My Projects

1 – Object Detection with Raspberry Pi 3 on Rover

Abstract: Efficient and accurate object detection has been an important topic in the advancement of computer vision systems. With the advent of deep learning techniques, the accuracy of object detection has increased drastically. The project aims to incorporate state-of-the-art techniques for object detection to achieve high accuracy with real-time performance. A major challenge in many of the object detection systems is the dependency on other computer vision techniques for helping the deep learning-based approach, which leads to slow and non-optimal performance. In this project, we use a completely deep learning-based approach to solve the problem of object detection in an end-to-end fashion. The network is trained on the most challenging publicly available dataset (PASCAL VOC), on which an object detection challenge is conducted annually. The resulting system is fast and accurate, thus aiding those applications which require object detection.

2 – Team DRC Off-Road Vehicle

The DRC team is capable to deliver the required amount of effort and ideas required to conquer the battle so it has come up with an idea and is viewing innovation as the application for a better solution that meets new requirements and unarticulated needs.

Since innovation is the result of solving a problem, even if the problem wasn’t identified. So to the same we have proposed the following modernizations To induce sliding joints in the arms of the vehicle, thus resulting in shock absorbing arms. It will not only assist the suspension assembly, but also will cover wider spectrum of vibrations enhancing the shock absorbing by the suspension unit and ride quality. Not only that but it also ensures higher tyre contact duration with the ground, thus improving the performance.

We plan to install tracking equipment and induced transponders, which will always keep us updated of vehicle’s location, speed and travel time. It will also help us to maintain good database for the vehicles performance

We have a strategy to implement fuel level measuring using piezoelectric material, as no tampering is allowed within the fuel tank. Crew members can constantly monitor the fuel on the screen. This type of fuel measuring apparatus is yet to be tried in off-road motorsports events.

One of our key innovations is supposed to be an unmanned aerial vehicle what we usually call as a Drone. A drone monitored track report and assisted view via drone mounted lights. In this mini yet highly effective project, we plan to run an automated drone over the vehicle during the event time, which will monitor the track using camera and display live view to the crew using screen, over which, fuel meter is also available. Also, since our event includes, endurance race in the dark, the drone will also provide extra lights on the track, thus assisting the driver, to get a better view. This is a sure shot booster for our performance and to top it all this is an original innovation exclusively thought by the team.

3 – Loan Approval Program by Machine Learning using Python

A simple comparison between KNN, SVM, Decision Tree, and Logistic Regression models on a given data set of loans records to get loan approval.

4 – Line Follower Robot with Arduino Uno

Line Following is one of the most important aspects of robotics. A-Line Following Robot is an autonomous robot that can follow either a black or white line that is drawn on the surface consisting of a contrasting color. It is designed to move automatically and follow the made plotline. The robot uses several sensors to identify the line thus assisting the robot to stay on track. The array of four sensors makes its movement precise and flexible. The robot is driven by DC gear motors to control the movement of the wheels. The Arduino Uno interface is used to perform and implement algorithms to control the speed of the motors, steering the robot to travel along the line smoothly. This project aims to implement the algorithm and control the movement of the robot by proper tuning of the control parameters and thus achieve better performance. In addition, the LCD interface is added to display the distance traveled by the robot. It can be used industrial automated equipment carriers, small household applications, tour guides in museums and other similar applications, etc.