Person Re-Identification by Unsupervised Video Matching

TL;DR

This paper presents an unsupervised video-based person re-identification method that leverages space-time dynamics and a novel alignment model to match individuals across camera views without requiring labeled pairwise data.

Contribution

Introduces a new unsupervised approach using space-time representations and a Time Shift Dynamic Time Warping model for scalable person re-identification across large camera networks.

Findings

Effective matching on PRID2011 and iLIDS-VID datasets

Outperforms state-of-the-art unsupervised methods

No need for labeled pairwise training data

Abstract

Most existing person re-identification (ReID) methods rely only on the spatial appearance information from either one or multiple person images, whilst ignore the space-time cues readily available in video or image-sequence data. Moreover, they often assume the availability of exhaustively labelled cross-view pairwise data for every camera pair, making them non-scalable to ReID applications in real-world large scale camera networks. In this work, we introduce a novel video based person ReID method capable of accurately matching people across views from arbitrary unaligned image-sequences without any labelled pairwise data. Specifically, we introduce a new space-time person representation by encoding multiple granularities of spatio-temporal dynamics in form of time series. Moreover, a Time Shift Dynamic Time Warping (TS-DTW) model is derived for performing automatically alignment whilst achieving data selection and matching between inherently inaccurate and incomplete sequences in a unified way. We further extend the TS-DTW model for accommodating multiple feature-sequences of an image-sequence in order to fuse information from different descriptions. Crucially, this model does not require pairwise labelled training data (i.e. unsupervised) therefore readily scalable to large scale camera networks of arbitrary camera pairs without the need for exhaustive data annotation for every camera pair. We show the effectiveness and advantages of the proposed method by extensive comparisons with related state-of-the-art approaches using two benchmarking ReID datasets, PRID2011 and iLIDS-VID.