Developing the Path Signature Methodology and Its Application to Landmark- Based Human Action Recognition

Weixin Yang (), Terry Lyons (), Hao Ni (), Cordelia Schmid () and Lianwen Jin ()
Additional contact information
Weixin Yang: University of Oxford, Mathematical Institute
Terry Lyons: Mathematical Institute, University of Oxford, UK and Alan Turing Institute
Hao Ni: University College London and Alan Turing Institute, Dept. of Mathematics
Lianwen Jin: South China University of Technology, College of Electronic and Information Engineering

A chapter in Stochastic Analysis, Filtering, and Stochastic Optimization, 2022, pp 431-464 from Springer

Abstract: Abstract Landmark-based human action recognition in videos is a challenging task in computer vision. One key step is to design a generic approach that generates discriminative features for the spatial structure and temporal dynamics. To this end, we regard the evolving landmark data as a high-dimensional path and apply path signature techniques to provide an expressive, robust, non-linear, and interpretable representation for the sequential events. We do not extract signature features from the raw path, rather we propose path disintegrations and path transformations as preprocessing steps. Path disintegrations turn a high-dimensional path linearly into a collection of lower-dimensional paths; some of these paths are in pose space while others are defined over a multi-scale collection of temporal intervals. Path transformations decorate the paths with additional coordinates in standard ways to allow the truncated signatures of transformed paths to expose additional features. For spatial representation, we apply the non-linear signature transform to vectorize the paths that arise out of pose disintegration, and for temporal representation, we apply it again to describe this evolving vectorization. Finally, all the features are joined together to constitute the input vector of a linear single-hidden-layer fully-connected network for classification. Experimental results on four diverse datasets demonstrated that the proposed feature set with only a linear shallow network is effective and achieves comparable state-of-the-art results to the advanced deep networks, and meanwhile, is capable of interpretation.

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-98519-6_18

Ordering information: This item can be ordered from
http://www.springer.com/9783030985196

DOI: 10.1007/978-3-030-98519-6_18

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().