Online Selection of Tracking Features Using AdaBoost

This paper presents an online feature selection algorithm for video object tracking. Using the object and background pixels from the previous frame as training samples, we model the feature selection problem as finding a good subset of features to better classify object from background in current frame. This paper aims to improve existing methods by taking correlation between features into consideration. We propose to use AdaBoost algorithm to iteratively select one feature which best compensates the previously selected features. Using the selected features, we then construct a compound likelihood image, which shows the ability to discriminate better than the original frame, as the input for the tracking process. We also propose to use ellipse fitting to eliminate mislabeled pixels from our training process. In addition, we propose an online feature validity test to monitor the selected features and only re-select features when the previously selected features become out-of-date. Experimental results demonstrate that the proposed algorithm combined with mean-shift based tracking algorithm achieves very promising results.