Rahul Mourya - Academia.edu (original) (raw)

Papers by Rahul Mourya

Cornell University - arXiv, May 17, 2017

Image deblurring is an economic way to reduce certain degradations (blur and noise) in acquired i... more Image deblurring is an economic way to reduce certain degradations (blur and noise) in acquired images. Thus, it has become essential tool in high resolution imaging in many applications, e.g., astronomy, microscopy or computational photography. In applications such as astronomy and satellite imaging, the size of acquired images can be extremely large (up to gigapixels) covering wide field-of-view suffering from shiftvariant blur. Most of the existing image deblurring techniques are designed and implemented to work efficiently on centralized computing system having multiple processors and a shared memory. Thus, the largest image that can be handle is limited by the size of the physical memory available on the system. In this paper, we propose a distributed nonblind image deblurring algorithm in which several connected processing nodes (with reasonable computational resources) process simultaneously different portions of a large image while maintaining certain coherency among them to finally obtain a single crisp image. Unlike the existing centralized techniques, image deblurring in distributed fashion raises several issues. To tackle these issues, we consider certain approximations that trade-offs between the quality of deblurred image and the computational resources required to achieve it. The experimental results show that our algorithm produces the similar quality of images as the existing centralized techniques while allowing distribution, and thus being cost effective for extremely large images.

Societies

The COVID-19 pandemic has completely transformed the education sector. Almost all universities an... more The COVID-19 pandemic has completely transformed the education sector. Almost all universities and colleges have had to convert their normal classroom teaching to online/remote or hybrid teaching during the COVID-19 pandemic. Online teaching has been found quite useful during an emergency situation. This switch to online teaching forced educators to come out of their comfort zone and learn new tools and techniques for online teaching. It is important, therefore, to analyse the problems faced by educators in online teaching because this has become the new normal. There are several studies identifying the issues faced by educators in online teaching but less is known about the issues faced by Computer Science (CS) educators. In this paper, we perform an exploratory study of the problems, questions, and associated responses from CS educators posted on popular Q&A forums, e.g., CS educators StackExchange. We identified six main challenges related to online teaching: platform recommendat...

2017 25th European Signal Processing Conference (EUSIPCO), 2017

Image deblurring techniques are effective tools to obtain high quality image from acquired image ... more Image deblurring techniques are effective tools to obtain high quality image from acquired image degraded by blur and noise. In applications such as astronomy and satellite imaging, size of acquired images can be extremely large (up to gigapixels) covering a wide field-of-view suffering from shiftvariant blur. Most of the existing deblurring techniques are designed to be cost effective on a centralized computing system having a shared memory and possibly multicore processor. The largest image they can handle is then conditioned by the memory capacity of the system. In this paper, we propose a distributed shift-variant image deblurring algorithm in which several connected processing units (each with reasonable computational resources) can deblur simultaneously different portions of a large image while maintaining a certain coherency among them to finally obtain a single crisp image. The proposed algorithm is based on a distributed Douglas-Rachford splitting algorithm with a specific structure of the penalty parameters used in the proximity operator. Numerical experiments show that the proposed algorithm produces images of similar quality as the existing centralized techniques while being distributed and being cost effective for extremely large images.

