Skip to content
naulon

Not checkedNot checked for notices yet.

Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection

C. J. Della Porta, Chein-I Chang

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 2021

doi:10.1109/jstars.2021.3128288 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

Compressive sensing (CS) has received considerable interest in hyperspectral sensing. Recent articles have also exploited the benefits of CS in hyperspectral image classification (HSIC) in the compressively sensed band domain (CSBD). However, on many occasions, the requirement of full bands is not necessary for HSIC to perform well. So, a great challenge arises in determining the minimum number of compressively sensed bands (CSBs), <italic>n</italic><sub>CSB</sub>, needed to achieve full-band performance. Practically, the value of <italic>n</italic><sub>CSB</sub> varies with the complexity of an imaged scene. Although virtual dimensionality (VD) has been used to estimate the number of bands to be selected, <italic>n</italic><sub>BS</sub>, it is not applicable to CSBD because a CSB is actually a mixture of <italic>n</italic><sub>CSB</sub> bands sensed by a random sensing matrix, while VD is used to estimate <italic>n</italic><sub>BS</sub> which is the number of single bands to be selected. As expected, <italic>n</italic><sub>CSB</sub> will be generally smaller than <italic>n</italic><sub>BS</sub>. To estimate an optimal value of <italic>n</italic><sub>CSB</sub>, two feature selection approaches, filter and wrapper methods, are proposed to extract scene features that can be used to estimate the minimum value of <italic>n</italic><sub>CSB</sub> required to maximize performance with minimum redundancy. Specifically, these methods are fully automated by leveraging optimal partitioning schemes which enable classification to further reduce storage requirements in CSBD. Finally, a set of experiments are conducted using real-world hyperspectral images to demonstrate the viability of the proposed approach.

Abstract licence: CC BY-NC-ND

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.