12 May 2018 Adaptive multiclass correlation filters and its applications in the time series recognition
Author Affiliations +
Abstract
The adaptive multiclass correlation filters (AMCF) method is proposed to exploit different kinds of features and information in a unified framework for recognition. Theoretical investigation into AMCF shows that it obtains a closed-form subsolution to constrain the optimization objective, simplifying the entire inference mechanism in the multiclass classification. The time series recognition problems, such as human action recognition and radar behavior recognition, are important yet challenging tasks. However, it is still time-consuming to acquire enough labeled training samples. AMCF is capable to exploit different kinds of features to solve the time series recognition problem. With this new correlation filters-based method, we extend the original signals and handle the insufficient training set effectively. Experiments are done on the depth image based action recognition and radar behavior recognition with a small number of training examples, including MSRAction3D, MSRGesture3D, UTD-MHAD, and radar behavior datasets. Particularly, we demonstrate that the proposed action recognition system is based on the completed local binary patterns and AMCF, and successfully achieves superior performances over the state-of-the-arts.
© 2018 SPIE and IS&T
Linlin Yang, Linlin Yang, Ce Li, Ce Li, Chunyu Xie, Chunyu Xie, Linna Wang, Linna Wang, Baochang Zhang, Baochang Zhang, } "Adaptive multiclass correlation filters and its applications in the time series recognition," Journal of Electronic Imaging 27(3), 033010 (12 May 2018). https://doi.org/10.1117/1.JEI.27.3.033010 . Submission: Received: 9 January 2018; Accepted: 13 April 2018
Received: 9 January 2018; Accepted: 13 April 2018; Published: 12 May 2018
JOURNAL ARTICLE
10 PAGES


SHARE
RELATED CONTENT

Adaptive image sequence noise filtering methods
Proceedings of SPIE (November 01 1991)
Three-dimensional color image processing procedures using DSP
Proceedings of SPIE (February 26 2007)
AFMM solution to the benchmark radar tracking problem
Proceedings of SPIE (July 15 1999)
Comparison of color median filters
Proceedings of SPIE (September 07 1998)
Scalable face synthesis algorithm
Proceedings of SPIE (September 21 2001)

Back to Top