Search Results (499)

The cost of hyperspectral image (HSI) classification primarily stems from the annotation of image pixels. In real-world classification scenarios, the measurement and annotation process is both time-consuming and labor-intensive. Therefore, reducing the number of labeled pixels while maintaining classification accuracy is a key research focus in HSI classification. This paper introduces a multi-strategy triple network classifier (MSTNC) to address the issue of limited labeled data in HSI classification by improving learning strategies. First, we use the contrast learning strategy to design a lightweight triple network classifier (TNC) with low sample dependence. Due to the construction of triple sample pairs, the number of labeled samples can be increased, which is beneficial for extracting intra-class and inter-class features of pixels. Second, an active learning strategy is used to label the most valuable pixels, improving the quality of the labeled data. To address the difficulty of sampling effectively under extremely limited labeling budgets, we propose a new feature-mixed active learning (FMAL) method to query valuable samples. Fine-tuning is then used to help the MSTNC learn a more comprehensive feature distribution, reducing the model’s dependence on accuracy when querying samples. Therefore, the sample quality is improved. Finally, we propose an innovative dual-threshold pseudo-active learning (DSPAL) strategy, filtering out pseudo-label samples with both high confidence and uncertainty. Extending the training set without increasing the labeling cost further improves the classification accuracy of the model. Extensive experiments are conducted on three benchmark HSI datasets. Across various labeling ratios, the MSTNC outperforms several state-of-the-art methods. In particular, under extreme small-sample conditions (five samples per class), the overall accuracy reaches 82.97% (IP), 87.94% (PU), and 86.57% (WHU). Full article

The standardized spectral mixture model combines the specificity of a physically based representation of a spectrally mixed pixel with the generality and portability of a spectral index. Earlier studies have used spectrally and geographically diverse collections of broadband and spectroscopic imagery to show that the reflectance of the majority of ice-free landscapes on Earth can be represented as linear mixtures of rock and soil substrates (S), photosynthetic vegetation (V) and dark targets (D) composed of shadow and spectrally absorptive/transmissive materials. However, both broadband and spectroscopic studies of the topology of spectral mixing spaces raise questions about the completeness and generality of the Substrate, Vegetation, Dark (SVD) model for imaging spectrometer data. This study uses a spectrally diverse collection of 40 granules from the EMIT imaging spectrometer to verify the generality and stability of the spectroscopic SVD model and characterize the SVD topology and plane of substrates to assess linearity of spectral mixing. New endmembers for soil and non-photosynthetic vegetation (NPV; N) allow the planar SVD model to be extended to a tetrahedral SVDN model to better accommodate the 3D topology of the mixing space. The SVDN model achieves smaller misfit than the SVD, but does so at the expense of implausible fractions beyond [0, 1]. However, a refined spectroscopic SVD model still achieves small (<0.03) RMS misfit, negligible sensitivity to endmember variability and strongly linear scaling over more than an order of magnitude range of spatial resolution. Full article

Due to the security weaknesses of chaos-based pseudorandom number generators, in this paper, a new pseudorandom number generator (PRNG) based on mixing three-dimensional variables of a cat chaotic map is proposed. A uniformly distributed chaotic sequence by a logistic map is used in the mixing step. Both statistical tests and a security analysis indicate that our PRNG has good randomness and is more complex than any one-dimensional variable of a cat map. Furthermore, a new image encryption algorithm based on the chaotic PRNG is provided to protect the content of artwork images. The core of the algorithm is to use the sequence generated by the pseudorandom number generator to achieve the process of disruption and diffusion of the image pixels, so as to achieve the effect of obfuscation and encryption of the image content. Several security tests demonstrate that this image encryption algorithm has a high security level. Full article

