UAV-based multispectral aerial image retrieval using spectral feature and semantic computing

The retrieval of Multispectral image is vast area in machine learning which has input data which is not static as per consideration. They has disadvantages in communication, memory in remote sensing area and compression over the lossy data which is very important, still it cannot be avoided for unnecessary objects. Because of the intricacies (spatial, ghastly, unique information sources, and fleeting irregularities) in on the web and time-arrangement multispectral picture investigation, there is a high event likelihood in varieties of otherworldly groups from an information stream, which decays the experiments in classification (in terms of accuracy) else can change as inefficient. For handling these problems with big data, deep learning is specifically efficient. By all accounts there is an extraordinary possibility for misusing the possibilities of such complex big data. The complex of retrieving remote sensed data with higher resolution in terms of effectiveness and accuracy, this research proposed architecture of neural network in feature extractionofimages collected from satellite using fast recurrent convolutional neural network (FRCNN). Here FRCNN is designed for retrieving the image collected by satellite without any loss of data and to identify objects and accurately locate them. Using the accuracy, precision, recall and F1 score the relevance of the results are computed.

BackgroundPepper Phytophthora blight is a devastating disease during the growth process of peppers, significantly affecting their yield and quality. Accurate, rapid, and non-destructive early detection of pepper Phytophthora blight is of great importance for pepper production management. This study investigated the possibility of using multispectral imaging combined with machine learning to detect Phytophthora blight in peppers. Peppers were divided into two groups: one group was inoculated with Phytophthora blight, and the other was left untreated as a control. Multispectral images were collected at 0-h samples before inoculation and at 48, 60, 72, and 84 h after inoculation. The supporting software of the multispectral imaging system was used to extract spectral features from 19 wavelengths, and textural features were extracted using a gray-level co-occurrence matrix (GLCM) and a local binary pattern (LBP). The principal component analysis (PCA), successive projection algorithm (SPA), and genetic algorithm (GA) were used for feature selection from the extracted spectral and textural features. Two classification models were established based on effective single spectral features and significant spectral textural fusion features: a partial least squares discriminant analysis (PLS_DA) and one-dimensional convolutional neural network (1D-CNN). A two-dimensional convolutional neural network (2D-CNN) was constructed based on five principal component (PC) coefficients extracted from the spectral data using PCA, weighted, and summed with 19-channel multispectral images to create new PC images.ResultsThe results indicated that the models using PCA for feature selection exhibit relatively stable classification performance. The accuracy of PLS-DA and 1D-CNN based on single spectral features is 82.6% and 83.3%, respectively, at the 48h mark. In contrast, the accuracy of PLS-DA and 1D-CNN based on spectral texture fusion reached 85.9% and 91.3%, respectively, at the same 48h mark. The accuracy of the 2D-CNN based on 5 PC images is 82%.ConclusionsThe research indicates that Phytophthora blight infection can be detected 48 h after inoculation (36 h before visible symptoms). This study provides an effective method for the early detection of Phytophthora blight in peppers.

The intent of this study is to remotely monitor the status of revegetation growth in a reclaimed, previously mined region on the island of Milos, Greece. Quickbird multispectral (spatial resolution 2.4m×2.4m) and panchromatic (spatial resolution 0.6m×0.6m) images have been fused to obtain an optimal combination of the initial spatial and spectral resolution. The Blue (450nm-520nm), Green (520nm-600nm) and Near Infrared (760nm-900nm) bands of the multispectral image have been used for vegetation monitoring. Different fusion methods, like the Principal Component Analysis, the Intensity-Hue-Saturation transform and the Wavelet The goal of this study is to remotely monitor the status of re-vegetation growth in a reclaimed, previously mined region on the island of Milos, Greece. Quickbird multispectral (spatial resolution 2.4m×2.4m) and panchromatic (spatial resolution 0.6m×0.6m) images have been fused to obtain an optimal combination of the initial spatial and spectral resolution. The Blue (450nm-520nm), Green (520nm-600nm) and Near Infrared (760nm-900nm) bands of the multispectral image have been used for vegetation monitoring. Different fusion methods, like the Principal Component Analysis, the Intensity-Hue-Saturation transform and the Wavelet Analysis have been applied to Quickbird images. Both statistical (correlation coefficient, accuracy measures, etc.) and subjective (i.e., visual) measures have been used to evaluate the produced fused images. The degree to which each of the fused images retains the spectral and spatial features of the initial images has been thus estimated. Based on statistical measures, it has been found that the Additive Wavelet Principal Component "A Trous" and the Additive Wavelet Intensity Mallat methods effectively preserve most of the spectral information of the original multispectral image. On the other hand, the "A Trous" and Intensity-Hue-Saturation fusion techniques retain most of the spatial information of the panchromatic image. Additionally, the IHS transform offers a compromise between the spectral and spatial content of the fused image. Since the spectral content in the NIR band is of primary importance for monitoring re-vegetation growth, the Additive Wavelet Mallat and the IHS transforms are the most suitable choices.

