Remote Sensing Information Processing Research Articles

Development demands for remote sensing information processing technology: inspired by the US PWSA

Development demands for remote sensing information processing technology: inspired by the US PWSA

Analysis on future development demands of remote sensing information processing techniques based on the development of US Missile Defense System

Analysis on future development demands of remote sensing information processing techniques based on the development of US Missile Defense System

Remote Sensing-Based Assessment of Soil and Water Pollution in Deep Excavation Scenario

Soil and water resource mismanagement can negatively intensify global poverty and jeopardize ecology. Soil can be contaminated by heavy metals, organic chemicals like biological pathogens, pesticides, micro plastics and nano particles. Contamination decreases the soil’s capability to yield food thereby affecting food production by means of pollution and disease. Moreover, soil contaminants move into rivers damaging the water quality. Numerous technologies have been established to tackle water and soil remediation, such as deep excavation technique where transportation of contaminated soils or water is done to remote unpopulated sites. Recent development in Remote Sensing and geographic information processing techniques have led to exciting new opportunities for investigating and closely monitoring environmental factors that influence key land and soil management approaches. Hence, this paper uses the Deep Excavation and Remote Sensing based Assessment Model (DERSAM) to assess the soil and water pollution in contaminated areas. The data are taken from the Europe soil contamination map to classify the contaminated and non-contaminated areas. This data obtained from the high-resolution satellite of Remote Sensing (RS) technique and Geographical Information System (GIS) with the parallel expansion of a fully assimilated geospatial database system that provides monitoring and feedback at suitable spatial scales. Thus, such data can be utilized for long-term environmental management and monitoring of remediation and rehabilitation of excavation areas. The numerical outcomes show that the recommended DERSAM model increases the land use and land cover change prediction by 90.2%, the classification ratio by 98.2%, the pollution reduction ratio by 96.6%, the soil contamination detection ratio by 95.9%, and the overall performance by 97.2% compared to other existing approaches.

An Efficient Object Detection Algorithm Based on Improved YOLOv5 for High-Spatial-Resolution Remote Sensing Images

The field of remote sensing information processing places significant research emphasis on object detection (OD) in high-spatial-resolution remote sensing images (HSRIs). The OD task in HSRIs poses additional challenges compared to conventional natural images. These challenges include variations in object scales, complex backgrounds, dense arrangement, and uncertain orientations. These factors contribute to the increased difficulty of OD in HSRIs as compared to conventional images. To tackle the aforementioned challenges, this paper introduces an innovative OD algorithm that builds upon enhancements made to the YOLOv5 framework. The incorporation of RepConv, Transformer Encoder, and BiFPN modules into the original YOLOv5 network leads to improved detection accuracy, particularly for objects of varying scales. The C3GAM module is designed by introducing the GAM attention mechanism to address the interference caused by complex background regions. To achieve precise localization of densely arranged objects, the SIoU loss function is integrated into YOLOv5. The circular smooth label method is used to detect objects with uncertain directions. The effectiveness of the suggested algorithm is confirmed through its application to two commonly utilized datasets, specifically HRSC2016 and UCAS-AOD. The average detection accuracies achieved on these datasets are 90.29% and 90.06% respectively, surpassing the performance of other compared OD algorithms for HSRIs.

Research on Remote Sensing Retrieval Method of PM2.5 Based on FY-4A Satellite with Multiple Machine Learning Methods

Satellite remote sensing technology can see the breadth and fineness that humans cannot see, and can see the spatio-temporal changes that humans cannot see. The inversion of PM2.5 based on remote sensing satellite has wide spatial coverage and relatively high spatial and temporal resolution, and the estimation results are reliable and easy to obtain, which can provide the data basis and scientific basis for managing PM2.5 pollution. This paper summarizes 2 aspects from remote sensing information processing technology and PM2.5 concentration estimation model. The development trend of current satellite remote sensing technology is analyzed from the perspective of the principle and development of satellite remote sensing technology, and the basic analytical thinking and analytical steps of current remote sensing information technology processing are described from the starting point of remote sensing information acquisition and processing technology; the advantages, disadvantages and adaptability of different models are pointed out through the comparative analysis of domestic and foreign estimation models of PM2.5 concentration. The study shows that the number of remote sensing satellites in China is increasing year by year, and remote sensing data and estimation models are being used effectively and improved gradually.

