Systems and methods for 3D image distification
摘要
說明書
At block 308, the computing device generates an output feature vector that includes the horizontal coordinate and the vertical coordinate of at least one of the points in the 2D matrix. The output feature vector can be represented, for example, in any number of data structures in computer memory, such as the memories(s) of the computing devices of
In some embodiments, the output feature vector may associate a depth coordinate (e.g., a z-value) of a 3D point in the 3D point cloud of the 3D image with the horizontal and vertical coordinates of the 2D matrix point in the output feature vector. In some embodiments, the chosen 3D point can have the nearest horizontal and vertical coordinate pair in a 2D-axis with respect to the horizontal and vertical coordinates of the 2D matrix point. In such an embodiment, the output feature vector may also generate and associate a distance value with the 2D matrix point based on the distance from the 2D matrix point to the chosen 3D point. In some embodiments, the distance value can be the Euclidean distance (i.e., straight-line or ordinary) distance between two points in 3D space. Other distance values can be determined by different distancing techniques, such as the Chebyshev distance, the Manhattan distance, etc.
