Comparative analysis of motion based and feature based algorithms for object detection and tracking

Object detection and tracking in the video sequence is a challenging task and time consuming process. Intrinsic factors like pose, appearance, variation in scale and extrinsic factors like variation in illumination, occlusion and clutter are major factors effecting this task. The main aim of this work is to implement and compare different algorithms in challenging conditions and find the algorithm that performs very efficiently on real time videos. In this paper, two motion based algorithms Zivkovic Adaptive Gaussian Mixture Model (ADGMM) and Grimson Gaussian Mixture Models (GGMM) and two feature based algorithms Speeded up Robust features (SURF) and Haar Cascade are implemented. The comparison of these algorithms in real life challenges and application is done to find out suitable algorithm for a particular application.