Triplet CNN and pedestrian attribute recognition for improved person re-identification

CNN en triplet et reconnaissance d'attribut pour la ré-identification de personne amélirorée

Yiqiang Chen (1) , Stefan Duffner (1) , Andrei Stoian (2) , Jean-Yves Dufour (3) , Atilla Baskurt (1)

1 imagine - Extraction de Caractéristiques et Identification
2 CEDRIC - Centre d'études et de recherche en informatique et communications
3 Thales Services

In this paper, we propose a pedestrian attribute recognition approach and a CNN-based person re-identification framework enhanced by pedestrian attributes. The knowledge of person attributes can help video surveillance tasks like person re-identification as well as person search, semantic video indexing and retrieval to overcome viewpoint changes with their robustness to the inherent visual appearance variations. Compared to previous approaches, our attribute recognition method using Local Maximal Occurrence (LOMO) features and a Multi-Label Multi-Layer Perceptron (MLMLP) classifier proves to be more robust to different view points and is computationally more efficient. The experiments on three public benchmarks show that the proposed method improves the state-of-the art on attribute recognition. Furthermore, we integrate our attribute recognition algorithm into a triplet CNN similarity learning framework for person re-identification fusing both learned CNN features and attributes. This fusion leads to an overall improvement, and we achieve state-of-the-art results on person re-identification.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt. Triplet CNN and pedestrian attribute recognition for improved person re-identification. 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2017), IEEE, Aug 2017, Lecce, Italy. ⟨10.1109/AVSS.2017.8078542⟩. ⟨hal-01625479⟩