Abstract

Most image fusion algorithms based on hyperspectral unmixing perform worse with the lower spatial resolution of hyperspectral image (HSI) for the reason that the estimated endmembers and abundance deviate from the truth value. Therefore, it is more meaningful to unmix the low spatial resolution hyperspectral image (LRHSI) accurately, which is also helpful to improve the image fusion performance. In order to enhance the spatial resolution of LRHSI, this article proposes an alternating direction iterative nonnegative matrix factorization (ADINMF) based on linear hyperspectral unmixing algorithm. It takes multispectral image as a constraint to improve the spatial resolution of LRHSI. First, we use blind source separation to initialize the endmember and abundance of hyperspectral and multispectral images, respectively. Then, we alternately update the endmembers and abundance in the framework of nonnegative matrix factorization by multiplication iterative algorithm. The updated endmembers and abundance are constrained to each other. We compare the experimental results of simulated dataset and three groups of real datasets. Experimental results show that the proposed method not only accurately extracts the endmembers of LRHSI, but also obtains a significant fusion performance improvement.

Highlights

  • T HE spectral resolution of hyperspectral image (HSI) is usually less than 10 nm, and its spectral dimension contains rich material information

  • The simulated data are consisted by nine substances in USGS spectral library as shown in Fig. 1, which are generated by the simulation program proposed by Hendrix et al [24]

  • We propose an alternating direction iterative nonnegative matrix factorization (ADINMF) algorithm for low spatial resolution hyperspectral image (LRHSI) and multispectral image (MSI) fusion

Read more

Summary

Introduction

T HE spectral resolution of hyperspectral image (HSI) is usually less than 10 nm, and its spectral dimension contains rich material information. HSI plays an important role in image classification, mineral detection, and other fields. The spatial resolution of most HSI is low, which is, on the one hand, related to the tradeoff between data volume and the signal-to-noise ratio (SNR) limitations, and, on the other hand, related to the different applications requirements [1]. The spatial resolution of different hyperspectral sensors is different. The spatial resolution of HYDICE hyperspectral sensor is 2 m per pixel, whereas the spatial resolution of AVIRIS hyperspectral sensor is 20 m per pixel.

Objectives
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.