用深度学习提升视觉回环检测，让机器人更准地认路。
Loop Closure using AnyLoc Visual Place Recognition in DPV-SLAM
- 用AnyLoc替代传统特征词袋，提升跨视角和光照的识别能力。
- 在室内外数据集上，回环检测准确率显著优于原DPV-SLAM。
- 自适应阈值机制无需手动调参，适合实际部署场景。
回环检测对维持视觉SLAM的精度与一致性至关重要。本文提出一种改进DPV-SLAM回环检测性能的方法，将基于学习的视觉场景识别技术AnyLoc作为经典词袋视觉单词（BoVW）检测方法的替代方案。与依赖人工设计特征的BoVW不同，AnyLoc利用深层特征表示，可在不同视角和光照条件下实现更鲁棒的图像检索。此外，我们提出一种自适应机制，根据环境条件动态调整相似性阈值，避免了人工调参。在室内外数据集上的实验表明，该方法在回环检测的准确性和鲁棒性方面均显著优于原始DPV-SLAM。所提方法为现代SLAM系统中的回环检测提供了实用且可扩展的解决方案。
原文摘要 · Abstract (English)
Loop closure is crucial for maintaining the accuracy and consistency of visual SLAM. We propose a method to improve loop closure performance in DPV-SLAM. Our approach integrates AnyLoc, a learning-based visual place recognition technique, as a replacement for the classical Bag of Visual Words (BoVW) loop detection method. In contrast to BoVW, which relies on handcrafted features, AnyLoc utilizes deep feature representations, enabling more robust image retrieval across diverse viewpoints and lighting conditions. Furthermore, we propose an adaptive mechanism that dynamically adjusts similarity threshold based on environmental conditions, removing the need for manual tuning. Experiments on both indoor and outdoor datasets demonstrate that our method significantly outperforms the original DPV-SLAM in terms of loop closure accuracy and robustness. The proposed method offers a practical and scalable solution for enhancing loop closure performance in modern SLAM systems.
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。