Browsing by Author "Rohil, Mukesh Kumar"

Now showing 1 - 20 of 59

Advanced 3D Modeling for Augmented Reality Visualizations in Engineering Education: Issues, Challenges, and Future
(IEEE, 2023) Rohil, Mukesh Kumar
Augmented Reality (AR), the superimposing of a virtual object on the view of the real environment, assists in visualizing engineering concepts in real-time. Computer graphics-based 3D modeling techniques evolved over the past five decades are being used in AR systems. Representations of 3D objects using polygons, surface patches, points (or voxels), and lines are insufficient to visualize the intricacies of objects having curved surfaces. To enable high-level control and accuracies pertaining to 3D representational details of 3D models, advanced 3D modeling approaches are needed. In this paper, we discuss (along with their suitability, examples, and advantages) several advanced 3D modeling techniques for AR visualizations. We emphasize that the use of AR visualizations for teaching and learning can help learners with a better understanding of concepts in engineering education. Additionally, we discuss some issues, challenges, and the future scope of use of AR in Engineering Education.
Advanced Intelligent Tutoring Systems: Featuring the Learning Management Systems of the Future
(Springer, 2024) Rohil, Mukesh Kumar
An Intelligent Tutoring System (ITS) is employed with two goals in mind: (1) to deliver one-on-one smart teaching guidance that is superior to standard computer-assisted education and a skilled human instructor, and (2) to establish appropriate guidelines for designing and evaluating models of the academic process. The “intelligence” of an ITS is derived from the use of artificial intelligence techniques in four interacting components, namely (1) the knowledge base (to represent and manipulate domain knowledge), (2) the student's model (to represent student's current academic state), (3) Pedagogical Model (to incorporate and use the teaching strategies), and (4) User Interface Model (to make the system usable, and to establish effective communication between the user and the system). On the other hand, a Learning Management System (LMS), an online (may be web-based)-integrated software, is used for creating, delivering, tracking, and reporting educational courses or training resources and also helps in assessing their outcomes. In this paper, we discuss various existing Intelligent Tutoring Systems and systematically present the comparison of an ITS with a LMS. We emphasise that the ITS usage should be encouraged because of number of advantages, including improving both the learning curve and the learning experience, associated with an ITS over an LMS.
An architecture to intertwine augmented reality and intelligent tutoring systems: towards realizing technology-enabled enhanced learning
(Springer, 2024-08) Rohil, Mukesh Kumar
Intelligent Tutoring Systems (ITS) and Augmented Reality (AR) have become greatly popular in current scenario, especially for helping students in mastering difficult subjects through a variety of different methods with the implementation of smart algorithms. There are many papers in the current literature that discuss the ITS architecture and the AR architecture independently; a few papers have even proposed designs for combining these systems, but the need for this article arises in order to suggest improvements that could theoretically increase the performance and overall robustness of the system for learning basic, complex, domain-specific and AR related concepts. This article discusses the existing ITS and AR systems and their flaws, followed by some potential benefits that can be achieved by combining ITS and AR effectively. We propose a novel architecture for improving the combined AR and ITS system scalable for supporting interaction for the diverse users and domain. The proposed system makes an effective use of three tier architecture, load sharing algorithms, data management techniques, multiple servers, marker-less AR, and modeling 3D object models on the fly, in order to make the system more effective, secure, reliant, and seamless for the users. For realizing 3D object modeling on the fly, the article presents an improved method by combining Level of Detail and Rasterization techniques in order to render in steps in accordance with the demand (i.e. processing up to adequate and sufficient level of details), which will help us use the architecture for small scale to large scale systems. Although 3D object modeling on the fly needs storage up to 33% more than the conventional geometrical structure of the mesh, the speed-up achieved can be as high as six times for coarse mesh and up to 1.46 times for fine mesh. At the core of the proposed system, is to make the ITS extendible to multiple domains of learning and education, and to reduce the response time and latency.
Big Data Security Challenges and Preventive Solutions
(Springer, 2019-10) Rohil, Mukesh Kumar
Big data has opened the possibility of making great advancements in many scientific disciplines and has become a very interesting topic in academic world and in industry. It has also given contributions to innovation, improvements in productivity and competitiveness. However, at present, there are various security risks involved in the process of collection, storage and use. The leakage of privacy caused by big data poses serious problems for the users; also the incorrect or false big data may lead to wrong or invalid analysis of results. The presented work analyzes the technical challenges of implementing big data security and privacy protection, and describes some key solutions to address the issues related with big data security and privacy.
