Search

Water Body Extraction (WBE) is a challenging task in remote sensing, owing to the complexity of recognizing surface body objects with rich texture, spatial, spectral, temporal, and radiometric features. The use of spectral indices has shown to be successful in separating surface water from its surroundings at the cost of knowledge of appropriate threshold values. In the absence of knowledge on threshold values, extracting the water from remote sensing data is challenging, which is addressed by several Machine Learning (ML) and Deep Learning (DL) algorithms. However, the effectiveness of both ML and DL classifications is witnessed from visual features to semantic categories at the cost of distinct recognition between the water body and non-water body features. In this paper, a novel Multi Scale Feature Extraction Network (MSFEN) for extracting the pixel-level features from medium resolution remote sensing images is proposed and used traditional ML classifiers to extract the surface water bodies using pixel-level features extracted by MSFEN. The proposed framework is trained and tested on Linear Imaging Self Scanning Sensor – III (LISS-III) multispectral satellite images over major water reservoirs in Tamilnadu, Karnataka, Madhya Pradesh, and Odisha. Experimental results indicate that the proposed model MSFEN+SVM provides accurate extraction results by outperforming the existing state-of-the-art models (Fully Convolutional Network (FCN), Unet, SegNet, Multi Scale Convolutional Neural Network (MSCNN), Deepwater Map, Pyramid Scene Parsing Network (PSPNet), Improved PSPNet, Multi-scale Water Extraction Convolutional Neural Network (MWEN) and Multi-Scale Lake Water Extraction Network (MSLWENet) in terms of performance metrics considered. [ABSTRACT FROM AUTHOR]

Image segmentation is a crucial step in remote sensing application, as it breaks down a larger image into smaller chunks, which contains useful information. Although there are several image segmentation algorithms available, evaluation of the algorithms is challenging. Furthermore, the evaluation of image segmentation can elucidate the best image segmentation algorithm for a single image or a group of image or a whole class of image. This paper explores and evaluates the benefits and the drawbacks of various qualitative and quantitative image segmentation evaluation metrics used in remote sensing applications. For all the metrics, a quantitative set of values for good and bad segmentation is provided. In addition, some image segmentation algorithms such as Multi Otsu Threshold, K Means clustering, Fuzzy C Means clustering, Improved K Means clustering (IFCM), Improved Fuzzy C Means clustering, Naïve Bayes classifier, K Nearest Neighbor, Decision Tree (DT) and Random Forest classifier are used in the experimental comparison of metrics. The qualitative and quantitative satellite image segmentation evaluation using the mentioned algorithms is measured. The results are analyzed to strengthen the impact of different metrics on the segmentation algorithms. In both qualitative and quantitative analysis, the IFCM outperformed the other unsupervised machine learning algorithms and the DT outperformed the other supervised machine learning algorithms. The effectiveness of the provided metrics in the remote sensing field is validated. [ABSTRACT FROM AUTHOR]

Aerosols are particles that are omnipresent in the atmosphere. They vary in size, shape and composition. They can be naturally occurring or might be produced artificially. However, proper classification and characterization of aerosols have been still in progress and this creates uncertainty in climatological studies. In this paper, an aerosol classification scheme has been presented based on the measurements done using a CIMEL sunphotometer in Thessaloniki, Greece from 1998 to 2017. The study has been mainly upheld by the direct measurements of Single Scattering Albedo (SSA) at 440nm and Fine Mode Fraction (FMF) at 500nm. These parameters have been used to establish testing and training datasets. Machine learning algorithms have been used to validate the classified data. Various performance metrics have been evaluated. Also, the bestfit algorithm for classifying aerosol data has been found out. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) refers to the recreation of human intelligence in machines that have been designed to think like humans and mimic their actions. AI has been used in many fields such as image processing, health care, education, and marketing. Machine Learning (ML) has been the sub-division of AI, and deep learning has been the subdivision of ML. Artificial Neural Network has been the most predominantly used deep learning technique. While implementing the ANN technique, knowing whether the implementation could have been done in hardware or software becomes necessary, which is essential to achieve the expected performance. This paper gives a survey on the available methods in which the ANN architecture has been implemented to achieve efficient output with minimal resources. It is vital to study and analyze various strategies for implementation and their functionality. This paper has also explained the advantages and disadvantages of different implementation techniques that allow selecting the most appropriate hardware and respective methodology for optimizing the hardware. [ABSTRACT FROM AUTHOR]