Pose Invariant Embedding For Deep Person Re-identification

Abstract

Pedestrian misalignment, which mainly arises from detector errors and pose variations, is a critical problem for a robust person re-identification (re-ID) system. With bad alignment, the background noise will significantly compromise the feature learning and matching process. To address this problem, this paper introduces the pose invariant embedding (PIE) as a pedestrian descriptor. First, in order to align pedestrians to a standard pose, the PoseBox structure is introduced, which is generated through pose estimation followed by affine transformations. Second, to reduce the impact of pose estimation errors and information loss during PoseBox construction, we design a PoseBox fusion (PBF) CNN architecture that takes the original image, the PoseBox, and the pose estimation confidence as input. The proposed PIE descriptor is thus defined as the fully connected layer of the PBF network for the retrieval task. Experiments are conducted on the Market-1501, CUHK03, and VIPeR datasets. We sho

Stats

• citations378
• S2 citations—
• github stars0
• HF likes0
• heat score19.34
• arxiv keyzheng2017pose

Related papers

• Pedestrian Alignment Network For Large-scale Person Re-identification (2017)18.71
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• GLAD: Global-local-alignment Descriptor For Pedestrian Retrieval (2017)18.69
• Devil's In The Details: Aligning Visual Clues For Conditional Embedding In Person Re-identification (2020)0.00
• Pgganet: Pose Guided Graph Attention Network For Person Re-identification (2021)0.00
• Pose-aided Video-based Person Re-identification Via Recurrent Graph Convolutional Network (2022)10.97
• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32