Search

This paper considers problems associated with the large size of the hyperspectral pansharpening network and difficulties associated with learning its spatial-spectral features. We propose a deep mutual-learning-based framework (SSML) for spectral-spatial information mining and hyperspectral pansharpening. In this framework, a deep mutual-learning mechanism is introduced to learn spatial and spectral features from each other through information transmission, which achieves better fusion results without entering too many parameters. The proposed SSML framework consists of two separate networks for learning spectral and spatial features of HSIs and panchromatic images (PANs). A hybrid loss function containing constrained spectral and spatial information is designed to enforce mutual learning between the two networks. In addition, a mutual-learning strategy is used to balance the spectral and spatial feature learning to improve the performance of the SSML path compared to the original. Extensive experimental results demonstrated the effectiveness of the mutual-learning mechanism and the proposed hybrid loss function for hyperspectral pan-sharpening. Furthermore, a typical deep-learning method was used to confirm the proposed framework's capacity for generalization. Ideal performance was observed in all cases. Moreover, multiple experiments analysing the parameters used showed that the proposed method achieved better fusion results without adding too many parameters. Thus, the proposed SSML represents a promising framework for hyperspectral pansharpening. [ABSTRACT FROM AUTHOR]

Pansharpening fuses spectral information from the multi-spectral image and spatial information from the panchromatic image, generating super-resolution multi-spectral images with high spatial resolution. In this paper, we proposed a novel 3D multi-scale attention convolutional network (MSAC-Net) based on the typical U-Net framework for multi-spectral imagery pansharpening. MSAC-Net is designed via 3D convolution, and the attention mechanism replaces the skip connection between the contraction and expansion pathways. Multiple pansharpening layers at the expansion pathway are designed to calculate the reconstruction results for preserving multi-scale spatial information. The MSAC-Net performance is verified on the IKONOS and QuickBird satellites' datasets, proving that MSAC-Net achieves comparable or superior performance to the state-of-the-art methods. Additionally, 2D and 3D convolution are compared, and the influences of the number of convolutions in the convolution block, the weight of multi-scale information, and the network's depth on the network performance are analyzed. [ABSTRACT FROM AUTHOR]

Deep learning constitutes a significant recent advance in machine learning and has been particularly successful in applications related to image processing, where it can already surpass human accuracy in some cases. In this paper, the use of a convolutional neural network, AlexNet, pretrained on a database of images of common objects was used as is to extract features from flotation froth images. These features could subsequently be used to predict the conditions or performance of the flotation systems. Two case studies are considered. In the first, froth regimes in an industrial flotation plant could be identified significantly more reliably with the features generated by AlexNet than with previous state-of-the-art approaches, such as wavelets, grey level co-occurrence matrices or local binary patterns. In the second case study, the arsenic concentration in the batch flotation of realgar-orpiment-quartz mixtures could be predicted more accurately than was possible with features extracted by wavelets, grey level co-occurrence matrices, local binary patterns or by use of colour. These results suggest that feature extraction with convolutional neural networks trained on complex data sets from other domains can serve as more reliable methods than previous state-of-the-art approaches to froth image analysis. [ABSTRACT FROM AUTHOR]

• Online analysis of particulate feed in mineral processing is not well established. • Segmentation of images of densely packed particles is a challenging task. • Here, particle boundaries were explicitly included in image segmentation. • The results obtained with a U-net neural network were promising. • Segmentation could be further improved with superpixelation of images. Particle size distributions in ore feed systems, as well as the identification of particles in these feed systems can provide important information in the advanced control of unit operations in mineral processing, such as crushing and grinding circuits. Image analysis has long been considered a promising approach to achieve this, as it is an inexpensive, unobtrusive means of acquiring information rich measurements. It typically requires segmentation of images in order to identify individual particles. This is a challenging task to accomplish reliably, as variable lighting, fines adhering to larger particles or contiguous particles, as well as variable particle sizes and shapes can all compromise the accuracy of traditional algorithms. Image segmentation with deep learning methods have recently been investigated to surmount these difficulties. In this investigation, U-net and U-net with superpixel preprocessing with simple linear iterative clustering (SLIC) are proposed and compared with a traditional watershed algorithm. The U-net approaches were markedly more reliable than the watershed algorithm. In addition, preprocessing of the images with SLIC resulted in further improvement of the results. [ABSTRACT FROM AUTHOR]