Moderate-Resolution Imaging Spectroradiometer (MODIS) Nadir Bidirectional Reflectance Distribution Function (BRDF)-Adjusted Reflectance (NBAR) products are being increasingly used for the quantitative remote sensing of vegetation. However, the assumption underlying the MODIS NBAR product’s inversion model—that surface anisotropy remains unchanged over the 16-day retrieval period—may be unreliable, especially since the canopy structure of vegetation undergoes stark changes at the start of season (SOS) and the end of season (EOS). Therefore, to investigate the MODIS NBAR product’s temporal effect on the quantitative remote sensing of crops at different stages of the growing seasons, this study selected typical phenological parameters, namely SOS, EOS, and the intervening stable growth of season (SGOS). The PROBA-V bioGEOphysical product Version 3 (GEOV3) Fractional Vegetation Cover (FVC) served as verification data, and the Pearson correlation coefficient (PCC) was used to compare and analyze the retrieval accuracy of FVC derived from the MODIS NBAR product and MODIS Surface Reflectance product. The Anisotropic Flat Index (AFX) was further employed to explore the influence of vegetation type and mixed pixel distribution characteristics on the BRDF shape under different stages of the growing seasons and different FVC; that was then combined with an NDVI spatial distribution map to assess the feasibility of using the reflectance of other characteristic directions besides NBAR for FVC correction. The results revealed the following: (1) Generally, at the SOSs and EOSs, the differences in PCCs before vs. after the NBAR correction mainly ranged from 0 to 0.1. This implies that the accuracy of FVC derived from MODIS NBAR is lower than that derived from MODIS Surface Reflectance. Conversely, during the SGOSs, the differences in PCCs before vs. after the NBAR correction ranged between –0.2 and 0, suggesting the accuracy of FVC derived from MODIS NBAR surpasses that derived from MODIS Surface Reflectance. (2) As vegetation phenology shifts, the ensuing differences in NDVI patterning and AFX can offer auxiliary information for enhanced vegetation classification and interpretation of mixed pixel distribution characteristics, which, when combined with NDVI at characteristic directional reflectance, could enable the accurate retrieval of FVC. Our results provide data support for the BRDF correction timescale effect of various stages of the growing seasons, highlighting the potential importance of considering how they differentially influence the temporal effect of NBAR corrections prior to monitoring vegetation when using the MODIS NBAR product. Full article

A range of remote sensing platforms provide high spatial and temporal resolution insights which are useful for monitoring vegetation growth. Very few studies have focused on fruit orchards, largely due to the inherent complexity of their structure. Fruit trees are mixed with inter-rows that can be grassed or non-grassed, and there are no standard protocols for ground measurements suitable for the range of crops. The assessment of biophysical variables (BVs) for fruit orchards from optical satellites remains a significant challenge. The objectives of this study are as follows: (1) to address the challenges of extracting and better interpreting biophysical variables from optical data by proposing new ground measurements protocols tailored to various orchards with differing inter-row management practices, (2) to quantify the impact of the inter-row at the Sentinel pixel scale, and (3) to evaluate the potential of Sentinel 2 data on BVs for orchard development monitoring and the detection of key phenological stages, such as the flowering and fruit set stages. Several orchards in two pedo-climatic zones in southeast France were monitored for three years: four apricot and nectarine orchards under different management systems and nine cherry orchards with differing tree densities and inter-row surfaces. We provide the first comparison of three established ground-based methods of assessing BVs in orchards: (1) hemispherical photographs, (2) a ceptometer, and (3) the Viticanopy smartphone app. The major phenological stages, from budburst to fruit growth, were also determined by in situ annotations on the same fields monitored using Viticanopy. In parallel, Sentinel 2 images from the two study sites were processed using a Biophysical Variable Neural Network (BVNET) model to extract the main BVs, including the leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fraction of green vegetation cover (FCOVER). The temporal dynamics of the normalised FAPAR were analysed, enabling the detection of the fruit set stage. A new aggregative model was applied to data from hemispherical photographs taken under trees and within inter-rows, enabling us to quantify the impact of the inter-row at the Sentinel 2 pixel scale. The resulting value compared to BVs computed from Sentinel 2 gave statistically significant correlations (0.57 for FCOVER and 0.45 for FAPAR, with respective RMSE values of 0.12 and 0.11). Viticanopy appears promising for assessing the PAI (plant area index) and FCOVER for orchards with grassed inter-rows, showing significant correlations with the Sentinel 2 LAI (R² of 0.72, RMSE 0.41) and FCOVER (R² 0.66 and RMSE 0.08). Overall, our results suggest that Sentinel 2 imagery can support orchard monitoring via indicators of development and inter-row management, offering data that are useful to quantify production and enhance resource management. Full article

With the continuous development of science and technology, laser ranging technology will become more efficient, convenient, and widespread, and it has been widely used in the fields of medicine, engineering, video games, and three-dimensional imaging. A time-of-flight (ToF) camera is a three-dimensional stereo imaging device with the advantages of small size, small measurement error, and strong anti-interference ability. However, compared to traditional sensors, ToF cameras typically exhibit lower resolution and signal-to-noise ratio due to inevitable noise from multipath interference and mixed pixels during usage. Additionally, in environments with scattering media, the information about objects gets scattered multiple times, making it challenging for ToF cameras to obtain effective object information. To address these issues, we propose a solution that combines ToF cameras with single-pixel imaging theory. Leveraging intensity information acquired by ToF cameras, we apply various reconstruction algorithms to reconstruct the object’s image. Under undersampling conditions, our reconstruction approach yields higher peak signal-to-noise ratio compared to the raw camera image, significantly improving the quality of the target object’s image. Furthermore, when ToF cameras fail in environments with scattering media, our proposed approach successfully reconstructs the object’s image when the camera is imaging through the scattering medium. This experimental demonstration effectively reduces the noise and direct ambient light generated by the ToF camera itself, while opening up the potential application of ToF cameras in challenging environments, such as scattering media or underwater. Full article

