| Document Type
|
:
|
BL
|
| Record Number
|
:
|
666029
|
| Doc. No
|
:
|
dltt
|
| Main Entry
|
:
|
Ahad, Md. Atiqur Rahman
|
| Title & Author
|
:
|
Motion history images for action recognition and understanding\ Md. Atiqur Rahman Ahad
|
| Publication Statement
|
:
|
London ;New York :: Springer,, c2013
|
| Series Statement
|
:
|
SpringerBriefs in computer science
|
| Page. NO
|
:
|
1 online resource (131 p.)
|
| ISBN
|
:
|
9781447147305 (electronic bk.)
|
|
|
:
|
: 1447147308 (electronic bk.)
|
|
|
:
|
9781447147299
|
| Bibliographies/Indexes
|
:
|
Includes bibliographical references and index
|
| Contents
|
:
|
Motion History Images for Action Recognition and Understanding; Foreword; Preface; Acknowledgments; Contents; Acronyms; 1 Introduction; 1.1 Introduction; 1.2 Action/Activity: Nomenclature; 1.2.1 Atomic Actions; 1.2.2 Action; 1.2.3 Activity; 1.3 Various Dimensions of Action Recognition; 1.3.1 Applications; 1.3.2 Action Recognition is Difficult: Why?; 1.3.3 Some Assumptions on Action Recognition; 1.3.4 Action Recognition: Some Basic Steps; 1.3.5 Motion History Image; 1.4 Conclusion; 2 Action Representation; 2.1 Action Recognition; 2.2 Approaches on Bag-of-Features; 2.3 XYT: Space-Time Volume
|
|
|
:
|
2.3.1 Spatio-Temporal Silhouettes2.4 Interest-Point Detectors; 2.5 Local Discriminative Approaches; 2.5.1 Large-Scale Features-Based Recognition; 2.5.2 Local Patches-Based Recognition; 2.5.3 Mixed Approach for Recognition; 2.6 View-Invariant Approaches; 2.7 Conclusion; 3 Motion History Image; 3.1 Motion History Image and its Importance; 3.1.1 Applications of the MHI Method/Representation; 3.2 Motion History Image: A Tutorial; 3.2.1 Construction of the Motion Energy Image (MEI); 3.2.2 Construction of the Motion History Image (MHI); 3.2.3 Importance of the MHI and the MEI
|
|
|
:
|
3.3 Limitations of the MHI Method3.4 MHI and its Variants: 2D/3D; 3.4.1 View-Based MHI and its Variants; 3.4.2 View-Invariant MHI Representations; 3.5 Conclusion; 4 Action Datasets and MHI; 4.1 Various Datasets; 4.2 Datasets Employed in MHI; 4.2.1 KTH Dataset; 4.2.2 Weizmann Dataset; 4.2.3 IXMAS Dataset; 4.2.4 CASIA Gait Database; 4.2.5 Virtual Human Action Silhouette (ViHASi) Dataset; 4.2.6 CMU MoBo Dataset; 4.2.7 USF HumanID Dataset; 4.2.8 Marcel's Dynamic Hand Poster and Gesture Dataset; 4.2.9 TRECVID Dataset; 4.3 Conclusion; References; Index
|
| Abstract
|
:
|
Human action analysis and recognition is a relatively mature field, yet one which is often not well understood by students and researchers. The large number of possible variations in human motion and appearance, camera viewpoint, and environment, present considerable challenges. Some important and common problems remain unsolved by the computer vision community. However, many valuable approaches have been proposed over the past decade, including the motion history image (MHI) method. This method has received significant attention, as it offers greater robustness and performance than other te
|
| Subject
|
:
|
Computer vision
|
| Subject
|
:
|
Image processing-- Digital techniques
|
| Subject
|
:
|
Pattern recognition systems
|
| Dewey Classification
|
:
|
006.3/7
|
| LC Classification
|
:
|
TA1634.A43 2013
|
|
|
:
|
TA1634.A43 2013
|
| Added Entry
|
:
|
Ohio Library and Information Network
|