Publication in the conference proceedings of EUSIPCO, Marrakech, Morocco, 2013

OCEANS 2018 MTS/IEEE Charleston, 2018

This paper presents a framework for spatiotemporal monitoring of ocean environment using large-sc... more This paper presents a framework for spatiotemporal monitoring of ocean environment using large-scale underwater acoustic sensor networks (UWASNs). Our goal is to exploit low-cost, battery-operated technology for acoustic communication to enable long-term, mass deployment of UWASNs for a wide range of monitoring applications in need of high spatiotemporal sampling rate and near real-time data delivery. Inspired by theory of compressive sensing (CS), the framework supports opportunistic random deployment of sensor nodes and relies on random channel access to harvest their data and construct spatiotemporal fields of the underlying sensed phenomena. In order to save bandwidth and energy, we consider a positioning scheme in which the sensor nodes remain silent and just listen for beacon signals from few reference nodes to localize themselves. After this initial localization phase, the sensing process begins. At regular intervals (frames), a set of random sensors sample their transducers and independently try to transmit their measurements to a fusion center (FC) for CS-based field reconstruction. Due to this random access of the acoustic channel, some of the packets may collide at the FC, wasting both energy and bandwidth. For slowly varying fields, consecutive frames have high correlations. We exploit this information during the field reconstruction, and show by simulation results that the number of sensors participating in each frame can be reduced drastically. This decreases the number of collisions at the FC, thus saving energy and prolonging the lifetime of the network.

2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2017

This paper introduces a constant step size adaptive algorithm for distributed optimization on a g... more This paper introduces a constant step size adaptive algorithm for distributed optimization on a graph. The algorithm is of diffusion-adaptation type and is asynchronous: at every iteration, some randomly selected nodes compute some local variable by means of a proximity operator involving a locally observed random variable, and share these variable with neighbors. The algorithm is built upon a stochastic version of the Douglas-Rachford algorithm. A practical application to target localization using measurements from multistatic continuous active sonar systems is investigated at length.

Proceedings of the Thirteenth ACM International Conference on Underwater Networks & Systems, 2018

In this paper, we present the results of deploying the first test prototype of the USMART low cos... more In this paper, we present the results of deploying the first test prototype of the USMART low cost underwater sensor network in sea trials in Fort William, UK, on 29/06/2018 and 03/07/2018. We demonstrate the first ever hardware implementation of the TDA-MAC protocol for data gathering in underwater acoustic sensor networks (UASNs). The results show a successful application of TDA-MAC to remote environmental monitoring, integrating a range of different sensor nodes developed by the Universities of Heriot-Watt, York, Newcastle and Edinburgh. We focus on the practical challenges and their mitigation strategies related to TDA-MAC to increase its robustness in real-world deployments, compared with theoretical and simulation-based studies. The lessons learned from the sea trials reported in this paper prompted several crucial modifications to TDA-MAC which, in turn, form a solid foundation for further work on the development of TDA-MAC based UASNs.

2019 Twelfth International Conference on Contemporary Computing (IC3), 2019

Online recruitment fraud (ORF) is a new challenge in the cyber security area. In ORF, scammers gi... more Online recruitment fraud (ORF) is a new challenge in the cyber security area. In ORF, scammers give job seekers lucrative job offers and in-return steal their money and personal information. In India, scammers have stolen millions of moneys from innocent job seekers. Hence, it is important to find solution to this problem. In this paper, we propose, ORFDetector, an ensemble learning based model for ORF detection. We test the proposed model on publicly available dataset of 17,860 annotated jobs. The proposed model is found to be effective and give average f1-score and accuracy of 94% and 95.4, respectively. Additionally, it increases the specificity by 8% as compared to the baseline classifiers.

Procedia Computer Science, 2020

Nowadays social Networking and micro-blogging sites like Twitter are very popular and millions of... more Nowadays social Networking and micro-blogging sites like Twitter are very popular and millions of users are registered on these websites. The users present on these website use these websites as a platform to express their thoughts and opinions. Our analysis of content posted on Twitter shows that users often post crime related information on Twitter. Among these crime related tweets some tweets are the crime messages that need police attention. Detection of such tweets can be beneficial in utilizing pattroling resources. The analysis of the data present on these websites can have an enormous impact. In this paper,the work is done on analyzing Twitter data to identify crime tweet that need police attention. Text mining based approach is used for classification of 369 tweets into crime and not-crime class. Classifiers such as Naive Bayesian, Random Forest, J48 and ZeroR are used. Among all of these four classifiers, Random forest classifier give the best accuracy of 98.1%.

