Demystifying Human Action Recognition in Deep Learning with Space-Time Feature Descriptors

Mike Nkongolo

ISBN 10: 3668642605 / ISBN 13: 9783668642607

Published by GRIN Verlag, 2018

About this Item

Druck auf Anfrage Neuware - Printed after ordering - Research Paper (postgraduate) from the year 2018 in the subject Computer Science - Internet, New Technologies, , course: Machine Learning, language: English, abstract: Human Action Recognition is the task of recognizing a set of actions being performed in a video sequence. Reliably and efficiently detecting and identifying actions in video could have vast impacts in the surveillance, security, healthcare and entertainment spaces.The problem addressed in this paper is to explore different engineered spatial and temporal image and video features (and combinations thereof) for the purposes of Human Action Recognition, as well as explore different Deep Learning architectures for non-engineered features (and classification) that may be used in tandem with the handcrafted features. Further, comparisons between the different combinations of features will be made and the best, most discriminative feature set will be identified.In the paper, the development and implementation of a robust framework for Human Action Recognition was proposed. The motivation behind the proposed research is, firstly, the high effectiveness of gradient-based features as descriptors - such as HOG, HOF, and N-Jets - for video-based human action recognition. They are capable of capturing both the salient spatialand temporal information in the video sequences, while removing much of the redundant information that is not pertinent to the action. Combining these features in a hierarchical fashion further increases performance.

Seller Inventory # 9783668642607

Bibliographic Details

• Title: Demystifying Human Action Recognition in Deep Learning with Space-Time Feature Descriptors
• Publisher: GRIN Verlag
• Publication Date: 2018
• Language: English
• ISBN 10: 3668642605
• ISBN 13: 9783668642607
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 210W x 148H x 4D millimeters 210 millimeters width by 148 millimeters height by 4 millimeters depth
• Weight: 73 grams

About this title

Synopsis

Research Paper (postgraduate) from the year 2018 in the subject Computer Science - Internet, New Technologies, , course: Machine Learning, language: English, abstract: Human Action Recognition is the task of recognizing a set of actions being performed in a video sequence. Reliably and efficiently detecting and identifying actions in video could have vast impacts in the surveillance, security, healthcare and entertainment spaces. The problem addressed in this paper is to explore different engineered spatial and temporal image and video features (and combinations thereof) for the purposes of Human Action Recognition, as well as explore different Deep Learning architectures for non-engineered features (and classification) that may be used in tandem with the handcrafted features. Further, comparisons between the different combinations of features will be made and the best, most discriminative feature set will be identified. In the paper, the development and implementation of a robust framework for Human Action Recognition was proposed. The motivation behind the proposed research is, firstly, the high effectiveness of gradient-based features as descriptors - such as HOG, HOF, and N-Jets - for video-based human action recognition. They are capable of capturing both the salient spatial and temporal information in the video sequences, while removing much of the redundant information that is not pertinent to the action. Combining these features in a hierarchical fashion further increases performance.

About the Author

Mike Nkongolo received the BSc (Hons) degree in computer science from the University of the Witwatersrand, Johannesburg, South Africa, in 2016. He is currently working toward the Masters degree in the School of Computer Science and Applied Mathematics, University of the Witwatersrand. His research interests include the theory and applications of Intelligent Systems, Web-based platforms and Machine Learning, Sentiment detection in Web Mining, and Artificial Intelligence-Natural Languages Processing.