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

Abstract

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.

Deep Residual Learning for Analyzing Customer Satisfaction using Video Surveillance

“…However, the absence of a large domain-specific dataset is still the main challenge in training a deeplearning based FER models for video surveillance context, as most of existing datasets are captured in a lab-controlled environment. Most of recent works of deep learning in video surveillance focus on face recognition [18][19][20][21].…”

Person re-identification across different datasets with multi-task learning

“…Person re-identification Many studies are lead on re-identification, and today CNN and deep learning approaches are well studied and show very good performance on many datasets [23,21,19,24]. Two types of approaches are usually chosen for recent re-identification works with CNN.…”

“…Two types of approaches are usually chosen for recent re-identification works with CNN. First one is based on siamese networks [25,18], triplet loss networks [26,19], quadruplet loss [20] to learn a representation based on different and identical couple/triplet. The other approach is based on identity losses [21,16], in which each identity is seen as a class.…”

“…These architectures can be trained with relatively large re-identification datasets annotated with attributes [34,13]. Some researchers use architectures with two branches, one for the re-identification and one for the attribute extraction and combine them [19,12]. Su et al [35] use three stages of fine tuning and a triplet based loss.…”

“…We will describe them in more detail in the next section. The first one [18,19,20] is based on siamese networks, contractive or triplet losses. The second one [21,14], used in our work, is based on classification losses.…”