Home > Research > Publications & Outputs > Multi-Temporal Depth Motion Maps-Based Local Bi...

Associated organisational unit

Electronic data

  • Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D human action recognition

    Rights statement: ©2017 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

    Accepted author manuscript, 2.9 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D Human Action Recognition

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D Human Action Recognition. / Chen, Chen; Liu, Mengyang; Liu, Hong et al.
In: IEEE Access, Vol. 5, 07.11.2017, p. 22590-22604.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Chen, C, Liu, M, Liu, H, Zhang, B, Han, J & Kahtarnavaz, N 2017, 'Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D Human Action Recognition', IEEE Access, vol. 5, pp. 22590-22604. https://doi.org/10.1109/ACCESS.2017.2759058

APA

Chen, C., Liu, M., Liu, H., Zhang, B., Han, J., & Kahtarnavaz, N. (2017). Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D Human Action Recognition. IEEE Access, 5, 22590-22604. https://doi.org/10.1109/ACCESS.2017.2759058

Vancouver

Chen C, Liu M, Liu H, Zhang B, Han J, Kahtarnavaz N. Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D Human Action Recognition. IEEE Access. 2017 Nov 7;5:22590-22604. Epub 2017 Oct 2. doi: 10.1109/ACCESS.2017.2759058

Author

Chen, Chen ; Liu, Mengyang ; Liu, Hong et al. / Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D Human Action Recognition. In: IEEE Access. 2017 ; Vol. 5. pp. 22590-22604.

Bibtex

@article{dc5ad038ace54735bdaac5b5da0ee8aa,
title = "Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D Human Action Recognition",
abstract = "This paper presents a local spatio-temporal descriptor for action recognition from depth video sequences which is capable of distinguishing similar actions as well as coping with different speeds of actions. This descriptor is based on three processing stages. In the first stage, the shape and motion cues are captured from a weighted depth sequence by temporally overlapped depth segments, leading to three improved depth motion maps (DMMs) compared to previously introduced DMMs. In the second stage, the improved DMMs are partitioned into dense patches, from which the local binary patterns histogram features are extracted to characterize local rotation invariant texture information. In the final stage, a Fisher kernel is used for generating a compact feature representation, which is then combined with a kernel-based extreme learning machine (ELM) classifier. The developed solution is applied to five public domain datasets and is extensively evaluated. The results obtained demonstrate the effectiveness of this solution as compared to the existing approaches.",
author = "Chen Chen and Mengyang Liu and Hong Liu and Baochang Zhang and Jungong Han and Nasser Kahtarnavaz",
note = "{\textcopyright}2017 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.",
year = "2017",
month = nov,
day = "7",
doi = "10.1109/ACCESS.2017.2759058",
language = "English",
volume = "5",
pages = "22590--22604",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3D Human Action Recognition

AU - Chen, Chen

AU - Liu, Mengyang

AU - Liu, Hong

AU - Zhang, Baochang

AU - Han, Jungong

AU - Kahtarnavaz, Nasser

N1 - ©2017 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2017/11/7

Y1 - 2017/11/7

N2 - This paper presents a local spatio-temporal descriptor for action recognition from depth video sequences which is capable of distinguishing similar actions as well as coping with different speeds of actions. This descriptor is based on three processing stages. In the first stage, the shape and motion cues are captured from a weighted depth sequence by temporally overlapped depth segments, leading to three improved depth motion maps (DMMs) compared to previously introduced DMMs. In the second stage, the improved DMMs are partitioned into dense patches, from which the local binary patterns histogram features are extracted to characterize local rotation invariant texture information. In the final stage, a Fisher kernel is used for generating a compact feature representation, which is then combined with a kernel-based extreme learning machine (ELM) classifier. The developed solution is applied to five public domain datasets and is extensively evaluated. The results obtained demonstrate the effectiveness of this solution as compared to the existing approaches.

AB - This paper presents a local spatio-temporal descriptor for action recognition from depth video sequences which is capable of distinguishing similar actions as well as coping with different speeds of actions. This descriptor is based on three processing stages. In the first stage, the shape and motion cues are captured from a weighted depth sequence by temporally overlapped depth segments, leading to three improved depth motion maps (DMMs) compared to previously introduced DMMs. In the second stage, the improved DMMs are partitioned into dense patches, from which the local binary patterns histogram features are extracted to characterize local rotation invariant texture information. In the final stage, a Fisher kernel is used for generating a compact feature representation, which is then combined with a kernel-based extreme learning machine (ELM) classifier. The developed solution is applied to five public domain datasets and is extensively evaluated. The results obtained demonstrate the effectiveness of this solution as compared to the existing approaches.

U2 - 10.1109/ACCESS.2017.2759058

DO - 10.1109/ACCESS.2017.2759058

M3 - Journal article

VL - 5

SP - 22590

EP - 22604

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -