Search

Faced with the problem of incompatibility between traditional information acquisition mode and spaceborne earth observation tasks, starting from the general mathematical model of compressed sensing, a theoretical model of block compressed sensing was established, and a full-process adaptive coding and decoding compressed sensing framework for remote sensing images was proposed, which includes five parts: mode selection, feature factor extraction, adaptive shape segmentation, adaptive sampling rate allocation and image reconstruction. Unlike previous semi-adaptive or local adaptive methods, the advantages of the adaptive encoding and decoding method proposed in this paper are mainly reflected in four aspects: (1) Ability to select encoding modes based on image content, and maximizing the use of the richness of the image to select appropriate sampling methods; (2) Capable of utilizing image texture details for adaptive segmentation, effectively separating complex and smooth regions; (3) Being able to detect the sparsity of encoding blocks and adaptively allocate sampling rates to fully explore the compressibility of images; (4) The reconstruction matrix can be adaptively selected based on the size of the encoding block to alleviate block artifacts caused by non-stationary characteristics of the image. Experimental results show that the method proposed in this article has good stability for remote sensing images with complex edge textures, with the peak signal-to-noise ratio and structural similarity remaining above 35 dB and 0.8. Moreover, especially for ocean images with relatively simple image content, when the sampling rate is 0.26, the peak signal-to-noise ratio reaches 50.8 dB, and the structural similarity is 0.99. In addition, the recovered images have the smallest BRISQUE value, with better clarity and less distortion. In the subjective aspect, the reconstructed image has clear edge details and good reconstruction effect, while the block effect is effectively suppressed. The framework designed in this paper is superior to similar algorithms in both subjective visual and objective evaluation indexes, which is of great significance for alleviating the incompatibility between traditional information acquisition methods and satellite-borne earth observation missions. [ABSTRACT FROM AUTHOR]

Despite mammography (MG) being among the most widespread techniques in breast cancer screening, tumour detection and classification remain challenging tasks due to the high morphological variability of the lesions. The extraction of radiomics features has proved to be a promising approach in MG. However, radiomics features can suffer from dependency on factors such as acquisition protocol, segmentation accuracy, feature extraction and engineering methods, which prevent the implementation of robust and clinically reliable radiomics workflow in MG. In this study, the variability and robustness of radiomics features is investigated as a function of lesion segmentation in MG images from a public database. A statistical analysis is carried out to assess feature variability and a radiomics robustness score is introduced based on the significance of the statistical tests performed. The obtained results indicate that variability is observable not only as a function of the abnormality type (calcification and masses), but also among feature categories (first-order and second-order), image view (craniocaudal and medial lateral oblique), and the type of lesions (benign and malignant). Furthermore, through the proposed approach, it is possible to identify those radiomics characteristics with a higher discriminative power between benign and malignant lesions and a lower dependency on segmentation, thus suggesting the most appropriate choice of robust features to be used as inputs to automated classification algorithms. [ABSTRACT FROM AUTHOR]

