Dynamic feature detection using virtual correction and camera oscillations

Visual SLAM algorithms exploit natural scene features to infer the camera motion and build a map of a static environment. In this paper, we relax the severe assumption of a static scene to allow for the detection and deletion of dynamic points. A new "virtual correction" method is introduced which serves to detect the dynamic points by checking the re-projection error of the points before and after the virtual measurement update. It can also recover the erroneously excluded useful features, particularly the distant points which may be deleted because of the change in its position after new measurement observation. Deliberate camera oscillations are also used to improve the VSLAM accuracy and the camera observability. The simulation results showed the effectiveness of the virtual correction when combined with camera oscillation in recovering the misclassified features and detecting the dynamic features even in difficult scenarios.