Umesh C. Pati

Umesh C. Pati
National Institute of Technology Rourkela | NITR · Department of Electronics and Communication Engineering (EC)

M.Tech, Ph.D
I am working in the research domains of Image/Video Processing, Computer Vision, IoT, AI, and Industrial Automation.

About

103
Publications
37,925
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
861
Citations
Introduction
Dr. Umesh C. Pati obtained B.Tech. from NIT , Rourkela, Odisha and both M.Tech. and Ph.D. from IIT Kharagpur, India. He is a full Professor in NIT Rourkela. His areas of research are Image/Video Processing, Computer Vision, IoT, Artificial Intelligence and Industrial Automation. He has authored/edited 2 books and published more than 100 research papers in international as well as national journals and conference proceedings. He is a senior member of IEEE and Fellow of The Inst. of Engineers.

Publications

Publications (103)
Chapter
Water pollution is a global problem. In developing countries like India, water pollution is growing exponentially due to faster unsustainable industrial developments and poor waste-water management. Hence, it is essential to predict the future levels of pollutants from the historical water quality data of the reservoir with the help of appropriate...
Chapter
Brain imaging has played a very crucial role in the detection of various brain disorders. Among many brain imaging modalities, Magnetic Resonance Imaging (MRI) has proven its importance due to its detailed information regarding the insight of the brain. Autism Spectrum Disorder (ASD) has emerged as a very serious brain disorder due to its late dete...
Conference Paper
Water pollution is a serious issue faced not only in India but also in the overall globe. Almost all major Indian rivers are polluted due to the rapid increase in industrialization and poor water quality management. Particularly, the pollution level in the river Ganga has increased significantly. Hence, it is necessary to monitor and manage the pol...
Conference Paper
Intelligent street light management system is one of the prominent applications of smart city. In this work, a selfpowered street light management system has been designed to save the electricity budget of a smart city. The system has been powered from ambient solar energy. It controls the illuminance of the street light according to traffic moveme...
Conference Paper
Water pollution is a global problem. In developing countries like India, water pollution is growing exponentially due to faster unsustainable industrial developments. Recently, the river Ganga has been polluted faster and caused lots of diseases among humans and aqua-animals. Hence, continuous water quality monitoring with appropriate water quality...
Conference Paper
Among various brain disorders, Autism Spectrum Disorder (ASD) is very different of its kind. It generally occurs at a very early age of children. It becomes difficult for even parents to identify an abnormality in their child due to its early occurrence. This paper presents the machine learning approach for the detection of ASD using surface morpho...
Article
Full-text available
The high‐resolution optical and synthetic aperture radar (SAR) images are widely used in many remote sensing application areas such as image fusion and change detection where image registration is a fundamental step. The latest high‐resolution optical and SAR satellites and airborne systems provide geometrically corrected images which do not contai...
Article
Over the last two decades, there has been a significant improvement in the quality and volume of the remote-sensing images. With the extensive availability of the images, these are used in many applications such as change detection, image mosaicing, and image fusion where image registration is very necessary. However, image registration is a challe...
Chapter
Object detection is an attractive research interest in recent years. It plays a significant role to understand the image in video analysis. Object detection technique has improved in computer vision when deep learning method came to the picture. From the last two decades, several algorithms have been developed and improved to detect the object in d...
Article
Video surveillance systems are popular and used in public places such as market places, shopping malls, hospitals, banks, streets, education institutions, city administrative offices, and smart cities to enhance the safety of public lives and assets. Most of the time, the timely and accurate detection of video anomalies is the main objective of sec...
Article
Full-text available
The scale‐invariant feature transform (SIFT) algorithm is the most widely used feature extraction as well as a feature matching method in remote sensing image registration. However, the performance of this algorithm is affected by the influence of speckle noise in synthetic aperture radar (SAR) images. It reduces the number of correct matches as we...
Conference Paper
A convolutional spatiotemporal autoencoder is used for video anomaly detection. The proposed model architecture comprises of three major sections, such as spatial encoder, temporal encoder-decoder, and spatial decoder. The spatial encoder is implemented using three layers of the convolutional layers. Then, the temporal encoder-decoder is realized w...
Article
Full-text available
Optical‐to‐synthetic aperture radar (SAR) image registration is a challenging task in remote sensing as the images have significant non‐linear intensity variations as well as large geometric differences. Moreover, the influence of speckle noise in the SAR image further affects the registration result. The structural descriptors are very effective t...
Article
For the problem of set point regulation of the liquid level in coupled tank systems, we present a continuous sliding mode control (SMC) with a “conditional integrator”, which only provides integral action inside the boundary layer. For a special choice of the controller parameters, our design can be viewed as a PID controller with anti-windup and a...
Conference Paper
A deep-learning-based Loitering Detection System (LDS) with re-identification (ReID) capability over a multicamera network is proposed. The proposed LDS is mainly comprising of object detection and tracking, loitering detection, feature extraction, camera switching, and re-identification of the loiterer. The person is detected using You Only Look O...
Conference Paper
There is a huge demand of video surveillance based intelligent security systems which can automatically detect the unauthorized entry or mal-intentional intrusion to the unattended sensitive areas and notify to the concerned authorities in real-time. A novel video-based Intrusion Detection System (IDS) using deep learning is proposed. Here, You Onl...
Article
Image mosaicing is an effective means of constructing a single seamless image by aligning multiple partially overlapped images. Over the years, the research attention on mosaicing has increased a lot due to the growing applications and subsequently, many algorithms related to mosaicing and its contributing steps have come into existence. Though, th...
Conference Paper
Abstract — Present day Wireless Sensor Networks (WSNs) and Internet of Thing (IoT) plays a vital role for Surveillance and security. This paper presents region based object/human detection and alert notification to the control room or administration. In this case PIR sensors are used in different region which helps to detect and alert the presence...
Article
Synthetic aperture radar (SAR) image registration is a challenging task in remote sensing because of the presence of significant intensity as well as geometric differences between the images. Moreover, the influence of multiplicative speckle noise in SAR images adversely affects the registration result. The synthetic aperture radar-scale invariant...
Chapter
This paper deals with the implementation of Model Predictive Control (MPC) in a Four Tank System (FTS). The nonlinear model of FTS has been developed from the mechanism modelling. There is coupling between the input and output and time delay in the FTS. Different control algorithms are implemented to the FTS. The objective is to track the level of...
Article
Synthetic aperture radar (SAR) image matching is a challenging issue in remote sensing as the images contain significant multiplicative speckle noise. Histogram of oriented gradients (HOG)-based descriptors have been used popularly for the matching of the SAR images. An appropriate gradient computation of the SAR images plays a significant role in...
Article
Rock deformation analysis in an underground mine is one of the most important safety aspects in the coal mining industry. Dedicated and reliable instrumentation systems are used to get real-time information about rock deformation. Various instruments such as telltales are widely used to warn the personnel inside the mine about a possible roof fall....
Article
Full-text available
This study provides a step-by-step analysis of closed-loop parametric system identification for DC-DC buck converter. In closed-loop parametric identification, input–output experimental data are used to estimate the transfer function coefficients of DC-DC buck converter. For system identification purpose, a high-frequency perturbation signal is inj...
Chapter
Although a variety of feature-based remote sensing optical image registration algorithms has been proposed in past decades, most of the algorithms suffer from the availability of a sufficient number of matched features between the input image pairs. In this paper, a modified version of scale-invariant feature transform (SIFT) is proposed to increas...
Article
In this letter, a block-based multifeature extraction scheme is proposed to register the synthetic aperture radar (SAR) images. With appropriate modifications, the scale-invariant feature transform (SIFT) and the SAR-SIFT operators are used to extract two types of features including texture points and corner points from the SAR images. The input im...
Article
With the advancement in computer vision and graphics tools, digital compositing has become an integral part of the present computer-generated visual effects. However, factors such as inaccurate mask generation, intensive user interaction, and the creation of boundary seams due to colour or texture difference, make it hard to achieve quality composi...
