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 show that PoseBox alone yields decent re-ID accuracy and that when integrated in the PBF network, the learned PIE descriptor produces competitive performance compared with the state-of-the-art approaches.

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Person Re-identification: Past, Present and Future
• Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation

Cited by in corpus (15)

• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• Bag of Tricks and A Strong Baseline for Deep Person Re-identification
• Learning Feature Pyramids for Human Pose Estimation
• Interaction-and-Aggregation Network for Person Re-identification
• Pose-driven Deep Convolutional Model for Person Re-identification
• Deep Attention-guided Hashing
• Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information
• Learning Context Graph for Person Search
• Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
• Cross-Entropy Adversarial View Adaptation for Person Re-identification
• Attributes-aided Part Detection and Refinement for Person Re-identification