Krishna Mohan Buddhiraju

Indian Institute of Technology Bombay | IIT Bombay · Centre of Studies in Resources Engineering (CSRE)

Synthetic aperture radar (SAR) is an active sensor. All weather, day and night observation capability of SAR made it special as compared to the passive sensors. This study proposed a methodology for marine vessel detection based on degree of polarization (DOP). It is a function of surface roughness and incident angle. The large dynamic range, DOP s...

Multiple and heterogenous Earth observation (EO) platforms are broadly used for a wide array of applications, and the integration of these diverse modalities facilitates better extraction of information than using them individually. The detection capability of the multispectral unmanned aerial vehicle (UAV) and satellite imagery can be significantl...

This paper presents a multiresolution textural approach to change detection in multitemporal polarimetric synthetic aperture radar images. Several change detection methods utilizing wavelet based features from remotely sensed images have been developed previously. The aim of this paper is to investigate and propose a texture based change detection...

As the global urban population grows due to the influx of migrants from rural areas, many cities in developing countries face the emergence and proliferation of unplanned and informal settlements. However, even though the rise of unplanned development influences planning and management of residential land-use, reliable and detailed information abou...

Single-image super-resolution (SISR) techniques attempt to reconstruct the finer resolution version of a given image from its coarser version. In the SISR of hyperspectral data sets, the simultaneous consideration of spectral bands is crucial for ensuring the spectral fidelity. However, the high spectral resolution of these data sets affects the pe...

The spectral super-resolution techniques attempt to re-project spectrally coarse images to a set of finer wavelength bands. However, complexity of the mapping between coarser and finer scale spectra, large variability of spectral signatures, and the difficulty in simultaneously modeling spatial and spectral contexts make the problem highly ill-pose...

Decision tree-based Rotation Forest could generate satisfactory but lower classification accuracy for a given training sample set and image data, owing to the inherent disadvantages in decision trees, namely myopic, replication and fragmentation problem. To improve performance of Rotation Forest technique, we propose to utilize two-hidden-layered-f...

In this paper, a Capsulenet-based framework is proposed for extracting spectral and spatial features for improving hyperspectral image classification. Unlike conventional strategies, the proposed framework simultaneously optimizes both feature extraction and classification. The spectral features/patterns derived at different levels of hierarchies a...

Achieving high classification accuracy is vital in reliable information extraction from images. Single classifiers and existing ensemble methods suffer from data dimensionality, insufficient ground truth information and lack in defining optimal feature selection. This paper presents a novel idea for constructing component classifiers that boost ran...

Multiresolution analysis (MRA) methods have been successfully used in texture analysis. Texture analysis is widely discussed in literature, but most of the methods which do not employ multiresolution strategy cannot exploit the fact that texture occurs at various spatial scales. This paper proposes a methodology to identify different classes in sat...

This contribution proposes a multiresolution analysis (MRA)-based composite technique for image restoration by noise filtering in satellite images. Multiresolution techniques provide a coarse–fine and scale-invariant decomposition of images for analysis and interpretation. MRA methods effectively handle the noise because of their multiscale feature...

Many cities in developing countries are facing rapid growth of dynamic slum areas but often lack detailed information and analysis on these informal settlements. Multiresolution analysis (MRA) has been successfully used in texture analysis. Texture analysis is widely discussed in literature, but most of the methods which do not employ multiresoluti...

With continuous increase in the utilization of satellite images in various engineering and science fields, it is imperative to equip students with additional educational aid in subject of satellite image processing and analysis. In this paper a web-based virtual laboratory, which is accessible via internet to anyone around the world with no cost or...

For improving security of any country, satellite images are playing vital role. Vessels detection using SAR imagery is one of the primary requirements for maritime surveillance. In this paper, the algorithm used for vessels detection has four parts. The first part includes pre-processing to reduce speckle noise, second part helps in the reduction o...

The monitoring of the water cycle at the Earth surface which tightly interacts with the climate change processes as well as a number of practical applications (agriculture, soil and water quality assessment, irrigation and water resource management, etc.) requires surface temperature measurements at local scale. Such is the goal of the Indian-Frenc...

