OBJECT TRACKING USING PARTICLE FILTER

Abstract

In this project, a particle filter is implemented in a color model based framework to track the moving object in outdoor environment. firstly the initialisation of samples is done in first frame by drawing them randomly on the screen or drawing them based on the region where the object is expected to appear.

Next the samples are predicted based on system model by propagating each sample based on this model. The samples are updated based on the observation model. In this report, we use color distribution of the object as the observation model. Then using the bhattacharya distance, the similarity between the color distribution of the target & the samples can be measured. Based on the bhattacharya distance weight of each sample is measured. The target state estimation is performed based on samples weight. The resampling is performed for the next sample iteration to generate a new sample set. During the resampling sample with a high weight are chosen leading to identical copies, while others with relatively low weights may be ignored & deleted.