Method and system for reconstructing scene as three-dimensional (3D) model

• Main Author: RAMALINGAM SRIKUMAR
• Format: Patent
• Language: Chinese; English
• Published: 28.09.2018
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

A method reconstructs a scene as a three-dimensional (3D) model by first acquiring a sequence of images of the scene with a camera. Then, feature point matches or line matches are extracted from the sequence of images, variables for camera optical centers and 3D points are initialized using random values, and n copies of the variables are made depending on an availability of n constraints. The n copies are projected to satisfy each of the n constraints. Then, the n copies are replaced with averages of the copies and the projecting and the replacing are repeated until convergence to provide the3D model. 种方法通过首先用摄像头获取场景的系列图像来将场景重建为三维(3D)模型。然后，从该系列图像提取特征点匹配或线匹配；使用随机值初始化针对摄像头光学中心和3D点的变量，并且根据n个约束的可用性形成所述变量的n个副本。投影n个副本来满足n个约束中的每个约束。然后，用副本的平均来替换n个副本；并且重复投影和替换，直到收敛，以提供3D模型。