Visual reconstruction of ground plane obstacles in a sparse view robot environment

The purpose of this study is to investigate a geometric/level set method to locate ground plane objects in a robot environment and reconstruct their structure from a collection of sparse views. In a first step, a model of the ground plane surface, on which the robot is operating, is obtained through the matching of the available views. This wide-baseline matching of the ground plane views allows also to compute camera pose information associated with each of these views. Based on the information obtained, reconstruction of the obstacles proceeds by minimizing an energy functional containing three terms: a term of shape-from-silhouettes consistency to characterize the ground plane objects structure and to account for possibly non-textured object surfaces; a term of visual information consistency to measure the conformity of the objects surface visual information to the acquired images; and finally, a term of regularization to bias the solution toward smooth object surfaces. The functional is minimized following the associated Euler–Lagrange surface evolution descent equations, implemented via level set PDEs to allow changes in topology while ensuring numerical stability. We provide examples of verification of the scheme on real data.