The composition of clay minerals in soils, and more particularly the presence of montmorillonite (as part of the smectite family), is a key factor in soil swell–shrinking as well as off–road vehicle mobility. Detecting these topsoil clay minerals and quantifying the montmorillonite abundance are a challenge since they are usually intimately mixed with other minerals, soil organic carbon and soil moisture content. Imaging spectroscopy coupled with unmixing methods can address these issues, but the quality of the estimation degrades the coarser the spatial resolution is due to pixel heterogeneity. With the advent of UAV-borne and proximal hyperspectral acquisitions, it is now possible to acquire images at a centimeter scale. Thus, the objective of this paper is to evaluate the accuracy and limitations of unmixing methods to retrieve montmorillonite abundance from very-high-resolution hyperspectral images (1.5 cm) acquired from a camera installed on top of a bucket truck over three different agricultural fields, in Loiret department, France. Two automatic endmember detection methods based on the assumption that materials are linearly mixed, namely the Simplex Identification via Split Augmented Lagrangian (SISAL) and the Minimum Volume Constrained Non-negative Matrix Factorization (MVC-NMF), were tested prior to unmixing. Then, two linear unmixing methods, the fully constrained least square method (FCLS) and the multiple endmember spectral mixture analysis (MESMA), and two nonlinear unmixing ones, the generalized bilinear method (GBM) and the multi-linear model (MLM), were performed on the images. In addition, several spectral preprocessings coupled with these unmixing methods were applied in order to improve the performances. Results showed that our selected automatic endmember detection methods were not suitable in this context. However, unmixing methods with endmembers taken from available spectral libraries performed successfully. The nonlinear method, MLM, without prior spectral preprocessing or with the application of the first Savitzky–Golay derivative, gave the best accuracies for montmorillonite abundance estimation using the USGS library (RMSE between 2.2–13.3% and 1.4–19.7%). Furthermore, a significant impact on the abundance estimations at this scale was in majority due to (i) the high variability of the soil composition, (ii) the soil roughness inducing large variations of the illumination conditions and multiple surface scatterings and (iii) multiple volume scatterings coming from the intimate mixture. Finally, these results offer a new opportunity for mapping expansive soils from imaging spectroscopy at very high spatial resolution. Full article

The detection of change in remote-sensing images is broadly applicable to many fields. In recent years, both supervised and unsupervised methods have demonstrated excellent capacity to detect changes in high-resolution images. However, most of these methods are sensitive to noise, and their performance significantly deteriorates when dealing with remote-sensing images that have been contaminated by mixed random noises. Moreover, supervised methods require that samples are manually labeled for training, which is time-consuming and labor-intensive. This study proposes a new unsupervised change-detection (CD) framework that is resilient to mixed random noise called self-supervised denoising network-based unsupervised change-detection coupling FCM_SICM and EMD (SSDNet-FSE). It consists of two components, namely a denoising module and a CD module. The proposed method first utilizes a self-supervised denoising network with real 3D weight attention mechanisms to reconstruct noisy images. Then, a noise-resistant fuzzy C-means clustering algorithm (FCM_SICM) is used to decompose the mixed pixels of reconstructed images into multiple signal classes by exploiting local spatial information, spectral information, and membership linkage. Next, the noise-resistant Earth mover’s distance (EMD) is used to calculate the distance between signal-class centers and the corresponding fuzzy memberships of bitemporal pixels and generate a map of the magnitude of change. Finally, automatic thresholding is undertaken to binarize the change-magnitude map into the final CD map. The results of experiments conducted on five public datasets prove the superior noise-resistant performance of the proposed method over six state-of-the-art CD competitors and confirm its effectiveness and potential for practical application. Full article

