from motion parameters. The data may be used in further optimization e.g. with a final non-linear optimization stage referred to as bundle adjustment to provide final refined structure from motion parameters.
摘要翻译： 描述了来自运动技术的线性结构，其是可扩展的，可并行化的，平均地对待图像，并且对异常值是鲁棒的，而不需要中间束调整。 图像的相机旋转使用特征点对应和跨图像匹配的消失点进行估计。 相机旋转数据被馈送到用于结构和平移估计的线性系统中，其消除异常值并提供对应于运动参数的结构的输出数据。 数据可以用于进一步的优化，例如 最终的非线性优化阶段被称为束调整，以从运动参数提供最终的精细结构。
-
公开(公告)号：US08933925B2
公开(公告)日：2015-01-13
申请号：US12484909
申请日：2009-06-15
CPC分类号： G06T7/0065 , G06T7/143 , G06T7/536 , G06T7/55 , G06T15/00 , G06T2207/10028 , G06T2207/20072
摘要： Methods, systems, and computer-readable media for reconstruction a three-dimensional scene from a collection of two-dimensional images are provided. A computerized reconstruction system executes computer vision algorithms on the collection of two-dimensional images to identify candidate planes that are used to model visual characteristics of the environment depicted in the two-dimensional images. The computer vision algorithms may minimize an energy function that represents the relationships and similarities among features of the two-dimensional images to assign pixels of the two dimensional images to planes in the three dimensional scene. The three-dimensional scene is navigable and depicts viewpoint transitions between multiple two-dimensional images.
摘要翻译： 提供了用于从二维图像集合重建三维场景的方法，系统和计算机可读介质。 计算机化重建系统对二维图像的收集执行计算机视觉算法，以识别用于对二维图像中描绘的环境的视觉特征进行建模的候选平面。 计算机视觉算法可以最小化表示二维图像的特征之间的关系和相似性的能量函数，以将二维图像的像素分配给三维场景中的平面。 三维场景可导航，并描绘了多维二维图像之间的视点转换。
-
公开(公告)号：US20110311104A1
公开(公告)日：2011-12-22
申请号：US12817216
申请日：2010-06-17
IPC分类号： G06T7/60
CPC分类号： G06T7/0042 , G06T7/579 , G06T7/73 , G06T2207/10016
摘要： Described is a linear structure from motion technique that is scalable, parallelizable, treats images equally, and is robust to outliers, without requiring intermediate bundle adjustment. Camera rotations for images are estimated using feature point correspondence and vanishing points matched across the images. The camera rotation data is fed into a linear system for structure and translation estimation that removes outliers and provides output data corresponding to structure from motion parameters. The data may be used in further optimization e.g. with a final non-linear optimization stage referred to as bundle adjustment to provide final refined structure from motion parameters.
摘要翻译： 描述了来自运动技术的线性结构，其是可扩展的，可并行化的，平均地对待图像，并且对异常值是鲁棒的，而不需要中间束调整。 图像的相机旋转使用特征点对应和跨图像匹配的消失点进行估计。 相机旋转数据被馈送到用于结构和平移估计的线性系统中，其消除异常值并提供对应于运动参数的结构的输出数据。 数据可以用于进一步的优化，例如 最终的非线性优化阶段被称为束调整，以从运动参数提供最终的精细结构。
-
公开(公告)号：US20100315412A1
公开(公告)日：2010-12-16
申请号：US12484909
申请日：2009-06-15
IPC分类号： G06T15/00
CPC分类号： G06T7/0065 , G06T7/143 , G06T7/536 , G06T7/55 , G06T15/00 , G06T2207/10028 , G06T2207/20072
摘要： Methods, systems, and computer-readable media for reconstruction a three-dimensional scene from a collection of two-dimensional images are provided. A computerized reconstruction system executes computer vision algorithms on the collection of two-dimensional images to identify candidate planes that are used to model visual characteristics of the environment depicted in the two-dimensional images. The computer vision algorithms may minimize an energy function that represents the relationships and similarities among features of the two-dimensional images to assign pixels of the two dimensional images to planes in the three dimensional scene. The three-dimensional scene is navigable and depicts viewpoint transitions between multiple two-dimensional images.
摘要翻译： 提供了用于从二维图像集合重建三维场景的方法，系统和计算机可读介质。 计算机化重建系统对二维图像的收集执行计算机视觉算法，以识别用于对二维图像中描绘的环境的视觉特征进行建模的候选平面。 计算机视觉算法可以最小化表示二维图像的特征之间的关系和相似性的能量函数，以将二维图像的像素分配给三维场景中的平面。 三维场景可导航，并描绘了多维二维图像之间的视点转换。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.03 秒)
