Qualitative Performance Metrics For Object Tracking Algorithms

Volume 4 Issue 4 October - December 2017

Research Paper

Qualitative Performance Metrics For Object Tracking Algorithms

Harihara Santosh Dadi*, Gopala Krishna Mohan Pillutla**, Madhavi Latha Makkena***

* Associate Professor, Aditya Institute of Technology and Management, Hyderabad, India.

** Professor, Institute of Aeronautical College of Engineering, Hyderabad, India.

*** Professor, Department of Electronics and Communication Engineering, JNT University, Telangana, India.

Dadi, H.S., Pillutla, G.K.M. and Makkena, M.L. (2017). Qualitative Performance Metrics for Object Tracking Algorithms. i-manager’s Journal on Image Processing, 4(4), 1-15. https://doi.org/10.26634/jip.4.4.14164

Abstract

In this paper, Qualitative metrics for object tracking algorithms is introduced. The two algorithms are subjectively analyzed, and four different types of datasets based on occlusion strength, contrast, illumination, and clutter are taken. Each dataset is of simple and hard type. Gaussian Mixture Model (GMM) and Weighted Running Window Background (WRWB) model based GMM are the two human tracking algorithms taken for subjective analysis. The algorithms are verified for both easy and hard type datasets. The performance metrics show that these parameters are best to analyze any object tracking algorithms subjectively. Precision and recall parameters are considered for subjective analysis.