TY - CONF ID - moreno2013erode T1 - ERODE: An Efficient and Robust Outlier Detector and its Application to Stereovisual Odometry A1 - Moreno, Francisco-Angel A1 - Blanco, José-Luis A1 - Gonzalez-Jimenez, Javier TI - IEEE International Conference on Robotics and Automation (ICRA) Y1 - 2013 SP - 4676 EP - 4682 PB - IEEE CY - Karlsruhe SN - 978-1-4673-5641-1 SN - 1050-4729 UR - http://mapir.isa.uma.es/mapirwebsite/index.php/mapir-downloads/papers/211 M2 - doi: 10.1109/ICRA.2013.6631245 N2 - This paper presents ERODE, an efficient outlier detector with a quality similar to that of standard RANSAC but at a fraction of its computational cost. In contrast to RANSAC-based methods which follow a hypothesis-and-verify approach, ERODE employs instead the whole set of observations together with a robust kernel to perform robustified least-squares minimization. Our proposal has important practical applications among computer vision problems, which we demonstrate with stereovisual odometry experiments with both simulated and real data. M1 - http://mapir.isa.uma.es/famoreno/images/papers/erode_thumbnail.png ER -