Selected Engineering Projects

These are some of the Selected Engineering Projects I have been a part of in the last few years - some as course projects during my undergrad. and rest independently outside coursework.

Swarath Autonomous Car

Guide: Dr. Saket Anand, Dr. Sanjit Kaul, Dr. Rahul Purandre
Team Size: 3
Team Member(s): Shivam Thukral, Gurshabad Grover
Time Period: May'15-present
Technologies/Concepts Used: ROS, C++, Design Patterns

Currently a member of IIIT-Delhiā€™s core team in the Driver Less Challenge by Mahindra. Led a team of 2 and designed the Test Bench and Perception Module in ROS/C++.

Fettle Crowd Souced Memory Sharing

Guide: Dr. Rahul Purandre
Team Size: 4
Team Member(s): Manan Gakhar, Danish Goel, Chaitanya Kumar
Course: Practice of Programming
Time Period: Jan'15-May'15
Technologies/Concepts Used: Android, Parse, Javascript, Lint, SonarQube

Additional content

Meri Awaaz Web Dashboard

Guide: Aditya Nayak
Team Size: 5
Team Member(s): Manan Gakhar, Danish Goel, Shashank Gautam, Anchita Goel
Time Period: Aug'14-present
Technologies/Concepts Used: Javascript, AJAX, JQuery, SAAS, Jekyll, Foundation, Parse, REST

Meri Awaaz is India's first platform that connects citizens with their netas and government officials for Open, Accessible and Accountable Governance. It is mobile-first real time public engagement tool that makes catching up with the work being done in your area as easy as following up your timeline. I develop and maintain the Dashboard which is being used by Candidates/Netas in Delhi to interact with citizens of their constituency and address their issues.

Kinect based 2-D Mesh Animation Computer Graphics

Guide: Dr. Ojaswa Sharma
Team Size: 1
Course: Computer Graphics
Time Period: Aug'15-Dec'15
Technologies/Concepts Used: QT, OpenGL, Kinect, Visual Studio

In this project we focus on animating a 2D mesh character and driving its actions through kinect. It has been a little more than five years since the first kinect was launched and even today it continues to draw a lot of attention and applications in various fields. In this approach we use Visual Studio to interact with our kinect device and fetch the skeleton data captured in the form of coordinates. We then create our 2D mesh in QT and use these coordinates to mimic the skeleton. The project follows a bone based skeleton model to construct our 2D mesh character. This projects finds applications in the animation industry for simplifying a lot of processes involved in animating 2D characters. The project can seamlessly by ported to work for 3D characters as well.

coDrive Crowd Souced Memory Sharing

Guide: Dr. Rahul Purandre
Team Size: 4
Team Member(s): Manan Gakhar, Danish Goel, Chaitanya Kumar
Course: Practice of Programming
Time Period: Jan'15-May'15
Technologies/Concepts Used: Android, Parse, Javascript, Lint, SonarQube

This page will be updated soon!

Color based Offside Detection Blob Detection

Guide: Dr. Mayank Vatsa
Team Size: 1
Course: Image Analysis (Minor)
Time Period: Aug'14-Dec'14
Technologies/Concepts Used: C#, EmguCV, Visual Studio 13

As a part of my Mini Bonus Project in my Image Analysis Course I built a software in C# using emguCV Library to detect players in a football field using Color based object Segmentation. I further wrote an algorithm to detect offside in the game by combining data coming from cameras located at various angles across the field.

reWise In-Class Quizzing Application

Guide: Dr. Vinayak Nayak
Team Size: 5
Team Member(s): Saumya Jain, Shuktika Jain, Mrinal Kachara, Manan Gakhar
Course: Mobile Computing
Time Period: Aug'14-Dec'14
Technologies/Concepts Used: Android, Parse, Javascript

An android application to hold quick in-class quizzes. Intuitive UI, Ever Growing Question Bank, Statistical Analysis of Quizzes as well as Individual Performances and Gamification using Badges.

He-or-She Speech based Gender Detection

Guide: Dr. Richa Singh
Team Size: 2
Team Member(s): Anchita Goel
Course: Pattern Recognition (Minor)
Time Period: Jan'15-May'15
Technologies/Concepts Used: Matlab, Speech Signal Processing, SVM

Detect gender of the speaker based on various features like MFCC, pitch, short-time energy, energy entropy, zero-crossing rate and spectral centroid. We also implemented an android application to detect gender based on the pitch of a person's voice. Uses different kinds of filters (mean, median, mode). The former uses a machine learning approach while the latter is a more direct and naive approach.

Image Recolorization Chrominance Blending

Guide: Dr. Mayank Vatsa
Team Size: 2
Team Member(s): Manan Gakhar
Course: Image Analysis (Major Project)
Time Period: Apr'14-Aug'14
Technologies/Concepts Used: Arduino, IR & Ultrasonic Sensors

As a part of my Major Project in my Image Analysis Course I along with my fellow team member, implemented and analysed the performance of Chrominance Blending Technique proposed by Liron Yatziv and Guillermo Sapiro in their paper on the same as compared to other Algorithm.

Scene Recognition using Bag-of-Words Machine Learning

Guide: Dr. Richa Singh
Team Size: 2
Team Member(s): Anchita Goel
Course: Machine Learning
Time Period: Aug'15-Dec'15
Technologies/Concepts Used: Matlab

Scene recognition is an important upcoming real world problem which finds application in the fields of robotics(autonomous systems), surveillance(wearable camera footage, evidence photographs, etc), and personal assistance devices(Google Glass). There has been a steady progress in the field and this project explains the developments made in this field leading to the current state-of-the-art approach, documenting the results obatined from our implementation with standard benchmarks and classifiers.

Pedestrian Detection based on HoG

Guide: Dr. Saket Anand
Team Size: 2
Team Member(s): Prateekshit Pandey
Course: Computer Vision
Time Period: Jan'15-May'15
Technologies/Concepts Used: Matlab, Computer Vision Toolbox

Human Detection in Images is a contemporary Computer Vision problem, still welcoming improved solutions. This subset area of object detection has seen many attempts made towards efficient implementation and in this project proposal we describe one based on Histogram of Oriented Gradients which proves to be superior than the rest in terms of both Detection rate and Error rate when using a Linear SVM Classifier

Travel Booking System SAAS

Guide: Mr. Manish Shrotriya
Team Size: 8
Team Member(s): Saumya Jain, Shuktika Jain, Mrinal Kachhara, Manan Gakhar, Mansi Verma, Akanksha, Danish Goel
Course: Software Engineering
Time Period: Aug'14-Dec'14
Technologies/Concepts Used: Ruby on Rails, Javascript, AGILE Paradigm

As a part of the Software Engineering course I along with the team made a SAAS web application using ruby on rails framework. The Web Application consisted of a system to allow a Travel Agent to effectively run his business by adding and using a set of applets that the service provides.