MARC details
| 000 -LEADER |
|---|
| fixed length control field |
08941nam a22002537a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
210112b2016 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 |
Abdelrahman Mohammed Elsayed Ahmed Eldesokey |
| 245 1# - TITLE STATEMENT |
|---|
| Title |
A Robust Feature-Based Visual Tracker For Micro-UAVs With Video Stabilization Enhancement / |
| Statement of responsibility, etc. |
Abdelrahman Mohammed Elsayed Ahmed Eldesokey |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. |
|---|
| Date of publication, distribution, etc. |
2016 |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
82 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, 2016 . |
| 504 ## - Bibliography |
|---|
| Bibliography |
"Includes bibliographical references" |
| 505 0# - Contents |
|---|
| Formatted contents note |
Contents:<br/>1 Chapter 1: INTRODUCTION ..............................................................................1<br/>1.1 Motivation and Objectives ............................................................................. 1<br/>1.2 Problem Definition ......................................................................................... 2<br/>1.3 Proposed Algorithm ....................................................................................... 2<br/>1.3.1 Algorithm Overview. .............................................................................. 2<br/>1.3.2 Tracking Enhancement using Video Stabilization .................................. 3<br/>1.3.3 Feature-Based Tracking with Context .................................................... 4<br/>1.3.4 Object Re-Detection after Full Occlusion ............................................... 4<br/>1.4 Thesis Organization ........................................................................................ 5<br/>2 Chapter 2: BACKGROUND ................................................................................6<br/>2.1 Unmanned Aerial Vehicles (UAVs) and their Evolution ............................... 6<br/>2.1.1 Evolution of UAVs ................................................................................. 6<br/>2.1.2 UAVs Types............................................................................................ 6<br/>2.1.3 UAVs Applications ................................................................................. 8<br/>2.2 Motion Compensation for Video Stabilization .............................................. 8<br/>2.3 Objects Detection and Tracking in Aerial Imagery ..................................... 10<br/>2.3.1 Object Detection in Aerial Imagery ...................................................... 10<br/>2.3.2 Object Tracking .................................................................................... 13<br/>2.3.3 State-of-Art Object Trackers ................................................................. 18<br/>2.4 Overview on Hand-Crafted Features ............................................................ 24<br/>2.4.1 Features from Accelerated Segment Test (FAST) ................................ 25<br/>2.4.2 Good Features To Track (GFTT) .......................................................... 26<br/>2.4.3 Scale-Invariant Feature Transform (SIFT) ........................................... 27<br/>2.4.4 Binary Robust Independent Elementary Features (BRIEF).................. 29<br/>2.4.5 Oriented FAST and Rotated BRIEF (ORB) ......................................... 30<br/>2.4.6 Binary Robust Invariant Scalable Keypoints (BRISK) ........................ 30<br/>vii<br/>3 Chapter 3: ROBUST FEATURE-BASED OBJECT TRACKING IN AERIAL<br/>IMAGERY WITH VIDEO STABILIZATION ...............................32<br/>3.1 Algorithm Architecture ................................................................................ 32<br/>3.2 The Choice of Video Stabilization and Object Tracking Techniques .......... 32<br/>3.3 Video Stabilization ....................................................................................... 33<br/>3.3.1 Pyramidal Lucas-Kanade Optical Flow ................................................ 34<br/>3.3.2 Homography Estimation using RANSAC ............................................ 35<br/>3.4 Object Tracking ............................................................................................ 37<br/>3.4.1 Choosing Feature Type ......................................................................... 38<br/>3.4.2 Object Model Initialization ................................................................... 38<br/>3.4.3 Non-Conflicting Features Matching ..................................................... 40<br/>3.4.4 Structure Consistency Check using RANSAC ..................................... 40<br/>3.4.5 Finding Object using Rigid Transformation Estimation ....................... 41<br/>3.4.6 Occlusion Detection and Pools Update ................................................. 41<br/>3.4.7 Feature Forgetting ................................................................................. 42<br/>3.4.8 Target Reacquisition After Occlusion .................................................. 42<br/>4 Chapter 4: RESULTS AND ANALYSIS ..........................................................45<br/>4.1 Datasets ........................................................................................................ 45<br/>4.2 Evaluation Metrics ....................................................................................... 47<br/>4.3 Qualitative Analysis ..................................................................................... 48<br/>4.4 Quantitative Analysis ................................................................................... 53<br/>5 Chapter 5: CONCLUSION AND FUTURE WORK .........................................62<br/>5.1 Conclusion Remarks .................................................................................... 62<br/>5.2 Summary of Contributions ........................................................................... 63<br/>5.3 Future Work ................................................................................................. 63<br/>REFERENCES ............................ |
| 520 3# - Abstract |
|---|
| Abstract |
Abstract:<br/>In this thesis, we propose an integrated framework for tracking targets of interest<br/>in aerial imagery acquired from micro unmanned aerial vehicles (MAVs). A tracker is<br/>very important for MAV target-oriented applications, such as search and rescue and<br/>traffic monitoring, as well as in cases where it is used as the main component for visual<br/>navigation. The task of visual tracking itself has been exhaustively investigated in the<br/>last few decades. Nevertheless, this task is significantly complicated in aerial imagery<br/>as several challenges arise. MAVs are very light and under-equipped, and hence<br/>vulnerable to vibrations due to air turbulence. The ‘trembling effects’ would lead to<br/>abrupt motion in the sequences captured by the on-board camera causing severe<br/>discrepancies in the video footage. Motion blur, focus changes and illumination<br/>variations are all examples of such discrepancies. The task of visual object tracking in<br/>MAV aerial video is further complicated by the conventional object tracking challenges<br/>such as scale changes, partial/full occlusions, similar-appearance objects, background<br/>clutter and pose alterations.<br/>We propose a visual tracker that is able to address the above challenges and<br/>perform the task of visual object tracking in aerial imagery efficiently. The problem of<br/>abrupt camera motion is addressed using video stabilization enhancement that<br/>estimates the global motion between consecutive frames and uses it to adjust the tracker<br/>search region. Problems due to background clutter and alike objects are alleviated using<br/>a structured object model based on robust features to discriminate between the target<br/>and background according to appearance and structure of the former. Target pose<br/>variations are addressed by making this structure adaptive to target appearance changes<br/>between video frames. Target tracking failures due to partial or full occlusions are<br/>alleviated using an improved target reacquisition mechanism that performs constrained<br/>search.<br/>The proposed tracker is evaluated against the state-of-art visual trackers on longduration<br/>real-life datasets using established evaluation metrics. The first sequence is<br/>taken from a quad copter and comprises most of the above-mentioned tracking<br/>challenges. The second sequence is a stabilized footage captured from a police<br/>helicopter and commonly used to evaluate visual trackers. The proposed tracker<br/>performs flawlessly in the first sequence using video stabilization enhancement<br/>whereas its robustness is demonstrated in the second sequence. Such claim is supported<br/>by quantitative analysis showing that our tracker outperforms existing trackers while<br/>sustaining real-time performance. Further qualitative analysis provides insights in the<br/>strengths of the proposed tracker versus the limitations of other trackers. |
| 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 |