DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network
This work addresses odometry for localization in point cloud-based systems, representing an incremental advance by applying deep learning to a domain where it has not been well explored.
The authors tackled point cloud odometry (PCO) by proposing DeepPCO, an end-to-end deep parallel neural network that estimates 6-DOF poses from consecutive point clouds, achieving good pose accuracy on the KITTI benchmark dataset.
Odometry is of key importance for localization in the absence of a map. There is considerable work in the area of visual odometry (VO), and recent advances in deep learning have brought novel approaches to VO, which directly learn salient features from raw images. These learning-based approaches have led to more accurate and robust VO systems. However, they have not been well applied to point cloud data yet. In this work, we investigate how to exploit deep learning to estimate point cloud odometry (PCO), which may serve as a critical component in point cloud-based downstream tasks or learning-based systems. Specifically, we propose a novel end-to-end deep parallel neural network called DeepPCO, which can estimate the 6-DOF poses using consecutive point clouds. It consists of two parallel sub-networks to estimate 3-D translation and orientation respectively rather than a single neural network. We validate our approach on KITTI Visual Odometry/SLAM benchmark dataset with different baselines. Experiments demonstrate that the proposed approach achieves good performance in terms of pose accuracy.