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

dc.contributor.authorChen, Chen
dc.contributor.authorLiu, Mengyuan
dc.contributor.authorLiu, Hong
dc.contributor.authorZhang, Baochang
dc.contributor.authorHan, Jungong
dc.contributor.authorKehtarnavaz, Nasser
dc.contributor.utdAuthorKehtarnavaz, Nasser
dc.description.abstractThis paper presents a local spatio-temporal descriptor for action recognistion 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 with the 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 classifier. The developed solution is applied to five public domain data sets and is extensively evaluated. The results obtained demonstrate the effectiveness of this solution as compared with the existing approaches.
dc.description.departmentErik Jonsson School of Engineering and Computer Science
dc.description.sponsorshipNatural Science Foundation of China under Grant 61672079, Grant 61473086, Grant U1613209, and Grant 6167021685
dc.identifier.bibliographicCitationChen, Chen, Mengyuan Liu, Hong Liu, Baochang Zhang, et al. 2017. "MultI-temporal depth motion maps-based local binary patterns for 3-D human action recognition." IEEE Access 5: 22590-22604, doi: 10.1109/ACCESS.2017.2759058
dc.publisherIEEE Electrical Electronics Engineers Inc
dc.rightsOAPA: users may copy the work, as well as translate it or reuse it for text/data mining, as long as the usage is for non-commercial purposes.
dc.rights©2017 IEEE
dc.source.journalIEEE Access
dc.subject3-D video (Three-dimensional imaging)
dc.titleMulti-Temporal Depth Motion Maps-Based Local Binary Patterns for 3-D Human Action Recognition


Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
3.93 MB
Adobe Portable Document Format