STA-VPR: Spatio-temporal Alignment for Visual Place Recognition

TL;DR

This paper introduces STA-VPR, a novel spatio-temporal alignment method for visual place recognition that enhances CNN-based features' robustness to viewpoint and appearance changes without re-training.

Contribution

It proposes an adaptive DTW algorithm for spatial feature alignment and a local matching DTW for temporal sequence matching, improving VPR accuracy and efficiency.

Findings

Significantly improves CNN-based VPR performance.

Outperforms several state-of-the-art methods.

Maintains good run-time performance.

Abstract

Recently, the methods based on Convolutional Neural Networks (CNNs) have gained popularity in the field of visual place recognition (VPR). In particular, the features from the middle layers of CNNs are more robust to drastic appearance changes than handcrafted features and high-layer features. Unfortunately, the holistic mid-layer features lack robustness to large viewpoint changes. Here we split the holistic mid-layer features into local features, and propose an adaptive dynamic time warping (DTW) algorithm to align local features from the spatial domain while measuring the distance between two images. This realizes viewpoint-invariant and condition-invariant place recognition. Meanwhile, a local matching DTW (LM-DTW) algorithm is applied to perform image sequence matching based on temporal alignment, which achieves further improvements and ensures linear time complexity. We perform extensive experiments on five representative VPR datasets. The results show that the proposed method significantly improves the CNN-based methods. Moreover, our method outperforms several state-of-the-art methods while maintaining good run-time performance. This work provides a novel way to boost the performance of CNN methods without any re-training for VPR. The code is available at https://github.com/Lu-Feng/STA-VPR.