Hyperspectral satellite images contain a lot of information in terms of spectral behaviour of objects and this information can be extracted by several mechanisms including image classification. Traditional spectral information-based methods of hyperspectral image classification are generally followed by spatial information-driven post-processing te...

Sub-pixel mapping techniques predict the spatial distribution of endmember abundances which are estimated through spectral unmixing. The sub-pixel mapping and spectral unmixing approaches are mostly unsupervised, and both are generally treated as independent optimization problems. This study explores convolutional encoder–decoder as well as recurre...

Digital representation of terrain surface is an important research area. A number of techniques have been proposed to represent the terrain surface in a realistic manner. They have been broadly categorized as 2D or 3D terrain models. Each of these models has its own merits and demerits. An ideal model will capture the minute details of the terrain,...

This letter investigates the use of coarse-image features for predicting class labels at a given finer spatial scale. In this regard, two unsupervised subpixel mapping approaches, a semivariogram method, and a pixel-affinity based method are proposed. Furthermore, segmentation-based spectral unmixing is explored so as to address the spectral variab...

The rapid development of technology has made archival and transmission of multimedia information such as music, image, and video very convenient. However, it has also introduced new challenges related to privacy and security of data. Therefore, there is a compelling need for ensuring of authenticity and protection of ownership. For providing securi...

The role of synthetic aperture radar (SAR)-image-based flood area mapping is proved beyond the doubts. It is also well known that different wavelength, polarization SAR reacts in varying ways over the same land-use/land-cover region. In line to this, this article mainly brings out the significance of comparing and analysing different wavelength, po...

Different graph theoretic approaches are prevalent in the field of image analysis. Graphs provide anatural representation of image pixels exploring their pairwise interactions among themselves. Graphtheoretic approaches have been used for problem like image segmentation, object representation, matchingfor different kinds of data. In this chapter, w...

We propose a novel coclustering-based domain-adaptation algorithm for simultaneously generating classification maps for a set of remote sensing (RS) multitemporal images in this letter. Unsupervised domain-adaptation techniques consider two different but related domains: a source domain with ample number of labeled samples and a target domain with...

In this paper, we propose an adaptive filtering technique for Synthetic Aperture Radar (SAR) images. A new windowing technique is introduced where the total window is divided into five equal sized overlapping sub-windows. The pixel to be filtered is a part of each of these sub-windows. A weighted mean of all sub-windows is computed for the pixel un...

In this research paper, a new framework is proposed to increase the total number of correct matches for stereo correspondence using tri-stereo images. The research work investigates some of the less explored properties of Disparity Space Image (DSI), and considers the local maxima in addition to the global maximum of the cost function and propose a...

With the development of remote sensing technologies, it has become possible to obtain an overview of landscape elements which helps in studying the changes on earth’s surface due to climate, geological, geomorphological and human activities. Remote sensing measures the electromagnetic radiations from the earth’s surface and match the spectral simil...

This paper presents a self-learning tool, which contains a number of virtual experiments for processing and analysis of Optical/Infrared and Synthetic Aperture Radar (SAR) images. The tool is named Virtual Satellite Image Processing and Analysis Lab (v-SIPLAB) Experiments that are included in Learning Tool are related to: Optical/Infrared - Image a...

This article presents a new technique for denoising of remotely sensed images based on multi-resolution analysis (MRA). Multi-resolution techniques provide a coarse-to-fine and scale-invariant decomposition of images for image processing and analysis. The multi-resolution image analysis methods have the ability to analyse the image in an adaptive m...

Copyright protection of multispectral images and its integrity become one of the key problems in spatial information service due to rapid development of communication network. This paper depicts a crypto-watermarking scheme by combining watermarking and encryption to protect copyright of multispectral images and to provide security to the watermark...

