Change Detection in 3D Models Based on Camera Images

Abstract

3D models of the environment are used in numerous robotic applications and should ideally reflect the current state of the world. In this work, we address the problem of quickly finding structural changes between the current state of the world and a given 3D model based only on a small number of images. Our approach finds inconsistencies between pairs of images by reprojecting an image onto another one by passing through the 3D model. Ambiguities about possible inconsistencies resulting from this process are resolved by combining multiple images such that the 3D location of the change can be estimated. A focus of our approach is that it can be executed fast so that the operation on a mobile system becomes possible. We implemented our approach in C++ and thoroughly tested it on an existing dataset for change detection as well as on self recorded images sequences. Our experiments suggest that our method quickly finds changes in the geometry of a scene and can do that fast enough to operate on a typical robot platform.