Histogram of Fuzzy Local Spatio-Temporal Descriptors for Video Action Recognition

Zheming Zuo, Longzhi Yang*, Yonghuai Liu, Fei Chao, Ran Song, Yanpeng Qu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)
16 Downloads (Pure)

Abstract

Feature extraction plays a vital role in visual action recognition. Many existing gradient-based feature extractors, including histogram of oriented gradients, histogram of optical flow, motion boundary histograms, and histogram of motion gradients, build histograms for representing different actions over the spatiooral domain in a video. However, these methods require to set the number of bins for information aggregation in advance. Varying numbers of bins usually lead to inherent uncertainty within the process of pixel voting with regard to the bins in the histogram. This article proposes a novel method to handle such uncertainty by fuzzifying these feature extractors. The proposed approach has two advantages: it better represents the ambiguous boundaries between the bins and, thus, the fuzziness of the spatiooral visual information entailed in videos; and the contribution of each pixel is flexibly controlled by a fuzziness parameter for various scenarios. The proposed family of fuzzy descriptors and a combination of them are evaluated on two publicly available datasets, demonstrating that the proposed approach outperforms the original counterparts and other state-of-the-art methods.

Original languageEnglish
Article number8919994
Pages (from-to)4059-4067
Number of pages9
JournalIEEE Transactions on Industrial Informatics
Volume16
Issue number6
Early online date3 Dec 2019
DOIs
Publication statusPublished - 1 Jun 2020

Fingerprint

Dive into the research topics of 'Histogram of Fuzzy Local Spatio-Temporal Descriptors for Video Action Recognition'. Together they form a unique fingerprint.

Cite this