The outstanding performance of deep neural networks (DNNs) in multiple computer vision in recent years has promoted its widespread use in aerial image semantic segmentation. Nonetheless, prior research has demonstrated the high susceptibility of DNNs to adversarial attacks. This poses significant security risks when applying DNNs to safety-critical earth observation missions. As an essential means of attacking DNNs, data poisoning attacks destroy model performance by contaminating model training data, allowing attackers to control prediction results by carefully crafting poisoning samples. Toward building a more robust DNNs-based aerial image semantic segmentation model, in this study, we proposed a robust invariant feature enhancement network (RIFENet) that can resist data poisoning attacks and has superior semantic segmentation performance. The constructed RIFENet improves the resistance to poisoning attacks by extracting and enhancing robust invariant features. Specifically, RIFENet uses a texture feature enhancement module (T-FEM), structural feature enhancement module (S-FEM), global feature enhancement module (G-FEM), and multi-resolution feature fusion module (MR-FFM) to enhance the representation of different robust features in the feature extraction process to suppress the interference of poisoning samples. Experiments on several benchmark aerial image datasets demonstrate that the proposed method is more robust and exhibits better generalization than other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In real-world scenarios, images may be affected by additional noise during compression and transmission, which interferes with postprocessing such as image segmentation and feature extraction. Image noise can also be induced by environmental variables and imperfections in the imaging equipment. Robust principal component analysis (RPCA), one of the traditional approaches for denoising images, suffers from a failure to efficiently use the background's low-rank prior information, which lowers its effectiveness under complex noise backgrounds. In this paper, we propose a robust PCA method based on a nonconvex low-rank approximation and total variational regularization (TV) to model the image denoising problem in order to improve the denoising performance. Firstly, we use a nonconvex γ -norm to address the issue that the traditional nuclear norm penalizes large singular values excessively. The rank approximation is more accurate than the nuclear norm thanks to the elimination of matrix elements with substantial approximation errors to reduce the sparsity error. The method's robustness is improved by utilizing the low sensitivity of the γ -norm to outliers. Secondly, we use the l 1 -norm to increase the sparsity of the foreground noise. The TV norm is used to improve the smoothness of the graph structure in accordance with the sparsity of the image in the gradient domain. The denoising effectiveness of the model is increased by employing the alternating direction multiplier strategy to locate the global optimal solution. It is important to note that our method does not require any labeled images, and its unsupervised denoising principle enables the generalization of the method to different scenarios for application. Our method can perform denoising experiments on images with different types of noise. Extensive experiments show that our method can fully preserve the edge structure information of the image, preserve important features of the image, and maintain excellent visual effects in terms of brightness smoothing. [ABSTRACT FROM AUTHOR]

The real-time nondestructive monitoring of plant water content can enable operators to understand the water demands of crops in a timely manner and provide a reliable basis for precise irrigation. In this study, a method for rapid estimation of water content in Aquilaria sinensis using multispectral imaging was proposed. First, image registration and segmentation were performed using the Fourier–Mellin transform (FFT) and the fuzzy local information c-means clustering algorithm (FLICM). Second, the spectral features (SFs), texture features (TFs), and comprehensive features (CFs) of the image were extracted. Third, using the eigenvectors of the SFs, TFs, and CFs as input, a random forest regression model for estimating the water content of A. sinensis was constructed, respectively. Finally, the monarch butterfly optimization (MBO), Harris hawks optimization (HHO), and sparrow search algorithm (SSA) were used to optimize all models to determine the best estimation model. The results showed that: (1) 60%–80% soil water content is the most suitable for A. sinensis growth. Compared with waterlogging, drought inhibited A. sinensis growth more significantly. (2) FMT + FLICM could achieve rapid segmentation of discrete A. sinensis multispectral images on the basis of guaranteed accuracy. (3) The prediction effect of TFs was basically the same as that of SFs, and the prediction effect of CFs was higher than that of SFs and TFs, but this difference would decrease with the optimization of the RFR model. (4) Among all models, SSA-RFR_CFs had the highest accuracy, with an R2 of 0.8282. These results confirmed the feasibility and accuracy of applying multispectral imaging technology to estimate the water content of A. sinensis and provide a reference for the protection and cultivation of endangered precious tree species. [ABSTRACT FROM AUTHOR]

Image segmentation, which has become a research hotspot in the field of image processing and computer vision, refers to the process of dividing an image into meaningful and non-overlapping regions, and it is an essential step in natural scene understanding. Despite decades of effort and many achievements, there are still challenges in feature extraction and model design. In this paper, we review the advancement in image segmentation methods systematically. According to the segmentation principles and image data characteristics, three important stages of image segmentation are mainly reviewed, which are classic segmentation, collaborative segmentation, and semantic segmentation based on deep learning. We elaborate on the main algorithms and key techniques in each stage, compare, and summarize the advantages and defects of different segmentation models, and discuss their applicability. Finally, we analyze the main challenges and development trends of image segmentation techniques. [ABSTRACT FROM AUTHOR]

