首页> 外国专利> COMPUTER IMPLEMENTED METHOD AND SYSTEM FOR RETRIEVAL OF MULTI SPECTRAL BRDF PARAMETERS

COMPUTER IMPLEMENTED METHOD AND SYSTEM FOR RETRIEVAL OF MULTI SPECTRAL BRDF PARAMETERS

机译:计算机实现的多光谱BRDF参数反演方法和系统

摘要

In summary the invention relates to a computer implemented method and apparatus for retrieval of multi spectral bidirectional reflectance distribution function, BRDF, parameters by using red-green-blue-depth, RGBD, data. The method comprises the steps of: Capturing (S1) by an RGB-D camera at least one image of one or more objects in a scene, wherein the captured at least one image of the one or more objects comprises RGB-D data including color and geometry information of said objects; Reconstructing (S2) by a processing unit the captured at least one image of the one or more objects to one or more 3D reconstructions by using the RGB-D data; Classifying (S3) by a deep neural network the BRDF of a surface of the one or more objects based on the 3D reconstructions, wherein the deep neural network comprises an input layer, an output layer, and at least one hidden layer between the input layer and the output layer; and Retrieving (S4) the multi spectral BRDF parameters by approximating the classified BRDF by using an iterative optimization method. Due to the present invention, the multi spectral BRDF parameters of objects in specified environments can be retrieved.
机译:总之,本发明涉及一种计算机实现的方法和装置,用于通过使用红-绿-蓝深度RGBD数据检索多光谱双向反射分布函数BRDF参数。该方法包括以下步骤:由RGB-D相机捕捉(S1)场景中一个或多个对象的至少一个图像,其中捕捉的一个或多个对象的至少一个图像包括包括所述对象的颜色和几何信息的RGB-D数据;由处理单元通过使用RGB-D数据将所述一个或多个对象的所捕获的至少一个图像重建(S2)为一个或多个三维重建;通过深度神经网络基于3D重建对一个或多个对象的表面的BRDF进行分类(S3),其中深度神经网络包括输入层、输出层和输入层和输出层之间的至少一个隐藏层;以及通过使用迭代优化方法近似分类的BRDF来检索(S4)多光谱BRDF参数。由于本发明,可以检索特定环境中物体的多光谱BRDF参数。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号