Please use this identifier to cite or link to this item:
Title: Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition
Authors: Ding, Runwei
He, Qinqin
Liu, Hong
Liu, Mengyuan
Keywords: Action Recognition
Depth Data
DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2018
Source: Ding, R., He, Q., Liu, H., & Liu, M. (2019). Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition. IEEE Access, 7, 5597-5608. doi:10.1109/ACCESS.2018.2886362
Series/Report no.: IEEE Access
Abstract: This paper presents a new framework for human action recognition by fusing human motion with skeletal joints. First, adaptive hierarchical depth motion maps (AH-DMMs) are proposed to capture the shape and motion cues of action sequences. Specifically, AH-DMMs are calculated over adaptive hierarchical windows and Gabor filters are used to encode the texture information of AH-DMMs. Then, spatial distances of skeletal joint positions are computed to characterize the structure information of the human body. Finally, two types of fusion methods including feature-level fusion and decision-level fusion are employed to combine the motion cues and structure information. The experimental results on public benchmark datasets, i.e., MSRAction3D and UTKinect-Action, show the effectiveness of the proposed method.
Rights: © 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See for more information
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Google ScholarTM



Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.