Loop closure detection (LCD) is an important portion of Simultaneous Localization and Mapping (SLAM) because of its ability to reduce accumulated position errors. In this letter, we propose a novel loop closure detection algorithm named ESA-VLAD. The crucial part of ESA-VLAD is a redesigned network with EfficientNetB0 as backbone for extracting global features, which integrates a second-order attention module in order to effectively learn the correlations between features within the feature map. A trainable Vector of Local Aggregated Descriptors (NetVLAD) is integrated in the last layer of the network to generate a compact and fixed-length global feature. Knowledge distillation strategy is adopted in training of the proposed network to accelerate the training process. For the global features, Hierarchical Navigable Small World (HNSW) is employed to retrieve the loop closure candidate images. In addition, an efficient geometrical consistency check based on local difference binary (LDB) descriptors is designed to verify loop closure matches. Experiments on several public datasets demonstrate that ESA-VLAD can obtain higher recall rates under 100% precision and less processing time per frame compared to other typical and state-of-the-art methods.

中文翻译：

---

ESA-VLAD：基于二阶注意力和 NetVLAD 的用于环路闭合检测的轻量级网络

闭环检测 (LCD) 是同步定位和映射 (SLAM) 的重要组成部分，因为它能够减少累积位置误差。在这封信中，我们提出了一种名为 ESA-VLAD 的新型闭环检测算法。ESA-VLAD 的关键部分是重新设计的网络，以 EfficientNetB0 作为提取全局特征的骨干，它集成了二阶注意力模块，以有效地学习特征图中特征之间的相关性。一个可训练的局部聚合描述符向量 (NetVLAD) 被集成在网络的最后一层，以生成一个紧凑且固定长度的全局特征。在所提出的网络的训练中采用知识蒸馏策略来加速训练过程。对于全局特征，采用分层导航小世界（HNSW）来检索闭环候选图像。此外，基于局部差异二进制 (LDB) 描述符的高效几何一致性检查旨在验证回环匹配。在几个公共数据集上的实验表明，与其他典型和最先进的方法相比，ESA-VLAD 可以在 100% 精度下获得更高的召回率和更少的每帧处理时间。