Vulnerable underground entrance understanding for visual surveillance systems

Abstract

Protecting critical infrastructure through visual surveillance is of vital importance, especially in underground entrance environments where large chunks of sloping glass ceilings are particularly susceptible to various types of terrorist activity. However, owing to the diversity of underground entrance environments, understanding them remains a challenge. Traditional 3D layout and object pose estimation that are evaluated on 3D point clouds or RGB-D data are energy-consuming and difficult to account for semantic information in environments. In this study, we present a methodology to understand underground entrance environments, and to recover their 3D reconstruction from a monocular camera. Clusters of sloping angle projections are extracted. Through their corresponding vanishing points (VPs), surfaces of sloping structures are estimated. Relative geometric constraints of different planes are built to bridge the gap between 2D sloping surfaces and 3D reconstruction without precise depth or point clouds. An underground entrance scene is approximated by Manhattan and sloping non-Manhattan structures in 3D reconstruction. The approach requires no prior training, and it requires neither the camera being calibrated nor the camera internal parameters being constant. Compared to the ground truth, the percentage of incorrectly understood pixels were measured and the results demonstrated that the method can successfully understand underground entrance scenes, meeting the requirements in safety monitoring for critical infrastructures from a resource-constrained surveillance camera.