Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item Effectiveness of Phase Correlation Spectral Similarity Measure in Distinguishing Target Signatures for Hyperspectral Data Analysis(Institute of Electrical and Electronics Engineers Inc., 2020) Yadav, P.P.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Hyperspectral imaging is one of the most information-rich sources of remote sensing data that exists. It can capture the entire, continuous spectrum of color and light. Feature extraction techniques that are selected for identifying diagnostic features influence classification accuracy. Spectral matching algorithms like similarity measures are developed to compare spectral features of materials with their reference spec-tral signatures in identifying different earth surfaces. Similarity measures are used as simple feature extraction techniques in target identification using hyperspectral data. Though there are several similarity measures, selecting a robust similarity measure requires further investigation. Influence of similarity measures are not studied much in distinguishing spectrally distinct signatures. In this article, we propose to study the performance of similarity measures in (i) discriminating endmember signatures (ii) mixed pixel identification (iii) clustering signatures of different classes and (iv) endmember extraction. Experimental results show an effective and a robust performance of proposed phase correlation similarity measure among all other similarity measures compared for all the problems under investigation. © 2020 IEEE.Item Similarity measures in generating spectrally distinct targets(Institute of Electrical and Electronics Engineers Inc., 2020) Yadav, P.P.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.In multispectral and hyperspectral remote sensing, classification of pixels is obtained by means of spectral similarity of known field or library spectra to unknown image spectra. Endmember extraction is the most decisive task in hyperspectral image analysis. Endmember initialization algorithms (EIAs) play a key role and support endmember extraction algorithms (EEAs) in extracting near optimal set of endmembers. Though there are few endmember initialization techniques available, similarity measures are not explored in detail in target generation. Hence, in this paper, it is proposed to explore similarity measures in identifying spectrally distinct signatures to use them as initial endmembers. Individual similarity measures are combined to form hybrid similarity measures to confirm their effectiveness in generating spectrally distinct targets. Initial set of endmembers extracted by proposed algorithm are used for initializing classical EEA, the NFINDR, which is sensitive to endmember initialization, and their performance in final endmembers selection is verified. Experimental results on two hyperspectral data sets show the superior performance of the similarity based endmember initialization algorithm (SMEIA). © 2020 IEEE.Item INFLUENCE OF THE DARKEST PIXEL ON ENDMEMBERS INITIALIZATION(Institute of Electrical and Electronics Engineers Inc., 2021) Yadav, P.P.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Endmember extraction is one of the necessary steps in hyperspectral data investigation. The eventual objective of hyperspectral data processing and analysis is to improve the accuracy of target identification, and the precise identification of endmembers is a challenging task. The several of the algorithms proposed for endmember extraction require knowledge on the targets for appropriate initialization. The endmember extraction algorithms (EEAs) rely on endmember initialization algorithms (EIAs) and in turn many EIAs also require the knowledge on targets of interest to begin the search process effectively. A comprehensive study on targets of interest to begin the search process is due expected. Therefore, in this paper, the concept of extreme or boundary pixels is explored to identify the targets of interest and the darkest pixel (a pixel with minimum length) is identified and proposed as a new target of interest to begin the endmember search process. The utility/influence of the proposed target of interest, i.e. the darkest pixel, is studied with that's of the brightest pixel (a pixel with maximum length) which has been in use as a popular target of interest for EIAs so far. An automatic target generation process (ATGP) and a similarity measures based endmember initialization algorithm (SMEIA) are adapted to test the proposed initialization strategy. The experimental results have revealed the usefulness of the darkest pixel as an additional target of interest in addition to the brightest pixel in searching for endmembers by EIAs. The strategy of choosing the darkest pixel enhanced the initial target knowledge and also improved the performance of the EIAs considerably. © 2021 IEEE.Item Gradient Based Spectral Similarity Measure for Hyperspectral Image Analysis(Institute of Electrical and Electronics Engineers Inc., 2021) Yadav, P.P.