Classification performance of PolSAR data, when used without speckle reduction is insufficient for most applications. Thus, speckle filtering becomes an essential preprocessing step. In this study we evaluate the effectiveness of different popular speckle filters and analyse their effects on the classification accuracy. We have used L-band and C-ba...

This research article addresses the problem of land-cover classification from the multi-spectral remotely sensed images using a novel self-training based semi-supervised learning (SSL) technique. The proposed system, instead of using a single classifier, builds an ensemble of classifiers with the hope that the ensemble system will have a lesser gen...

With the rapid growth of the Internet, the copyright protection problem occurs frequently, and unauthorized copying and distributing of geospatial data threaten the investments of data producers. Digital watermarking is a possible solution to solve this issue. However, watermarking causes modifications in the original data resulting in distortion a...

This paper addresses the problem of land-cover classification of remotely sensed image pairs in the context of domain adaptation. The primary assumption of the proposed method is that the training data are available only for one of the images (source domain), whereas for the other image (target domain), no labeled data are available. No assumption...

The aim of this paper is to study the effect of speckle on wide frequency components in synthetic aperture radar (SAR) images. In this study, the presence of speckle in SAR images is analysed using frequency domain techniques. SAR images consists of many features such as lines, edges, point targets, structural boundaries, homogeneous areas. In freq...

This letter addresses the problem of unsupervised land-cover classification of remotely sensed multispectral satellite images from the perspective of cluster ensembles and self-learning. The cluster ensembles combine multiple data partitions generated by different clustering algorithms into a single robust solution. A cluster-ensemble-based method...

Neural networks are growing in popularity today as a tool for classification of remotely sensed images. One of the major stumbling blocks for neural networks to be accepted for operational use in remote sensing has been the long computational times involved. This is particularly relevant in the case of the well-known back-propagation (BP) algorithm...

Hyperspectral data pose challenges to image interpretation, because of the need for calibration, redundancy in information, and high data volume due to large dimensionality of the feature space. In this article, a general framework is presented for working with hyperspectral imagery, including removal of atmospheric effects, imaging spectroscopy, d...

Intensity Driven Adaptive Neighborhood (IDAN) filter, is an adaptive filtering technique where a neighbourhood is formed using region growing method around each pixel. Pixels belonging to an adaptive intensity driven region are more likely to respect the local stationarity hypothesis than pixels belonging to a squared fixed size window. The advanta...

We address the problem of automatic land-cover map updating of multi-temporal and multi-spectral remotely sensed images in this paper. Given a pair of images acquired on the same geographical area at two distinct time instants, it is assumed here that the training data are available for one of the acquisitions, which is known as the source domain i...

The present study was undertaken with the objective to check effectiveness of spectral similarity measures to develop precise crop spectra from the collected hyperspectral field spectra. In Multispectral and Hyperspectral remote sensing, classification of pixels is obtained by statistical comparison (by means of spectral similarity) of known field...

In remote sensing community, Principal Component Analysis (PCA) is widely utilized for dimensionality reduction in order to deal with high spectral-dimension data. However, dimensionality reduction through PCA results in loss of some spectral information. Analysis of an Earth-scene, based on first few principal component bands/channels, introduces...

This article presents techniques for noise filtering of remotely sensed images based on Multi-resolution Analysis (MRA). Multiresolution techniques provide a coarse-to-fine and scale-invariant decomposition of images for image interpretation. The multiresolution image analysis methods have the ability to analyze the image in an adaptive manner, cap...

This paper presents a perspective based model for creating diverse ensemble members in a multi-classifier system. With this technique different input feature sets are constructed using standard digital image processing and analyzing techniques viz. Haralick texture features, Gabor texture features, normalized difference vegetation index, standard d...

A probabilistic neural-network-based feature-matching algorithm for a stereo image pair is presented in this paper, which will be useful as a constraint initializing method for further dense matching technique. In this approach, scale-invariant feature transform (SIFT) features are used to detect interest points in a stereo image pair. The descript...

A novel ant colony optimization based domain adaptation for satellite images has been proposed in the paper. Given a source domain and a target domain image, it has been considered here that we have labeled training data for the source domain image. The goal is to classify the target domain image for which no prior information is available. The pro...

