Visual Object Tracking using Deep Learning

AvAshish Kumar

Inbunden, Engelska, 2023

1 796 kr

Beställningsvara. Skickas inom 10-15 vardagar. Fri frakt över 249 kr.

Fler format och utgåvor

E-bok

977 kr

E-bok

977 kr

Häftad

808 kr

Beskrivning

This book covers the description of both conventional methods and advanced methods. In conventional methods, visual tracking techniques such as stochastic, deterministic, generative, and discriminative are discussed. The conventional techniques are further explored for multi-stage and collaborative frameworks. In advanced methods, various categories of deep learning-based trackers and correlation filter-based trackers are analyzed. The book also:Discusses potential performance metrics used for comparing the efficiency and effectiveness of various visual tracking methodsElaborates on the salient features of deep learning trackers along with traditional trackers, wherein the handcrafted features are fused to reduce computational complexityIllustrates various categories of correlation filter-based trackers suitable for superior and efficient performance under tedious tracking scenariosExplores the future research directions for visual tracking by analyzing the real-time applicationsThe book comprehensively discusses various deep learning-based tracking architectures along with conventional tracking methods. It covers in-depth analysis of various feature extraction techniques, evaluation metrics and benchmark available for performance evaluation of tracking frameworks. The text is primarily written for senior undergraduates, graduate students, and academic researchers in the fields of electrical engineering, electronics and communication engineering, computer engineering, and information technology.

Produktinformation

Utgivningsdatum:2023-11-20
Mått:156 x 234 x 16 mm
Vikt:449 g
Format:Inbunden
Språk:Engelska
Antal sidor:202
Förlag:Taylor & Francis Ltd
ISBN:9781032490533

Utforska kategorier

Mer om författaren

Dr. Ashish Kumar, Ph.D., is working as an assistant professor with Bennett University, Greater Noida, U.P., India. He has completed his Ph.D. in Computer Science and Engineering from Delhi Technological University (formerly DCE), New Delhi, India in 2020. He has received best researcher award from the Delhi Technological University for his contribution in the computer vision domain. He has completed M.Tech with distinction in computer Science and Engineering from GGS Inderpratha University, New Delhi. He has published many research papers in various reputed national and international journals and conferences. His current research interests include object tracking, image processing, artificial intelligence, and medical imaging analysis.

Recensioner i media

Select Guide Rating

Innehållsförteckning

Chapter 1Introduction to visual tracking in video sequences1.1 Overview of visual tracking in video sequences1.2 Motivation and challenges1.3 Real-time applications of visual tracking1.4 Emergence from the conventional to deep learning approaches1.5 Performance evaluation criteria1.6 SummaryChapter 2Background and research orientation for visual tracking appearance model: Standards and Models2.1 Background and preliminaries2.2 Conventional tracking methods2.3 Deep learning-based methods2.4 Correlation filter based visual trackers2.5 SummaryChapter 3Target feature extraction for robust appearance model3.1. Saliency feature extraction for visual tracking3.2 Handcrafted features3.3 Deep learning for feature extraction3.4 Multi-feature fusion for efficient tracking3.5 SummaryChapter 4Performance metrics for visual tracking: A Qualitative and Quantitative analysis4.1 Introduction4.2 Performance metrics for tracker evaluation4.3 Performance metrics without ground truth4.4 Performance metrics with ground truth4.5 SummaryChapter 5Visual tracking datasets: Benchmark for Evaluation5.1 Introduction5.2 Problem with the self-generated datasets5.3 Salient features of visual tracking public datasetsChapter 6Conventional framework for visual tracking: Challenges and solutions6.1 Introduction6.2 Deterministic tracking approach6.2.1 Meanshift and its variant-based trackers6.2.2 Multi-modal deterministic approach6.3 Generative tracking approach6.4 Discriminative tracking approach 6.5 SummaryChapter 7Stochastic framework for visual tracking: Challenges and Solutions7.1 Introduction7.2 Particle filter for visual tracking7.3 Framework and procedure7.4 Fusion of multi-feature and State estimation7.5 Experimental Validation of the particle filter based tracker7.6 Discussion on PF-variants based tracking7.7 SummaryChapter 8Multi-stage and collaborative framework for visual tracking 8.1 Introduction8.2 Multi-stage tracking algorithms8.3 Framework and procedures 8.4 Collaborative tracking algorithms8.5 SummaryChapter 9Deep learning based visual tracking model: A paradigm shift9.1 Introduction9.2 Deep learning-based tracking framework9.3 Hyper-feature based deep learning networks 9.4 Multi-modal based deep learning trackers9.5 SummaryChapter 10Correlation filter-based visual tracking model: Emergence and upgradation10.1 Introduction10.2 Correlation filter-based tracking framework10.3 Deep Correlation Filter based trackers10.4 Fusion-based correlation filter trackers10.5 Discussion on correlation filter-based trackers10.6 SummaryChapter 11Future prospects of visual tracking: Application Specific Analysis11.1 Introduction11.2 Pruning for deep neural architecture11.3 Explainable AI11.4 Application-specific visual tracking11.6 SummaryChapter 12Deep learning-based multi-object tracking: Advancement for intelligent video analysis12.1 Introduction12.2 Multi-object tracking algorithms12.3 Evaluation metrics for performance analysis 12.4 Benchmark for performance evaluation12.5 Application of MOT algorithms 12.6 Limitations of existing MOT algorithms 12.7 Summary