Hyperspectral remote sensing IQA via learning multiple kernels from mid-level features

Hyperspectral image quality assessment (HIQA) is an indispensable technique in both academic and industry domain However, HIQA is still a challenging task since those fine-grained and quality-aware visual details are difficult to be captured. Compared with the conventional low-level features, mid-le...

Full description

Saved in:
Bibliographic Details
Published in:Signal processing. Image communication 2020-04, Vol.83, p.115804, Article 115804
Main Authors: Chen, Guobin, Zhang, Yu, Wang, Suling
Format: Article
Language:English
Subjects:
Algorithms
Deep features
Hyperspectral image quality assessment
Hyperspectral imaging
Image quality
Image reconstruction
Kernels
Mathematical analysis
Matrix algebra
Matrix methods
Mid-level feature
Mosaics
Multiple kernel learning
Quality assessment
Quality-aware
Remote sensing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hyperspectral image quality assessment (HIQA) is an indispensable technique in both academic and industry domain However, HIQA is still a challenging task since those fine-grained and quality-aware visual details are difficult to be captured. Compared with the conventional low-level features, mid-level features usually contain more semantic and quality clues and exhibit higher discriminant ability. Thus, we aim to leverage the mid-level features for HIQA. More specifically, three-scale superpixel mosaics are generated from the input image pre-processed by PCA. Each superpixel scale corresponds to various homogeneousobject parts. Subsequently, three mid-level visual features (fisher vector, combined mean features, reconstructed image matrix) as well as deep features of hyperspectral images are calculated with three-scale superpixel images to constitute multiple kernels. Afterwards, we integrate these kernels into a multimodal one, which is further integrated into a feature vector by row-wise stacking. The image quality evaluation can be calculated based on the designed similarity metric. Comprehensive experiments have demonstrated the effectiveness of our proposed HIQA algorithm. •The designed mid-level features can better represent attributes of hyperspectral images.•The designed framework can integrate multiple scale features of hyperspectral images.•Comprehensive experiments have demonstrated the effectiveness of our proposed HIQA algorithm.
ISSN:0923-5965
1879-2677
DOI:10.1016/j.image.2020.115804