Qualification: 
MCA, M.Tech
Email: 
vv_sajithvariyar@cb.amrita.edu

Sajith Variyar V. V.  currently serves as Research Associate at Amrita Center for Computational Engineering and Networking (CEN), Coimbatore Campus. He pursued his M.Tech in Computational Engineering and Networking (CEN).

Invited Talks 

  1. An invited talk on ED RASP PI V1.0 at Computer Science and Engineering, Royal College of Engineering and Technology from July-31 to August 1, 2015. 
  2. An invited talk on IIIC Programme on “Arduino and Raspberry PI” at the Department of Information Technology, Government  Engineering College ,Sreekrishnapuram  from March 13-14, 2015.
  3. An invited talk on “Pi Your Day” at the two-day Workshop on Raspberry Pi by Department of Electronics and Communication Engineering  Rajagiri School of Engineering & Technology, Kochi.

Workshop Conducted 

  1. Two day workshop on Embedded system and IOT  in the month of June 2015 at Amrita Vishwa Vidyapeetham, Ettimadai.

Publications

Publication Type: Conference Paper

Year of Publication Publication Type Title

2017

Conference Paper

P. G. Parakkal and Variyar, V. V. Sajith, “GPS Based Navigation System for Autonomous Car”, in 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, 2017.[Abstract]


Navigation is an indispensable part of a mobile robot, especially the ability to self-navigate is of immense importance to an autonomous car. For this purpose, it is necessary for the car to know its current position as well as an area of a map it has to navigate. GPS provides the required position data and a compass gives the current heading. This data in conjunction with a list of way-points obtained from the map is used to calculate the required correction in heading. This is then used to obtain the steering angle to navigate the vehicle.

More »»

2017

Conference Paper

N. Deepika and Variyar, V. V. Sajith, “Obstacle Classification and Detection for Vision Based Navigation for Autonomous Driving”, in 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, 2017.[Abstract]


With the rising trend in research and development of autonomous vehicles, it is important to keep in mind the cost effectiveness of the system. The cost of high-end sensor technologies being astronomically expensive, the research opportunities are restricted to a select few of high-tech companies and research laboratories such as Google, Tesla, Ford, and the likes of it. Hence our main focus is to develop an autonomous system suitable for academic and research purposes as well. This can be achieved by using available sensors such as the monocular cameras. The existing computer vision techniques along with the deep learning tools like Convolutional Neural Network (CNN) can together be used for developing a robust vision based autonomous driving system. The proposed method uses the SegNet encoder-decoder architecture for pixel-wise semantic segmentation of the video frame followed by an obstacle detection algorithm. The entire algorithm was implemented and tested on a mobile embedded platform of NVIDIA's Jetson TK1.

More »»

2017

Conference Paper

S. Jose, Variyar, V. V. Sajith, and Soman, K. P., “Effective Utilization and Analysis of Ros on Embedded Platform for Implementing Autonomous Car Vision and Navigation Modules”, in 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, 2017.[Abstract]


In the last few decades, the mobile robotic field has witnessed an incredible progress in the field of development. It finds application in different areas like space exploration, military, intelligent transportation, medical areas, agriculture and in the field of entertainment. Hence, the need for a practical integration tool is necessary in the field of robotics research. Nowadays, the main problems relating to different engineering applications are the high computational time requirement and the power related issues. To use the robots in real-Time applications, the output should obtain within a fraction of seconds. We need real-Time robots having the capability to respond within a limited amount of time. An autonomous car, which is also called a driver-less car is a vehicle, that is skilled of sensing its surroundings and can navigate without any human input. Self-driving cars have become a cutting-edge research topic in the robotics automation domain. The complexity associated with modelling, computation, implementation of various functionality hindered the development of self-driving cars in academia and research. The ROS gave an easy platform, where we can integrate and test various modules of robotics and automation. This paper deals with the effective utilization of ROS in an embedded platform to implement self-driving cars tasks like vision and navigation.

More »»

2017

Conference Paper

A. G. Babu, Guruvayoorappan, K., Variyar, V. V. Sajith, and Soman, K. P., “Design and Fabrication of Robotic Systems: Converting a Conventional Car to a Driverless Car”, in 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, 2017.[Abstract]


Drastic changes in the robotics and intelligent controls brought a radical change in Automotive engineering sector that leads to the driverless vehicles in this new era. For these vehicles to safely run in today's traffic and in harsh environments, a number of problems in vision, navigation, and control have to be solved. Driverless cars use sensors to detect the environment, computers to process the data and actuators for mechanical systems. To adopt the self driving car technology to current academic and research , we need a cost efficient and affordable mechanisms. In this scenario we need a system that can incorporate existing vehicles and convert that driverless cars which will reach to academicians and research fields. Considering the possibilities and implementation of driverless vehicles in Indian scenario we need an agile mechanical design to be included on existing vehicles. This paper proposes a portable mechanical design that can be fabricated and fit into existing vehicles and can be used as a platform to develop an autonomous car. Conventional cars can be altered to be a driverless car by using different actuators. Popularly motors are used as actuators in the automation of the vehicle. A pneumatic system is designed to automate the intended platform apart from the motors. The mechanical structure is an essential part of an autonomous car and is to be altered and designed in such a way that it is dynamically unwavering. Further improvements will make the system capable of being commercially produced.