Traditional spectral imaging systems mainly rely on spatial scanning or spectral scanning methods to acquire spatial and spectral features. The acquisition is time-consuming and cannot fully satisfy the need of monitoring dynamic phenomenon and observing different structures of the specimen simultaneously. To overcome these barriers, we develop a video-rate simultaneous multispectral imaging system built with a spectral multiplexed volume holographic grating (VHG) and few optical components. Four spectral multiplexed volume holograms optimized for four discrete spectral bands (centered at 488 nm, 530 nm, 590 nm and 620 nm) are recorded into an 8×12 mm photo-thermal refractive glass. The diffraction efficiencies of all the holograms within the multiplexed VHG are greater than 80%. With the high throughout multiplexed VHG, the system can work with both reflection and fluorescence modes and allow simultaneous acquisition of spectral and spatial information with a single exposure. Imaging experiments demonstrate that the multispectral images of the target illuminated with white light source can be obtained. Fluorescence images of multiple fluorescence objects (two glass beads filled with 20 uL 1.0 mg/mL quantum dots solutions that emit 530 ± 15 nm and 620 ± 15 nm fluorescence, respectively) buried 3 mm below the surface of a tissue mimicking phantom are acquired. The results demonstrate that the system can provide complementary information in fluorescence imaging. The design diagram of the proposed system is given to explain the advantage of compactness and flexibility in integrating with other imaging platforms.

Most cartographic work is made extracting features from aerial or space images. A first step in this work is segmenting the images in regions that represent, as close as possible, cartographic entities (e.g., roads, buildings, vegetation). Region-Growing segmentation is implemented in a multispectral image using an open source programming language. This segmentation method is analyzed for land used and land cover applications, and it is compared with classification-based segmentation, known as Fuzzy K-Means. Both algorithms, Region Growing and Fuzzy K-Means, are run in an aerial image with four spectral bands (red, green, blue, and near infrared). Depending on the scale, the values of the parameters of the algorithms can yield an under segmentation or over segmentation results. Advantages and disadvantages of both segmentation methods are provided.

Hyperspectral images (HSI) have high spectral and low spatial resolutions. However, multispectral images (MSI) usually have low spectral and high spatial resolutions. In various applications HSI with high spectral and spatial resolutions are required. In this paper, a new method for spatial resolution enhancement of HSI using high resolution MSI based on sparse coding and linear spectral unmixing (SCLSU) is introduced. In the proposed method (SCLSU), high spectral resolution features of HSI and high spatial resolution features of MSI are fused. In this case, the sparse representation of some high resolution MSI and linear spectral unmixing (LSU) model of HSI and MSI is simultaneously used in order to construct high resolution HSI (HRHSI). The fusion process of HSI and MSI is formulated as an ill-posed inverse problem. It is solved by the Split Augmented Lagrangian Shrinkage Algorithm (SALSA) and an orthogonal matching pursuit (OMP) algorithm. Finally, the proposed algorithm is applied to the Hyperion and ALI datasets. Compared with the other state-of-the-art algorithms such as Coupled Nonnegative Matrix Factorization (CNMF) and local spectral unmixing, the SCLSU has significantly increased the spatial resolution and in addition the spectral content of HSI is well maintained.

Convolutional neural networks (CNNs) have recently achieved outstanding performance for hyperspectral (HS) and multispectral (MS) image fusion. However, CNNs cannot explore the long-range dependence for HS and MS image fusion because of their local receptive fields. To overcome this limitation, a transformer is proposed to leverage the long-range dependence from the network inputs. Because of the ability of long-range modeling, the transformer overcomes the sole CNN on many tasks, whereas its use for HS and MS image fusion is still unexplored. In this article, we propose a spectral-spatial transformer (SST) to show the potentiality of transformers for HS and MS image fusion. We devise first two branches to extract spectral and spatial features in the HS and MS images by SST blocks, which can explore the spectral and spatial long-range dependence, respectively. Afterward, spectral and spatial features are fused feeding the result back to spectral and spatial branches for information interaction. Finally, the high-resolution (HR) HS image is reconstructed by dense links from all the fused features to make full use of them. The experimental analysis demonstrates the high performance of the proposed approach compared with some state-of-the-art (SOTA) methods.

