Abstract
Object tracking is a challenging task in many computer vision applications due to occlusion, scale variation and background clutter, etc. In this paper, we propose a tracking algorithm by combining discriminative global and generative multi-scale local models. In the global model, we teach a classifier with sparse discriminative features to separate the target object from the background based on holistic templates. In the multi-scale local model, the object is represented by multi-scale local sparse representation histograms, which exploit the complementary partial and spatial information of an object across different scales. Finally, a collaborative similarity score of one candidate target is input into a Bayesian inference framework to estimate the target state sequentially during tracking. Experimental results on the various challenging video sequences show that the proposed method performs favorably compared to several state-of-the-art trackers.
Highlights
Object tracking plays an important role in the field of computer vision [1,2,3,4,5] and serves as a preprocessing step for a lot of applications in areas such as human-machine interaction [6], robot navigation [7] and intelligent transportation [8], etc
In [12], a tracking algorithm using the structural local sparse appearance model was proposed, which exploits both partial information and spatial information of the target based on an alignment-pooling method
Our tracker is compared with several state-of-the-art trackers, including tracking-learning-detection method (TLD) [27], structured output tracker (STRUCK) [28], tracking via sparse collaborative appearance model (SCM) [22], tracker with multi-task sparse learning (MTT) [29] and tracking with kernelized correlation filters (KCF) [19]
Summary
Object tracking plays an important role in the field of computer vision [1,2,3,4,5] and serves as a preprocessing step for a lot of applications in areas such as human-machine interaction [6], robot navigation [7] and intelligent transportation [8], etc. Current tracking algorithms based on an object appearance model can be roughly categorized into generative, discriminative or hybrid methods. In [12], a tracking algorithm using the structural local sparse appearance model was proposed, which exploits both partial information and spatial information of the target based on an alignment-pooling method. Yu et al [21]two utilized twomodels different models for tracking, where the target appearance described by linear subspaces and a discriminative classifier is trained to focus on recent appearance. Inspired by a hybrid tracking method by the of discriminative global global and generative multi-scale local models is proposed in thisDifferent paper. Our tracker exploits both partial and spatial information of an object across different scales.
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.
