5 January 2018 Improved compressive tracking based on pixelwise learner
Author Affiliations +
J. of Electronic Imaging, 27(1), 013003 (2018). doi:10.1117/1.JEI.27.1.013003
This work expands upon state-of-the-art multiscale tracking based on compressive sensing (CT) by increasing the overall tracking accuracy. A pixelwise classification stage is incorporated in the CT-based tracker to obtain a relatively stable appearance model, by distinguishing object pixels from the background. In addition, we identify potential distracting regions that are used in a feedback strategy to handle occlusion and avoid drifting toward nearby regions with similar appearances. We evaluate our approach on several benchmark datasets to demonstrate its effectiveness with respect to the state-of-the-art tracking algorithms.
© 2018 SPIE and IS&T
Ting Chen, Hichem Sahli, Yanning Zhang, Tao Yang, "Improved compressive tracking based on pixelwise learner," Journal of Electronic Imaging 27(1), 013003 (5 January 2018). https://doi.org/10.1117/1.JEI.27.1.013003 Submission: Received 5 April 2017; Accepted 4 December 2017
Submission: Received 5 April 2017; Accepted 4 December 2017

Detection and tracking algorithms

Optical tracking


Compressed sensing

Statistical modeling

Target detection

Feature extraction

Back to Top