AN ADAPTIVE SUPERPIXELS FOR VEGETATION DETECTION ON HIGH RESOLUTION IMAGES BASED ON MLP

Abstract. Vegetation detection aims to find the area which should be attributed with the labels of vegetation on the captured images, such as forest, grass land etc., and nowadays it is a key research topic in the field of remote sensing information processing and application. Over the last few years, the deep learning method based on convolutional neural network (CNN) has become the mainstream method for vegetation detection. However, due to the peculiarities of the underlying encoding and decoding structures, it is common for some CNN methods to loss some boundary details of vegetation when employing high-resolution images with rich details and clear boundaries. In order to improve the boundary localization capability of vegetation, this paper proposes a hybrid solution, i.e., an MLP (MultiLayer Perceptron)-based high-resolution image adaptive superpixels vegetation detection method. Compared with the traditional watershed transform algorithm, this method adopts the two-step boundary marching criterion to generate superpixels with more adherent boundary and compact regularity which contains adaptive neighborhood information by design. Based on the generated superpixels with boundary detail information, this paper applies MLP for binary predictions, i.e., vegetation or non-vegetation. The experimental results show that our method has more precise vegetation boundary localization and higher accuracy compared with several state-of-the-art methods on the UAV image data set and ISPRS data set.

Thermal-Infrared Spectral Feature Analysis and Spectral Identification of Monzonite Using Feature-Oriented Principal Component Analysis

Rock spectral analysis is an important research field in hyperspectral remote sensing information processing. Compared with the spectra in the short-wave infrared and visible–near-infrared regions, the emittance spectrum of rocks in the thermal infrared (TIR) region is highly significant for identifying some major rock-forming minerals, including feldspar, biotite, pyroxene and hornblende. Even for the same rock type, slight differences in mineral composition generally result in varying spectral signatures, undoubtedly increasing the difficulty in discriminating rock types on the Earth’s surface via TIR spectroscopy. In this study, amounts of monzonite samples from different regions were collected in the central part of Hunan Province, China, and emission spectra at 8–14 μm were measured using a portable thermal infrared spectrometer. The experimental result illustrates 13 remarkable feature positions for all the monzonite samples from different geological environments. Furthermore, by combining the extracted features with the principal component analysis (PCA) method, feature-oriented PCA was applied to establish a model for identifying monzonite accurately and quickly without performing spectral library matching and spectral deconvolution. This study provides an important method for rock type identification in the TIR region that is helpful for the rock spectral analysis, geological mapping and pixel unmixing of remote sensing images.

Hyperspectral Data Classification Algorithm considering Spatial Texture Features

As a cutting-edge technology, hyperspectral remote sensing has been widely applied in many fields, including agricultural production, mineral identification, target detection, disaster warning, military reconnaissance, and urban planning. The collected hyperspectral data have high spectral resolution and spatial resolution and are characterized by a large amount of information, redundancy, and high dimension. At the same time, there is a strong correlation between the bands. Therefore, hyperspectral data not only provides rich information but also brings great challenges for subsequent processing. Hyperspectral image classification is a hot issue in remote sensing information processing. Traditional hyperspectral remote sensing image classification methods only use the spectral features of the image without considering the spatial features of each pixel in the hyperspectral remote sensing image. In this paper, a hyperspectral image classification method is proposed not only considering spectral features but also considering texture features. This method jointly considers both these features. Firstly, six texture features contributing a lot to each pixel of hyperspectral remote sensing image are extracted by using a gray level cooccurrence matrix, and then, the spectral features of each pixel in neighbor are combined to form the texture-spectral features. Finally, the classification experiment of the Indian Pines and Pavia University scene is carried out based on a support vector machine and extreme random tree algorithm, and the obtained results show that the proposed method achieves higher classification performance than the traditional method.

A Study on Quality Evaluation Methods of Hyperspectral Image

Because of great theoretical value and application prospects in civil and military affairs, hyperspectral image quality assessment method has been a hot research issue in current target recognition and remote sensing information processing field. In this article, firstly, we explicitly described evaluation methods which affect the quality of hyperspectral image based on two aspects of image quality and spectral quality evaluation. Afterwards, we used data cube provided by Australia Airborne Imaging Spectrometer Hymap as ideal raw spectral data to separately restored the degraded images by using Wiener Recovery, R-L Recovery and CGA Recovery, and then verified the recovery results through image quality assessment methods and spectral assessment methods introduced in this article, and finally made a general judgement on the merits of each method.

Application of hyperspectral image anomaly detection algorithm for Internet of things

Hyperspectral image(HSI) anomaly detection, as one of the hottest topics in current remote sensing information processing and image processing,has important theoretical value and has been widely used in military and civilian applications. Anomaly detection aims to detect and label small man-made abnormal targets or objects without any prior knowledge. In this paper, we proposed a segmented three-order Tucker decomposition for HSI anomaly detection. There are three major steps:1) the original HSI data is divided along the three dimensions into a grid of multiple of small-sized sub-tensors. 2)Tucker decomposition followed by anomaly detection algorithm is applied onto each sub-tensor. 3) the detection results from those sub-tensors are fused. Experiments reveal that the proposed method outperforms other current anomaly detectors with better detection performance. Finally, we introduce the application of hyperspectral image anomaly detection algorithm in the Internet of things(IOT).

