Author
Prabukumar Manoharan
Bio: Prabukumar Manoharan is an academic researcher from VIT University. The author has contributed to research in topics: Hyperspectral imaging & Convolutional neural network. The author has an hindex of 8, co-authored 17 publications receiving 155 citations.
Papers
More filters
TL;DR: This paper deals with the most frequent methods used by researchers on various processes like pre-processing, classification, and prediction of time series satellite images for analyzing the LU/LC changes using satellite images.
Abstract: The surface of the earth is rapidly changing every day due to certain natural reasons and other impacts by society. Over the last few decades, the hottest topics in the field of remote sensing and GIS (geographic information system) environments have evolved from observing the nature of the earth. Owing to the enlargement of several worldwide modifications related to the nature of the earth, land use/land cover (LU/LC) change is considered as the matter of utmost importance in the natural atmosphere, and it has also become an interesting area to be studied by the researchers. As there is a lack of review articles in the land use/land cover change analysis process, we presented a comprehensive review which may help the researchers to proceed further. This paper deals with the most frequent methods used by researchers on various processes like pre-processing, classification, and prediction of time series satellite images for analyzing the LU/LC changes using satellite images. The generic flow of the LU/LC change analysis process and the challenges faced during each process by the researchers are discussed. Varied resolutions of the environmental image captured by remote sensing satellites for analyzing the LU/LC changes are discussed. Various LU/LC classes depending on change in the earth’s surface are also studied and the constraint used in each application is stated. The importance of this review lies in the motivation for future researchers to work on the LU/LC change analysis problem effectively.
70 citations
TL;DR: This paper presents an approach for remote sensing hyper spectral image classification based on data normalization and CNN, which has achieved significant performance over the state-of-art methods.
70 citations
TL;DR: The Three Dimensional Discrete Cosine Transform (3D DCT)-based information entropy is used for band selection from a high-dimensional data space and demonstrates the promising discriminant capability of the DCT features.
Abstract: Band selection is an effective means of reducing the dimensionality of the hyperspectral image by selecting the most informative and distinctive bands. Bands are usually selected by adoptin...
49 citations
TL;DR: A method that uses unsupervised band selection called optimal neighboring reconstruction (ONR), which extracts a subset of spectral bands to linearly reconstruct the original data with minimum loss and Structure-Preserving Recursive Filter (SPRF) to extract spatial features is proposed.
35 citations
TL;DR: A modified WDO (MWDO) is proposed for band selection, which is able to avoid the premature convergence and control the exploration–exploitation search trade-off and provides high classification accuracy with fewer bands in comparison with other approaches.
Abstract: The presence of irrelevant and highly correlated spectral bands significantly reduces the classification accuracy of the hyperspectral images. Therefore, the selection of suitable bands from the se...
28 citations
Cited by
More filters
TL;DR: A novel triple-image encryption and hiding algorithm is proposed by combining a 2D chaotic system, compressive sensing (CS) and the 3D discrete cosine transform (DCT) to obtain a visually meaningful cipher image.
106 citations
Johns Hopkins University1, Global Alliance for Improved Nutrition2, International Center for Tropical Agriculture3, International Food Policy Research Institute4, International Institute for Environment and Development5, Harvard University6, Cornell University7, University of British Columbia8, Food and Agriculture Organization9, University of Cape Town10, World Food Programme11, University of Montpellier12, Bioversity International13, American University14, University of Pretoria15, Peking University16, University of Ghana17, Ohio State University18, The Nature Conservancy19
TL;DR: In this paper, a rigorous, science-based monitoring framework can support evidence-based policymaking and the work of those who hold key actors accountable in this transformation process, which can illustrate current performance, facilitate comparisons across geographies and over time, and track progress.
84 citations
TL;DR: Wang et al. as discussed by the authors proposed a double image encryption algorithm based on convolutional neural network (CNN) and dynamic adaptive diffusion, which not only ensures the security of double image but also improves the encryption efficiency and reduces the possibility of being attacked.
Abstract: To realize the secure transmission of double images, this paper proposes a double image encryption algorithm based on convolutional neural network (CNN) and dynamic adaptive diffusion. This scheme is different from the existing double image encryption technology. According to the characteristics of digital image, we design a dual-channel (digital channel / optical channel) encryption method, which not only ensures the security of double image, but also improves the encryption efficiency and reduces the possibility of being attacked. First, a chaotic map is used to control the initial values of the 5D conservative chaotic system to enhance the security of the key. Secondary, in order to effectively resist known-plaintext attack and chosen-plaintext attack, we employ a chaotic sequence as convolution kernel of convolution neural network to generate plaintext related chaotic pointer to control the scrambling operation of two images. On this basis, a novel image fusion method is designed, which splits and fuses two images into two different parts according to the amount of information contained. In addition, a dual-channel image encryption scheme, optical encryption channel and digital encryption channel, is designed for the two parts after fusion. The former has better parallelism and higher encryption efficiency, while the latter has higher computational complexity and better encryption reliability. Especially in the digital encryption channel, a new dynamic adaptive diffusion method is designed, which is more flexible and secure than the existing encryption algorithm. Finally, numerical simulation and experimental analysis verify the feasibility and effectiveness of the scheme.
70 citations
TL;DR: This paper presents an approach for remote sensing hyper spectral image classification based on data normalization and CNN, which has achieved significant performance over the state-of-art methods.
70 citations
TL;DR: An information theoretic normalized Mutual Information (nMI)-based minimum Redundancy Maximum Relevance (mRMR) non-linear measure to select the intrinsic features from the transformed space of the previously proposed Segmented-Folded-PCA (Seg-Fol- PCA) and Spectrally Segmenting-Folding-PC a (SSeg-FOL-PCa) FE methods.
Abstract: Hyperspectral image (HSI) usually holds information of land cover classes as a set of many contiguous narrow spectral wavelength bands. For its efficient thematic mapping or classification, band (f...
68 citations