MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints

• URL: http://arxiv.org/abs/2109.06768v2
• Date: Wed, 15 Sep 2021 07:58:20 GMT
• Title: MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints
• Authors: Cong Wang, Yu-Ping Wang, Dinesh Manocha
• Abstract summary: We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) Our MotionHint algorithm can be easily applied to existing open-sourced state-of-the-art SSM-VO systems.
• Score: 70.76761166614511
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) that takes motion constraints into account. A key aspect of our approach is to use an appropriate motion model that can help existing self-supervised monocular VO (SSM-VO) algorithms to overcome issues related to the local minima within their self-supervised loss functions. The motion model is expressed with a neural network named PPnet. It is trained to coarsely predict the next pose of the camera and the uncertainty of this prediction. Our self-supervised approach combines the original loss and the motion loss, which is the weighted difference between the prediction and the generated ego-motion. Taking two existing SSM-VO systems as our baseline, we evaluate our MotionHint algorithm on the standard KITTI benchmark. Experimental results show that our MotionHint algorithm can be easily applied to existing open-sourced state-of-the-art SSM-VO systems to greatly improve the performance by reducing the resulting ATE by up to 28.73%.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.