专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US07061485B2 Method and system for producing a model from optical images 有权
标题翻译：从光学图像生成模型的方法和系统
公开(公告)号：US07061485B2
公开(公告)日：2006-06-13
申请号：US10684067
申请日：2003-10-09
申请人： Donald O. Tanguay, Jr. , W. Bruce Culbertson , Daniel G. Gelb , Michael Harville
发明人： Donald O. Tanguay, Jr. , W. Bruce Culbertson , Daniel G. Gelb , Michael Harville
IPC分类号： G06T15/00
CPC分类号： G06F15/7867 , G06Q40/08
摘要： Disclosed is a method for producing a model of an object, comprising receiving at least one image of the object in a computing device, processing one or more of the at least one image to produce a model of the object, generating feedback information corresponding to the model of the object, and imparting the feedback information to a user of the computing device concurrently with the processing such that a determination is enabled to be made whether the model of the object is of a desired quality while the computing device is disposed to receive a further image of the object. The feedback information can be an image of the model which enables a user to determine whether an additional image is necessary or the feedback information can be direction to acquire an additional image of the object.
摘要翻译：公开了一种用于产生对象的模型的方法，包括：在计算设备中接收所述对象的至少一个图像，处理所述至少一个图像中的一个或多个以产生所述对象的模型，生成与所述对象相对应的反馈信息并且将所述反馈信息与所述处理同时地发送给所述计算装置的用户，使得能够确定所述对象的模型是否具有期望的质量，同时所述计算装置被设置为接收所述对象对象的进一步图像。反馈信息可以是模型的图像，其使得用户能够确定是否需要附加图像，或者反馈信息可以是获取对象的附加图像的方向。

22. 发明授权

US06373487B1 Methods and apparatus for constructing a 3D model of a scene from calibrated images of the scene 失效
标题翻译：用于从场景的校准图像构建场景的3D模型的方法和装置
公开(公告)号：US06373487B1
公开(公告)日：2002-04-16
申请号：US09398489
申请日：1999-09-17
申请人： W. Bruce Culbertson , Thomas Malzbender
发明人： W. Bruce Culbertson , Thomas Malzbender
IPC分类号： G06T1700
CPC分类号： G06T17/00
摘要： Methods and apparatus are provided for volumemetric scene reconstruction. Given a set of images of the scene taken from arbitrary but known locations, a 3D model of the scene is reconstructed. Voxels are used to model the scene and exploit the fact that surface points in the scene, and the voxels that represent them, project to consistent colors in the input images. Input cameras may be placed at arbitrary locations in and around the scene. When checking the color consistency of a voxel, the entire set of images from which the voxel is visible is used. A GVC algorithm utilizes item buffers which contain, for each pixel in each image, the ID of the closest voxel that projects onto to the pixel. A GVC-LDI algorithm uses layered depth images which store at each pixel location a list of all the surface voxels that project onto the pixel, sorted according to the distance of the voxel from the image's camera.
摘要翻译：提供了用于体积现场重建的方法和装置。给定一组从任意但已知位置拍摄的场景的图像，重建场景的3D模型。体素被用于对场景进行建模，并利用场景中的表面点和表示它们的体素在输入图像中投射到一致的颜色的事实。输入摄像机可以放置在场景中和周围的任意位置。当检查体素的颜色一致性时，使用体素体内可见的整组图像。 GVC算法使用项目缓冲器，其对于每个图像中的每个像素包含投影到像素的最接近的体素的ID。 GVC-LDI算法使用分层深度图像，其在每个像素位置处存储投影到像素上的所有表面体素的列表，根据体素与图像相机的距离进行排序。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式