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

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

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

15 Dyfyniadau(SciVal)
54 Wedi eu Llwytho i Lawr (Pure)

Crynodeb

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 spatio-temporal 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 spatio-temporal 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.
Iaith wreiddiolSaesneg
Rhif yr erthygl8919994
Tudalennau (o-i)4059 - 4067
Nifer y tudalennau9
CyfnodolynIEEE Transactions on Industrial Informatics
Cyfrol16
Rhif cyhoeddi6
Dyddiad ar-lein cynnar03 Rhag 2019
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 30 Meh 2020
Cyhoeddwyd yn allanolIe

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'Histogram of Fuzzy Local Spatio-Temporal Descriptors for Video Action Recognition'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn