Visual Sequence Place Recognition with Improved Dynamic Time Warping

Abstract

Recently, the methods based on Deep Convolutional Neural Networks have achieved state-of-the-art performance in visual place recognition. In this paper, we utilize deep feature representations of images and the dynamic time warping (DTW) algorithm for image sequence place recognition. We propose a novel image similarity measurement, which is derived from cosine distance and can better distinguish match and mismatch. Meanwhile, we improve the DTW algorithm to design a local matching method that can reduce time complexity from O(n3) to O(n). Extensive experiments are conducted on two challenging datasets, the results show high precision-recall characteristics in the cases of severe appearance changes. Besides, our method achieves substantial improvements over the methods using the deep feature representations of a single image for recognition, which makes us believe that the spatiotemporal information contained in the image sequence is significant for place recognition. Furthermore, the proposed method outperforms the classical sequence-based method SeqSLAM [1].