HBRB-BoW: 一种通过分层BRB-KMeans重新训练的ORB-SLAM视觉词汇
HBRB-BoW: A Retrained Bag-of-Words Vocabulary for ORB-SLAM via Hierarchical BRB-KMeans
AI总结：
HBRB-BoW通过分层BRB-KMeans改进ORB-SLAM的视觉词汇，提升复杂环境下的表示完整性与定位性能。
摘要：
在视觉同时定位与建图（SLAM）中，视觉词汇的质量对于系统表示环境和识别位置的能力至关重要。虽然ORB-SLAM是一个广泛使用的框架，但其二进制词汇，通过基于k-多数的bag-of-words（BoW）方法训练，会受到固有精度损失的影响。传统二进制聚类无法表示细微的特征分布，导致视觉词汇退化，这一问题在错误积累并通过分层树结构传播时更加严重。为了解决这些结构缺陷，本文提出了一种改进的分层二进制到实数再返回（HBRB）-BoW方法，即一种精炼的分层二进制词汇训练算法。通过在分层聚类过程中整合一个全局实值流，我们的方法在最终的叶节点二值化之前保留高保真的描述符信息。实验结果表明，所提出的方法比传统方法产生了更具判别力和结构更合理的词汇，显著增强了复杂环境中的视觉词典的表示完整性。此外，用我们的HBRB-BoW文件替换默认的ORB-SLAM词汇文件，预计能提高回环闭合和重定位任务的性能。
英文摘要：
In visual simultaneous localization and mapping (SLAM), the quality of the visual vocabulary is fundamental to the system's ability to represent environments and recognize locations. While ORB-SLAM is a widely used framework, its binary vocabulary, trained through the k-majority-based bag-of-words (BoW) approach, suffers from inherent precision loss. The inability of conventional binary clustering to represent subtle feature distributions leads to the degradation of visual words, a problem that is compounded as errors accumulate and propagate through the hierarchical tree structure. To address these structural deficiencies, this paper proposes hierarchical binary-to-real-and-back (HBRB)-BoW, a refined hierarchical binary vocabulary training algorithm. By integrating a global real-valued flow within the hierarchical clustering process, our method preserves high-fidelity descriptor information until the final binarization at the leaf nodes. Experimental results demonstrate that the proposed approach yields a more discriminative and well-structured vocabulary than traditional methods, significantly enhancing the representational integrity of the visual dictionary in complex environments. Furthermore, replacing the default ORB-SLAM vocabulary file with our HBRB-BoW file is expected to improve performance in loop closing and relocalization tasks.
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。