Bit-Stuffing in 802.11 Beacon Frame: Embedding Non-Standard Custom Information
(International Journal of Computer Applications, 2013-02) Gupta, Vishal; Rohil, Mukesh Kumar
In an infrastructure Basic Service Set (BSS) beacon frames are transmitted periodically by the Access Point (AP) and announce the presence of a wireless network. It mainly consists of network specific information and thus one of its main purposes is the "advertisement" of this information. Based on this information mobile devices can take many decisions, for example, whether to attempt association with the network or not. To facilitate the communication between devices developed by different vendors, IEEE 802.11 standardizes the arrangement of this information in beacon frames. Often it is required to embed non-standard vendor/network specific additional information in the beacon frame. In this paper we show that without disturbing the arrangement of information as per the standard, how the IEEE 802.11-2012 compatible beacon frames can be overloaded with additional non-standard information. Moreover, the 802.11 standard limits the maximum size of the beacon frame. In this perspective we also show that how to send large amount of information in multiple successive beacon frames using the already implemented concept of fragmentation and sequence numbers. The proposed technique is flexible in terms of fields used for embedding the information and maximizes the number of additional non-standard information octets per beacon. The results of its implementation in ns-3 simulator are also shown.
CLIM: Co-occurrence with Laplacian Intensity Modulation and Enhanced Color Space Transform for Infrared-Visible Image Fusion
(Elsevier, 2023-12) Rohil, Mukesh Kumar
Thermal infrared and multispectral visible remote sensing image fusion combines thermal image information with corresponding visible scene content to generate a better representative fused image. Thermal images can distinguish targets using difference in thermal radiation measurements, whereas visible images contain better texture detail in multispectral wavelength bands. The article presents a novel methodology named CLIM to sharpen coarser spatial resolution multispectral remote sensing images using relatively higher spatial resolution broadband thermal infrared image. The boundary-preserving information is extracted from high resolution thermal infrared image using co-occurrence image filter, and is combined with Laplacian of Gaussian based sharpened image to extract salient features for injection. In addition, visible image is transformed to IHS color space, and intensity component is enhanced using CLAHE and inverse transformation to generate enhanced visible image for fusion. The procedure developed is evaluated with Indian Nano Satellite (INS) broadband thermal infrared images available at a spatial resolution of 175 m with same day acquisition MODIS multispectral visible images available at a relatively coarser spatial resolution of 500 m. The nearest acquisition of Landsat-8 thermal infrared images with MODIS multispectral visible images is also used for infrared–visible multi-modal image fusion. The CLIM fused image confirms that distinct features such as dam, ship docking zones and refinery regions, are better demarked and semantically more meaningful in comparison with individual thermal infrared and multispectral visible image. The proposed CLIM approach is compared with, and found to perform better than state-of-the-art image fusion techniques, both visually and quantitatively.
CYGNSS-derived soil moisture: Status, challenges and future
(Elsevier, 2022-07) Rohil, Mukesh Kumar
In the last few years, Global Navigation Satellite System-Reflectometry (GNSS-R) technology has provided an exciting solution to retrieve fine-scale spatiotemporal soil moisture predictions. The most promising data source for this task has been Cyclone Global Navigation Satellite System (CYGNSS) of the National Aeronautics and Space Administration (NASA). Several methodologies have been proposed in the literature to repurpose CYGNSS data for soil moisture estimation. In this work, we first describe the theoretical background of GNSS-R based soil moisture retrieval. We discuss the challenges associated with using GNSS-R (in particular CYGNSS) data, and present the current issues in the CYGNSS-based methodologies for estimating soil moisture. Some of the key limitations identified are in the areas of observation geometry, improper consideration of coherent and incoherent reflections, effect of vegetation on CYGNSS recording and consideration of ancillary data sources. We finally discuss potential Machine Learning based solutions for soil moisture estimation, which may provide researchers a path forward to achieve low error estimates.
