Research On Fast Object Tracking Via Spatio-temporal Context Learning

Despite years of research,fast and high-performance target tracking algorithms are still missing.One of the key issues is that the spatio-temporal context information in frame video is not fully utilized,and this part of information has a significant impact on correlation filtering tracking performance.In order to solve the above problems,in this thesis,we develop fast object tracking algorithms mainly based on spatio-temporal context learning.The main contribution of this thesis is summarized as follows:(1)Despite the demonstrated success of numerous correlation filter(CF)based tracking approaches,their assumption of circulant structure of samples introduces significant redundancy to learn an effective classifier.In this paper,we develop a fast manifold regularized context-aware correlation tracking algorithm that mines the local manifold structure information of different types of samples.First,different from the traditional CF based tracking that only uses one base sample,we employ a set of contextual samples near to the base sample,and impose a manifold structure assumption on them.Afterwards,to take into account the manifold structure among these samples,we introduce a linear graph Laplacian regularized term into the objective of CF learning.Fortunately,the optimization can be efficiently solved in a closed form with fast Fourier transforms(FFTs),which contributes to a highly efficient implementation.Extensive evaluations on the OTB100 and VOT2016 datasets demonstrate that the proposed tracker performs favourably against several state-of-the-art algorithms in terms of accuracy and robustness.Especially,our tracker is able to run in real-time with 28 fps on a single CPU.(2)However,above-mentioned methods only employ a single correlation filter tracker and can not handle complex non-rigid deformation or color changes.In order to solve the problem,based on spatio-temporal regularization,we design a novel color-clustering histogram to make up the insufficiency of the standard correlation framework,presenting a dual color clustering and spatio-temporal regularized correlation regressions based complementary tracker(CSCT).The proposed CSCT includes two components with complementary merits to adaptively deal with significant color variations and deformations for each sequence: First,we design a novel color clustering based histogram model that first adaptively divides the colors of the target in the 1st frame into several cluster centers,and then the cluster centers are taken as references to construct adaptive color histograms for targets in the coming frames,which enable to adapt significant target deformations.Second,we propose to learn spatio-temporal regularized CFs,which not only enable to avoid boundary effects but also provides a more robust appearance model than the discriminative CFs in Staple in the case of large appearance variations.Compared with the state-of-the-art real-time trackers,our CSCT with handcrafted features achieves considerable performance on OTB100,Temple-Color and VOT2016 benchmarks,respectively.