Suaeda salsa (S. salsa) has a significant protective effect on salt marshes in coastal wetlands. In this study, the abilities of airborne multispectral images, spaceborne hyperspectral images, and LiDAR data in spatial distribution extraction and aboveground biomass (AB) estimation of S. salsa were explored for mapping the spatial distribution of S. salsa AB. Results showed that the increasing spectral and structural features were conducive to improving the classification accuracy of wetland vegetation and the AB estimation accuracy of S. salsa. The fusion of hyperspectral and LiDAR data provided the highest accuracies for wetlands classification and AB estimation of S. salsa in the study. Multispectral images alone provided relatively high user's and producer's accuracies of S. salsa classification (87.04% and 88.28%, respectively). Compared to multispectral images, hyperspectral data with more spectral features slightly improved the Kappa coefficient and overall accuracy. The AB estimation reached a relatively reliable accuracy based only on hyperspectral data (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.812, root-mean-square error of 0.295, estimation error of 24.56%, residual predictive deviation of 2.033, and the sums of squares ratio of 1.049). The addition of LiDAR data produced a limited improvement in the process of extraction and AB estimation of S. salsa. The spatial distribution of mapped S. salsa AB was consistent with the field survey results. This study provided an important reference for the effective information extraction and AB estimation of wetland vegetation S. salsa.

This paper presents an experimental investigation of the application of multispectral imaging in dermatology. The focus areas of this work are as follows: a) the improving the color reproduction accuracy of skin lesions, b) exploring the spectral feature of skin disease using the multispectral color enhancement technique, and c) multispectral image analysis aiming at supporting quantitative diagnosis. The experiment focused on inflammatory and immunologic diseases; the color of skin lesions associated with these diseases is believed to be difficult to reproduce by conventional imaging devices. In view of this fact, we demonstrate the effectiveness of using spectral information for the color reproduction and quantitative analysis of skin disorders.

We recently introduced the notion of Fourier Multispectral Imaging (Fourier MSI), a novel technique for undersampling spectral images without significant sacrifices to the spectral features that may be useful for material identification. The idea originated in Fourier transform spectroscopy, where multiple interferometric measurements are used to take spectral samples while varying optical path difference (OPD). Since interference is equivalent to spectral modulation by a filter with sinusoidally shaped transmittance function, we designed a sinusoidal filter using thin film Fabry-Perot to acquire OPD samples at every pixel. Owing to the rapid decay of OPD samples, Fourier MSI is an ideal multispectral imaging modality for preserving spectral features with the fewest spectral samples. We detail our prototyping efforts and demonstrate the advantages of such multispectral imaging configurations.

Fusing low spatial resolution (LR) hyperspectral (HS) data and high spatial resolution (HR) multispectral (MS) data aims to obtain HR HS data. However, due to bad weather and the aging of sensor equipment, HS images usually contain a lot of noise, e.g., Gaussian noise, strip noise, and mixed noise, which would make the fused image have low quality. To solve this problem, we propose the multiscale low-rank deep back projection fusion network (MLR-DBPFN). First, HS and MS are superimposed, and multiscale spectral features of the stacked image are extracted through multiscale low-rank decomposition and convolution operation, which effectively removes noisy spectral features. Second, the upsampling and downsampling network mechanisms are used to extract the multiscale spatial features from each layer of spectral features. Finally, the multiscale spectral features and multiscale spatial features are combined for network training, and the weight of the noisy spectrum features is reduced through the network feedback mechanism, which suppresses the noisy spectrum and improves the noisy HS fusion performance. Experimental results on datasets of different noise demonstrate that MLR-DBPFN has superior spatial and spectral fidelity, comparative fusion quality, and robust antinoise performance compared with state-of-the-art methods.

