Chapter 4.3 - Robust Recognition of Planar Mirrored Walls

Abstract

Buildings consume around 40% of the overall energy in the world. A planar mirror detection problem (PMDP) arises when surveying reflective building surfaces for building energy retrofits. PMDP is also important for collision avoidance when robots navigate close to highly reflective glassy walls. Our approach uses two views from an onboard camera. First, we derive geometric constraints for corresponding real–virtual features across two views. The constraints include (1) the mirror normal as a function of vanishing points of lines connecting the real–virtual feature point pairs and (2) the mirror depth in a closed-form format derived from a mirror plane-induced homography. Based on the geometric constraints, we employ a random sample consensus framework and an affine scale-invariant feature transformed to develop a robust mirror detection algorithm. We have implemented the algorithm and have tested it in both in-lab and field settings. The algorithm achieved an overall detection accuracy rate of 91.0%.