Search

Deep learning (DL) has been proven to be a powerful method in computer vision and is receiving increasing attention in remote sensing. It is important to analyse the research progress, hotspots, trends and methods in the field of deep learning in remote sensing. First, the main research countries (11), research institutions (20), researchers (20), and the most cited references (20) and hotspots (8) in this field were identified by analysing a total of 2,467 published papers with the bibliometric and visualized analysis (BVA) method. Then, based on the above analysis results, the research basis and the progress of hotspots in this field were summarized by reading a total of 181 relevant papers in detail with the traditional literature combing (TLC) method. The results indicate that deep learning is becoming an important tool for remote sensing and has been widely used in the vast majority of remote sensing tasks related to image processing. Among the following deep learning methods, the convolutional neural network (CNN) is undoubtedly the most widely used model. [ABSTRACT FROM AUTHOR]

Underwater biological, optical and physical measurements have been carried out at the Acqua Alta Oceanographic Tower (AAOT) in the northern Adriatic Sea on behalf of the European project 'Coastal region long-term measurements for colour remote sensing development and validation' (COLORS). This project is aimed at studying the variability of bio-optical properties and testing existing bio-optical algorithms for the major water parameters. In particular, this paper deals with the analysis of underwater profiles of optical and physical parameters, which are aimed at studying the seasonal development of stratification in the water column. The first part of this paper describes the analysis of long-term series of physical measurements, such as temperature, salinity and conductivity, to enhance the development of stratification. The influence of stratification on the optical properties of the water column is discussed in the second part of the paper, and illustration is made of the application of the previous results to the analysis of the underwater profiles of downwelling irradiance and upwelling radiance. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the editor discusses articles in the issue on topics including peer-review report, strong empirical evidence and research journals.

The imaging spectrometer MOS on IRS-P3 was launched in March 1996 as the first example of a new generation of ocean colour sensors. It consists of three different spectrometers in the visible/near-infrared spectral region with 18 channels. The IRS-P3 mission is focused on the remote sensing of case 2 water, particularly the derivation of different water constituents in coastal waters. Due to the more complex spectral behaviour of case 2 water, a new methodological approach was developed which works directly with satellite measured top-of-atmosphere radiance and accounts for the correlation of the different water constituents as well as for the spectral shape. This paper gives an overview of the mission, the scientific goals and the development and improvement of the retrieval algorithms. The potential of the algorithm is demonstrated and examples of selected European coasts are shown. Derived maps of water constituents are presented. [ABSTRACT FROM AUTHOR]

The present paper proposes an automated approach to estimate the aerosol reflectance at the Advanced Very High Resolution Radiometer (AVHRR) red channel. The aerosol dominant pixels were separated through two orthogonal transforms. The aerosol reflectance ratio at these pixels was estimated through regression. The results are validated with in situ measurements. The retrieved water-leaving reflectance matched the modelled values with a relative error below 45%. The smallest error values were at the stations with the closest sampling time to image acquisition. However, a weak correlation of 16% was found between water-leaving reflectance and aerosol signals. This suggested that these errors could be attributed to the spatial and temporal variability between the two sampling methods (ship measurement and pixel reflectance). [ABSTRACT FROM AUTHOR]

This paper presents a study of the characteristics of extra-tropical oceanic Rossby waves from datasets of Sea Surface Height (SSH), Sea Surface Temperature (SST) and ocean colour. The main focus is on the propagation speed of the waves and a comparison is made between the observational results and the speeds predicted by the classical theory and by the most recent extended theory of Rossby waves. There is also discussion, with an example, of the additional information that can be derived by a comparison of the wave signatures in the different datasets. [ABSTRACT FROM AUTHOR]

