Abstract: Dynamic environments are challenging for visual SLAM as moving objects can impair camera pose tracking and cause corruptions to be integrated into the map. We propose a method for dense RGB-D SLAM in dynamic environments based on a strategy of static background reconstruction. While most methods employ implicit robust penalizers or outlier filtering techniques in order to handle moving objects, our approach is to simultaneously estimate the camera motion as well as a probabilistic static/dynamic segmentation of the current RGB-D image pair. This segmentation is then used for weighted dense RGB-D fusion to estimate a 3D model of only the static parts of the environment. By leveraging the 3D model for frame-to-model alignment, as well as static/dynamic segmentation, camera motion estimation has reduced overall drift --- as well as being more robust to the presence of dynamics in the scene. We compare the proposed method to related state-of-the-art approaches using both static and dynamic sequences. The proposed method achieves similar performance in static environments and improved accuracy and robustness in dynamic scenes.
Biography: Raluca Scona is a 3rd year PhD student in the EPSRC Robotics and Autonomous Systems Centre for Doctoral Training lead by Heriot-Watt University and the University of Edinburgh. She received her BSc in Artificial Intelligence in 2013 from the University of Edinburgh (First Class Degree) and her MSc in Robotics and Autonomous Systems in 2015 from Heriot-Watt University (Distinction). During the summer of 2017 she was a visiting researched in the Computer Vision Group at the Technical University of Munich. Her interests lie in robust methods for visual pose estimation and simultaneous localisation and mapping (SLAM) through sensor fusion and motion segmentation.