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 (10)

• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Person Re-identification: Past, Present and Future
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Stacked Hourglass Networks for Human Pose Estimation
• Convolutional Pose Machines
• Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation
• Person Re-identification in the Wild
• DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

Cited by in corpus (46)

• Improving Person Re-identification by Attribute and Identity Learning
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Deep Representation Learning with Part Loss for Person Re-Identification
• 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
• SVDNet for Pedestrian Retrieval
• 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
• Bag of Tricks and A Strong Baseline for Deep Person Re-identification
• ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
• Attention-Aware Compositional Network for Person Re-identification
• Learning Multi-Attention Context Graph for Group-Based Re-Identification
• ABD-Net: Attentive but Diverse Person Re-Identification
• Learning Feature Pyramids for Human Pose Estimation
• Horizontal Pyramid Matching for Person Re-identification
• Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
• Interaction-and-Aggregation Network for Person Re-identification
• Pose-driven Deep Convolutional Model for Person Re-identification
• Person Re-Identification by Semantic Region Representation and Topology Constraint
• Pose-Normalized Image Generation for Person Re-identification
• Batch DropBlock Network for Person Re-identification and Beyond
• Densely Semantically Aligned Person Re-Identification
• Deep Attention-guided Hashing
• Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search
• Dissecting Person Re-identification from the Viewpoint of Viewpoint
• Semantics-Aligned Representation Learning for Person Re-identification
• Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification
• Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information
• SPCNet:Spatial Preserve and Content-aware Network for Human Pose Estimation
• Learning Context Graph for Person Search
• An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
• Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
• Apparel-invariant Feature Learning for Apparel-changed Person Re-identification
• Cross-Entropy Adversarial View Adaptation for Person Re-identification
• Attributes-aided Part Detection and Refinement for Person Re-identification
• In Defense of the Classification Loss for Person Re-Identification
• IAUnet: Global Context-Aware Feature Learning for Person Re-Identification
• Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity
• A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification
• SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
• A framework with updateable joint images re-ranking for Person Re-identification
• Cross-Correlated Attention Networks for Person Re-Identification
• Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification
• Attention Driven Person Re-identification