Please use this identifier to cite or link to this item:
Title: Learning sparse representation via spatio-temporal smoothing for human activity recognition
Authors: Peng, Haiyun
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Issue Date: 2014
Abstract: Recent years have seen popularities of sparse coding in many research fields. One of these fields is computer vision, where sparse coding has been applied in the process of feature quantization and selection. Although the general sparse coding method reduces the complexity of coding process (hence saves memory space), and makes the reconstruction of the feature from the sparse codes easy, the data that feed into the coding process are not in the optimal state and can cause errors in the subsequent processes. In this dissertation, we propose a new graph-based sparse coding model that optimizes the human activity feature to improve the accuracy of human activity recognition. We demonstrate how exactly the model can optimize the data by using correlation computation. We achieve encouraging performance gains after using this new model. We also compare and discuss three methods for sparsity estimation of feature coefficients. In the end, we find the optimal parameter settings for features, dictionary size, etc. for human activity recognition based on KTH and HMDB51 video datasets.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
  Restricted Access
6.05 MBAdobe PDFView/Open

Page view(s)

checked on Oct 24, 2020


checked on Oct 24, 2020

Google ScholarTM


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