Hyperspectral unmixing (HU) aims to decompose mixed pixels into a set of endmembers and corresponding abundances. Deep learning-based HU methods are currently a hot research topic, but most existing unmixing methods still rely on per-pixel training or employ convolutional neural networks (CNNs), which overlook the non-local correlations of materials and spectral characteristics. Furthermore, current research mainly focuses on linear mixing models, which limits the feature extraction capability of deep encoders and further improvement in unmixing accuracy. In this paper, we propose a nonlinear unmixing network capable of extracting global spatial-spectral features. The network is designed based on an autoencoder architecture, where a dual-stream CNNs is employed in the encoder to separately extract spectral and local spatial information. The extracted features are then fused together to form a more complete representation of the input data. Subsequently, a linear projection-based multi-head self-attention mechanism is applied to capture global contextual information, allowing for comprehensive spatial information extraction while maintaining lightweight computation. To achieve better reconstruction performance, a model-free nonlinear mixing approach is adopted to enhance the model’s universality, with the mixing model learned entirely from the data. Additionally, an initialization method based on endmember bundles is utilized to reduce interference from outliers and noise. Comparative results on real datasets against several state-of-the-art unmixing methods demonstrate the superior of the proposed approach. Full article

In order to improve the accuracy of multispectral image inversion of soil and plant analytical development (SPAD) of the cotton canopy, image segmentation methods were utilized to remove the background interference, such as soil and shadow in UAV multispectral images. UAV multispectral images of cotton bud stage canopies at three different heights (30 m, 50 m, and 80 m) were acquired. Four methods, namely vegetation index thresholding (VIT), supervised classification by support vector machine (SVM), spectral mixture analysis (SMA), and multiple endmember spectral mixture analysis (MESMA), were used to segment cotton, soil, and shadows in the multispectral images of cotton. The segmented UAV multispectral images were used to extract the spectral information of the cotton canopy, and eight vegetation indices were calculated to construct the dataset. Partial least squares regression (PLSR), Random forest (FR), and support vector regression (SVR) algorithms were used to construct the inversion model of cotton SPAD. This study analyzed the effects of different image segmentation methods on the extraction accuracy of spectral information and the accuracy of SPAD modeling in the cotton canopy. The results showed that (1) The accuracy of spectral information extraction can be improved by removing background interference such as soil and shadows using four image segmentation methods. The correlation between the vegetation indices calculated from MESMA segmented images and the SPAD of the cotton canopy was improved the most; (2) At three different flight altitudes, the vegetation indices calculated by the MESMA segmentation method were used as the input variable, and the SVR model had the best accuracy in the inversion of cotton SPAD, with R² of 0.810, 0.778, and 0.697, respectively; (3) At a flight altitude of 80 m, the R² of the SVR models constructed using vegetation indices calculated from images segmented by VIT, SVM, SMA, and MESMA methods were improved by 2.2%, 5.8%, 13.7%, and 17.9%, respectively, compared to the original images. Therefore, the MESMA mixed pixel decomposition method can effectively remove soil and shadows in multispectral images, especially to provide a reference for improving the inversion accuracy of crop physiological parameters in low-resolution images with more mixed pixels. Full article

Pest damage is a major factor in reducing crop yield and has negative impacts on the economy. However, the complex background, diversity of pests, and individual differences pose challenges for classification algorithms. In this study, we propose a patch-based neural network (PMLPNet) for multi-class pest classification. PMLPNet leverages spatial and channel contextual semantic features through meticulously designed token- and channel-mixing MLPs, respectively. This innovative structure enhances the model’s ability to accurately classify complex multi-class pests by providing high-quality local and global pixel semantic features for the fully connected layer and activation function. We constructed a database of 4510 images spanning 40 types of plant pests across 4 crops. Experimental results demonstrate that PMLPNet outperforms existing CNN models, achieving an accuracy of 92.73%. Additionally, heat maps reveal distinctions among different pest images, while patch probability-based visualizations highlight heterogeneity within pest images. Validation on external datasets (IP102 and PlantDoc) confirms the robust generalization performance of PMLPNet. In summary, our research advances intelligent pest classification techniques, effectively identifying various pest types in diverse crop images. Full article

Nowadays, autonomous driving technology has become widely prevalent. The intelligent vehicles have been equipped with various sensors (e.g., vision sensors, LiDAR, depth cameras etc.). Among them, the vision systems with tailored semantic segmentation and perception algorithms play critical roles in scene understanding. However, the traditional supervised semantic segmentation needs a large number of pixel-level manual annotations to complete model training. Although few-shot methods reduce the annotation work to some extent, they are still labor intensive. In this paper, a self-supervised few-shot semantic segmentation method based on Multi-task Learning and Dense Attention Computation (dubbed MLDAC) is proposed. The salient part of an image is split into two parts; one of them serves as the support mask for few-shot segmentation, while cross-entropy losses are calculated between the other part and the entire region with the predicted results separately as multi-task learning so as to improve the model’s generalization ability. Swin Transformer is used as our backbone to extract feature maps at different scales. These feature maps are then input to multiple levels of dense attention computation blocks to enhance pixel-level correspondence. The final prediction results are obtained through inter-scale mixing and feature skip connection. The experimental results indicate that MLDAC obtains 55.1% and 26.8% one-shot mIoU self-supervised few-shot segmentation on the PASCAL-$5^i$ and COCO-${20}^i$ datasets, respectively. In addition, it achieves 78.1% on the FSS-1000 few-shot dataset, proving its efficacy. Full article