Direct feature extraction and image co-registration of morphological structure from Bayer pattern raw planetary images
(Elsevier, 2024-03) Rohil, Mukesh Kumar
Feature extraction from planetary remote sensing images is a primary image processing task for object recognition, crater counter, morphological structure dimension and unpaired image co-registration. The paper presents a novel methodology to extract features directly from Bayer Pattern raw planetary images. Gradient information is extracted from Bayer Pattern image using standard edge operator that follows Color Difference Constancy (CDC) assumption. The proposed method's advantage is that it can skip the computationally intensive image processing pipeline and can have the Bayer Pattern raw planetary image flow directly for useful information extraction. Sobel Edge Detector is applied on Indian Mars Color Camera (MCC) Bayer Pattern raw images, and Gradient Magnitude Map (GMM) is generated at different Martian terrains. In addition, we have developed a direct image co-registration approach for MCC Bayer intensity raw image with respect to Mars Digital Image Model (MDIM) 2.1 reference using Mode-Mean Combo Patch Filler and Gradient Intensity induced Scale Invariant Feature Transform (GI-SIFT) based feature matching. The outlier matched points are removed by Feature Similarity Score guided Random Sample Consensus (FSS-RANSAC) estimation technique. The visual evaluation and quantitative metrics indicate that GMM from MCC Bayer Pattern raw image has negligible degradation with respect to GMM extracted from MCC demosaic image. The Root Mean Square Error (RMSE) is computed at different Mars regions, and it is found that the average image co-registration accuracy is less than 0.5 pixel.
Effect of Illumination and Blur Change on Markerless Image Registration Methods
(IEEE, 2018) Rohil, Mukesh Kumar
Image registration forms a basis for a wide variety of applications in Computer Vision. The methods used for image registration are generally divided into two categories: 1) Extrinsic: based on some external object placed in an image. 2) Intrinsic: based on image information. Intrinsic methods work upon image features, pixel intensity levels etc. to determine measurements with respect to the requirements of a particular application. This paper presents a comparative analysis of three widely used image registration methods i.e. SIFT, ASIFT and SURF, for intrinsic image registration process. Quality of images describing medical, natural and structured scenes with different illumination and blur conditions is correlated with the performance analysis of the three image registration methods. Results show that the total count of extracted features in an image and correspondences found between two images (for determining the correct number of matches between an image pair, RANSAC algorithm is used for eliminating outliers) decreases with decreasing quality in terms of both blur and illumination conditions. Also, ASIFT outperforms SIFT and SURF in these changing imaging conditions.
Efficient implementation of some statistical and fuzzy classifiers for remote sensing data in context of geographical information systems
(BITS, Pilani, 2004-07) Rohil, Mukesh Kumar
EgoCentric+: A Multipurpose Data Set for Head-Mounted Wearable Computing Devices
(ACM Digital Library, 2024-06) Rohil, Mukesh Kumar
Detecting the user’s action, anticipating his or her needs and performing realistic virtual and physical world mapping are the major modules for wearable computing devices. However, the wearable computing community lacks a multipurpose dataset to develop all these methods. In this work, we employed a ZED camera to generate a novel, challenging benchmark dataset that can be used to develop hand detection, hand gesture estimation (egocentric), stereo visual odometry/ SLAM trajectory estimation and disparity estimation methods. Our "EgoCentric+" dataset comprises 231 stereo image pair sequences along with ground truth trajectory values, hand gesture annotations and 2D bounding boxes for hand detection. We designed 20 continuous and 15 static hand gestures focused on interactions with virtual content in head-mounted wearable computers. Furthermore, the dataset is collected with a head-mounted camera under diverse backgrounds and illumination settings to resemble the wearable glasses environment. These settings can help researchers to develop appropriate and robust methodologies for head-mounted wearable devices and to thoroughly test and evaluate their models and applications.
An elliptical sampling based fast and robust feature descriptor for image matching
(Springer, 2024-01) Rohil, Mukesh Kumar
Local features of an image provide a robust way of image matching if they are invariant to large variations in scale, viewpoint, illumination, rotation, and affine transformations. In this paper, we propose a novel feature descriptor based on circular and elliptical local sampling of image pixels to attain fast and robust results under varying imaging conditions. The proposed descriptor is tested on a standard benchmark dataset comprising of images with varying imaging conditions and compression quality. Results show that the proposed method generates sufficient or more number of stable and correct matches between an image pair (original image and distorted image) as compared to SIFT with a speedup of 1.6 on average basis. The paper also discusses the reason of choosing SIFT descriptor for comparison and its efficacy in different scenarios. The paper also reasons the robustness of hand crafted feature descriptors and why they hold an upper hand among many other deep learning methods.
