Abstract
The increasing availability of sensors enables the combination of a high-spatial-resolution panchromatic image and a low-spatial-resolution multispectral image, which has become a hotspot in recent years for many applications. To address the spectral and spatial distortions that adversely affect the conventional methods, a pan-sharpening method based on a convolutional neural network (CNN) architecture is proposed in this paper, where the low-spatial-resolution multispectral image is upgraded and integrated with the high-spatial-resolution panchromatic image to produce a new multispectral image with high spatial resolution. Based on the pyramid structure of the CNN architecture, the proposed method has high learning capacity to generate more representative and robust hierarchical features for construction tasks. Moreover, the highly nonlinear fusion process can be effectively simulated by stacking several linear filtering layers, which is suitable for learning the complex mapping relationship between a high-spatial-resolution panchromatic and low-spatial-resolution multispectral image. Both qualitative and quantitative experimental analyses were carried out on images captured from a Landsat 8 on-board operational land imager (LOI) sensor to demonstrate the method’s performance. The results regarding the sensitivity analysis of the involved parameters indicate the effects of parameters on the performance of our CNN-based pan-sharpening approach. Additionally, our CNN-based pan-sharpening approach outperforms other existing conventional pan-sharpening methods with a more promising fusion result for different landcovers, with differences in Erreur Relative Globale Adimensionnelle de Synthse (ERGAS), root-mean-squared error (RMSE), and spectral angle mapper (SAM) of 0.69, 0.0021, and 0.81 on average, respectively.
Highlights
High-resolution remote sensing imagery contains sufficient target details and dynamically offers global observation data for many military and civilian applications
The pan-sharpening-based method [5] to combine multispectral and panchromatic images can effectively obtain high-spatial-resolution multispectral images such that the fused images have the characteristics of high spatial resolution and high spectral resolution at the same time
To deal with the mentioned challenges from which the state-of-the-art pan-sharpening methods suffer, this study presents a convolutional neural network (CNN)-based pan-sharpening approach for representing the mapping relationships such that a high-spatial-resolution multispectral imagery is produced while maintaining the spectral information
Summary
High-resolution remote sensing imagery contains sufficient target details and dynamically offers global observation data for many military and civilian applications (such as aeronautics [1], astronautics [1], hazard monitoring [2], and military reconnaissance [3]). To deal with the mentioned challenges from which the state-of-the-art pan-sharpening methods suffer, this study presents a CNN-based pan-sharpening approach for representing the mapping relationships such that a high-spatial-resolution multispectral imagery is produced while maintaining the spectral information. The contributions of this paper are as follows: (1) To avoid annotating a large-scale dataset and training the network from scratch, the CNN-based pan-sharpening method based on a transfer learning strategy is proposed to produce high-spatial-resolution multispectral imagery while maintaining the spectral information; and (2) both qualitative and quantitative experimental analyses were carried out on images captured from Landsat 8’s on-board operational land imager (LOI) sensor to verify the effectiveness and robustness of the proposed CNN-based architecture.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
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