MotionRFCN: Motion Segmentation Using Consecutive Dense Depth Maps

It is important to enable autonomous robots to detect or segment moving objects in dynamic scenes as they must perform collision-free navigation. Motion segmentation from a moving platform is challenging due to the dual motion caused by the background and the moving objects. Existing approaches for motion segmentation either have long multistage pipelines which are inefficient for real-time application or utilize optical flow which is sensitive to environment. In this paper, this challenging task is tackled by constructing spatiotemporal features from two consecutive dense depth maps. Depth maps can be generated either by LiDaR scans data or stereo vision algorithms. The core of the proposed approach is a fully convolutional network with inserted Gated-Recurrent-Units, denoted as MotionRFCN. We also create a publicly available dataset (KITTI-MoSeg) which contains more than 2000 frames with motion annotations. Qualitative and quantitative evaluation of MotionRFCN are presented to demonstrate its state-of-the-art performance on the KITTI dataset. The basic MotionRFCN can run in real time and segment moving objects whether the platform is stationary or moving. To the best of our knowledge, the proposed method is the first to implement motion segmentation with only dense depth maps inputs.