Learning Sequence Descriptor based on Spatio-Temporal Attention for Visual Place Recognition

• Published in: arXiv.org
• Main Authors: Zhao, Junqiao, Zhang, Fenglin, Cai, Yingfeng, Tian, Gengxuan, Mu, Wenjie, Chen, Ye, Feng, Tiantian
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 27.01.2024
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Recognition
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2305.11467

Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame. To improve the robustness of VPR in perceptually aliasing scenarios, sequence-based VPR methods are proposed. These methods are either based on matching between frame sequences or extracting sequence descriptors for direct retrieval. However, the former is usually based on the assumption of constant velocity, which is difficult to hold in practice, and is computationally expensive and subject to sequence length. Although the latter overcomes these problems, existing sequence descriptors are constructed by aggregating features of multiple frames only, without interaction on temporal information, and thus cannot obtain descriptors with spatio-temporal discrimination.In this paper, we propose a sequence descriptor that effectively incorporates spatio-temporal information. Specifically, spatial attention within the same frame is utilized to learn spatial feature patterns, while attention in corresponding local regions of different frames is utilized to learn the persistence or change of features over time. We use a sliding window to control the temporal range of attention and use relative positional encoding to construct sequential relationships between different features. This allows our descriptors to capture the intrinsic dynamics in a sequence of frames.Comprehensive experiments on challenging benchmark datasets show that the proposed approach outperforms recent state-of-the-art methods.The code is available at https://github.com/tiev-tongji/Spatio-Temporal-SeqVPR.