|
Mukesh A. Zaveri Research Interest
Computer Vision, Image Processing |
Contact Information
Department of Computer Science and Engineering |
Ph D Department of Electrical Engineering, Indian Institute of Technology Bombay, April 2005
M.E. (Microprocessor Systems & Applications) Electrical Engineering, M. S. University of Baroda, May 1993
B.E. Electronics, S. V. R. College of Engg. and Tech, Surat (REC, Surat), July 1990
6 Feb 2019 - 6 Feb 2022 : Head, Department of Computer Science and Engineering, S. V. National Institute of Technology, Surat
3 Feb 2010 - 19 Dec 2011, 24 Nov 2015 - 25 Nov 2016 : Professor In-Charge Central Computer Center, SVNIT, Surat
2 Feb 2007 - 3 Feb 2010 : Head, Computer Engineering Department, S. V. National Institute of Technology, Surat
28 Jan 2019 - Present : Professor, Department of Computer Science and Engineering, S. V. National Institute of Technology, Surat
16 Oct 2006 - 27 Jan 2019 : Associate Professor, Computer Engineering Department, S. V. National Institute of Technology, Surat
March 2009 - Feb 2010 : Reliance Chair Professor, Computer Engineering Department, S. V. National Institute of Technology, Surat
April 2005 - Oct 2006 : Assistant Professor, Computer Engineering Department, S. V. National Institute of Technology, Surat
Aug 1993 - April 2005 : Lecturer, Computer Engineering Department, S. V. National Institute of Technology, Surat
July 2001 - July 2004 : On deputation for Ph D under QIP at IIT Bombay
Aug 1992 - Aug 1993 : at ORG Systems, R&D, Baroda
Jan 1991 - July 1991 Instrumentation Trainee Engineer at Citurgia Biochemicals Ltd., Surat
Nov 1990 - Jan 1991 Instrumentation Trainee Engineer at Garden Silk Mills, Vareli, Surat
Ph.D. Thesis Title: Detection and Tracking of Point Targets in IR Video Sequence
Under the guidance of Prof. Uday B. Desai and Prof. S. N. Merchant, Electrical Engineering Department, IIT Bombay
(This research project was funded by Department of Extramural Research and Intellectual Property Rights, (IRDE Lab) DRDO, Govt. of India, New Delhi.)
In this thesis the algorithms are introduced to detect and track targets in an air-borne infrared image sequences. The algorithms are mainly developed for detection and tracking of multiple point targets without using any apriori information about the target dynamics. Generally, the movement of the targets is arbitrary. The tracking algorithms must be able to track maneuvering and non-maneuvering targets simultaneously. The detection of point target is very challenging task due to lack of any texture information. In such a case, the motion is used as a cue and the detection algorithm is proposed which uses the wavelet transform for temporal multiscale decomposition. The algorithm is further extended for detecting the approaching targets in infrared image sequences.
The detection is followed by the tracking of multiple point targets in the presence of dense clutter. Two important factors for success of any tracking algorithms are; the selection of the dynamic model used for tracking and the data association method used for observation to track assignment. The data association is required for updating the target hidden state parameters. In the thesis various tracking algorithms are proposed targeting mainly the following issues: (i) tracking arbitrary movement of the targets with minimal number of models (ii) robust and efficient data association method and, (iii) the filtering method used for tracking.
Data association is crucial in the presence of multiple targets and clutter. In the current research work, the various methods are explored (a) based on an implicit observation to track assignment, and (b) the methods which evaluates the assignment weights for each observation and subsequently, these weights are used for state update. The use of assignment weights of data association avoids the uncertainty about the origin of an observation. The later method uses all observations, validated by means of statistical minimum distance criterion, for state update and does not assign an observation to any track implicitly. In this context, various data association methods based on (a) implicit observation to track assignment, i.e. nearest neighbor method, using state vector of the model and the genetic algorithm, (b) assignment weights for each observation using Expectation Maximization algorithm, neural network, Markov random field, and the genetic algorithm, have been proposed.
The proposed target detection and tracking algorithms are as follows:
Infrared Search and Tracking System (IRST) for IRDE Lab, DRDO (Govt. of India), Dehradun, December 2003. Project invigilator: Prof. Uday B. Desai and Prof. S. N. Merchant, Department of Electrical Engineering, Indian Institute of Technology Bombay
Single Target Tracking (STT) for ADA, Bangalore, December 2004. Project invigilator: Prof. Uday B. Desai and Prof. S. N. Merchant, Department of Electrical Engineering, Indian Institute of Technology-Bombay
Co-PI for Indian Digital Heritage (IDH) -Hampi DST sponsored project on Immersive Navigation for Walk through Application, Research project proposed jointly by DAIICT, Gadhinagar and SVNIT, Surat, 18 January 2011 - 31 July 2016 (Rs. 37.6 lacs) DST No. F.No. NRDMS/11/1586/2009/Phase-II (Project No:23)
PI for MeitY (DeitY) research project on Collaborative Data Processing and Resource Optimization for Post Disaster Management and Surveillance using Internet of Things sponsored by the Ministry of Communications & Information Technology, Department of Electronics & Information Technology, Government of India, New Delhi, vide Administrative Approval No. 13(4)/2016-CC&BT dated 18 July 2016, received on 25 July 2016 for a duration of three years (Sanctioned Amount Rs. 65 lacs, Released Amount 57.2 lacs, Status: Completed 25 July 2016 - August 31 2019)
Indian Society for Technical Education (ISTE) Life Membership number: LM 15557
Computer Society of India (CSI): Associate Life Membership Life Membership number: 00130379
Cryptology Research Society of India Life Membership number: L/268 Life
10th Ranked in Surat Center in S.S.C. Board Examination (85.67%)
Awarded merit scholarship as per scheme of Ministry of Human Resources Development, Government of India, New Delhi for all four years of B.E.
First class with distinction throughout all the eight semesters of B.E. (overall 72.47%)
Secured 97.6 percentile in Electronics subject paper and overall percentile 88.20 in GATE- 1990 examination
First class with distinction throughout all the three semesters of M.E. and first rank in the M.S. University (overall 83.57%)
CPI at Ph. D. Course work