Adaptive Optics Systems V, 2016

Most current imaging instruments have a spatially variant point spread function (PSF). An optimal... more Most current imaging instruments have a spatially variant point spread function (PSF). An optimal exploitation of these instruments requires to account for this non-stationarity. We review existing models of spatially variant PSF with an emphasis on those which are not only accurate but also fast because getting rid of non-stationary blur can only be done by iterative methods.

2015 IEEE International Conference on Image Processing (ICIP), 2015

Many image processing tasks are formulated as a large scale optimization problem:

2015 23rd European Signal Processing Conference (EUSIPCO), 2015

With the progress of adaptive optics systems, ground-based telescopes acquire images with improve... more With the progress of adaptive optics systems, ground-based telescopes acquire images with improved resolutions. However, compensation for atmospheric turbulence is still partial, which leaves good scope for digital restoration techniques to recover fine details in the images. A blind image deblurring algorithm for a single long-exposure image is proposed, which is an instance of maximum-a-posteriori estimation posed as constrained non-convex optimization problem. A view of sky contains mainly two types of sources: pointlike and smooth extended sources. The algorithm takes into account this fact explicitly by imposing different priors on these components, and recovers two separate maps for them. Moreover, an appropriate prior on the blur kernel is also considered. The resulting optimization problem is solved by alternating minimization. The initial experimental results on synthetically corrupted images are promising, the algorithm is able to restore the fine details in the image, and recover the point spread function.

International Journal of Computer Vision, 2015

Image deblurring is essential in high resolution imaging, e.g., astronomy, microscopy or computat... more Image deblurring is essential in high resolution imaging, e.g., astronomy, microscopy or computational photography. Shift-invariant blur is fully characterized by a single point-spread-function (PSF). Blurring is then modeled by a convolution, leading to efficient algorithms for blur simulation and removal that rely on fast Fourier transforms. However, in many different contexts, blur cannot be considered constant throughout the field-of-view, and thus necessitates to model variations of the PSF with the location. These models must achieve a trade-off between the accuracy that can be reached with their flexibility, and their computational efficiency. Several fast approximations of blur have been proposed in the literature. We give a unified presentation of these methods in the light of matrix decompositions of the blurring operator. We establish the connection between different computational tricks that can be found in the literature and the physical sense of corresponding approximations in

Lecture Notes in Computer Science, 2015

Memory color plays an important role in the perceptual process. The aim of this research is to co... more Memory color plays an important role in the perceptual process. The aim of this research is to collect, analyze and represent memory color data for certain natural scenes objects: sky, grass and tree leaves. To emphasize reliable data collection, we consider several sources: (a) psychophysical experiment; (b) multispectral image; (c) standard image database and (d) random image collection. Moreover, we consider different daylight conditions and locations. We perform an in-depth analysis of the collected information in the CIE-xy chromaticity space and present the natural scene objects as a memory color ellipse or polygon. Finally, we demonstrate a potential use of the collected information for natural image segmentation and enhancement.

Sensors, 2021

Underwater acoustic sensor networks (UWASNs) can revolutionize the subsea domain by enabling low-... more Underwater acoustic sensor networks (UWASNs) can revolutionize the subsea domain by enabling low-cost monitoring of subsea assets and the marine environment. Accurate localization of the UWASNs is essential for these applications. In general, range-based localization techniques are preferred for their high accuracy in estimated locations. However, they can be severely affected by variable sound speed, multipath spreading, and other effects of the acoustic channel. In addition, an inefficient localization scheme can consume a significant amount of energy, reducing the effective life of the battery-powered sensor nodes. In this paper, we propose robust, efficient, and practically implementable localization schemes for static UWASNs. The proposed schemes are based on the Time-Difference-of-Arrival (TDoA) measurements and the nodes are localized passively, i.e., by just listening to beacon signals from multiple anchors, thus saving both the channel bandwidth and energy. The robustness i...