In flooded elevated regions, mapping and differentiating the shadow-layover pixels of input SAR image from the overall inundated region is a major challenge which is not addressed in earlier studies. This paper will brings out the details about a DEM based SAR image analyzing techniques that can help in identifying the pixels of shadow/layover regi...

This correspondence proposes a generic framework for land-cover classification using support vector machine (SVM) classifier for polarimetric synthetic aperture radar (SAR) images considering the optimum Touzi decomposition parameters. Some new concerns have been raised recently with the Cloude–Pottier decomposition. Cloude’s $alphab$ scattering ty...

An unsupervised object based segmentation, combining a modified mean-shift (MS) and a novel minimum spanning tree (MST) based clustering approach of remotely sensed satellite images has been proposed in this correspondence. The image is first pre-processed by a modified version of the standard MS based segmentation which preserves the desirable dis...

Deserts are one of the major landforms on the Earth. While deserts occupy about one-fifth of Earth's land surface, they have been studied to a much lesser extent. All over the world, desert landforms are expanding ever rapidly and more and more human settlements are finding place in desert regions for habitation. Thus, quantifying and monitoring du...

The data from remote sensing satellites provide opportunities to acquire information about land at varying resolutions and has been widely used for change detection studies. A large number of change detection methodologies and techniques utilizing remotely sensed data have been developed, and newer techniques are still emerging. In this paper, a no...

Fast development of Internet makes the process of data sharing very easy. However, this leads to unlimited copying and duplication of data. Digital watermarking has been used from many years to protect images from piracy. Geospatial vector data acquisition and generation is very complex and expensive task and it needs to be protected from unauthori...

This paper proposes a novel unsupervised graph based clustering method for the purpose of hybrid segmentation of multi-spectral satellite images. In hybrid image segmentation framework, the source image is initially (over)segmented while preserving the fine image details. A region merging strategy has to be adopted next for further refinement. Here...

Speckle has a nature of multiplicative noise which is diffi-cult to deal as compared to additive noise. It complicates the problem of interpretation of the image segmentation and classification. The primary goal of existing speckle filtering algorithms, which are subjective in nature is to reduce the speckle without loss of information. Various tec...

The very high effectiveness of hyperspectral sensors in vegetation discrimination increases the applications of crop classification using hyperspectral data. However, for this capability to be exploitable, it is essential that a well-populated spectral library exists and is accessible in a user-friendly way by the user of this technology. To addres...

The problem of 2-D building extraction from high resolution satellite images has been addressed in this correspondence. Research in the domain of building detection and/or extraction has been going on for a long time, yet automatic building extraction has remained a difficult problem due to variations in the spectral and spatial image properties, p...

Complete polarimetric information allows for better target characterization. However, the polarimetric SAR system suffers from an increase in complexity. Dual-pol imaging modes operate at lower pulse repetition frequencies and hence have a higher swath coverage as compared to quad-pol imaging modes. Hybrid polarimetric techniques have been develope...

The objective of the paper is to analyze, assess and compare the flood area extent of multi polarization SAR images against the landuse/landcover units of disaster affected region. A comparative flood area assessment of L- and C-band SAR images of the same disaster region has been carried out. The output results which represent the deep, shallow an...

Polarimetric SAR (PolSAR) has emerged as a powerful remote sensing technology and used for wide range of applications. Speckle suppression in PolSAR images is an important step for the extraction of meaningful information which is subjective in nature. In this paper, we propose Cornered Difference Weighted Mean (CDWM) SAR speckle filter. This filte...

The problem of road segment extraction from high resolution satellite or aerial images has been considered in this paper. Efficient extraction of road segments is a difficult task due to the problems regarding image acquisition, local road width and orientation etc. A novel method of road region extraction using local spectral and geometrical prope...

