Moving Objects Detection Using Machine Learning

ISBN-13: 9783030909093 / Angielski / Miękka / 2021 / 96 str.

Navneet Ghedia;Chandresh Vithalani;Ashish M. Kothari

Opis

This book shows how machine learning can detect moving objects in a digital video stream. The authors present different background subtraction approaches, foreground segmentation, and object tracking approaches to accomplish this. They also propose an algorithm that considers a multimodal background subtraction approach that can handle a dynamic background and different constraints. The authors show how the proposed algorithm is able to detect and track 2D & 3D objects in monocular sequences for both indoor and outdoor surveillance environments and at the same time, also able to work satisfactorily in a dynamic background and with challenging constraints. In addition, the shows how the proposed algorithm makes use of parameter optimization and adaptive threshold techniques as intrinsic improvements of the Gaussian Mixture Model. The presented system in the book is also able to handle partial occlusion during object detection and tracking. All the presented work and evaluations were carried out in offline processing with the computation done by a single laptop computer with MATLAB serving as software environment.

Spis treści

Chapter1. Introduction.- Chapter2. Existing Research in Video Surveillance System .- Chapter3. Background Modeling.- Chapter4. Object Tracking.- Chapter5. Summary of Book.

O autorze

Dr. Navneet Ghedia is currently working as a Principal & Professor in Electronics and Communication Department, Sanjaybhai Rajguru College of Engineering, Rajkot. Dr. Navneet Ghedia received his Ph.D. degree in Image and Video Processing from Gujarat Technological University, Ahmedabad, Gujarat in 2018 with outstanding research contribution in his doctoral research program. He has over 20 years of academic and 5 year of industrial experience in research, teaching and entrepreneurship. His research interests are focused on Video Processing, Image Processing, Speech and Signal Processing. He is having more than 18 Research Publications in referred and Indexed Journals. The innovative teaching practices he introduced include integrating entrepreneurship into class material as well as involving engineering students with the local community. Also, he is active participant in various international in referred organizations, program committees and reviewer of journals. He is committed to excellence for his work and has a mission to embark and embrace students with Deep Knowledge and resources by taking academia to next level by incorporating with large corporations, non-profits organizations and research centers.

Dr. Chandresh Vithalani is currently working as Head of Department & Professor in Electronics and Communication Department, Government Engineering College, Rajkot. Dr. Vithalani received his Ph.D. degree from Gujarat University, Ahmedabad, Gujarat in 2006 with outstanding research contribution in his doctoral research program. He has more than 23 years of academic and phenomenal deep intense of industrial experience in research, teaching and entrepreneurship namely Hindustan Conductors Pvt. Ltd., Canada India Institute Industry Linkage Project, Telecom officer at Telecommunication department and many more to go. He is also a man with strength in field of Electronics and telecommunication by means of deep internships, as a tutor, a coach and upskilled work by internship and training from renowned organizations and research centers. His research interests are focused on Video Processing, Image Processing, Speech Analysis and Signal Processing, Wireless Communication and many more are a few to refer his strength in different conglomerate of areas. He is having more than 32 Research Publications in various International and National Journals in referred and Indexed Journals namely IEEE International Journal, ISSN, Internal ARAB Journal etc. He is famed for as a distinguished personality due to his energetic active participation and enthusiasm in numerous seminars and Workshops which forged him into a precious knowledge of library. He has delivered many expert talks on magnificent topics in field of electronics & Communication in esteemed organization namely Tata Telecom Ltd., SVNIT, I.E.T.E Center- Vadodara, Government Institutes, private Institutes and many more. He guided more than 100 Post Graduations dissertation, 8 Ph.D. Students and many other Ph. D students are still currently under the guidance of him.

Dr. Ashish Kothari received his Ph.D. in Digital Video Watermarking from JJT University, Rajasthan, India in 2013. He is working as a Deputy Registrar, Atmiya University, Gujarat, India. He is also working as an Associate professor and Electronics and Communication Engineering, Atmiya Institute of Technology and Science, Rajkot, Gujarat, India. He is also recognized Ph.D. supervisor at Gujarat Technological University, Ahmedabad, Gujarat, India. His area of research interest is Image Processing, Video Processing, Digital Watermarking, and Signal Processing. He has published 2 books, 1 book chapters and more than 25 research papers to his credit in refereed & indexed journals, and conferences at the international and national level. His international recognition includes his professional memberships & services in refereed organizations, program committees and reviewer for journals.

Dr. Rohit Thanki is a computer vision expert and AI researcher with more than 8 years of research and development experience in computer vision, artificial intelligence, medical image analysis & security, and biometrics, including more than 3 years of academic experience in various engineering institutions in India. Presently, he is working as a head of research & development, Prognica Labs Tech FZCO, Dubai, UAE. Also, he was associated as a software consultant for Ennoventure Technologies Private Limited, Bengaluru, India. He earned his bachelor's in electronics & communication, a master's in communication engineering, and a doctorate in electronics & communication specializing in digital image processing and biometric security. His areas of research interest are medical image analysis, artificial intelligence, machine learning, deep learning, digital watermarking, biometric security, compressive sensing, and signal processing. He has over 40 publications to his credit and has published in reputed journals with high impact factors and international conferences indexing in Scopus / SCIE / WOS. Also, He has authored and contributed more than 20 books with respected publishers, i.e., Springer, CRC Press, Elsevier, De Gruyter, and IGI Global. In addition, he has been invited as a reviewer in various reputed journals such as IEEE Transactions on Audio, Speech and Natural Language Processing, ACM Transactions on Multimedia Computing, Communications and Applications, IEEE Consumer Electronics Magazine, IEEE Access, IEEE Journal of Biomedical and Health Informatics, Signal Processing: Image Communication, Pattern Recognition, Computers, and Electrical Engineering, Informatics in Medicine, Journal of Ambient Intelligence and Humanized Computing, IET Biometrics, and IET Image Processing.