Road vector data are an important part of geographic information databases and play a leading role in social and economic development. Among them, the accuracy and current situation of vector data are the key values of their application. In recent years, with the development of remote sensing technology, remote sensing images contain increasingly more road information, which provides a large number of available features for the establishment of vector correction models. Therefore, the vector-to-image vector correction method based on remote sensing images has become an important means to ensure the accuracy and current situation of vector data. However, in actual scenes, there are great differences in the design structure and design index between urban roads and rural roads, which is reflected in the serious spatial heterogeneity between them in the remote sensing images. Therefore, when the existing methods use remote sensing images for vector correction, the universality is limited by the change of regional scenes, so it is difficult to realize the simultaneous correction of urban road and rural road vectors, with poor applicability and low compatibility. To solve this problem, this paper proposes a vector data partition correction method supported by deep learning. First, the U2-net model and line segment sequence method are used to generate the feature set. Second, according to the characteristics of the poor quality of urban road extraction results, the regular geometric form of vector data and the poor structural information of road images, the methods of vector line decomposition, subvector line correction, subvector line centralization and vector line synthesis are proposed to correct the vector lines of urban roads. Finally, according to the characteristics of high-quality rural road extraction, the irregular geometric form of vector data and the strong information of road image structures, this paper proposes road edge extraction, a road centreline reasoning model and a vector line connection method to complete the correction of rural vector road data. The quantitative analysis of the experimental results shows that compared with other methods, the urban road vector correction method in this paper is much better than the comparison methods and has achieved better correction results in rural areas. This method has the advantages of compatibility and better accuracy for roads in different areas. [ABSTRACT FROM AUTHOR]

Due to background clutter in synthetic aperture radar (SAR) images, the detection of dense ship targets suffers from a low detection rate, high false alarm rate, and high missed detection rate. To address this issue, an FSM-DFF-YOLOv5+Confluence algorithm is proposed in this paper for the detection of near-shore ship targets in SAR images with complex backgrounds. First, based on the YOLOv5 target detection algorithm, two improvements are made in the feature extraction network: feature refinement and multi-feature fusion; in the feature extraction network, deformable convolutional neural networks are adopted to change the position of the target sampling points of the convolution to improve the feature extraction capability of the target and the detection rate of ship targets in SAR images with a complex background; in the multi-feature fusion network structure, cascading and parallel pyramids are used in the multi-feature fusion network to realize feature fusion at different levels; the visual perceptual field of feature extraction is expanded by using null convolution to enhance the adaptability of the network to detect near-shore multi-scale ship targets with complex backgrounds and reduce the false alarm rate of ship target detection in SAR images with complex environments. In this way, the DFF-YOLOv5 near-shore ship target detection algorithm is established. Meanwhile, to address the problem of missed detection in near-shore dense ship target detection, this paper adds rectangular convolution kernels to the convolution of the feature extraction network to better realize the feature extraction of dense ship targets in SAR images with complex backgrounds. Besides, the Confluence algorithm instead of non-maximum suppression is used in the prediction stage. Through experiments on the constructed complex background near-shore ship detection dataset, it is indicated that the average accuracy of the FSM-DFF-YOLOv5+Confluence detection algorithm reaches 88.96%, and the recall rate reaches 88.80%. [ABSTRACT FROM AUTHOR]

Light Detection and Ranging (LiDAR) intensity is associated with the target surface material, which could help the points cloud classification. However, the intensity is also associated with the laser beam incident angle and the transmitting distance, which obstructs its further application in points cloud classification. Motivated by this problem, this paper proposed a practical method for employing the LiDAR intensities in points cloud classification without distance and incident angle calibration, specifically, ratio values between different spectral channels from a newly invented Hyper-spectral LiDAR (HSL) were defined and calculated for generating robust spectral features. Since the HSL different channels had the same transmitting distance and incident angle, therefore, the ratio values were independent on the laser pulse transmitting distance and laser beam incident angle. An indoor experiment was conducted for fully assessing the proposed method. The HSL had eight different spectral channels with spectral wavelength covering from 650 nm to 1000 nm. In the experiments, papers with different colours were pasted on a flat glass; the HSL scanned them at four distinctive positions with 60 cm displacement. The spectral ratio values between different channels at each position were calculated using the obtained multiple spectral profiles from the HSL. The results showed that the points cloud scanned at different incident and distance could be classified though the spectral ratio values without complex distance and incident angle calibration. [ABSTRACT FROM AUTHOR]

The aim of this research is to automatically detect and visualize dynamic ocean colour phenomena such as algae blooms, fronts and eddies from a sequence of cloudy satellite images. The composite front map methodology has been extended to combine feature observations from multiple ocean colour and temperature products in a single map, to explore the interaction between physical and biological oceanic processes. Sample maps showing chlorophyll, sediment and sea surface temperature fronts are presented, derived from long sequences of cloud-affected Advanced Very High Resolution Radiometer (AVHRR) and Sea viewing Wide Field of view Sensor (SeaWiFS) data. The successful detection and animation of many ocean colour features suggests a valuable application to summarize the increased multi-spectral data provided by the National Aeronautics & Space Administration's (NASA) Moderate Resolution Imaging Spectroradiometer (MODIS) instrument. [ABSTRACT FROM AUTHOR]