Unsupervised Adaptive Re-identification in Open World Dynamic Camera Networks

TL;DR

This paper introduces an unsupervised adaptive re-identification method for dynamic camera networks, effectively handling open-world scenarios where cameras are added or removed, and significantly improves accuracy over existing methods.

Contribution

It proposes a domain perceptive re-identification approach using geodesic flow kernel and a transitive inference algorithm for dynamic, open-world camera networks, without requiring extensive retraining.

Findings

Outperforms state-of-the-art unsupervised methods on benchmark datasets

Efficiently adapts to new cameras without expensive retraining

Improves re-identification accuracy across multiple camera pairs

Abstract

Person re-identification is an open and challenging problem in computer vision. Existing approaches have concentrated on either designing the best feature representation or learning optimal matching metrics in a static setting where the number of cameras are fixed in a network. Most approaches have neglected the dynamic and open world nature of the re-identification problem, where a new camera may be temporarily inserted into an existing system to get additional information. To address such a novel and very practical problem, we propose an unsupervised adaptation scheme for re-identification models in a dynamic camera network. First, we formulate a domain perceptive re-identification method based on geodesic flow kernel that can effectively find the best source camera (already installed) to adapt with a newly introduced target camera, without requiring a very expensive training phase. Second, we introduce a transitive inference algorithm for re-identification that can exploit the information from best source camera to improve the accuracy across other camera pairs in a network of multiple cameras. Extensive experiments on four benchmark datasets demonstrate that the proposed approach significantly outperforms the state-of-the-art unsupervised learning based alternatives whilst being extremely efficient to compute.