Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
13 results
Search Results
Item Depth image super-resolution with local medians and bilateral filtering(Institute of Electrical and Electronics Engineers Inc., 2016) Balure, C.S.; Ramesh Kini, M.; Bhavsar, A.In this paper, we propose an approach for depth image super-resolution (SR). Given a noisy low resolution (LR) depth image and its corresponding registered high resolution (HR) colour image, our approach improves the resolution of the LR image while suppressing noise. We use the segmentation of HR colour images as a cue for depth image super-resolution. Our method begins with a highly over-segmented color image (using well-known segmentation approaches such as mean shift (MS) or simple linear iterative clustering (SLIC), and an interpolated LR depth image. We then use a combination of the local medians in the depth image (corresponding to the colour segments) and bicubic interpolation, followed by bilateral filtering to compute the SR depth image. We performed experiments for higher magnification factors 4, 8 using the Middlebury depth image dataset and evaluate the SR performance using the PSNR and SSIM metrics. The experimental results show that proposed method (including some variants), while being relatively simplistic, shows an average improvement of 1.2dB and 1.7dB on noiseless and noisy data respectively, over the popular method of guided image filtering (GIF) for upsampling factor 8. © 2016 IEEE.Item Depth image super-resolution: A review and wavelet perspective(Springer Verlag service@springer.de, 2017) Balure, C.S.; Ramesh Kini, M.We propose an algorithm which utilizes the Discrete Wavelet Transform (DWT) to super-resolve the low-resolution (LR) depth image to a high-resolution (HR) depth image. Commercially available depth cameras capture depth images at a very low-resolution as compared to that of the optical cameras. Having an highresolution depth camera is expensive because of the manufacturing cost of the depth sensor element. In many applications like robot navigation, human-machine interaction (HMI), surveillance, 3D viewing, etc. where depth images are used, the LR images from the depth cameras will restrict these applications, thus there is a need of a method to produce HR depth images from the available LR depth images. This paper addresses this issue using DWT method. This paper also contributes to the compilation of the existing methods for depth image super-resolution with their advantages and disadvantages, along with a proposed method to super-resolve depth image using DWT. Haar basis for DWT has been used as it has an intrinsic relationship with super-resolution (SR) for retaining the edges. The proposed method has been tested on Middlebury and Tsukuba dataset and compared with the conventional interpolation methods using peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) performance metrics. © Springer Science+Business Media Singapore 2017.Item Self-optimal clustering technique using optimized threshold function(Institute of Electrical and Electronics Engineers Inc., 2014) Verma, N.K.; Roy, A.This paper presents a self-optimal clustering (SOC) technique which is an advanced version of improved mountain clustering (IMC) technique. The proposed clustering technique is equipped with major changes and modifications in its previous versions of algorithm. SOC is compared with some of the widely used clustering techniques such as K-means, fuzzy C-means, Expectation and Maximization, and K-medoid. Also, the comparison of the proposed technique is shown with IMC and its last updated version. The quantitative and qualitative performances of all these well-known clustering techniques are presented and compared with the aid of case studies and examples on various benchmarked validation indices. SOC has been evaluated via cluster compactness within itself and separation with other clusters. The optimizing factor in the threshold function is computed via interpolation and found to be effective in forming better quality clusters as verified by visual assessment and various standard validation indices like the global silhouette index, partition index, separation index, and Dunn index. © 2007-2012 IEEE.Item Spatial variability of topsoil chemical properties(Agricultural Research Communication Centre 1130 Sadar Bazar Karnal, Haryana 132 001, 2015) Gopal, B.; Shetty, A.; Jayaprakash; Chaya, D.Y.Soil properties vary spatially and temporally because of soil formation processes, land use pattern, fertilizations etc. Geo-statistics, remote sensing and GIS offer some of the best tools and techniques to capture the spatial variability of soil properties. Study area chosen for the investigation is situated in the coastal zone, covering a part of Dakshina Kannada and Udupi Districts, Karnataka. Study area predominantly consists of sandy, loamy sand and gravelly elay soils. Harvested agricultural paddy fields were identified as soil sampling locations. A total of 260 soil samples were collected from top 0-20 cm of soil surface and were air dried. Measurement of topsoil chemical properties such as Organic Matter (OM), pH, Electrical Conductivity (EC), Nitrogen (N), Phosphorus (P), Potassium (K), Calcium (Ca) and Iron Oxide (Fe2O3) were carried out as per Indian Standard Codes. Descriptive statistics were computed, correlation between the soil properties was explored and also soil properties were interpolated and mapped using IDW interpolation method. Soil properties have very large variability. In this region topography and vegetation is homogeneous, and no erosion activity is observed. So the only reason for the high variability of soil properties is agricultural practices. Correlation among soil properties is not consistent. There is no significant influence of soil type on soil properties range. Restoration of small scale farmers is important in food security point of view.Item Integer and fractional order-based viscoelastic constitutive modeling to predict the frequency and magnetic field-induced properties of magnetorheological elastomer(American Society of Mechanical Engineers (ASME), 2018) Poojary, U.R.; Gangadharan, K.V.Magnetorheological elastomer (MRE)-based semi-active vibration mitigation device demands a mathematical representation of its smart characteristics. To model the material behavior over broadband frequency, the simplicity of the mathematical formulation is very important. Material modeling of MRE involves the theory of viscoelasticity, which describes the properties intermediate between the solid and the liquid. In the present study, viscoelastic property of MRE is modeled by an integer and fractional order derivative approaches. Integer order-based model comprises of six parameters, and the fraction order model is represented by five parameters. The parameters of the model are identified by minimizing the error between the response from the model and the dynamic compression test data. Performance of the model is evaluated with respect to the optimized parameters estimated at different sets of regularly spaced arbitrary input frequencies. A linear and quadratic interpolation function is chosen to generalize the variation of parameters with respect to the magnetic field and frequency. The predicted response from the model revealed that the fractional order model describes the properties of MRE in a simplest form with reduced number of parameters. This model has a greater control over the real and imaginary part of the complex stiffness, which facilitates in choosing a better interpolating function to improve the accuracy. Furthermore, it is confirmed that the realistic assessment on the performance of a model is based on its ability to reproduce the results obtained from optimized parameters. © © 2018 by ASME.Item Comparison of modeling methods for wind power prediction: a critical study(Higher Education Press Limited Company, 2020) Shetty, R.P.; Sathyabhama, A.; Pai, P.S.Prediction of power generation of a wind turbine is crucial, which calls for accurate and reliable models. In this work, six different models have been developed based on wind power equation, concept of power curve, response surface methodology (RSM) and artificial neural network (ANN), and the results have been compared. To develop the models based on the concept of power curve, the manufacturer’s power curve, and to develop RSM as well as ANN models, the data collected from supervisory control and data acquisition (SCADA) of a 1.5 MW turbine have been used. In addition to wind speed, the air density, blade pitch angle, rotor speed and wind direction have been considered as input variables for RSM and ANN models. Proper selection of input variables and capability of ANN to map input-output relationships have resulted in an accurate model for wind power prediction in comparison to other methods. © 2018, Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature.Item Guidance-based improved depth upsampling with better initial estimate(Inderscience Publishers, 2021) Balure, C.S.; Ramesh Kini, M.Like optical images, depth images are also gaining popularity because of its use in many applications like robot navigation, augmented reality, 3DTV and more. The commercially available depth cameras generate depth images which suffer from low spatial resolution, corrupted with noise, and missing regions. Such images need to be super-resolved, denoised and inpainted before using them to have better accuracy. Super-resolution (SR) techniques can be used to produce a high-resolution output. Since SR is an ill-posed inverse problem, a good initial estimate is always a good regulariser to find the optimal solution. We propose an initial estimate as part of our SR pipeline, esp. ×8, which will helps in quick convergence and accurate output. We propose a cascade approach by combining residual interpolation (RI) method with anisotropic total generalised variation (ATGV) method, both uses HR guidance image. The improvements are shown qualitative and quantitative with different levels of noise. © 2021 Inderscience Publishers. All rights reserved.Item Static, free vibrational and buckling analysis of laminated composite beams using isogeometric collocation method(Elsevier Ltd, 2022) Pavan, G.S.; Muppidi, H.; Dixit, J.Isogeometric collocation (IGA-C) method is a computational approach to solve boundary value problems. In this method (IGA-C), the differential equations are solved in strong form instead of the weak form approach adopted by Galerkin based formulations. IGA-C method is computationally efficient in comparison to conventional finite element method and Galerkin-Isogeometric approaches. IGA-C method does not involve the process of assembling global stiffness matrix from element stiffness matrix. Another advantage of IGA-C is that it requires a single integration point per element irrespective of the order of Non-Uniform Rational B-Spline functions (NURBS) adopted. Isogeometric collocation has also been demonstrated as a stable, efficient and accurate higher order computational method for explicit problems. For a wider adoption of isogeometric collocation method, beam/plate/shell finite elements within the framework of IGA-C method need to be formulated. Owing to the extensive adoption of laminated composites in structural components, development of beam finite elements for laminated composite beams based on isogeometric collocation method will prove useful during analysis of composite structures. IGA-C method is proposed in this study for the static bending, free vibration and buckling analysis of laminated composite beams. Classical laminated plate theory (CLPT), first order shear deformation theory (FSDT) and higher order shear deformation theory (HSDT) are considered for all the three analyses. The computational approach proposed for laminated beam based on HSDT contains two Degrees of Freedom (DOF) per node. Computational approach for analysing laminated composite beams based on each of these kinematic theories and using IGA-C method is presented. Accuracy of the proposed computational approaches is checked by solving different numerical examples. Values of normalized transverse displacement, normalized stresses, normalized natural frequencies and normalized critical buckling loads are compared with results from the literature and are found to be accurate. © 2022 Elsevier Masson SASItem Driving Cycle-Based Design Optimization and Experimental Verification of a Switched Reluctance Motor for an E-Rickshaw(Institute of Electrical and Electronics Engineers Inc., 2024) Bhaktha, B.S.; Jose, N.; Vamshik, M.; Pitchaimani, J.; Gangadharan, K.V.This article deals with the design and optimization of a 2 kW switched reluctance motor (SRM) for an electric rickshaw (E-rickshaw). Previously published research on SRM optimization has mostly focused on the optimization of their design and control variables only at the rated conditions. In electric vehicle (EV) applications, the load operating points (LOPs) of a traction motor are dynamic and spread widely across the torque speed envelope. To enhance their overall performance, it is vital to include them in the design optimization process; therefore, in this article, a novel procedure for implementing the multiobjective design optimization (MODO) of an SRM based on a driving cycle has been demonstrated. Higher starting torque and torque density with reduced electromagnetic losses throughout the driving cycle are established as the design objectives, subject to practical restrictions on current density and slot fill factor. The design objectives have been accurately evaluated through transient finite element analysis (FEA) and a computationally efficient SRM drive model (developed in MATLAB/Simulink) with consideration of the excitation control parameters. Kriging models have been constructed to reduce the computation cost of FEA during the optimization process. Then, a nondominated sorting genetic algorithm II (NSGA II) based multiobjective optimization coupled with the constructed Kriging models is conducted to generate a Pareto front. An optimal design that offers the best balance between the design objectives is selected from the Pareto-optimal set, and the dimensions of corresponding design variables are used to build a prototype. Finally, the static and dynamic performance of the SRM prototype are experimentally evaluated and validated with the FEA simulations. © 2024 IEEE.Item Downscaled XCO2 Estimation Using Data Fusion and AI-Based Spatio-Temporal Models(Institute of Electrical and Electronics Engineers Inc., 2024) Pais, S.M.; Bhattacharjee, S.; Anand Kumar, M.; Chen, J.One of the well-known greenhouse gases (GHGs) produced by anthropogenic human activity is carbon dioxide (CO2). Understanding the carbon cycle and how negatively it affects the ecosystem requires analysis of the rise in CO2 concentration. This work aims to map CO2 concentration for the entire surface, making it useful for regional carbon cycle analysis. Here, column-averaged CO2 dry mole fraction, called XCO2, measured by the orbiting carbon observatory-2 (OCO-2) satellite, is used. Because of spectral interference by the clouds and aerosols, there are many missing footprints in the Level-2 swath of OCO-2, making it disruptive to understand any assessment related to the carbon cycle. The objective of this work is to predict 1 km2 XCO2 using data resampling and machine learning models. This work achieves a minimum mean absolute error (MAE) and root mean square error (RMSE) of 0.3990 and 0.8090 ppm, using the monthly models. © 2004-2012 IEEE.