More »»

2017

Conference Paper

V. S. Dev, Variyar, V. V. Sajith, and Soman, K. P., “Steering Angle Estimation for Autonomous Vehicle”, in 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, 2017.[Abstract]


The modern era has witnessed huge spike in the number of road accidents and fatalities. The common origin of traffic accidents is driver error. This is not going to change anytime soon thanks to the immense number of cell-phone users, in-car entertainment audio and video systems, and finally abundant traffic. There's one death every four minutes due to road accident in India. Such severe situation asks for a better scope that can propitiate the burden on the human drivers in certain critical instants. This demands a computationally efficient and fast responsive decision-making methods. But the course of autonomous vehicles is still in its early stages with companies still booming to build a fully autonomous vehicle. Volvo, Google, Tesla, BMW and more are still in the autonomous car research area. The mechanization and industrial science related to this field will mature over time, it is only a matter of time where the capability of driverless cars will outpace the outlook of any vehicle in the city. This paper exemplifies a novel approach to figure out the steering angle required to control the vehicle in the center of the road.

More »»

2017

Conference Paper

C. K. Chandni, Variyar, V. V. Sajith, and Guruvayurappan, K., “Vision Based Closed Loop PID Controller Design and Implementation for Autonomous Car”, in 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, 2017.[Abstract]


Autonomous cars are one of the fascinating technological trends in the present automotive industry. These cars enticed substantial attention in industry as well as in academia. It aims at safety regulations along with the emerging customary needs, traffic safety and transportation efficiency. In general, autonomous car integrates environmental perception, control and automatic driving modules for path tracking and effective navigation. The automatic driving module maneuvers the corresponding actuators according to the requisite of planning module, and ensure that the vehicle moves at the desired speed profile and path trajectory. This paper propounds closed loop PID control architecture for accurate steering, acceleration and braking control of an autonomous self-driving car designed from scratch. The control signals are triggered, when the perception module detects the lane and obstacle inputs. Then the actuators of the vehicle are controlled. Steering control subsystem constitutes a PWM motor, driving a steering linkage that eventually steers the front axle of the car. The steering subsystem receives the PWM input from the PID controller and outputs the current wheel angle. The closed loop PID controlling enables accurate steering control and hence efficient path tracking.

More »»

Publication Type: Journal Article

Year of Publication Publication Type Title

2016

Journal Article

V. V. Sajith Variyar, Haridas, N., Aswathy, C., and Soman, K. P., “Pi doctor: A low cost aquaponics plant health monitoring system using infragram technology and raspberry Pi”, Advances in Intelligent Systems and Computing, vol. 397, pp. 909-917, 2016.[Abstract]


The technological and scientific advancement in the field of agriculture has opened a new era for design and development of modern devices for plant health monitoring. The analysis of various parameters, which affects the plant health such as soil temperature, moisture level and pH are easier with the use of advanced devices like Raspberry Pi and Arduino integrated with different types of sensors. The development of infragram technology has created new possibilities to capture infragram images, where both infrared and visible reflectance are obtained in a single image. The rationale of this paper is to monitor the health of a small scale aquaponics vegetation using Infragram technology and Raspberry Pi. The proposed experimental setup captures infragram images using a low cost modified web camera containing infra-blue filter. These images are post-processed to calculate normalized difference vegetation index (NDVI), which is a good indicator of photosynthetic activity in plants. The study also assesses and monitors the influence of various parameters in the aquaponics system such as nitrogen usage by plants and pH change in the system under different illumination conditions. The study shows that the change in pH and health condition of the plant due to the variation in photosynthesis are the major factors that affects the balance of nitrogen cycle in the aquaponics system. © Springer India 2016.

More »»

2016

Journal Article

S. Chandran, Variyar, V. V. Sajith, Prabhakar, T. V. Nidhin, and Dr. Soman K. P., “Aerial image classification using regularized least squares classifier”, Journal of Chemical and Pharmaceutical Sciences, vol. 9, pp. 889-895, 2016.[Abstract]


The land cover classification and urban analysis of remotely sensed images has become a challenging problem, hence efficient classifiers are required in order to combat the problem of classifying the huge remote sensing aerial datasets. In this paper we have proposed the use of Random Kitchen Sink (RKS) algorithm and Regularized Least Squares (RLS) classifier for the classification of aerial image. The new machine learning algorithm RKS, primarily engages in mapping the feature data to a higher dimensional space and thereby generates random features. These randomized data are then adopted by RLS classifier for the classification task. It is observed that the randomization of the data reduces the computation time needed for training. The experiment is performed on five classes of the UC Merced Land Use Aerial Imagery Dataset. The efficiency of the proposed method is estimated by comparing the accuracy results with the conventional classifier namely, Support Vector Machine (SVM). Experimental result shows that the proposed method produces a high degree of classification accuracy i.e. 94.4%, when RBF kernel with LOO (Leave One Out) cross-validation was used, when compared to SVM. In this paper, statistical features show better precision and accuracy in classifying different set of classes, compared to textural features in both the classification approaches. Hence, better accuracies could be attained for multi class classification when compared to other classification technique like, SVM since, the random features reduces computation time and enhance the performance of kernel machines.

More »»
207
PROGRAMS
OFFERED
5
AMRITA
CAMPUSES
15
CONSTITUENT
SCHOOLS
A
GRADE BY
NAAC, MHRD
8th
RANK(INDIA):
NIRF 2018
150+
INTERNATIONAL
PARTNERS