Robust Multi Sensor Classification via Jointly Sparse Representation
Abstract
In this project, we have developed various novel collaborative sparse representation methods for multi-sensor classification problem, which take into account correlation as well as complementary information between heterogeneous sensors simultaneously while considering joint sparsity within each sensor's observations. We also robustify our models to deal with the presence of sparse noise and low-rank interference terms. Especially, we observe that incorporating the noise or interfered signal as a low-rank component is essential in a multi-sensor problem when multiple co-located sources/sensors simultaneously record the same physical event. Essentially, our proposal combines the strengths of multiple ideas: (i) incorporating related information from different sources (sensors) to achieve an improvement in the classification performance; (ii) extracting and suppressing a large, dense and correlated (hence low-rank) signal/noise interference normally appeared in multi-sensor data; and (iii) exploiting prior structure in sparsity representations for efficiency and robustness.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 14, 2016
- Accession Number
- AD1009706
Entities
People
- Trac D. Tran
Organizations
- Johns Hopkins University