Confidence-Based Dynamic Classifier Combination For Mean-Shift Tracking

TL;DR

This paper presents a new mean-shift tracking method that dynamically fuses two classifiers based on confidence levels, significantly improving tracking accuracy in visual object tracking tasks.

Contribution

It introduces a novel confidence-based classifier fusion technique within mean-shift tracking, enhancing robustness and accuracy over traditional methods.

Findings

Dynamic classifier fusion improves tracking accuracy.

The method adapts contributions based on confidence measures.

Experimental results show significant performance gains.

Abstract

We introduce a novel tracking technique which uses dynamic confidence-based fusion of two different information sources for robust and efficient tracking of visual objects. Mean-shift tracking is a popular and well known method used in object tracking problems. Originally, the algorithm uses a similarity measure which is optimized by shifting a search area to the center of a generated weight image to track objects. Recent improvements on the original mean-shift algorithm involves using a classifier that differentiates the object from its surroundings. We adopt this classifier-based approach and propose an application of a classifier fusion technique within this classifier-based context in this work. We use two different classifiers, where one comes from a background modeling method, to generate the weight image and we calculate contributions of the classifiers dynamically using their confidences to generate a final weight image to be used in tracking. The contributions of the classifiers are calculated by using correlations between histograms of their weight images and histogram of a defined ideal weight image in the previous frame. We show with experiments that our dynamic combination scheme selects good contributions for classifiers for different cases and improves tracking accuracy significantly.