Electronics and communication

Hyperspectral Image (HSI) processing is the new advancement in image / signal processing field. The growth over the years is appreciable. The main reason behind the successful growth of the Hyperspectral imaging field is due to the enormous amount of spectral and spatial information that the imagery contains. The spectral band that the HSI which contains is also more in number. When an image is captured through the HSI cameras, it contains around 200-250 images of the same scene. Nowadays HSI is used extensively in the fields of environmental monitoring, Crop-Field monitoring, Classification, Identification, Remote sensing applications, Surveillance etc. The spectral and spatial information content present in Hyperspectral images are with high resolutions.Hyperspectral imaging has shown significant growth and widely used in most of the remote sensing applications due to its presence of information of a scene over hundreds of contiguous bands In. Hyperspectral Image Classification of materials is the critical application of HSI using Hyperspectral sensors. It collects hundreds of spectrum channels, where each channel consists of a sharp point of Electromagnetic Spectrum. The paper mainly focuses on Deep Learning techniques such as Convolutional Neural Network (CNN), Artificial Neural Network (ANN), and Support Vector machines (SVM), K-Nearest Neighbour (KNN) for the accuracy in classification. Finally in the summary the current state-of-the-art scheme, a critical discussion after reviewing the research work by other professionals and organizing it into review-based paper, also implying about the present status on classification accuracy using neural networks is carried out.

Monitoring the quantity and quality of urban vegetation accurately aids regional greening efforts and enhances knowledge of vegetation's environmental impact. Building shadows and synthetic materials, on the other hand, can severely obscure vegetation estimations. Furthermore, vegetation indices (VIs) quickly saturate in high biomass settings, making vegetation quality assessments more challenging. Plant Indices (VIs) are the most effective and simple ways for computing both the qualitative and quantitative assessments of aspects like vegetation cover, vigor, and boom dynamics, among other things, derived from remote sensing-based canopies. The indices are being used enormously inside RS for a variety of objectives, including the usage of exceptional airborne and satellite television for computer systems, as well as the use of Unmanned Aerial Vehicles (UAVs). For now, there is no unifying mathematical equation that defines all the VIs due to complexity of many mild spectra combinations, equipment, platforms, and resolutions that are being used. As a result, customized algorithms based on unique mathematical expressions that are combined see mild radiation from vegetation, normally inexperienced spectra region, and nonvisible spectra to achieve proxy quantifications of the vegetation surface have been developed and tested for a variety of applications. Optimization VIs are typically adjusted to specific software requirements in real-world applications, and they are frequently utilized in tandem with excellent validation equipment and methods on the ground. The current study discusses spectral features in plants and describes the development of VIs, as well as the advantages and risks of developing unique indices. In agricultural improvement analytics, vegetation indices are a critical metric. Information precision and miles-away management are two primary motivators for employing vegetation indices in remote sensing, which are just two of the technology's many advantages.

Image classification has become a hot topic in the field of remote sensing. In general, the complex characteristics of multispectral data make the accurate classification of such data challenging for traditional machine learning methods. In addition, multispectral imaging often deals with an inherently nonlinear relation between the captured spectral information and the corresponding materials. In this paper, we propose a novel classification method for multispectral imagery, named as support vector machine (SVM). Pixel multispectral imagery can be represented by amplitude, phase and residual in frequency. Its applicability and effects are assessed by the experiment using data set, in which CNN, and KNN based feature extraction methods are adopted for comparison, aiming to evaluate the performance of the proposed method. Experimental results illustrate that the proposed model gains the highest classification accuracy. Comparison of various performance parameters showed that KNN works better than SVM.