MARC details
| 000 -LEADER |
|---|
| fixed length control field |
08232nam a22002537a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
210112b2013 a|||f mb|| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE |
|---|
| Original cataloging agency |
EG-CaNU |
| Transcribing agency |
EG-CaNU |
| 041 0# - Language Code |
|---|
| Language code of text |
eng |
| Language code of abstract |
eng |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
610 |
| 100 0# - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
abubakrelsedik alsebai karali |
| 245 1# - TITLE STATEMENT |
|---|
| Title |
Fusion of Motion History of Skeletal Volumes and Temporal Bounding Volumes for View-Invariant Human Action Recognition / |
| Statement of responsibility, etc. |
abubakrelsedik alsebai karali |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. |
|---|
| Date of publication, distribution, etc. |
2013 |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
71 p. |
| Other physical details |
ill. |
| Dimensions |
21 cm. |
| 500 ## - GENERAL NOTE |
|---|
| Materials specified |
Supervisor: Mohamed A. El-Helw |
| 502 ## - Dissertation Note |
|---|
| Dissertation type |
Thesis (M.A.)—Nile University, Egypt, 2013 . |
| 504 ## - Bibliography |
|---|
| Bibliography |
"Includes bibliographical references" |
| 505 0# - Contents |
|---|
| Formatted contents note |
Contents:<br/>Chapter 1 Introduction ............................................................................................................... 10<br/>1.1 Introduction and Problem Statement ............................................................................ 10<br/>1.2 Objectives and Approach .............................................................................................. 11<br/>1.3 Dissertation Overview .................................................................................................. 11<br/>1.4 Publications and Awards............................................................................................... 12<br/>1.5 Conclusion ................................................................................................................... 12<br/>Chapter 2 Background ............................................................................................................... 13<br/>2.1 Human Action Recognition .......................................................................................... 13<br/>2.2 Human Action Recognition System Block Diagram .................................................... 14<br/>2.3 Related Work ................................................................................................................ 16<br/>2.3.1 Work Utilizes 3D Data.............................................................................................. 16<br/>2.4 3d Shape Features ......................................................................................................... 18<br/>2.5 Skeletons and Skeletonization ...................................................................................... 20<br/>2.6 Skeleton Properties ....................................................................................................... 21<br/>2.6.1 Blum Skeleton Properties ......................................................................................... 21<br/>2.6.2 Curve Skeleton Properties......................................................................................... 25<br/>2.7 Pattern Recognition ....................................................................................................... 27<br/>2<br/>2.7.1 Naïve Bayesian ......................................................................................................... 28<br/>2.7.2 K-Star ........................................................................................................................ 28<br/>2.7.3 Multilayer Perceptron ............................................................................................... 29<br/>2.7.4 Logistic Model Trees ................................................................................................ 29<br/>2.7.5 C4.5 Decision Trees .................................................................................................. 30<br/>2.7.6 Multiple Classifier Systems ...................................................................................... 30<br/>2.8 Conclusion .................................................................................................................... 32<br/>Chapter 3 Framework for Activity Classification ..................................................................... 33<br/>3.1 Feature extraction.......................................................................................................... 34<br/>3.1.1 Motion History of Skeletal Volumes for Human Action Recognition ..................... 34<br/>3.1.2 Motion History of Skeletal Volumes (MHSV) ......................................................... 35<br/>3.1.3 Motion Temporal Change in Bounding Volume (TCBV) ........................................ 36<br/>3.1.4 Temporal Changes in Bounding Volumes (TCBVS) ............................................... 39<br/>3.2 Processing And Classification ...................................................................................... 40<br/>3.2.1 Motion History Of Skeletal Volumes Classification ................................................ 40<br/>3.2.2 Temporal Changes in Bounding Volumes Classification ......................................... 42<br/>3.2.3 MHSV And TCBV Decision Fusion Using Multiple Classifier Systems ................ 42<br/>3.3 Conclusion .................................................................................................................... 43<br/>Chapter 4 Experiments and Evaluation ..................................................................................... 45<br/>4.1 Datasets ......................................................................................................................... 45<br/>4.1.1 The IXMAS Dataset ................................................................................................. 45<br/>4.1.2 The I3DPOST Dataset .............................................................................................. 47<br/>4.2 Motion History of Skeletal Volume Results ................................................................. 47<br/>3<br/>4.3 Temporal Changes in Bounding Volumes Results ....................................................... 52<br/>4.4 Fusion ............................................................................................................................ 54<br/>4.5 Conclusion .................................................................................................................... 57<br/>Chapter 5 Conclusion and Future work ..................................................................................... |
| 520 3# - Abstract |
|---|
| Abstract |
Abstract:<br/>Human Activity Recognition is an active area of research in computer vision with wide range of<br/>applications in video surveillance, motion analysis, virtual reality interfaces, robot navigation<br/>and recognition, video indexing, browsing, HCI, choreography, ports video analysis, to name a<br/>few. It consists of analyzing the characteristic features of various human actions and classifying<br/>them. A human activity recognition system typically consists of the following stages:<br/>background subtraction, tracking, feature extraction and classification.<br/>Several approaches have been developed to solve this problem in 2D and 3D spaces. Due<br/>to the enhanced robustness of 3D vision-based recognition techniques, we focus in this thesis on<br/>human action recognition from 3D data. We present a framework for reliable action recognition<br/>systems designed to achieve the objective of automatic classification of ongoing activities in<br/>unlabeled 3D sequences. The major challenges within this framework are the extraction of<br/>representative motion descriptors and the usage of suitable classification methods to build a<br/>model for each motion. to this end, the thesis introduces a novel view-invariant features (a) the<br/>motion history of skeletal volumes and (b) the temporal change in bounding volumes, where<br/>both are used to describe specific actions. Furthermore, we propose a number of classification<br/>techniques for action recognition as well as decision fusion rules to combine decisions when the<br/>human action recognition system deals with multiple features using state-of-art multiple<br/>classifier systems. Obtained results demonstrate that skeletons produce better results than<br/>volumes and that the use of bounding volumes along with the skeletons further improves the<br/>recognition accuracy and can hence be used to recognize human actions independent of<br/>viewpoint and scale. |
| 546 ## - Language Note |
|---|
| Language Note |
Text in English, abstracts in English. |
| 650 #4 - Subject |
|---|
| Subject |
Informatics-IFM |
| 655 #7 - Index Term-Genre/Form |
|---|
| Source of term |
NULIB |
| focus term |
Dissertation, Academic |
| 690 ## - Subject |
|---|
| School |
Informatics-IFM |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
Dewey Decimal Classification |
| Koha item type |
Thesis |
| 650 #4 - Subject |
|---|
| -- |
266 |
| 655 #7 - Index Term-Genre/Form |
|---|
| -- |
187 |
| 690 ## - Subject |
|---|
| -- |
266 |