Hyperion- a hyperspectral sensor is carried on NASA's EO1 satellite. This study was carried out for Lonar area of Jalna district, Maharashtra using data of January 2008. Hyperion data contains 242 spectral bands ranging from 356 to 2577 nm out of which 196 calibrated bands (bands: 8-57 and 79-224) are used for further processing. Level 1 product (....

In recent years, remote sensing has become an increasing data source to support urban planning and management due to availability of very high resolution (VHR) images having resolution of less than 0.5 m. Such images allow extracting of detailed information of various targets of urban areas with the help of object-based image analysis (OBIA) in con...

Many countries are producing high quality remotely sensed images from spaceborne sensors mounted on Earth orbiting satellites. One of the handicaps in the spread of this technology among endusers is lack of trained manpower and sometimes lack of resources for teaching and imparting training in this area. In this paper, a system developed to address...

Desert regions are typically characterized by the texture of sand that particular place and the orientation of dunes. We have attempted to visualize and quantify the sand dunes by local surface orientations calculated by Radon transform of sliding window region that covers entire image. This kind of representation can be used as a pre-processing st...

Segmentation of satellite images using a novel adaptive non parametric mean-shift clustering algorithm is proposed in this paper. Image segmentation refers to the process of splitting up an image into its constituent objects. It is also an important step in bridging the semantic gap between low level image interpretation and high level visual analy...

In this paper a virtual laboratory for the Satellite Image Processing and Analysis (v-SIPAL) being developed at the Indian Institute of Technology Bombay is described. v-SIPAL comprises a set of experiments that are normally carried out by students learning digital processing and analysis of satellite images using commercial software. Currently, th...

In this paper we have proposed a symmetric, positive semi definite kernel function for support vector machine classifier. Pixel classification is a form of supervised image segmentation where the actual object classes present in the image are known a priori. In case of satellite image, this prior information plays a huge role to estimate the actual...

Image segmentation is a process of sub-dividing a given image into its constituent objects. Segmentation algorithms are inherently unsupervised as there is no available a priori knowledge regarding the approximate number of objects actually present in the image. In this respect, unsupervised clustering techniques are of particular importance. This...

Object-based image analysis is quickly gaining acceptance among remote sensing community, and object-based image classification methods are increasingly being used for clas- sification of land use/cover units from high-resolution satellite images with results closer to human interpretation compared to per-pixel classifiers. The problem of nonlinear...

Change Detection using multi-temporal satellite images of same area is an established as well as actively pursued research problem. Most of the change detection techniques use algebraic or transform methods to do a pixel by pixel comparison of change detection. These techniques heavily depend upon the correct choice of threshold value to segregate...

A number of algorithms have been reported to process and remove geometric distortions in satellite images. Ortho-correction, geometric error correction, radiometric error removal, etc are a few important examples. These algorithm require supplementary meta-information of the satellite images such as ground control points and correspondence, sensor...

Image segmentation is a decisive and fundamental step for remote sensing information retrieval and classification. High-resolution satellite image classification using standard per-pixel approaches is difficult because of the high volume of data, as well as high spatial variability within the objects. One approach to deal with this problem is to re...

Object-based image analysis is quickly gaining acceptance among remote sensing community, and object-based image classification methods are increasingly being used for classification of land use/cover units from high-resolution satellite images with results closer to human interpretation compared to per-pixel classifiers. The problem of nonlinear s...

Image classification is an important task for many aspects of global change studies and environmental applications. In this study we compare two different classification approaches, which are Object based and Pixel based. Object Based Classification (OBC) methods are increasingly used for classification of land cover/land use from high resolution i...

A number of new geological structures have been revealed in the Great Nicobar Island, Indian Ocean, from the analysis of airborne synthetic aperture radar (SAR) data. The advantages of SAR images for mapping geological structures over other images for the Great Nicobar Island, the southern most island of Andaman-Nicobar arc, have been highlighted....

Image classification is an important task for many aspects of global change studies and environmental applications. This paper emphasizes on the analysis and usage of different advanced image classification techniques like Cloud Basis Functions (CBFs) Neural Networks, Artificial Neural Networks (ANN) and Support Vector Machines (SVM) for object bas...