Full-scaled deep metric learning for pedestrian re-identification
- PDF / 2,938,995 Bytes
- 31 Pages / 439.642 x 666.49 pts Page_size
- 40 Downloads / 237 Views
Full-scaled deep metric learning for pedestrian re-identification Wei Huang1,2
· Mingyuan Luo3 · Peng Zhang4 · Yufei Zha4
Received: 27 March 2020 / Revised: 15 September 2020 / Accepted: 29 September 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The pedestrian re-identification problem (i.e., re-id) is essential and pre-requisite in multicamera video surveillance studies, provided the fact that pedestrian targets need to be accurately re-identified across a network of multiple cameras with non-overlapping fields of views before other post-hoc high-level utilizations (i.e., tracking, behaviors analyses, activities monitoring, etc.) can be carried out. Driven by recent developments in deep learning techniques, the important re-id problem is often tackled via either deep discriminant learning or deep generative learning techniques. However, most contemporary deep learning-based models with tremendously deep structures are not easy to be trained because of the notorious vanishings gradient problem. In this study, a novel full-scaled deep discriminant learning model is proposed. The novelty of the full-scale model is significant, as three crucial concepts in designing a deep learning model, including depth, width, and cardinality, are all taken into consideration, simultaneously. Therefore, the new model needs not to be tremendously deep but is more convenient to be trained. Moreover, based on the new model, a novel deep metric learning method is proposed to further solve the important re-id problem. Technically, two algorithms either based on the conventional SGD (stochastic gradient descent) or an alternative more efficient PGD (proximal gradient descent) are both derived. For experimental analyses, the newly introduced full-scaled deep metric learning method has been comprehensively compared with dozens of popular re-id methods proposed from either deep learning or shallow learning perspectives. Several well-known public re-id datasets have been incorporated and rigorous statistical analyses have been carried out to compare all methods regarding their re-id performance. The superiority of the novel full-scaled deep metric learning method has been substantiated, from the statistical point of view. Keywords Re-identification · Metric learning · Deep learning
Wei Huang
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
1 Introduction The pedestrian re-identification (a.k.a re-id) problem, which mainly aims to recognize the same pedestrian target when moving across a network of cameras with non-overlapping fields of view, is an important and challenging problem in multi-camera video surveillance studies [76]. The general idea to solve the challenging re-id problem in most contemporary studies can be summarized as follows. When the pedestrian target is determined within a camera view, an image patch eliminating the main background and highlighting the pedestrian target will be selected. Then, extract
Data Loading...
