Transformer neural networks for human activity recognition

dc.contributor.authorWensel, James
dc.date.accessioned2022-08-18T16:37:13Z
dc.date.available2022-08-18T16:37:13Z
dc.date.graduationmonthAugust
dc.date.issued2022
dc.description.abstractHuman activity recognition is an emerging and important area in computer vision which seeks to determine the activity an individual or group of individuals are performing. The applications of this field ranges from generating highlight videos in sports, to intelligent surveillance and gesture recognition. Most activity recognition systems rely on a combination of convolutional neural networks (CNNs) to perform feature extraction from the data and recurrent neural networks (RNNs) to determine the time dependent nature of the data. This paper proposes and designs two transformer neural networks for human activity recognition: a recurrent transformer, a specialized neural network used to make predictions on sequences of data, as well as a vision transformer, a transformer optimized for extracting salient features from images, to improve speed and scalability of activity recognition. We have provided an extensive comparison of the proposed transformer neural networks with the contemporary CNN and RNN-based human activity recognition models in terms of speed and accuracy.
dc.description.advisorArslan Munir
dc.description.degreeMaster of Science
dc.description.departmentDepartment of Computer Science
dc.description.levelMasters
dc.description.sponsorshipAir Force Office of Scientific Research
dc.identifier.urihttps://hdl.handle.net/2097/42481
dc.language.isoen_US
dc.publisherKansas State University
dc.rights© the author. This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/
dc.subjectTransformer
dc.subjectRecurrent transformer
dc.subjectVision transformer
dc.subjectHuman activity recognition
dc.subjectComputer vision
dc.subjectMachine learning
dc.titleTransformer neural networks for human activity recognition
dc.typeThesis

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
JamesWensel2022.pdf
Size:
1.54 MB
Format:
Adobe Portable Document Format
Description:
Thesis

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.62 KB
Format:
Item-specific license agreed upon to submission
Description: