Abstract
Image-to-point cloud registration refers to finding relative transformation between the camera and the reference frame of the 3D point cloud, which is critical for autonomous driving. Recently, a two-stage “frustum point cloud classification + camera pose optimization” pipeline has shown impressive results on this task. This paper focuses on the second stage and reformulates the optimization procedure as a Markov decision process. An initial pose is modified incrementally, sequentially aligning a virtual 3D point observation towards a previous classification solution. We consider such an iterative update process as a reinforcement learning task and, to this end, propose a novel agent (AgentI2P) to conduct decision making. To guide AgentI2P, we employ behaviour cloning (BC) and reinforcement learning (RL) techniques: cloning an expert to learn accurate pose movement and reinforcing an alignment reward to improve the policy further. [We demonstrate the effectiveness and efficiency of our approach on Oxford Robotcar and KITTI datasets. The (RTE, RRE) metrics are (1.34m,1.46∘) on Oxford Robotcar and (3.90m,5.94∘) on KITTI, and the inference time is 60 ms, both achieving state-of-the-art performance]. The source code will be publicly available upon publication of the paper.
Funder
National Natural Science Foundation of China
Natural Science Foundation of Hunan Province of China
Key Basic Research Project of the China Basic Strengthening Program
Subject
General Earth and Planetary Sciences
Reference67 articles.
1. Long-term visual localization revisited;Toft;IEEE Trans. Pattern Anal. Mach. Intell.,2020
2. Fan, B., Yang, Y., Feng, W., Wu, F., Lu, J., and Liu, H. (2022). Seeing through Darkness: Visual Localization at Night via Weakly Supervised Learning of Domain Invariant Features. IEEE Trans. Multimed.
3. Real-time monocular image-based 6-DoF localization;Lim;Int. J. Robot. Res.,2015
4. An Accurate, Robust Visual Odometry and Detail-Preserving Reconstruction System;Gong;IEEE Trans. Multimed.,2020
5. EgoCart: A benchmark dataset for large-scale indoor image-based localization in retail stores;Spera;IEEE Trans. Circuits Syst. Video Technol.,2019
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献