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Spectral matching algorithms or similarity measures dis-criminate spectral signatures of unknown materials by comparing them with the reference spectral signatures. Spectral matching algorithms play an important role in identifying different earth surface features using hyperspectral image analysis. Identification of diagnostic features and discriminating spectral signatures, especially of mineral signatures, which exhibit subtle differences among themselves is still a challenging task. Thus, developing or coming up with a new spectral matching algorithms is expected. Therefore, in this paper, we present a gradient based spectral similarity measure (GSSM) that captures the diagnostic (absorption) features to measure the degree of closeness between spectral signatures. Effectiveness of the proposed GSSM in distinguishing spectrally distinct signatures is studied with that of other spectral matching algorithms in (i) discriminating endmember signatures (ii) mixed pixel identification (iii) clustering spectral signatures of different classes and (iv) endmember extraction. Experimental results on a spectral library of 5 minerals formed using a benchmark mineral dataset called Cuprite data clearly show that the proposed GSSM is capable of (i) discriminating different spectral signatures in a better manner and also (ii) bringing into notice of the user the locations of diagnostic features by highlighting them to recognize easily. © 2021 IEEE.Item Fusing Conventional and Deep Learning Features for Hyperspectral Image Change Detection(Institute of Electrical and Electronics Engineers Inc., 2022) Bobate, N.; Yadav, P.P.; Narasimhadhan, A.V.In the field of remote sensing technology Change Detection (CD) is one of the major areas of research. Changes that have occurred on the earth's surface over time can be detected with this tool. Hyperspectral Image (HSI) data with high spectral resolution can help in identifying subtle changes than the typical multispectral image (MSI), and CD technology has benefitted immensely with the applications of HSI. Traditional CD techniques that used MSI as their input data are challenging to implement on HSI due to the high dimensionality of hyperspectral data. Furthermore, HSI data is affected by a lot of distortion and redundancy, contaminating the spectral-only information for CD purposes. CD accuracy can be improved by extracting the useful features of HSI. In Change Detection algorithms, the initial step is to extract features. Traditionally it is done using arithmetic operation, image transformation, and statistical methods. While some advanced strategies for extracting features are utilizing convolutional neural networks (CNNs) using the deep learning method. In this work, we aimed to integrate the conventional features with CNN extracted features to boost the overall ac-curacy of popular DL-based CD techniques. Spectral matching algorithms are used for extracting conventional features. In addition, appropriate changes are made to the recent deep learning architectures called Three-Directions Spectral-Spatial Convolution neural network (TDSSC) and General End-To-End Neural Network (GETNET), to fuse the conventional features. Farmland, River and USA data sets are used for experimentation. The proposed approach proves to be useful in improving the performance of DL-based CD techniques. © 2022 IEEE.Item Gradient Correlation Incorporated Similarity Measures in Matching Spectral Signatures(Institute of Electrical and Electronics Engineers Inc., 2022) Yadav, P.P.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Hyperspectral images provide ample information which is needed to be analyzed carefully by the spectral processing algorithms for identifying objects, finding minerals etc. Spectral matching algorithms (SMAs) which make use of similarity measures discriminate and identify earth surface features by comparing spectral signatures with the ground-truth. SMAs that discriminate overall patterns capturing the diagnostic features of spectral signatures is of great use. In view of this, in this paper, we explore spectral gradient as a diagnostic feature to discriminate spectral signatures. Applicability of the proposed spectral gradient which is incorporated with SMAs in distinguishing spectrally distinct signatures is experimented in the following cases: (i) discriminating endmember signatures (ii) mixed pixel identification (iii) clustering spectral signatures of different classes and (iv) endmember extraction. Overall, the experimental results on a benchmark mineral Cuprite dataset library of five minerals have shown significantly improved performance in discriminating various spectral signatures. © 2022 IEEE.Item ATGP based Change Detection in Hyperspectral Images(IEEE Computer Society, 2022) Yadav, P.P.; Bobate, N.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Hyperspectral images (HSIs) due to advancements in spatial-spectral resolutions and availability of multi-temporal information is in demand for many remote sensing (RS) applications including change detection (CD). The high dimensionality of HSIs and limited availability of HSI-CD data sets with ground-truth change maps make CD not so easy but a difficult task. Though there are many classical and deep learning (DL) based algorithms to detect changes, the performance of classical algorithms is not up to the satisfactory level and the final performance of DL models depend on efficiency of pre-detection techniques which provide prior knowledge on changed and unchanged areas that are required to get appropriate training samples to learn to detect changes. Classical and DL approaches consider change information at pixel level i.e. pixel to pixel change either by