Conference Paper
Full-text available
Sub-pixel accuracy is the vital requirement of remote sensing optical image registration. For this purpose, a coarse-to-fine registration algorithm is proposed to register the remote sensing optical images. The coarse registration operation is performed by the scale-invariant feature transform (SIFT) approach with an outlier removal method. The ou...
Article
Full-text available
To utilize the power generated from renewable energy sources and use it in stand-alone or grid integrated application, power conditioning unit (PCU) is required. The main consideration in designing a PCU is lower cost, higher reliability, higher efficiency, and robust operation. One of the major components of PCU is high-step-up and high-efficient...
Conference Paper
Full-text available
The home automation technology makes human life comfortable and luxurious. That is why today every person wants a smart home. This technology provides the control of the home devices as well as a secure and intelligent interaction between personnel inside and outside of the room. The control system gives the status concerning ON or OFF of the selec...
Chapter
Panoramic images have numerous important applications in the area of computer vision, video coding/enhancement, virtual reality and surveillance. The process of building panorama using mosaicing technique is a challenging task as it requires consideration of various factors such as camera motion, sensor noise and illumination difference, that deter...
Conference Paper
Full-text available
An energy storage system plays an important role in the operation of micro-grid and electric vehicle. Battery management system (BMS) in micro-grid and electric vehicle is one of the challenging areas and has witnessed much research interest. This paper provides the design and implementation details of photovoltaic (PV) based charger for lead-acid...
Article
Uniformly distributed feature extraction and availability of a sufficient number of correctly matched points between the input images are the key challenges for remote sensing optical image registration. Because of its robustness and distinctiveness, the scale-invariant feature transform (SIFT) is a well-known approach for an automatic image regist...
Conference Paper
Full-text available
Power electronic converters play an important role in integrating renewable energy sources in to the electrical grid. A power conditioning unit (PCU) which comprises of different power electronic converters is essential to process the power of renewable energy sources and make it useable for stand-alone or grid-tied application. DC-DC converters ar...
Article
In multimedia applications, compositing is an inevitable step for creating special visual effects from entertainment to education. It is often desirable to merge two regions or an object from one image over background of another image to get a completely new image. However, compositing multiple images with different textures and colors results in t...
Conference Paper
Full-text available
The recent technology in home automation provides security, safety and comfortable life at home. That is why in the competitive environment and fast world, home automation technology is required for every person. This purposed home automation technology provides smart monitoring and control of the home appliances as well as door permission system f...
Conference Paper
Full-text available
This paper provides modeling of photovoltaic (PV) panel, designing of maximum power point tracking (MPPT) control algorithm for a standalone PV based distributed generation (DG) system. A detailed mathematical model of PV panel is provided. One of the most classical MPPT (Perturb and Observe MPPT) is used to track the maximum power point of the sys...
Conference Paper
Full-text available
The human incapability in diving in the deep ocean for a long time has increased the challenges of underwater analysis. However, the challenges contain problems like aggressive light absorption and disrupting scattering effect in the deep ocean enabling lighting problem. These days UROV (Underwater remotely operated vehicle) are used to acquire ima...
Conference Paper
Full-text available
This paper describes the design details of a measurement and data acquisition laboratory. The main purpose of this laboratory is to experimentally validate the theoretical concept of sensors, signal conditioning circuits and data acquisition devices. The developed laboratory course emphasizes on theoretical concept of different temperature sensors,...
Conference Paper
Full-text available
Multi converter based distributed power system (DPS) comprises of several interconnected switched mode power converters. The large scale implementation of DPS in variety of applications has provided new research directions in modeling and control of switched mode power converter. With evolution of DPS, black box, grey box modeling and identificatio...
Article
Full-text available
Mutual information is used widely as a similarity measure for registration of images. In order to improve the robustness of this similarity measure, spatial information is combined with normalised mutual information. In this paper, mutual information is multiplied with a gradient term to integrate spatial information with mutual information and thi...
Article
Mutual information is used widely as a similarity measure for registration of images. In order to improve the robustness of this similarity measure, spatial information is combined with normalised mutual information. In this paper, mutual information is multiplied with a gradient term to integrate spatial information with mutual information and thi...
