融合直接法与特征法，实现低速自动驾驶的快速高精度定位
HS-SLAM: A Fast and Hybrid Strategy-Based SLAM Approach for Low-Speed Autonomous Driving
- 通过IMU预估帧间位姿，再用多层直接法逐级优化
- 在EuRoC数据集上定位精度高于ORB-SLAM3，追踪效率提升15%
- 仅对关键帧提取描述子，显著加速处理流程
视觉惯性同时定位与地图构建（SLAM）是机器人及低速自动驾驶的核心模块，但常受限于高计算负担。为此，本文提出一种基于策略的混合框架HS-SLAM，融合直接法与特征法的优势，实现快速计算且不降低性能。首先在跟踪线程中利用IMU姿态估计连续帧间的相对位置；随后通过多层直接法，从粗到精逐步校正相对位姿，最终实现基于角点的特征匹配。该方法替代传统恒速追踪模型。通过有选择地跳过非关键帧的描述子提取，显著提升追踪速度。在EuRoC MAV数据集上的实验表明，HS-SLAM在定位精度上优于ORB-SLAM3，平均追踪效率提升15%。
原文摘要 · Abstract (English)
Visual-inertial simultaneous localization and mapping (SLAM) is a key module of robotics and low-speed autonomous vehicles, which is usually limited by the high computation burden for practical applications. To this end, an innovative strategy-based hybrid framework HS-SLAM is proposed to integrate the advantages of direct and feature-based methods for fast computation without decreasing the performance. It first estimates the relative positions of consecutive frames using IMU pose estimation within the tracking thread. Then, it refines these estimates through a multi-layer direct method, which progressively corrects the relative pose from coarse to fine, ultimately achieving accurate corner-based feature matching. This approach serves as an alternative to the conventional constant-velocity tracking model. By selectively bypassing descriptor extraction for non-critical frames, HS-SLAM significantly improves the tracking speed. Experimental evaluations on the EuRoC MAV dataset demonstrate that HS-SLAM achieves higher localization accuracies than ORB-SLAM3 while improving the average tracking efficiency by 15%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。