Recently, deep hashing dominated single label image retrieval approaches. However, the complex nature of remote sensing images, which likely contains multi-labels, hardly benefits from the above approaches. To overcome single-label image retrieval limitations in remote sensing domain, we address this problem by proposing a multi-label remote sensing image retrieval (MLRSIR-NET) framework. Specifically, the proposed MLRSIR-NET composed of two main sub-networks: multi-level feature extraction and deep hash. The multi-level feature extraction network predicts multi-level features to exploit different levels of Convolution Neural Network (CNN (characteristics. To suppress discriminative feature representation, the multi-level features are aggregated and feed to Convolutional Block Attention Module (CBAM) to amplify the representation of relevant multi-label features. CBAM is flexibly integrated into our network with end-to-end training. The hash network stacked two fully connected layers aimed to learn multiple hashing functions to encode the feature vector into a compact hash code. Finally, we conduct experiments on two benchmarks for multi-label images: Dense Labelling Remote Sensing Dataset (DLRSD) and Wuhan Dense Labeling Dataset (WHDLD) to systematically assess the performance. The results show that the proposed framework improved the accuracy in terms of Mean Average Precision (MAP) by a considerable margin of 85.4%, 87.2%, 90.8% and 92.9% for 12-bit, 24-bit, 32-bit and 48-bit code lengths respectively on DLRSD. For WHDLD, it can be noted that the proposed framework supers the DCH by 93.8%, 98.7%, 91.9%, and 94.6% on average respectively.
Abstract-this paper examined the applicability of quantum genetic algorithms to solve optimization problems posed by satellite image enhancement techniques, particularly superresolution, and fusion. We introduce a framework starting from reconstructing the higher-resolution panchromatic image by using the subpixel-shifts between a set of lower-resolution images (registration), then interpolation, restoration, till using the higher-resolution image in pan-sharpening a multispectral image by weighted IHS+Wavelet fusion technique. For successful superresolution, accurate image registration should be achieved by optimal estimation of subpixel-shifts. Optimal-parameters blind restoration and interpolation should be performed for the optimal quality higher-resolution image. There is a trade-off between spatial and spectral enhancement in image fusion; it is difficult for the existing methods to do the best in both aspects. The objective here is to achieve all combined requirements with optimal fusion weights, and use the parameters constraints to direct the optimization process. QGA is used to estimate the optimal parameters needed for each mathematic model in this framework "Super-resolution and fusion." The simulation results show that the QGA-based method can be used successfully to estimate automatically the approaching parameters which need the maximal accuracy, and achieve higher quality and efficient convergence rate more than the corresponding conventional GAbased and the classic computational methods.
Microalgae-based biodiesel synthesis is currently not commercially viable due to the high costs of culture realizations and low lipid yields. The main objective of the current study was to determine the possibility of growing Nannochloropsis oceanica on Saccharomyces cerevisiae yeast wastewater for biodiesel generation at an economical rate. N. oceanica was grown in Guillard F/2 synthetic medium and three dilutions of yeast wastewater (1, 1.25, and 1.5%). Biodiesel properties, in addition to carbohydrate, protein, lipid, dry weight, biomass, lipid productivity, amino acids, and fatty acid methyl ester (FAMEs) content, were analyzed and the quality of the produced biodiesel is assessed. The data revealed the response of N. oceanica to nitrogen-deficiency in the three dilutions of yeast wastewater. N. oceanica in Y2 (1.25%) yeast wastewater dilution exhibited the highest total carbohydrate and lipid percentages (21.19% and 41.97%, respectively), and the highest lipid productivity (52.46 mg L−1 day −1) under nitrogen deficiency in yeast wastewater. The fatty acids profile shows that N. oceanica cultivated in Y2 (1.25%) wastewater dilution provides a significant level of TSFA (47.42%) and can be used as a feedstock for biodiesel synthesis. In addition, N. oceanica responded to nitrogen shortage in wastewater dilutions by upregulating the gene encoding delta-9 fatty acid desaturase (Δ9FAD). As a result, the oleic and palmitoleic acid levels increased in the fatty acid profile of Y2 yeast wastewater dilution, highlighting the increased activity of Δ9FAD enzyme in transforming stearic acid and palmitic acid into oleic acid and palmitoleic acid. This study proved that the Y2 (1.25%) yeast wastewater dilution can be utilized as a growth medium for improving the quantity of specific fatty acids and lipid productivity in N. oceanica that affect biodiesel quality to satisfy global biodiesel requirements.
The satellite images fusion is a process of merging data of the same scene from the panchromatic (PAN) and multispectral (MS) images captured by different instruments. This paper introduces a new satellite images fusion method using Bidimensional Empirical Mode Decomposition (BEMD) and shearlet Transform (ST). BEMD is an efficient method for satellite images processing due to its advantage of spectral data maintaining. Basically, it is used to transform the MS image into subsets named Intrinsic Mode Functions (IMFs). Hence these IMFs and the PAN image are divided by shearlet into high and low frequencies subsets, then the high frequency ones of IMFs are replaced with their corresponding subsets of the PAN image. At last, inverse shearlet and inverse BEMD are implemented to get the fused MS image. Shearlet is preferred due to its optimal representation of the anisotropic elements in the image and due to its capability in processing the continuity and digital data unlike curvelet and contourlet. The experiment results illustrated that the proposed method extracts more spatial details from PAN images with fewer losses in spectral quality of MS images compared to other classic fusion methods. For more enhancements, the fusion weights are estimated efficiently by a quantum genetic algorithm (QGA)-based approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.