Person Re-identification for Real-world Surveillance Systems
This addresses the challenge of scalable and transferable person re-identification for surveillance systems, reducing human annotation effort and enabling easier network expansion, though it is incremental as it builds on existing unsupervised methods.
The paper tackles the problem of person re-identification in real-world surveillance systems by proposing a novel unsupervised modeling approach that avoids the need for supervised learning and camera-specific annotations, achieving significant performance improvements over current state-of-the-art unsupervised methods on multiple benchmark datasets.
Appearance based person re-identification in a real-world video surveillance system with non-overlapping camera views is a challenging problem for many reasons. Current state-of-the-art methods often address the problem by relying on supervised learning of similarity metrics or ranking functions to implicitly model appearance transformation between cameras for each camera pair, or group, in the system. This requires considerable human effort to annotate data. Furthermore, the learned models are camera specific and not transferable from one set of cameras to another. Therefore, the annotation process is required after every network expansion or camera replacement, which strongly limits their applicability. Alternatively, we propose a novel modeling approach to harness complementary appearance information without supervised learning that significantly outperforms current state-of-the-art unsupervised methods on multiple benchmark datasets.