Enhanced multispectral band-to-band registration using co-occurrence scale space and spatial confined ransac guided segmented affine transformation
(IEEE, 2024-11) Rohil, Mukesh Kumar
Band-to-Band Registration (BBR) is a pre-requisite image processing operation essential for specific remote sensing multispectral sensors. BBR aims to align spectral wavelength channels at sub-pixel level accuracy over each other. The paper presents a novel BBR technique utilizing Co-occurrence Scale Space (CSS) for feature point detection and Spatial Confined RANSAC (SC-RANSAC) for removing outlier matched control points. Additionally, the Segmented Affine Transformation (SAT) model reduces distortion and ensures consistent BBR. The methodology developed is evaluated with Nano-MX multispectral images onboard the Indian Nano Satellite (INS-2B) covering diverse landscapes. BBR performance using the proposed method is also verified visually at a 4X zoom level on satellite scenes dominated by cloud pixels. The band misregistration effect on the Normalized Difference Vegetation Index (NDVI) from INS-2B is analyzed and cross-validated with the closest acquisition Landsat-9 OLI NDVI map before and after BBR correction. The experimental evaluation shows that the proposed BBR approach outperforms the state-of-the-art image registration techniques.
Enhancing Wi-Fi with IEEE 802.11u for Mobile Data Offloading
(International Journal of Mobile Network Communications & Telematics, 2012-08) Rohil, Mukesh Kumar; Gupta, Vishal
Apart from voice services, data made its foray in cellular networks with 2.5G networks. Today, with 3G network already in place, the data requirements of mobile subscribers is very high. With the increasing demand for mobile internet and rich data services such as streaming media for audio and video, this data requirement is expected to multifold in near future. Correspondingly the network operators have started looking for alternative means of satisfying these data needs. Among many alternatives, mobile data offloading (MDO) is the most promising one. This paper presents the extensive need, benefits, and technological solutions for MDO. Qualitatively, it is also shown that Wi-Fi, or 802.11 network is the most promising technology for MDO. Also, to further popularize Wi-Fi as a candidate network for MDO, IEEE published the enhancements to the base IEEE 802.11-2007 standard in the form of its ninth amendment (i.e. IEEE 802.11u). Restricting the scope to beacon frame only, we show how this amendment supports interworking of 802.11 network with external networks. We also show the benefit of 802.11u compatible Wi-Fi, as a candidate network for MDO, by modelling the problem of taking user's choice for assisting any vertical handover decision algorithm.
EPOCH: enhanced procedure for operational change detection using historical invariant features and PCA guided multivariate statistical technique
(Taylor & Francis, 2021) Rohil, Mukesh Kumar
In this article, we have presented a methodology developed for automatic historical change detection using multi-decadal time-lapse remote sensing images, which we call as EPOCH. The unpaired bi-temporal images are spatially aligned using Mode Improved Scale Invariant Feature Transform (M-SIFT) to achieve sub-pixel co-registration accuracy. The surface changes are detected using Guided Image Filter Enhanced Multivariate Alteration Detection (GIF-MAD). The guidance image is extracted using Principal Component Analysis (PCA), and an operational processing framework is devised to generate change detection map. EPOCH is evaluated with Indian Remote Sensing (IRS) images and Landsat multi-temporal images that observe Earth for more than three decades. The procedure is generalized to detect changes using different satellite images over one of our neighboring planet Mars. EPOCH is compared with state-of-the-art techniques, and found to have closest consensus with ground truth data. The proposed approach achieved an overall accuracy of 90.9% with kappa value of 0.81
An experimental measurement of contradictory judgement matrices in AHP
(IEEE, 2012) Rohil, Mukesh Kumar; Gupta, Vishal
Often Multi Criteria Decision Making (MCDM) techniques are used to assist in deciding a best choice, or alternative, in many different types of environment. Analytic Hierarchy Process (AHP) is one of the most popular MCDM technique used in variety of domains. It not only generates numerical order of alternatives that indicates an order of preference among them but also reflect there intensity or cardinal preference among them. Despite its advantages and popularity, AHP is often criticized in the literature for many reasons. One such reason is the Consistency Index which it requires to compute for every judgement matrix. As a result of this, it allows the consideration of Contradictory matrices for which no true ordinal ranking satisfying all the relations contained in the judgement matrix can exist. This paper shows the results of an experimental analysis as an attempt to measure the magnitude of this problem. Results show that as the order of pair wise comparison matricx increases the intensity of this problem also increases.
