AUT LibraryAUT
View Item 
  •   Open Theses & Dissertations
  • Doctoral Theses
  • View Item
  •   Open Theses & Dissertations
  • Doctoral Theses
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Deep Learning Methods for Human Behavior Recognition

Lu, Jia
Thumbnail
View/Open
Thesis (3.496Mb)
Permanent link
http://hdl.handle.net/10292/14058
Metadata
Show full metadata
Abstract
With the decreased costs of security monitoring equipment such as cameras, video surveillance has been broadly applied to our communities and public places. However, at present most of the surveillance systems acquire anomalies and visual evidences only through video playback. Hence, it is necessary to develop the methods of real-time human behavior recognition so as to reduce security staff’s workload and improve work efficiency.

The existing work needs feature extraction from the video frames to detect human body and achieve human behavior recognition. In this thesis, our focus is on the state-of-the-art methods for human behavior recognition based on deep learning. Since deep learning methods have been well investigated in the past decades, as an end-to-end computational method, it simplifies feature extraction as the operations in a black box.

In this thesis, we explore and exploit the state-of-the-art methods, which are utilized for human behavior recognition. More importantly, in order to attain our goal, spatiotemporal information was collected and employed to the implementation of our research project. We firstly adopted ensemble learning with deep learning methods. We proposed Selective Kernel Network (SKNet) and ResNeXt with attention mechanism, which generate positive results to recognize human behaviours.

The contributions of this thesis are: (1) The ResNeXt and SKNet with attention mechanism make the best accuracy of overall human behavior recognition at the rate up to 98.7% based on public datasets; (2) The YOLOv3 + LSTM network to reply on both spatiotemporal information with class score fusion is able to achieve 97.58% accuracy based on our dataset for sign language processing.
Keywords
Deep learning (DL); Convolutional neural network (CNN); Long short-term memory (LSTM); You Only Look Once (YOLO); Ensemble learning; Selective kernel network (SKNet); Attention mechanism
Date
2021
Item Type
Thesis
Supervisor(s)
Yan, Weiqi; Nguyen, Minh
Degree Name
Doctor of Philosophy
Publisher
Auckland University of Technology

Contact Us
  • Admin

Hosted by Tuwhera, an initiative of the Auckland University of Technology Library

 

 

Browse

Open Theses & DissertationsTitlesAuthorsDateThesis SupervisorDoctoral ThesesTitlesAuthorsDateThesis Supervisor

Alternative metrics

 

Statistics

For this itemFor all Open Theses & Dissertations

Share

 
Follow @AUT_SC

Contact Us
  • Admin

Hosted by Tuwhera, an initiative of the Auckland University of Technology Library