Spectral-spatial classification of hyperspectral images (HSIs) has recently attracted great attention in the research domain of remote sensing. It is well-known that, in remote sensing applications, spectral features are the fundamental information and spatial patterns provide the complementary information. With both spectral features and spatial patterns, hyperspectral image (HSI) applications can be fully explored and the classification performance can be greatly improved. In reality, spatial patterns can be extracted to represent a line, a clustering of points or image texture, which denote the local or global spatial characteristic of HSIs. In this paper, we propose a spectral-spatial HSI classification model based on superpixel pattern (SP) and kernel based extreme learning machine (KELM), called SP-KELM, to identify the land covers of pixels in HSIs. In the proposed SP-KELM model, superpixel pattern features are extracted by an advanced principal component analysis (PCA), which is based on superpixel segmentation in HSIs and used to denote spatial information. The KELM method is then employed to be a classifier in the proposed spectral-spatial model with both the original spectral features and the extracted spatial pattern features. Experimental results on three publicly available HSI datasets verify the effectiveness of the proposed SP-KELM model, with the performance improvement of 10% over the spectral approaches. [ABSTRACT FROM AUTHOR]

Cracks can occur on different surfaces such as buildings, roads, aircrafts, etc. The manual inspection of cracks is time-consuming and prone to human error. Machine vision has been used for decades to detect defects in materials in production lines. However, the detection or segmentation of cracks on a randomly textured surface, such as marble, has not been sufficiently investigated. This work provides an up-to-date systematic and exhaustive study on marble crack segmentation with color images based on deep learning (DL) techniques. The authors conducted a performance evaluation of 112 DL segmentation models with red–green–blue (RGB) marble slab images using five-fold cross-validation, providing consistent evaluation metrics in terms of Intersection over Union (IoU), precision, recall and F1 score to identify the segmentation challenges related to marble cracks' physiology. Comparative results reveal the FPN model as the most efficient architecture, scoring 71.35% mean IoU, and SE-ResNet as the most effective feature extraction network family. The results indicate the importance of selecting the appropriate Loss function and backbone network, underline the challenges related to the marble crack segmentation problem, and pose an important step towards the robotic automation of crack segmentation and simultaneous resin application to heal cracks in marble-processing plants. [ABSTRACT FROM AUTHOR]

In the processing of remotely sensed data, classification may be preceded by feature extraction, which helps in making the most informative parts of the data emerge. Effective feature extraction may boost the efficiency and accuracy of the following classification, and hence various methods have been proposed to perform it. Recently, Singular Spectrum Analysis (SSA) and its 2-D variation (2D-SSA) have emerged as popular, cutting-edge technologies for effective feature extraction in Hyperspectral Images (HSI). Using 2D-SSA, each band image of an HSI is initially decomposed into various components, and then the image is reconstructed using the most significant eigen-tuples relative to their eigen-values, which represent strong spatial features for the classification task. However, instead of performing reconstruction on the whole image, it may be more effective to apply reconstruction to object-specific spatial regions, which is the proposed objective of this research. As an HSI may cover a large area, multiple objects are generally present within a single scene. Hence, spatial information can be highlighted accurately by specializing the reconstruction based on the local context. The local context may be defined by the so-called superpixels, i.e., finite sets of pixels that constitute a homogeneous set. Each superpixel may undergo tailored reconstruction, with a process expected to perform better than non-spatially-adaptive approaches. In this paper, a Superpixel-based SSA (SP-SSA) method is proposed where the image is first segmented into multiple regions using a superpixel segmentation approach. Next, each segment is individually reconstructed using 2D-SSA. In doing so, the spatial contextual information is preserved, leading to better classifier performance. The performance of the reconstructed features is evaluated using an SVM classifier. Experiments on four popular benchmark datasets reveal that, in terms of the classification accuracy, the proposed approach overperforms the standard SSA technique and various common spatio-spectral classification methods. [ABSTRACT FROM AUTHOR]

This paper presents a machine vision method for detection and classification of copper ore grains. We proposed a new method that combines both seeded regions growing segmentation and edge detection, where region growing is limited only to grain boundaries. First, a 2D Fast Fourier Transform (2DFFT) and Gray-Level Co-occurrence Matrix (GLCM) are calculated to improve the detection results and processing time by eliminating poor quality samples. Next, detection of copper ore grains is performed, based on region growing, improved by the first and second derivatives with a modified Niblack's theory and a threshold selection method. Finally, all the detected grains are characterized by a set of shape features, which are used to classify the grains into separate fractions. The efficiency of the algorithm was evaluated with real copper ore samples of known granularity. The proposed method generates information on different granularity fractions at a time with a number of grain shape features. [ABSTRACT FROM AUTHOR]