Recognising occluded multi-view actions using local nearest neighbour embedding

Long, Yang, Zhu, Fan and Shao, Ling (2016) Recognising occluded multi-view actions using local nearest neighbour embedding. Computer Vision and Image Understanding, 144. pp. 36-45. ISSN 1077-3142

Full text not available from this repository.
Official URL: http://dx.doi.org/10.1016/j.cviu.2015.06.003

Abstract

The recent advancement of multi-sensor technologies and algorithms has boosted significant progress to human action recognition systems, especially for dealing with realistic scenarios. However, partial occlusion, as a major obstacle in real-world applications, has not received sufficient attention in the action recognition community. In this paper, we extensively investigate how occlusion can be addressed by multi-view fusion. Specifically, we propose a robust representation called local nearest neighbour embedding (LNNE). We then extend the LNNE method to 3 multi-view fusion scenarios. Additionally, we provide detailed analysis of the proposed voting strategy from the boosting point of view. We evaluate our approach on both synthetic and realistic occluded databases, and the LNNE method outperforms the state-of-the-art approaches in all tested scenarios.

Item Type: Article
Uncontrolled Keywords: Occlusion; Action recognition; Multi-view fusion; Naive bayes; Local nearest neighbour; Embedding
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Related URLs:
Depositing User: Ay Okpokam
Date Deposited: 14 Mar 2016 09:46
Last Modified: 31 Oct 2017 11:51
URI: http://nrl.northumbria.ac.uk/id/eprint/26342

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics


Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence