Pixel-wise motion segmentation for SLAM in dynamic environments

Abstract

Visual simultaneous localization and mapping (SLAM) is a key prerequisite for many mobilerobotic systems. A common assumption for SLAM methods is a static environment. The interference ofdynamic objects can lead to impairment of the camera pose tracking and permanent distortions of the map.This limits the use of many visual SLAM systems in real world scenarios, where dynamic environmentsare typical. We present a novel method for pixel-wise segmentation of dynamic image sequences based ona scene flow model estimation. We detect and eliminate outlying pixels sparsely by evaluating each pixelmotion separately and maintain the most possible area of static scene background for SLAM. The evaluationwith the public TUM dataset demonstrates that our proposed method outperforms other comparable state-of-the-art approaches for dynamic removal for SLAM systems.