arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.10195cs.RO

BEV-ODOM:利用BEV表示减少单目视觉里程计中的尺度漂移

BEV-ODOM: Reducing Scale Drift in Monocular Visual Odometry with BEV Representation

Zhejiang University(浙江大学)

Yufei Wei, Sha Lu, Fuzhang Han, Rong Xiong, Yue Wang

AI总结:

本文提出BEV-ODOM框架,通过集成PV到BEV编码器、相关性特征提取颈部和CNN-MLP解码器,在无需深度监督下估计三自由度运动,有效减少单目视觉里程计的尺度漂移,并在多个数据集上实现更高精度的运动估计。

摘要:

单目视觉里程计(MVO)在自主导航和机器人领域至关重要,提供了一种低成本且灵活的运动追踪解决方案,但单目设置中固有的尺度模糊性常导致误差随时间累积。本文提出BEV-ODOM,一种利用鸟瞰图(BEV)表示来解决尺度漂移的新型MVO框架。与现有方法不同,BEV-ODOM集成了基于深度的透视图(PV)到BEV编码器、相关性特征提取颈部以及基于CNN-MLP的解码器,使其能够在无需深度监督或复杂优化技术的情况下估计三个自由度的运动。该框架减少了长期序列中的尺度漂移,并在NCLT、Oxford和KITTI等多个数据集上实现了精确的运动估计。结果表明,BEV-ODOM优于当前的MVO方法,展现出更低的尺度漂移和更高的精度。

英文摘要:

Monocular visual odometry (MVO) is vital in autonomous navigation and robotics, providing a cost-effective and flexible motion tracking solution, but the inherent scale ambiguity in monocular setups often leads to cumulative errors over time. In this paper, we present BEV-ODOM, a novel MVO framework leveraging the Bird's Eye View (BEV) Representation to address scale drift. Unlike existing approaches, BEV-ODOM integrates a depth-based perspective-view (PV) to BEV encoder, a correlation feature extraction neck, and a CNN-MLP-based decoder, enabling it to estimate motion across three degrees of freedom without the need for depth supervision or complex optimization techniques. Our framework reduces scale drift in long-term sequences and achieves accurate motion estimation across various datasets, including NCLT, Oxford, and KITTI. The results indicate that BEV-ODOM outperforms current MVO methods, demonstrating reduced scale drift and higher accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