Data
Full-text available
The fingerprint identification is a challenging task in criminal investigation due to less area of interest (ridges and valleys) in the fingerprint. In criminal incidences, the obtained fingerprints are often partial having less area of interest. Therefore, it is required to combine such partial fingerprints and make them entire such that it can be...
Conference Paper
This paper presents an image mosaicing technique based on an improved discrete cosine transform (DCT)-based phase correlation (PC). The improved DCT-based PC method is an extension of DCT-based PC with added blur invariance property. Though fast Fourier transform (FFT)-based methods are efficient for mosaicing of images, they often fail to achieve...
Conference Paper
Full-text available
Enhanced Thematic Mapper is a eight-band multispectral sensor in LANDSAT satellite capable of providing high resolution images. These remote sensing images have a wide range of applications in agriculture, deforestation, land cover, volcanic flow activity monitoring etc. All these applications require very accurate image registration. But, automati...
Conference Paper
In this paper, we propose a modified version of demons algorithm (non-linear intensity based approach) for registration of medical images. We revise demons algorithm and use anisotropic regularization in place of Gaussian smoothing to introduce an efficient mono-modal 2D image registration method. Here, in particular, the velocity field calculation...
Conference Paper
Full-text available
The fingerprint identification is a challenging task in criminal investigation due to less area of interest (ridges and valleys) in the fingerprint. In criminal incidences, the obtained fingerprints are often partial having less area of interest. Therefore, it is required to combine such partial fingerprints and make them entire such that it can be...
Conference Paper
This paper reports design of an automated, low cost multi-channel data acquisition and data logging system for meteorological application. Different meteorological parameters such as environmental temperature, barometric pressure, altitude, light intensity, and relative humidity are acquired in real time and stored in a database for future referenc...
Conference Paper
Full-text available
Fingerprint is most important and widely used biometrics trait for identification. However, the fingerprint identification is still a challenging task in forensic science for criminal investigation and identification due to less area of region of interest (i.e. ridges and valleys) in the obtained fingerprints. Entire fingerprint is obtained only wh...
Conference Paper
Full-text available
Fuel cell is one of the renewable energy sources used extensively in stand-alone as well as grid tied applications. Fuel cell provides a low voltage and high current DC output which has to be properly conditioned according to the demand of load. Therefore, a power conditioning unit (PCU) is essential for processing the unregulated DC voltage. The P...
Conference Paper
Fingerprint is most important and widely used biometrics trait for identification. However, the fingerprint identification is still a challenging task in forensic science for criminal investigation and identification due to less area of region of interest (i.e.ridges and valleys) in the obtained fingerprints. Entire fingerprint is obtained only whe...
Conference Paper
Image registration is the process of overlaying images (two or more) of the same scene taken at different times, from different viewpoints, and/or by different sensors. Image registration geometrically aligns two images (the reference and test images). In this paper, we discuss about the problematic issue that arises during the feature matching sta...
Article
Image mosaicing has numerous applications in the area of computer vision, virtual reality, robotics, medical imaging, computer graphics and advertising. The creation of the seamless image mosaic often becomes a difficult task due to the presence of alignment errors and intensity discrepancies. The present paper discusses the development and impleme...
Conference Paper
The paper has analyzed the four tank system (FTS) from the mechanism modeling and has also established the nonlinear and linear mathematical model. The FTS is a typical control system with nonlinear, coupling and time delay characteristics which can be used to test the applications of different control algorithms on complex systems. The aim of the...
Conference Paper
Full-text available
In this paper, the performance of different tuning methods of PID controller is evaluated. Tuning of PID controller parameters is necessary due to the wide applications of controllers in industry. Different tuning methods such as Empirical Ziegler-Nichols, Cohen-Coon, Chien-Hrones-Reswick and optimum tuning methods are considered. The performance o...
Conference Paper
Full-text available
The paper describes about the liquid level control system which is commonly used in many process control applications. The output of the level process is non-linear and it is converted into the linear form by using Taylor Series method. The aim of the process is to keep the liquid level in the tank at the desired value. The conventional proportiona...
