The first book of its kind dedicated to the challenge of person re-identification, this text provides an in-depth, multidisciplinary discussion of recent developments and state-of-the-art methods. Features: introduces examples of robust feature representations, reviews salient feature weighting and selection mechanisms and examines the benefits of semantic attributes; describes how to segregate meaningful body parts from background clutter; examines the use of 3D depth images and contextual constraints derived from the visual appearance of a group; reviews approaches to feature transfer function and distance metric learning and discusses potential solutions to issues of data scalability and identity inference; investigates the limitations of existing benchmark datasets, presents strategies for camera topology inference and describes techniques for improving post-rank search efficiency; explores the design rationale and implementation considerations of building a practical re-identification system.
Author(s): Shaogang Gong, Marco Cristani, Chen Change Loy (auth.), Shaogang Gong, Marco Cristani, Shuicheng Yan, Chen Change Loy (eds.)
Series: Advances in Computer Vision and Pattern Recognition
Edition: 1
Publisher: Springer-Verlag London
Year: 2014
Language: English
Pages: 445
Tags: Image Processing and Computer Vision; Pattern Recognition; Math Applications in Computer Science; Information Systems Applications (incl. Internet); User Interfaces and Human Computer Interaction; Artificial Intelligence (incl. Robotics)
Front Matter....Pages i-xviii
The Re-identification Challenge....Pages 1-20
Front Matter....Pages 21-21
Discriminative Image Descriptors for Person Re-identification....Pages 23-42
SDALF: Modeling Human Appearance with Symmetry-Driven Accumulation of Local Features....Pages 43-69
Re-identification by Covariance Descriptors....Pages 71-91
Attributes-Based Re-identification....Pages 93-117
Person Re-identification by Attribute-Assisted Clothes Appearance....Pages 119-138
Person Re-identification by Articulated Appearance Matching....Pages 139-160
One-Shot Person Re-identification with a Consumer Depth Camera....Pages 161-181
Group Association: Assisting Re-identification by Visual Context....Pages 183-201
Evaluating Feature Importance for Re-identification....Pages 203-228
Front Matter....Pages 229-229
Learning Appearance Transfer for Person Re-identification....Pages 231-246
Mahalanobis Distance Learning for Person Re-identification....Pages 247-267
Dictionary-Based Domain Adaptation Methods for the Re-identification of Faces....Pages 269-285
From Re-identification to Identity Inference: Labeling Consistency by Local Similarity Constraints....Pages 287-307
Re-identification for Improved People Tracking....Pages 309-330
Front Matter....Pages 331-331
Benchmarking for Person Re-identification....Pages 333-349
Person Re-identification: System Design and Evaluation Overview....Pages 351-370
People Search with Textual Queries About Clothing Appearance Attributes....Pages 371-389
Large-Scale Camera Topology Mapping: Application to Re-identification....Pages 391-411
Scalable Multi-camera Tracking in a Metropolis....Pages 413-438
Back Matter....Pages 439-445