Aboveground biomass (AGB) serves as a crucial indicator of the carbon sequestration capacity of coastal wetland ecosystems. Conducting extensive field surveys in coastal wetlands is both time-consuming and labor-intensive. Unmanned aerial vehicles (UAVs) and satellite remote sensing have been widely utilized to estimate regional AGB. However, the mixed pixel effects in satellite remote sensing hinder the precise estimation of AGB, while high-spatial resolution UAVs face challenges in estimating large-scale AGB. To fill this gap, this study proposed an integrated approach for estimating AGB using field sampling, a UAV, and Sentinel-2 satellite data. Firstly, based on multispectral data from the UAV, vegetation indices were computed and matched with field sampling data to develop the Field–UAV AGB estimation model, yielding AGB results at the UAV scale (1 m). Subsequently, these results were upscaled to the Sentinel-2 satellite scale (10 m). Vegetation indices from Sentinel-2 data were calculated and matched to establish the UAV–Satellite AGB model, enabling the estimation of AGB over large regional areas. Our findings revealed the AGB estimation model achieved an R² value of 0.58 at the UAV scale and 0.74 at the satellite scale, significantly outperforming direct modeling from field data to satellite (R² = −0.04). The AGB densities of the wetlands in Xieqian Bay, Meishan Bay, and Hangzhou Bay, Zhejiang Province, were 1440.27 g/m², 1508.65 g/m², and 1545.11 g/m², respectively. The total AGB quantities were estimated to be 30,526.08 t, 34,219.97 t, and 296,382.91 t, respectively. This study underscores the potential of integrating UAV and satellite remote sensing for accurately assessing AGB in large coastal wetland regions, providing valuable support for the conservation and management of coastal wetland ecosystems. Full article

Intelligent urban perception is one of the hot topics. Most previous urban perception models based on semantic segmentation mainly used RGB images as unimodal inputs. However, in natural urban scenes, the interplay of light and shadow often leads to confused RGB features, which diminish the model’s perception ability. Multimodal polarization data encompass information dimensions beyond RGB, which can enhance the representation of shadow regions, serving as additional data for assistance. Additionally, in recent years, transformers have achieved outstanding performance in visual tasks, and their large, effective receptive field can provide more discriminative cues for shadow regions. For these reasons, this study proposes a novel semantic segmentation model called MixImages, which can combine polarization data for pixel-level perception. We conducted comprehensive experiments on a polarization dataset of urban scenes. The results showed that the proposed MixImages can achieve an accuracy advantage of 3.43% over the control group model using only RGB images in the unimodal benchmark while gaining a performance improvement of 4.29% in the multimodal benchmark. Additionally, to provide a reference for specific downstream tasks, we also tested the impact of different combinations of polarization types on the overall segmentation accuracy. The proposed MixImages can be a new option for conducting urban scene perception tasks. Full article

Land surface water is a key part in the global ecosystem balance and hydrological cycle. Remote sensing has become an effective tool for its spatio-temporal monitoring. However, remote sensing results exemplified in so-called water indices are subject to several limitations. This paper proposes a new and effective water index called the Sentinel Multi-Band Water Index (SMBWI) to extract water bodies in complex environments from Sentinel-2 satellite imagery. Individual tests explore the effectiveness of the SMBWI in eliminating interference of various special interfering cover features. The Iterative Self-Organizing Data Analysis Technique Algorithm (ISODATA) method and confusion matrix along with the derived accuracy evaluation indicators are used to provide a threshold reference when extracting water bodies and evaluate the accuracy of the water body extraction results, respectively. The SMBWI and eight other commonly used water indices are qualitatively and quantitatively compared through vision and accuracy evaluation indicators, respectively. Here, the SMBWI is proven to be the most effective at suppressing interference of buildings and their shadows, cultivated lands, vegetation, clouds and their shadows, alpine terrain with bare ground and glaciers when extracting water bodies. The overall accuracy in all tests was consistently greater than 96.5%. The SMBWI is proven to have a high ability to identify mixed pixels of water and non-water, with the lowest total error among nine water indices. Most notably, better results are obtained when extracting water bodies under interfering environments of cover features. Therefore, we propose that our novel and robust water index, the SMBWI, is ready to be used for mapping land surface water with high accuracy. Full article