Sparse Representation Based Multi Object Tracking using GPU
Anuja Kumar Acharya1, Rajalakshmi Satapathy2, Biswajit Sahoo3
1Anuja Kumar Acharya, School of Computer Engineering, KIIT University, Bhubaneswar (Odisha), India.
2Rajalakshmi Satapathy, School of Computer Engineering, KIIT University, Bhubaneswar (Odisha), India.
3Biswajit Sahoo, School of Computer Engineering, KIIT University, Bhubaneswar (Odisha), India.
Manuscript received on 07 December 2019 | Revised Manuscript received on 15 December 2019 | Manuscript Published on 31 December 2019 | PP: 585-591 | Volume-9 Issue-2S December 2019 | Retrieval Number: B10551292S19/2019©BEIESP | DOI: 10.35940/ijitee.B1055.1292S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This work proposes a sparse based representation for tracking multi object for the longer sequence of video frame. Object of interest are first identified and then represented with set of low dimensional feature covariance matrix. These feature of different object are kept in a dictionary. In order to classify the object, sparse based Orthogonal matching pursuit(OMP) algorithm is used. Furthermore, towards reducing the computational overhead, proposed model is implemented on a graphical processing unit enhanced with the multi threaded resource for parallelization of the task. Experimental results shows that proposed method out perform as compared with the state of art in identifying the objects.
Keywords: Sparse Representation, OMP, Feature Space, GPU, CUDA.
Scope of the Article: Parallel Computing on GPU