Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Human action recognition with 3D convolutional neural networks
Convolutional neural networks (CNNs) adapt the regular fully-connected neural network (NN) algorithm to facilitate image classification. Recently, CNNs have been demonstrated to provide superior performance across numerous image classification databases including large natural images (Krizhevsky et...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Statistical Sciences
2015
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613324644974593 |
|---|---|
| access_status_str | Open Access |
| author | Cronje, Frans |
| author2 | Clark, Allan |
| author_browse | Clark, Allan Cronje, Frans |
| author_facet | Clark, Allan Cronje, Frans |
| author_sort | Cronje, Frans |
| collection | Thesis |
| description | Convolutional neural networks (CNNs) adapt the regular fully-connected neural network (NN) algorithm to facilitate image classification. Recently, CNNs have been demonstrated to provide superior performance across numerous image classification databases including large natural images (Krizhevsky et al., 2012). Furthermore, CNNs are more readily transferable between different image classification problems when compared to common alternatives. The extension of CNNs to video classification is simple and the rationale behind the components of the model are still applicable due to the similarity between image and video data. Previous CNNs have demonstrated good performance upon video datasets, however have not employed methods that have been recently developed and attributed improvements in image classification networks. The purpose of this research to build a CNN model that includes recently developed elements to present a human action recognition model which is up-to-date with current trends in CNNs and current hardware. Focus is applied to ensemble models and methods such as the Dropout technique, developed by Hinton et al. (2012) to reduce overfitting, and learning rate adaptation techniques. The KTH human action dataset is used to assess the CNN model, which, as a widely used benchmark dataset, facilitates the comparison between previous work performed in the literature. Three CNNs are built and trained to provide insight into design choices as well as allow the construction of an ensemble model. The final ensemble model achieved comparative performance to previous CNNs trained upon the KTH data.
While the inclusion of new methods to the CNN model did not result in an improvement on previous models, the competitive result provides an alternative combination of architecture and components to other CNN models. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/15482 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:34:20.437Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2015 |
| publishDateRange | 2015 |
| publishDateSort | 2015 |
| publisher | Department of Statistical Sciences |
| publisherStr | Department of Statistical Sciences |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/15482 Human action recognition with 3D convolutional neural networks Cronje, Frans Clark, Allan Statistical Sciences Convolutional neural networks (CNNs) adapt the regular fully-connected neural network (NN) algorithm to facilitate image classification. Recently, CNNs have been demonstrated to provide superior performance across numerous image classification databases including large natural images (Krizhevsky et al., 2012). Furthermore, CNNs are more readily transferable between different image classification problems when compared to common alternatives. The extension of CNNs to video classification is simple and the rationale behind the components of the model are still applicable due to the similarity between image and video data. Previous CNNs have demonstrated good performance upon video datasets, however have not employed methods that have been recently developed and attributed improvements in image classification networks. The purpose of this research to build a CNN model that includes recently developed elements to present a human action recognition model which is up-to-date with current trends in CNNs and current hardware. Focus is applied to ensemble models and methods such as the Dropout technique, developed by Hinton et al. (2012) to reduce overfitting, and learning rate adaptation techniques. The KTH human action dataset is used to assess the CNN model, which, as a widely used benchmark dataset, facilitates the comparison between previous work performed in the literature. Three CNNs are built and trained to provide insight into design choices as well as allow the construction of an ensemble model. The final ensemble model achieved comparative performance to previous CNNs trained upon the KTH data. While the inclusion of new methods to the CNN model did not result in an improvement on previous models, the competitive result provides an alternative combination of architecture and components to other CNN models. 2015-12-01T09:20:48Z 2015-12-01T09:20:48Z 2015 Master Thesis Masters MSc http://hdl.handle.net/11427/15482 eng application/pdf Department of Statistical Sciences Faculty of Science University of Cape Town |
| spellingShingle | Statistical Sciences Cronje, Frans Human action recognition with 3D convolutional neural networks |
| thesis_degree_str | Master's |
| title | Human action recognition with 3D convolutional neural networks |
| title_full | Human action recognition with 3D convolutional neural networks |
| title_fullStr | Human action recognition with 3D convolutional neural networks |
| title_full_unstemmed | Human action recognition with 3D convolutional neural networks |
| title_short | Human action recognition with 3D convolutional neural networks |
| title_sort | human action recognition with 3d convolutional neural networks |
| topic | Statistical Sciences |
| url | http://hdl.handle.net/11427/15482 |
| work_keys_str_mv | AT cronjefrans humanactionrecognitionwith3dconvolutionalneuralnetworks |