Abstract:A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem. Moreover, to improve performance without increasing complexity, we augment the input by including several maps of nonlinear radiometric indices typical of remote sensing. Experiments on three representative datasets show the proposed method to provide very promising results, largely competitive with the current state of the art in terms of both full-reference and no-reference metrics, and also at a visual inspection.

We recently proposed a convolutional neural network (CNN) for remote sensing image pansharpening obtaining a significant performance gain over the state of the art. In this paper, we explore a number of architectural and training variations to this baseline, achieving further performance gains with a lightweight network which trains very fast. Leveraging on this latter property, we propose a target-adaptive usage modality which ensures a very good performance also in the presence of a mismatch w.r.t. the training set, and even across different sensors. The proposed method, published online as an off-theshelf software tool, allows users to perform fast and high-quality CNN-based pansharpening of their own target images on generalpurpose hardware.

No abstract

Despeckling techniques based on the nonlocal approach provide an excellent performance, but exhibit also a remarkable complexity, unsuited to time-critical applications. In this letter, we propose a fast nonlocal despeckling filter. Starting from the recent SAR-BM3D algorithm, we propose to use a variable-size search area driven by the activity level of each patch, and a probabilistic early termination approach that exploits speckle statistics in order to speed up block matching. Finally, the use of look-up tables helps in further reducing the processing costs. The technique proposed conjugates excellent performance and low complexity, as demonstrated on both simulated and real-world SAR images and on a dedicated SAR despeckling benchmark.

No abstract

We present a new image segmentation algorithm based on a tree-structured binary MRF model. The image is recursively segmented in smaller and smaller regions until a stopping condition, local to each region, is met. Each elementary binary segmentation is obtained as the solution of a MAP estimation problem, with the region prior modeled as an MRF. Since only binary fields are used, and thanks to the tree structure, the algorithm is quite fast, and allows one to address the cluster validation problem in a seamless way. In addition, all field parameters are estimated locally, allowing for some spatial adaptivity. To improve segmentation accuracy, a split-and-merge procedure is also developed and a spatially adaptive MRF model is used. Numerical experiments on multispectral images show that the proposed algorithm is much faster than a similar reference algorithm based on "flat" MRF models, and its performance, in terms of segmentation accuracy and map smoothness, is comparable or even superior.

The solution-processability of organic photodetectors allows a straightforward combination with other materials, including inorganic ones, without increasing cost and process complexity significantly compared with conventional crystalline semiconductors. Although the optoelectronic performance of these organic devices does not outmatch their inorganic counterparts, there are certain applications exploiting the benefit of the solution-processability. Here we demonstrate that the small pixel fill factor of present complementary metal oxide semiconductor-imagers, decreasing the light sensitivity, can be increased up to 100% by replacing silicon photodiodes with an organic photoactive layer deposited with a simple low-cost spray-coating process. By performing a full optoelectronic characterization on this first solution-processable hybrid complementary metal oxide semiconductor-imager, including the first reported observation of different noise types in organic photodiodes, we demonstrate the suitability of this novel device for imaging. Furthermore, by integrating monolithically different organic materials to the chip, we show the cost-effective portability of the hybrid concept to different wavelength regions.

In this study, we demonstrate the feasibility of TCO-free, fully sprayed organic photodiodes on flexible polyethylene terephthalate (PET) substrates. Transparent conducting films of single-wall carbon nanotubes are spray deposited from aqueous solutions. Low roughness is achieved, and films with sheet resistance values of 160 Ω/sq at 84% in transmittance are fabricated. Process issues related to the wetting of CNTs are then examined and solved, enabling successive spray depositions of a poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate) (PEDOT:PSS) layer and a blend of regioregular poly(3-hexylthiophene-2,5-diyl) and [6,6]-phenyl C61 butyric acid methyl ester (PCBM). The active layer is then optimized, achieving a process yield above 90% and dark currents as low as 10(-4) mA/cm(2). An external quantum efficiency of 65% and high reproducibility in the performance of the devices are obtained. Finally, the impact of the characteristics of the transparent electrode (transmittance and sheet resistance) on the performances of the device are investigated and validated through a theoretical model and experimental data.