Semi automatic road extraction from digital images

Road extraction from digital images is of fundamental importance in the context of automatic mapping, effective urban planning and updating GIS databases. Very high spatial resolution (VHR) imagery acquired by airborne and space borne sensors is the main source for accurate road extraction. Manual techniques are fading away as they are time consuming and costly. Hence, road extraction method that is significantly more automated has become a research hotspot in remote sensing information processing. This paper proposes a semi-automatic approach to extract different road types from high-resolution remote sensing images. The approach is based on edge detection and SVM and mathematical morphology method. First the outline of the road is detected based on Canny operator. Then, Full Lambda Schedule merging method combines adjacent segments. Then the entire image was classified using Support Vector Machine (SVM) and various spatial, spectral, and texture attributes to form a road image. Finally, the quality of detected roads is improved using morphological operators. The algorithm was systematically evaluated on a variety of satellite images from Worldview, QuickBird and UltraCam airborne Images. The results of the accuracy evaluation demonstrate that the proposed road extraction approach can provide high accuracy for extraction of different road types.

Remote Sensing Intelligentized Geo-Analysis

With the rapid development of space technology, computing technology and information technology, much deep research is carried through on remote sensing information processing and analysis model and methods. The remote sensing information science, which integrate with earth sciences, mathematics, physics, computer science and information science, is being formed in recent years. Remote sensing geo\|analysis is also developed to the direction of intelligentization. In this paper, the key questions on remote sensing intelligentized Geo\|Interpretation Model(RSIGIM)is presented. RSIGIM includes statistical model based RS image process and analysis, physiological vision model based RS image cognition, and psychological symbolic logic model based RS image cognition.

A Semi-Supervised Hyperspectral Unmixing Method based on Enhanced Sparsity

Hyperspectral unmixing is the key of hyperspectral remote sensing information processing. A novel semi-supervised hyperspectral unmixing method based on spectral libraries by enhanced sparsity is proposed, which adopts a weighted formulation of L1 minimization to represent the enhanced sparsity of fractional abundances vector. Tests on simulated data and real hyperspectral images are carried out for evaluating performances. The results indicate that the proposed method can improve the accuracy of hyperspectral unmixing.

Feature extraction for target identification and image classification of OMIS hyperspectral image

In order to combine feature extraction operations with specific hyperspectral remote sensing information processing objectives, two aspects of feature extraction were explored. Based on clustering and decision tree algorithm, spectral absorption index (SAI), continuum-removal and derivative spectral analysis were employed to discover characterized spectral features of different targets, and decision trees for identifying a specific class and discriminating different classes were generated. By combining support vector machine (SVM) classifier with different feature extraction strategies including principal component analysis (PCA), minimum noise fraction (MNF), grouping PCA, and derivate spectral analysis, the performance of feature extraction approaches in classification was evaluated. The results show that feature extraction by PCA and derivate spectral analysis are effective to OMIS (operational modular imaging spectrometer) image classification using SVM, and SVM outperforms traditional SAM and MLC classifiers for OMIS data.

Human-centered concepts for exploration and understanding of Earth observation images

The progress in information retrieval, computer vision, and image analysis makes it possible to establish very complete bases of algorithms and operators. A specialist in remote sensing or image processing now has the tools that allow him, at least in theory, to configure applications solving complex problems of image understanding. However, in reality, earth observation (EO) data analysis is still performed in a very laborious way at the end of repeated cycles of trial and error. To overcome this, we proposed a novel advanced remote sensing information processing system knowledge-driven information mining (KIM). KIM is based on human-centered concepts (HCCs), which implements new features and functions allowing improved feature extraction, search on a semantic level, the availability of collected knowledge, interactive knowledge discovery, and new visual user interfaces. We assess the HCC methodology for solving several difficult tasks in EO image interpretation, using a broad variety of sensor data, from meter-resolution synthetic aperture radar and optical images to hyperspectral data.

Study on Airport Change Detection

Change detection is playing more and more important role in remote sensing information processing. However, there are two aspects of shortcoming in existing change detection algorithms. One is that too large amount of raw data is usually needed to implement the change detection. The other is that it is sometimes difficult to acquire enough amount of quantitative information. In this paper, the runway in airport is detected by taking Hough transform in single-band images. The region of interest is then located by region-growing. After a coarse step of calibration, a judgement is made on whether there is change occurring within ROI based on the edge-correlation. Finally, the elastic mask matching procedure is adopted to make an explanation to the changes detected. Satisfactory results are obtained in the experiments.