View Item 
      •   Home
      • 7. Theses and Dissertations
      • Theses and Dissertations (Doctor of Philosophy)
      • View Item
      •   Home
      • 7. Theses and Dissertations
      • Theses and Dissertations (Doctor of Philosophy)
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.
      Subject Lookup

      Browse

      All of DR-NTUCommunities & CollectionsTitlesAuthorsBy DateSubjectsThis CollectionTitlesAuthorsBy DateSubjects

      My Account

      Login

      Statistics

      Most Popular ItemsStatistics by Country/RegionMost Popular Authors

      About DR-NTU

      Skeleton-based human activity understanding

      Thumbnail
      thesis_LiuJun.pdf (8.021Mb)
      Author
      Liu, Jun
      Date of Issue
      2019-08-01
      School
      School of Electrical and Electronic Engineering
      Research Centre
      Research Techno Plaza
      Abstract
      Human activity understanding is an important research problem due to its relevance to a wide range of applications. Recently, 3D skeleton-based activity analysis becomes popular due to its succinctness, robustness, and view-invariant representation. In this thesis, we focus on human activity understanding in 3D skeleton sequences. Recent works attempted to utilize recurrent neural networks (RNNs) and long short-term memory (LSTM) networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activities in the 3D skeletal data. As the first work of this thesis, we apply recurrent analysis to spatial domain as well as temporal domain to better analyze the hidden sources of action-related information within the human skeleton sequences in both of these domains simultaneously. Based on the pictorial structure of Kinect's skeletal data, an effective tree-structure based traversal framework is also proposed. In order to deal with the noise in the skeletal data, a new gating mechanism within LSTM module is introduced, with which the network can learn the reliability of the sequential data and accordingly adjust the effect of the input data on the updating procedure of the long-term context representation stored in the unit's memory cell. The comprehensive experimental results on seven challenging benchmark datasets for human action recognition demonstrate the effectiveness of the proposed method. In skeleton-based action recognition, not all skeletal joints are informative for activity analysis, and the irrelevant joints often bring noise which can degrade the performance. Therefore, we need to pay more attention to the informative ones. However, the original LSTM network does not have explicit attention ability. In our second piece of work, we propose a new class of LSTM network, global context-aware attention LSTM, for skeleton-based action recognition, which is capable of selectively focusing on the informative joints in each frame by using a global context memory cell. The proposed method achieves state-of-the-art performance on five challenging datasets for skeleton-based action recognition. The aforementioned two works focus on action recognition in well-segmented skeleton sequences, in which each sequence includes one action sample and we need to recognize its class. In the third work, we focus on online action prediction in untrimmed streaming skeleton data, in which each sequence contains multiple action samples and we need to recognize the class label of the current ongoing activity when only a part of it is observed. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis for online action prediction. As there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed, which makes our network focus on the performed part of the ongoing action and suppress the possible incoming interference from the previous actions. The proposed approach is evaluated on four challenging datasets. The extensive experiments demonstrate the effectiveness of the proposed method for skeleton-based online action prediction.
      Subject
      Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
      Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
      Type
      Thesis
      Collections
      • Theses and Dissertations (Doctor of Philosophy)
      https://doi.org/10.32657/10220/49510
      Get published version (via Digital Object Identifier)

      Show full item record

      Related items

      Showing items related by title, author, creator and subject.

      • Medical imaging algorithm research for diagnosis of ocular diseases 

        Tan, Ngan Meng (2015)
        Color retinal fundus images provide visual documentation of the health of a person's retina. With the widespread adoption of higher quality medical imaging techniques and data, there are increasing demands for medical ...
      • Writing style modelling based on grapheme distributions : application to on-line writer identification. 

        Tan, Guoxian. (2013)
        The increasingly pervasive spread of mobile digital devices such as mobile smartphones or digital tablets that use digital pens brought about the emergence of a new class of documents; online handwritten documents. The ...
      • Efficient feature extraction and classification for staining patterns of HEP-2 Cells 

        Xu, Xiang (2016)
        The occurrence of antinuclear antibodies (ANAs) in patient serum has significant relation to autoimmune diseases. The ANAs detection can be accomplished via indirect immunofluorescence (IIF) technique using human epithelial ...

      NTU Library, Nanyang Avenue, Singapore 639798 © 2011 Nanyang Technological University. All rights reserved.
      DSpace software copyright © 2002-2015  DuraSpace
      Contact Us | Send Feedback
      Share |    
      Theme by 
      Atmire NV
       

       


      NTU Library, Nanyang Avenue, Singapore 639798 © 2011 Nanyang Technological University. All rights reserved.
      DSpace software copyright © 2002-2015  DuraSpace
      Contact Us | Send Feedback
      Share |    
      Theme by 
      Atmire NV
       

       

      DCSIMG