Human Action Recognition in Videos Employing 2-DPCA on 2DHHOF and Radon Transform / (Record no. 8807)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 06738nam 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 | Fadwa Fawzy Fouad |
| 245 1# - TITLE STATEMENT | |
| Title | Human Action Recognition in Videos Employing 2-DPCA on 2DHHOF and Radon Transform / |
| Statement of responsibility, etc. | Fadwa Fawzy Fouad |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Date of publication, distribution, etc. | 2013 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 90 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/>\1 Introduction 1<br/>1.1 Challenges and characteristics of the domain . . . . . . . . . . . . . . . . . . 2<br/>1.1.1 inter- and Intra-class variations . . . . . . . . . . . . . . . . . . . . . 2<br/>1.1.2 Environmental Variations and Capturing conditions . . . . . . . . . . 2<br/>1.1.3 Temporal variations . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3<br/>1.2 Proposed Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3<br/>2 Overview 5<br/>2.1 Input videos . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5<br/>2.2 Human detection/segmentation . . . . . . . . . . . . . . . . . . . . . . . . . 6<br/>2.2.1 Background subtraction . . . . . . . . . . . . . . . . . . . . . . . . . 8<br/>2.2.2 Optical Flow (OF) . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8<br/>2.2.3 Histogram of Oriented Gradients (HOG) . . . . . . . . . . . . . . . . 10<br/>2.3 Feature Extraction and Modeling . . . . . . . . . . . . . . . . . . . . . . . . 10<br/>2.3.1 Non-Parametric Approaches . . . . . . . . . . . . . . . . . . . . . . . 11<br/>2.3.2 Volumetric Approaches . . . . . . . . . . . . . . . . . . . . . . . . . . 12<br/>2.3.3 Parametric Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . 13<br/>2.4 Action Classication . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13<br/>2.4.1 Direct classication . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13<br/>2.4.2 Temporal state-space models . . . . . . . . . . . . . . . . . . . . . . . 16<br/>3 2DHOOF/2DPCA Contour Based Optical Flow Algorithm 18<br/>3.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18<br/>vi<br/>3.2 What 2DHOOF Features are . . . . . . . . . . . . . . . . . . . . . . . . . . . 19<br/>3.2.1 Optical Flow Techniques . . . . . . . . . . . . . . . . . . . . . . . . . 19<br/>3.2.2 Alignment issues with OF . . . . . . . . . . . . . . . . . . . . . . . . 22<br/>3.2.3 The Calculation of 2D Histogram of Optical Flow(2DHOOF) . . . . . 23<br/>3.3 Overall System Description . . . . . . . . . . . . . . . . . . . . . . . . . . . 28<br/>3.3.1 Training Mode . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29<br/>3.3.2 Testing Mode . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33<br/>3.4 Used Data-sets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34<br/>3.4.1 Weizmann Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34<br/>3.4.2 IXMAS Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34<br/>3.5 Experimental Results and Analysis . . . . . . . . . . . . . . . . . . . . . . . 35<br/>3.5.1 Weizmann Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35<br/>3.5.2 IXMAS Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41<br/>4 Human Gesture Recognition Employing Radon Transform/2DPCA 48<br/>4.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48<br/>4.2 Radon Transform (RT) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49<br/>4.3 Overall System Description . . . . . . . . . . . . . . . . . . . . . . . . . . . 51<br/>4.3.1 Training Mode . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52<br/>4.3.2 Testing Mode . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53<br/>4.4 Used Data-sets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54<br/>4.4.1 ChaLearn Gesture Data . . . . . . . . . . . . . . . . . . . . . . . . . 54<br/>4.5 Experimental Results and Analysis . . . . . . . . . . . . . . . . . . . . . . . 55<br/>4.5.1 Input videos . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55<br/>4.5.2 Segmentation and Blob extraction . . . . . . . . . . . . . . . . . . . . 55<br/>4.5.3 Alignment using RT of the First Frame . . . . . . . . . . . . . . . . . 60<br/>4.5.4 Video Chopping . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62<br/>4.5.5 Calculate the MEI and MHI . . . . . . . . . . . . . . . . . . . . . . . 66<br/>4.5.6 Get Radon Transform for MEI and MHI . . . . . . . . . . . . . . . . 68<br/>4.5.7 2DPCA and Feature Extraction . . . . . . . . . . . . . . . . . . . . . 69<br/>vii<br/>5 Conclusion 73<br/>5.1 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 73<br/>5.2 Future Work . . |
| 520 3# - Abstract | |
| Abstract | Abstract:<br/>Human action recognition is a very important trend of research with a great interest in<br/>computer vision area. It has applications in various elds such as surveillance, content-based<br/>video retrieval, gesture recognition and sports analysis. The speed, storage requirements,<br/>and accuracy of the human action recognition system are highly dependent on the extracted<br/>features, and modeling approaches. All dierent recognition techniques aim to extract the<br/>most representative and accurate features with low storage requirements. In this thesis, two<br/>algorithms are proposed for human action recognition which target the high accuracy and<br/>the low computation complexity.<br/>For the rst algorithm the novel Two Dimensions Histogram of Oriented Optical <br/>ow<br/>(2DHOOF) features where extracted using the actor's contour. Two Dimensions Principal<br/>Component Analysis (2DPCA) was used for feature extraction. The Euclidean Distance<br/>Classier was used for the nal classication decision. Experimental results applied on<br/>Weizmann and the IXMAS datasets achieved the highest reported recognition accuracy and<br/>the fastest runtime compared to recent methods.<br/>In the second algorithm Radon Transform (RT) was extracted from the moving parts of<br/>the actor. Using RT enables us to easily align the actor's silhouette with the center of the<br/>frame without the need of further pre-processing. 2DPCA was used for feature extraction.<br/>The Euclidean Distance Classier was used for the nal classication decision. Experimental<br/>results applied on one shot learning ChaLearn Gesture Data-set achieved high recognition<br/>accuracy and the fast runtime.<br/>Experimental results promote our algorithms for real time applications. |
| 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 |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Home library | Current library | Date acquired | Total Checkouts | Full call number | Date last seen | Price effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | Not For Loan | Main library | Main library | 01/12/2021 | 610/ FF.H 2013 | 01/12/2021 | 01/12/2021 | Thesis |