Author : Kavita V. Wagh 1
Date of Publication :28th February 2018
Abstract: The paper includes the different tracking methods, classify them into different categories according to its performance, speed, accuracy. Tracking, in general, is a challenging problem. Difficulties in tracking any object or human can arise due to its abrupt motion, changing appearance patterns of both human and the scene, nonrigid object structures, object-to-object and object to-scene occlusions, and camera motion. The goal of human tracking is segmenting a region of interest from a video scene and keeping track of its motion, positioning, and occlusion. Human detection and classification are preceding steps for tracking human in the sequence of images. Detection is performed to check the existence of an object in the video and to precisely locate that object. The detected object can be classified into various categories like human, vehicle, floating clouds, swaying trees and other moving objects. It is used in video surveillance, robot vision, traffic monitoring, Animation. The paper presents a brief analysis and comparative study of algorithms i.e Kalman Filter and Particle filter related to human tracking.
Reference :
-
- Kaipio, J. and Somersalo, E., 2004, Statistical and Computational Inverse Problems, Applied Mathematical Sciences 160, Springer-Verlag.
- Maybeck, P., 1979, Stochastic models, estimation and control, Academic Press, New York.
- Kavita Vilas Wagh and Dr. R.K.Kulkarni, Human Tracking System, International Technological Conference-2014 (I-TechCON), Jan. 03 – 04, 2014
- Kaipio, J., Duncan S., Seppanen, A., Somersalo, E., Voutilainen, A., 2005, State Estimation for Process Imaging, Chapter in Handbook of Process Imaging for Automatic Control, editors: David Scott and Hugh McCann, CRC Press.
- Chandrashekhar N. Padole, Luís A. Alexandre,” Motion based Particle Filter for Human Tracking with Thermal Imaging”, Third International Conference on Emerging Trends in Engineering and Technology, 978-0-7695-4246-1/10 $26.00 © 2010 IEEE DOI 10.1109/ICETET.2010.120.