An Experimental Study of Markerless Image Registration Methods on Varying Quality of Images for Augmented Reality Applications
(ACM Digital Library, 2017-10) Rohil, Mukesh Kumar; Gupta, Neetika
Robustness of Augmented Reality (AR) applications depends heavily on image registration procedures. The registration process in AR either make use of manually placed markers in the scene or use natural features extracted from the scene. These markers or detected features estimate the correct position of virtual objects that are to be integrated with the view of real environment. Use of markers for this purpose have only limited applicability. Therefore, for incorporating AR in a wide variety of applications, there is a need for detecting affine invariant and stable natural features from an image. This paper presents a comparative study of six feature detectors, which could be used for the 3D registration process in AR. These feature detectors are applied on 48 images (eight image-sets with six images in each set) varying in terms of change of viewpoint, scale, blur, illumination and compression ratio. Detectors chosen for comparison are Harris-Affine, Hessian-Affine, MSER, SIFT, ASIFT and SURF. The novelty of the work done is the usage of image quality metrics and Pearson Coefficient to study the traits of number of detected keypoints in an image and number of matches between two images with respect to image quality. RANSAC algorithm is used for determining correct number of correspondences between two images by eliminating outliers. Experimental results show that in most cases, performance of feature detectors could be correlated with the quality of images used for experimentation. The comparative evaluation of feature detectors is also done with respect to computational complexity to reason detector's applicability or inapplicability in an AR system.
An Experimental Study on No-Reference Image Quality Assessment of Image Datasets
(IEEE, 2022) Rohil, Mukesh Kumar
Image quality assessment algorithms are of various types depending upon the the method they are employing. Over the years, these algorithms have found various applications like image compression, image restoration, image transmission etc. Image quality assessment algorithms have played a significant in these fields by appropriately evaluating the quality of the images. Based on the structure of these algorithms, in this paper, we further explored the application of Image Quality Assessment algorithm especially Non-Reference Algorithm in the world of AI. In this paper, we have showed how the Non-reference IQA algorithms can be used to assess the quality of the images in the data that are being used in for training the deep learning models. In our study, we specially focused on the datasets that are being used in the training of the deep learning models that are used in the healthcare sector. We have showed how non-reference algorithms can be used to create a more quality data so that the efficiency of the automated systems which heavily relies on the data quality can be increased.
An exploratory study of automatic text summarization in biomedical and healthcare domain
(Elsevier, 2022-11) Rohil, Mukesh Kumar
In the last two decades, the uses of automatic text summarization have been realized in a wide range of applications in various fields cutting across a number of verticals. Amongst these, one of the most inquired is the domain of healthcare and medicine. Many of the studies have revealed that the use of automatic text summarization in the biomedical and healthcare domain helps researchers and medical professionals save their time and access more information in considerably short spans of time. This article reports some of the recent studies that enumerate the benefits and limitations of the uses of automatic text summarization in the biomedical and healthcare domain. In addition, the paper also explores certain new possible applications of automatic text summarization in the biomedical and healthcare domain. Furthermore, it discusses the trends and vision towards future opportunities for possible research in automatic text summarization in the context of medical and healthcare domain.
Exploring Possibilities of Reducing Maintenance Effort in Object Oriented Software by Minimizing Indirect Coupling
(Springer, 2012) Rohil, Mukesh Kumar
The quality of a good object oriented software design is much effective when it has highly maintainable class components. This paper describes an investigation into the use of indirect coupling to provide early indications of maintenance effort in object oriented software. The properties of interest are: (i) the potential maintainability of a class and (ii) the likelihood that a class will be affected by maintenance changes made to the overall system. The research explores that minimizing indirect coupling can provide useful indications of software maintenance effort that may have a significant influence on the effort during system maintenance and testing.