Earticle

초록

영어

Tracking is an important process of computer vision research. But still after so many researches accuracy is still become a bottleneck. Within different tracking techniques covariance based tracking is a new technique which gives more accuracy than other techniques. There are several methods and researches have been done on covariance tracking. The covariance tracking process also uses some distance measures to calculate the dissimilarity between two target regions. Here we have list down some of the most useful distance measurement techniques which provide accurate results. We have also implemented those distance measurement techniques and shown their results with accuracy comparison. Even the distance between the target and the candidate covariance matrix is itself enough track an object, but to get more accurate result some techniques are applied on covariance tracking. Here we have listed some of those techniques which happen to provide better results after applying on covariance tracking and also pointed out the advantages and drawbacks of those techniques.

목차

Abstract
 1. Introduction
 2. Introduction to Covariance Tracking
  2.1. Feature Matrix Design
  2.2. Covariance Matrix Embodiment
  2.3. Techniques for Dissimilarity Measurements
 3. Diverse Techniques of Covariance Tracking
  3.1. Kernel Based Tracking
  3.2. Better Occlusion Handling Technique
  3.3. Otha Color Method
  3.4. Salient Feature Matching
  3.5. Particle Filtering Approach:
 4. Experiment Result
 5. Conclusion
 References

키워드

저자

• Sanchita Singha [ School of Computer Engineering KIIT University Bhubaneswar, Odissa, India ]
• Sujoy Datta [ School of Computer Engineering KIIT University Bhubaneswar, Odissa, India ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605