GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval

Abstract

The huge variance of human pose and the misalignment of detected human images significantly increase the difficulty of person Re-Identification (Re-ID). Moreover, efficient Re-ID systems are required to cope with the massive visual data being produced by video surveillance systems. Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively. GLAD explicitly leverages the local and global cues in human body to generate a discriminative and robust representation. It consists of part extraction and descriptor learning modules, where several part regions are first detected and then deep neural networks are designed for representation learning on both the local and global regions. A hierarchical indexing and retrieval framework is designed to eliminate the huge redundancy in the gallery set, and accelerate the online Re-ID procedure. Extensive experimental results show GLAD achieves competitive accuracy compared to the state-of-the-art methods. Our retrieval framework significantly accelerates the online Re-ID procedure without loss of accuracy. Therefore, this work has potential to work better on person Re-ID tasks in real scenarios.

Accepted by ACM MM2017, 9 pages, 5 figures

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Pose Invariant Embedding for Deep Person Re-identification

Cited by in corpus (24)

• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
• Bag of Tricks and A Strong Baseline for Deep Person Re-identification
• Interaction-and-Aggregation Network for Person Re-identification
• Identity-Guided Human Semantic Parsing for Person Re-Identification
• EANet: Enhancing Alignment for Cross-Domain Person Re-identification
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification
• AANet: Attribute Attention Network for Person Re-Identifications
• Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
• CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
• Spatial and Temporal Mutual Promotion for Video-based Person Re-identification
• Real-world Person Re-Identification via Degradation Invariance Learning
• In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
• Learning Context Graph for Person Search
• Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
• Pedestrian re-identification based on Tree branch network with local and global learning
• Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification
• Apparel-invariant Feature Learning for Apparel-changed Person Re-identification
• Robust Partial Matching for Person Search in the Wild
• End-to-End Training of CNN Ensembles for Person Re-Identification
• GAN-based Pose-aware Regulation for Video-based Person Re-identification
• Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
• Cross-Correlated Attention Networks for Person Re-Identification
• Single Camera Training for Person Re-identification