comparing the corresponding pixels alone or with their local neighborhood pixels. Therefore, identification of features for every pixel that relate the most significant information of the whole HSI-CD data in a simple and an efficient way to detect changes effectively is the need of the hour. In addition, there is not much comprehensive study on developing CD algorithms that not only simple to use but also as efficient as that of DL models is available. Therefore, in this paper, an endmember based feature extraction is proposed to detect changes in HSI. An automatic target generation process (ATGP) algorithm is adapted to extract endmembers present in the HSI-CD data set. Then, various spectral matching algorithms are used to measure endmember relations for all the pixels so that dimensionality of the data is reduced as well as the effective features to detect changes can be extracted. The experimental results on three benchmark HSI-CD data sets show that proposed ATGP based change vector analysis (CVA) algorithm yields remarkable results on comparing both with the classical as well as DL based CD approaches. © 2022 IEEE.Item Virtual Sample Generation Of Hyperspectral Mineral Data(Institute of Electrical and Electronics Engineers Inc., 2023) Yadav, P.P.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Identification of earth surface features or useful resources even at inaccessible locations for humans made possible with the help of spatial-spectral information provided by remote sensing data especially hyperspectral images. At present deep learning (DL) based models have become a best choice to address the issues and provide better solutions in many fields including remote sensing data analysis. Due to very subtle differences exhibited by mineral signatures and also lack of sufficient training samples, geo-science and remote sensing research community has not much explored the DL techniques in analyzing mineral data. Therefore, in this paper, a virtual sample generation technique using vector rotation is proposed to increase the mineral data for training DL models. The proposed virtual sample generation technique is explored on a spectral library of 5 minerals that is formed from Cuprite scene, a benchmark mineral data set. The quality of the mineral samples generated are assessed using visual inspection as well as a relative spectral discriminating power of target minerals with respect to non-target or remaining minerals. Results show that mineral samples generated by the proposed virtual sample generation technique are not only qualitative in nature but also helpful or encouraging in exploration of DL in mineral data analysis. © 2023 IEEE.Item A Meaningful Reformulation of Relative Spectral Discrimination Power to Analyze Hyperspectral Data(Institute of Electrical and Electronics Engineers Inc., 2023) Yadav, P.P.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Spectral matching algorithms (SMAs) discriminate and distinguish spectral signatures of earth surface features by comparing with their ground-truth spectra. Though different SMAs developed based on different theoretical strategies, choosing an effective SMA is still a challenging task. To study the performance of SMAs in distinguishing spectral signatures, few performance measure are developed and relative spectral discrimination power (RSDPW) is one such a measure. RSDPW discriminates how one spectral signature is distinct from another relative to a reference spectral signature. Classical way of measuring RSDPW do not takes into account of spectral matching between the two spectral signatures to be discriminated. Therefore, in this paper, a reformulation for RSDPW is presented to get a good idea about the spectral diversity of spectral signatures to measure RSDPW in a more meaningful manner and also to make it perspicacious. The experimental results show that the proposed reformulated RSDPW not only a meaningful way to measure it but also robust/standard enough to compare various SMAs by measuring it. Additionally, the range of RSDPW values for different levels of discrimination is demonstrated for the present study. © 2023 IEEE.Item 1-D CNN for Mineral Classification using Hyperspectral Data(Institute of Electrical and Electronics Engineers Inc., 2023) Yadav, P.P.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Hyperspectral Image (HSI) is a potent remote sensing (RS) technique, capturing images over numerous narrow, contiguous spectral bands. Unlike traditional RS methods, HSI offers detailed spectral insights for each pixel, enhancing comprehension of the Earth's surface and its contents. Initially intended for mining and geology, its application has expanded across various domains. Yet, mineral identification poses challenges due to spectral signature variations and limited ground truth. Despite various advanced algorithms, including machine learning, no dedicated Deep Learning (DL) expert system exists for mineral classification in HSI. DL models require abundant training data and ground-truth, which are scarce in hyperspectral mineral data. Introducing the 1-D CNN model as a proposed method, we focus on enhancing mineral classification by increasing the available training data. The utilization of augmented training samples through the 1-D CNN model tackles the challenge of limited ground truth data, enabling accurate classification of mineral classes. © 2023 IEEE.