Article
Full-text available
This paper presents non-recursive computation equation for 8�8 two-dimensional (2D) discrete cosine transform (DCT) along with novel VLSI architecture for direct computation of DCT without transposition memory. All intermediate operations are performed in non-fraction format. Being non-recursive and all intermediate calculations free of fractions,...
Conference Paper
Pedestrian detection is one of the vital issues in advanced driving assistance applications. It is even more important in nighttime. This paper presents a robust algorithm for a nighttime pedestrian detection system. A NIR (Near Infrared) camera is used in this system to take images of a night scene. As there are large intra class variations in the...
Conference Paper
Full-text available
Image Mosaicing is a method of assembling multiple overlapping images of the same scene into a larger image. The output of the image mosaic will be the union of two input images. In this paper, the detection of interest point is based on unsharp masking technique. This interest point detection algorithm produces an efficient and informative output...
Article
Full-text available
Listless set partitioning embedded block (LSK) and set partitioning embedded block (SPECK) are known for their low complexity and simple implementation. However, the drawback is that these block-based algorithms encode each insignificant subband by a zero. This generates many zeros at earlier passes because the number of significant coefficients at...
Conference Paper
Full-text available
This paper presents an overview of data acquisition, data logging and supervisory control of different parameters for green house application. In this work a Green House system is considered, where data from various parameters are needed to be acquired, logged in a database for further analysis and supervisory control. This paper acquires data of s...
Article
Full-text available
Since last few decades, multi sensor image fusion has been an emerging field of research in remote sensing, medical imaging and variety of computer vision applications. The primary objective of image fusion lies in the formation of a perceptually enhanced image from several multi sensor images using an appropriate fusion rule. The discrete wavelet...
Chapter
Since last three decades, edge detection techniques have been drawing the attention of researchers due to its applications in 3D reconstruction, motion recognition, morphing, restoration, watermarking, image compression, and so on. Again, detecting edges in multi-focused images are one of the most challenging tasks. This paper deals with a novel ed...
Conference Paper
Image mosaicing has been used in various arenas of image engineering. The main purpose of this research work is to develop a novel blending algorithm for mosaicing of two non-overlapping images with minimum distortion and no visible seam. In the proposed method, images are mosaiced using the pyramid technique and Savitzky-Golay filter is used for s...
Article
Full-text available
This paper presents a listless variant of modified wavelet block tree coding (MLBTC) algorithm. Wavelet block-tree coding (WBTC) improves the image compression performance of set partitioning in hierarchical trees (SPIHT) at lower rates by efficiently encoding both inter- and intra-scale correlations. The use of auxiliary lists makes WBTC undesirab...
Article
Full-text available
This paper presents an efficient orthogonal sparse 8×8 transform matrix for color image compression particularly at lower bit rate applications. The transform matrix is made sufficiently sparse by appropriately inserting additional zeros into the matrix proposed by Bouguezel. The algorithm for fast computation is also developed. It is shown that th...
Conference Paper
A Non-Destructive Testing (NDT) has been a popular analysis technique used in industrial product evaluation and for troubleshooting in research work without causing damage which can also save both money and time. This paper deals with a novel crack detection technique based on NDT for cracks in walls suppressing the diversity and complexity of wall...
Article
Full-text available
In this paper, a comparative simulation study of Peak Signal to Noise Ratio (PSNR) in JPEG image compression is done using two quantisation tables, one recommended by JPEG committee and another suitable for hardware simplification. Simulation results confirm that quantisation table suitable for hardware simplification can be used for designing JPEG...
Conference Paper
The processes encountered in the real world are usually multiple input multiple output systems (MIMO). The interacting level process is described in this paper. The output of the level process is non-linear and it is converted into the linear form by using Taylor Series method. By using Taylor series method in the non-linear equation, the converted...
Conference Paper
Electrocardiogram (ECG) is the graphical representation of heart functionality. The ECG finds its importance in the detection of cardiac abnormalities. The electrocardiographic signals are often contaminated by noise from diverse sources. It is essential to reduce these disturbances and improve the accuracy as well as reliability. The noises that c...