Model-based visual tracking : the OpenTL framework / Giorgio Panin

Von:

Panin, Giorgio [aut]

Resource type: Ressourcentyp: Buch (Online)Buch (Online)Sprache: Englisch Verlag: Hoboken, N.J : Wiley, c2011Auflage: Online-AusgBeschreibung: Online-Ressource (1 online resource (xiii, 302 p.)) : illISBN:

9781283025737
1283025736
9780470943915

Weitere Titel:

Open Tracking Library framework

Schlagwörter:

Andere physische Formen: 9780470943915 | 9780470876138. | 1282073982 | 9780470876138 | Erscheint auch als: 1282073982 Druck-Ausgabe | Erscheint auch als: 9780470876138 Druck-Ausgabe | Erscheint auch als: Model-based visual tracking. Druck-Ausgabe Hoboken, N.J : Wiley, 2011. XIII, 302 S.DDC-Klassifikation:

006.37
006.3/7

MSC: MSC: *68T45 | 68U10 | 94A08 | 68-04 | 68-02RVK: RVK: ST 278LOC-Klassifikation:

TA1634

Online-Ressourcen:

Zugang im Netz des KIT

Zusammenfassung: This book has two main goals: to provide a unifed and structured overview of this growing field, as well as to propose a corresponding software framework, the OpenTL library, developed by the author and his working group at TUM-Informatik. The main objective of this work is to show, how most real-world application scenarios can be naturally cast into a common description vocabulary, and therefore implemented and tested in a fully modular and scalable way, through the defnition of a layered, object-oriented software architecture.The resulting architecture covers in a seamless way all processing levels, from raw data acquisition up to model-based object detection and sequential localization, and defines, at the application level, what we call the tracking pipeline. Within this framework, extensive use of graphics hardware (GPU computing) as well as distributed processing, allows real-time performances for complex models and sensory systems.Zusammenfassung: Intro -- MODEL-BASED VISUALTRACKING: The OpenTL Framework -- CONTENTS -- PREFACE -- CHAPTER 1: INTRODUCTION -- 1.1 OVERVIEW OF THE PROBLEM -- 1.1.1 Models -- 1.1.2 Visual Processing -- 1.1.3 Tracking -- 1.2 GENERAL TRACKING SYSTEM PROTOTYPE -- 1.3 THE TRACKING PIPELINE -- CHAPTER 2: MODEL REPRESENTATION -- 2.1 CAMERA MODEL -- 2.1.1 Internal Camera Model -- 2.1.2 Nonlinear Distortion -- 2.1.3 External Camera Parameters -- 2.1.4 Uncalibrated Models -- 2.1.5 Camera Calibration -- 2.2 OBJECT MODEL -- 2.2.1 Shape Model and Pose Parameters -- 2.2.2 Appearance Model -- 2.2.3 Learning an Active Shape or Appearance Model -- 2.3 MAPPING BETWEEN OBJECT AND SENSOR SPACES -- 2.3.1 Forward Projection -- 2.3.2 Back-Projection -- 2.4 OBJECT DYNAMICS -- 2.4.1 Brownian Motion -- 2.4.2 Constant Velocity -- 2.4.3 Oscillatory Model -- 2.4.4 State Updating Rules -- 2.4.5 Learning AR Models -- CHAPTER 3: THE VISUAL MODALITY ABSTRACTION -- 3.1 PREPROCESSING -- 3.2 SAMPLING AND UPDATING REFERENCE FEATURES -- 3.3 MODEL MATCHING WITH THE IMAGE DATA -- 3.3.1 Pixel-Level Measurements -- 3.3.2 Feature-Level Measurements -- 3.3.3 Object-Level Measurements -- 3.3.4 Handling Mutual Occlusions -- 3.3.5 Multiresolution Processing for Improving Robustness -- 3.4 DATA FUSION ACROSS MULTIPLE MODALITIES AND CAMERAS -- 3.4.1 Multimodal Fusion -- 3.4.2 Multicamera Fusion -- 3.4.3 Static and Dynamic Measurement Fusion -- 3.4.4 Building a Visual Processing Tree -- CHAPTER 4: EXAMPLES OF VISUAL MODALITIES -- 4.1 COLOR STATISTICS -- 4.1.1 Color Spaces -- 4.1.2 Representing Color Distributions -- 4.1.3 Model-Based Color Matching -- 4.1.4 Kernel-Based Segmentation and Tracking -- 4.2 BACKGROUND SUBTRACTION -- 4.3 BLOBS -- 4.3.1 Shape Descriptors -- 4.3.2 Blob Matching Using Variational Approaches -- 4.4 MODEL CONTOURS -- 4.4.1 Intensity Edges -- 4.4.2 Contour Lines.PPN: PPN: 807330248Package identifier: Produktsigel: ZDB-26-MYL | ZDB-30-PAD | ZDB-30-PQE

Exemplare ( 0 )

Dieser Titel hat keine Exemplare