Abstract
A great deal of robustness is allowed when visual tracking is considered as a classification problem. This paper combines a finite number of weak classifiers in a SMC framework as a strong classifier. The time-varying ensemble parameters (confidence of weak classifiers) are regarded as sequential arriving states and their posterior distribution is estimated in a Bayesian manner. Therefore, both the adaptiveness and stability are kept for the ensemble classification in handling scene changes and target deformation. Moreover, to increase the tracking accuracy, weak classifiers including Support Vector Machine (SVM) and Large Margin Distribution Machine (LDM) are combined as a hybrid strong one, with adaptiveness to the sample scales. Comprehensive experiments are performed on benchmark videos with various tracking challenges, and the proposed method is demonstrated to be better than or comparable to the state-of-the-art trackers.
Highlights
The goal of visual tracking is to locate the target states over a video sequence
Represented by an appropriate visual model, the detection region is projected into the feature space as samples, positive ones for the target and negative ones for the background
The detection region is represented as pyramid patches
Summary
The goal of visual tracking is to locate the target states over a video sequence. Usually, the tracking-by-detection methods can be categorized into two main branches: the generative model and the discriminative model. Scale-adaptive hybrid weak classifiers are weightcombined as the strong classifier Their weights are modelled in a SMC framework to realize more generality, and both the classifiers group and their weights are updated in the time sequence. We propose updating the ensemble tracker in a Bayesian framework We update both the weight vectors and the pool of weak classifiers after the classification stage in each time step to evolve the model. Features play an important role in tracking performance [26].We employ a patches-based visual model to generate weak hypotheses. We represent the detection region in a pyramid model as in [27] and provide features with various scales to the weak classifiers In this way, the target is observed in a multiscale model. To resolve this constraint optimization problem, the dual coordinate descent method (CD) is employed; and the solution details can be found in the paper [23] of Gao and Zhou
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
