Human action recognition using local two-stream CNN features with SVMs
dc.contributor.author | Torpey, David | |
dc.date.accessioned | 2020-02-07T07:19:46Z | |
dc.date.available | 2020-02-07T07:19:46Z | |
dc.date.issued | 2019 | |
dc.description | A dissertation submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, in fulfillment of the requirements for the degree of Master of Science. May 2019 | en_ZA |
dc.description.abstract | This dissertation serves to survey existing methods for human action recognition; compare those existing methods on some of the publicly-available benchmark datasets; and to introduce a novel method to solve the problem of human action recognition. The proposed method separately extracts appearance and motion features using state-of-the-art three-dimensional convolutional neural networks from sampled snippets of a video. These local features are then concatenated to form global representations for the videos. These global feature vectors are then used to train a linear SVM to perform the action classification. Additionally, we show the benefit of performing two simple, intuitive pre-processing steps, termed crop filling and optical flow scaling. We test the method extensively, and report results on the KTH and HMDB51 datasets | en_ZA |
dc.description.librarian | M T 2019 | en_ZA |
dc.identifier.uri | https://hdl.handle.net/10539/28820 | |
dc.language.iso | en | en_ZA |
dc.title | Human action recognition using local two-stream CNN features with SVMs | en_ZA |
dc.type | Thesis | en_ZA |