Timely and accurate information on the spatial distribution of urban trees is critical for sustainable urban development, management and planning. Compared with satellite-based remote sensing, Unmanned Aerial Vehicle (UAV) remote sensing has a higher spatial and temporal resolution, which provides a new method for the accurate identification of urban trees. In this study, we aim to establish an efficient and practical method for urban tree identification by combining an object-oriented approach and a random forest algorithm using UAV multispectral images. Firstly, the image was segmented by a multi-scale segmentation algorithm based on the scale determined by the Estimation of Scale Parameter 2 (ESP2) tool and visual discrimination. Secondly, spectral features, index features, texture features and geometric features were combined to form schemes S1–S8, and S9, consisting of features selected by the recursive feature elimination (RFE) method. Finally, the classification of urban trees was performed based on the nine schemes using the random forest (RF), support vector machine (SVM) and k-nearest neighbor (KNN) classifiers, respectively. The results show that the RF classifier performs better than SVM and KNN, and the RF achieves the highest accuracy in S9, with an overall accuracy (OA) of 91.89% and a Kappa coefficient (Kappa) of 0.91. This study reveals that geometric features have a negative impact on classification, and the other three types have a positive impact. The feature importance ranking map shows that spectral features are the most important type of features, followed by index features, texture features and geometric features. Most tree species have a high classification accuracy, but the accuracy of Camphor and Cinnamomum Japonicum is much lower than that of other tree species, suggesting that the features selected in this study cannot accurately distinguish these two tree species, so it is necessary to add features such as height in the future to improve the accuracy. This study illustrates that the combination of an object-oriented approach and the RF classifier based on UAV multispectral images provides an efficient and powerful method for urban tree classification.

Accurate crop-weed segmentation is critical for precision spraying but is hindered by visual similarity and occlusion. This study aims to develop a lightweight yet high-accuracy multispectral segmentation network to address these challenges. We propose ASVLB-Net, a novel lightweight multiscale feature extraction network guided by normalized difference vegetation index (NDVI) priors for crop-weed segmentation in multispectral imagery. First, we design the Adaptive Spectral-Vegetation Fusion (ASVF) module at the input stage. It achieves adaptive allocation of spectral and spatial features, enhancing the discriminability of vegetation regions. Additionally, we adopt a U-shaped architecture based on the Layer-wise Concatenated Multi-Scale Feature (LCMF) encoder. It efficiently extracts fine-grained features and boundary information with low computational cost. Finally, we use the Bottleneck -SCSA (Spatial and Channel Synergistic Attention) module to capture long-range dependencies, improving segmentation in overlapping areas. Experimental results demonstrate that ASVLB-Net achieves a mean intersection over union (mIOU) of 86.5% and a mean precision of 91.89%, outperforming several state-of-the-art (SOTA) models, while maintaining high efficiency with only 0.47 million parameters. The ASVLB-Net significantly improves segmentation accuracy and robustness in unmanned aerial vehicle (UAV) multispectral imagery, offering a robust solution for precision weeding applications. © 2026 Society of Chemical Industry.

Pan-sharpening is now indispensable in remote-sensing computing by means of its ability to render not only high-spatial-resolution images but also precise spectral fidelity to the images. These features are essential for competent environmental measurement and investigation. The paper presents a contourlet-based pan-sharpening algorithm, which aims to combine the high spatial resolution of the panchromatic (PAN) images with the multispectral (MS) ones to extract high spectral resolution of the fused image. The algorithm tends to enhance the details of the space and reduce the spectral distortion of a multi-stage fusion procedure to some extent. The structure initiates with contourlet decomposition images captured by both PAN and MS, thus resembling directional and multi-scale structure. At the high-frequency sub-bands, an anisotropic filter is used to reduce noise, leaving salient edges intact, and a maximum-absolute selection rule is applied iteratively to inject spatial details effectively. In order to have spectral fidelity and to maintain global contrast on low-frequency components, saliency maps are used in conjunction with adaptive weight maps. The sub-bands reconstructed progressively give a high-resolution, artifact-minimal fused image. The proposed framework is validated through benchmark remote sensing datasets. The proposed methodology is based on objective metrics. Performance evaluation based on a benchmark remote sensing dataset demonstrates that the proposed methodology outperforms existing approaches in terms of sharper edges, contrast, and spectral features and offers an efficient solution for environmental applications.

Personalized Web search is an effective means of providing specific results to different users when they submit the same query. How to obtain user's real-time information need is a key issue in personalized search. Existing methods concentrate more on the building user profile based on Web pages/documents which affects the efficiency of search engine. In addition, dynamics of user profile is often ignored. To address this problem, we introduce an approach that captures the user context to accurately provide preferences of users for effective personalized search in this paper. First, short-term query context is generated from Web-snippets to play a role of semantic background of user's search behavior, identifying related concepts of the query. Second, user context snap is built based on query context according to user's interactive search behavior. Finally, evolution of user context is considered by introducing forgetting factor to merge the independent user context snap in a user session. The experimental results fully demonstrate that our approach can successfully build user context according to individual user information need.