Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben

2011 | Buch

Introduction Kapitel lesen Erstes Kapitel lesen

Computer Vision and Action Recognition

A Guide for Image Processing and Computer Vision Community for Action Understanding

verfasst von: Md. Atiqur Rahman Ahad

Verlag: Atlantis Press

Buchreihe : Atlantis Ambient and Pervasive Intelligence

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

Human action analyses and recognition are challenging problems due to large variations in human motion and appearance, camera viewpoint and environment settings. The field of action and activity representation and recognition is relatively old, yet not well-understood by the students and research community. Some important but common motion recognition problems are even now unsolved properly by the computer vision community. However, in the last decade, a number of good approaches are proposed and evaluated subsequently by many researchers. Among those methods, some methods get significant attention from many researchers in the computer vision field due to their better robustness and performance. This book will cover gap of information and materials on comprehensive outlook – through various strategies from the scratch to the state-of-the-art on computer vision regarding action recognition approaches. This book will target the students and researchers who have knowledge on image processing at a basic level and would like to explore more on this area and do research. The step by step methodologies will encourage one to move forward for a comprehensive knowledge on computer vision for recognizing various human actions.

Inhaltsverzeichnis

Frontmatter
Chapter 1. Introduction
Abstract
This book deals with action and activity recognition. In seven chapters, this book covers nomenclature of actions, application realms, low-level processing issues for action representations, various approaches for action recognition, motion history image method, shape representations and feature vector analysis, action datasets, and some future issues. In this Chapter, we define action and its nomenclature, and applications of action recognition.
Md. Atiqur Rahman Ahad
Chapter 2. Low-level Image Processing for Action Representations
Abstract
In this book, readers are assumed to have basic knowledge of various low-level image processing. Therefore, this chapter will not cover everything that is related to action representations and understanding. However, we cite some issues, which we consider more relevant and important for action analysis.
Md. Atiqur Rahman Ahad
Chapter 3. Action Representation Approaches
Abstract
This chapter concentrates on various action or activity recognition approaches. The field of action and activity representation and recognition is relatively old, yet still immature [500]. However, various excellent surveys on human activity analysis and related issues have illustrated different methods and approaches for motion analysis [436, 447, 448, 452, 481, 488–507, 641]. This chapter concisely covers most of the recent advancements on human motion recognition. Among the various motion analysis related surveys, [436, 447, 448, 481, 489, 500–502, 641] cover the issues related to human motion recognition extensively.
Md. Atiqur Rahman Ahad
Chapter 4. MHI: A Global-based Generic Approach
Abstract
The Motion History Image (MHI) approach is a view-based temporal template approach, which is simple but robust in representing movements and is widely employed by various research groups for action recognition, motion analysis and other related applications. In this paper, we overview the Motion History Image (MHI)-based human motion recognition techniques and applications. Since the inception of the Motion History Image template for motion representation, various approaches have been adopted to improve this basic MHI technique. Ahad et al. [641] survey the MHI and its variants.
Md. Atiqur Rahman Ahad
Chapter 5. Shape Representation and Feature Vector Analysis
Abstract
In earlier chapters, we present various feature points for different perspectives. However, one key concern is to track these points from one frame to another or on image sequences. This section analyzes frame-to-frame feature point detection and tracking algorithms due to their importance in action understanding. In order to reconstruct a 3D structure from image sequences we have to track feature points on the sequence.
Md. Atiqur Rahman Ahad
Chapter 6. Action Datasets
Abstract
Based on the contents of the previous chapters, it is evident that human action understanding and recognition are exploited for different applications in the field of computer vision and human-machine interaction. However, different researchers experiment with various datasets, having different number of subjects, variations in gender, size, number of action classes, background, number of cameras and their respective positions, image size, illumination, indoor or outdoor, fixed or moving cameras, etc.
Md. Atiqur Rahman Ahad
Chapter 7. Challenges Ahead
Abstract
This last chapter illustrates some future issues based on the present progress of action recognition and understanding. Some of the aspects mentioned here may seem very difficult to accomplish soon, but due to the presence of growing research community in this arena, we can be very hopeful about the future.
Md. Atiqur Rahman Ahad
Backmatter
Metadaten
Titel
Computer Vision and Action Recognition
verfasst von
Md. Atiqur Rahman Ahad
Copyright-Jahr
2011
Verlag
Atlantis Press
Electronic ISBN
978-94-91216-20-6
Print ISBN
978-94-91216-19-0
DOI
https://doi.org/10.2991/978-94-91216-20-6

Premium Partner

    Bildnachweise