Eimran-Eimon

Education

Institution: Notre Dame College, Dhaka

GPA: 5.00/5.00
Major: Science

Institution: Rajshahi University of Engineering & Technology (RUET)

CGPA: 3.15/4.00
Bachelor of Science in Engineering
Department: Computer Science & Engineering (CSE)
Thesis: “Superpixel Based Inter-Frame Prediction for Video Coding”
Supervisors: Dr. Ashek Ahmmed, Dr. Shahid Uz Zaman

Work Experience

Full-Stack Software Engineer (Mar 2020 - Present) at CoKreates Limited

As part of its digitalization process, the Bangladesh government has developed Government Resource Planning (GRP), an Enterprise Resource Planning (ERP) solution of its own, to manage works electronically to optimize and economize assets and expenses. GRP is consists of eleven modules. From which, I have worked on the “Accounts Module”. Accounts Module is designed to manage all kinds of financial activities records and transactions electronically to facilitate extensive search along with the generation of standard accounting reports.

Back-end: Java Spring Boot (Microservice Architecture)
Report Generation Tool: Jasper
Database: PostgreSQL
Front-end: Angular

Computer Vision Engineer (Nov 2019 - Mar 2020) at Business Accelerate BD Ltd.

Project - People Counter: The primary goal of this project is to find some useful business insight using the live CCTV feed of a store. Some main goals include:

Count the number of the person entered in and exited from the store.
Count the number of the person in a zone (like no. of people playing VR games).
Find the average time spent by a customer in a zone.
Generate a heatmap using a customer’s trajectories.
Store the age, gender, and emotion of a customer when they are in a specific zone(e.g. when they are seeing a new product or buying a product)

I have used YOLOv3(You Only Look Once), MobilenetSSD(Single Shot Detection), Fast-RCNN for detecting people in real-time. And for tracking, I have used the “dlib correlation tracker”, which is based on Danelljan et al.’s 2014 paper “Accurate Scale Estimation for Robust Visual Tracking”. I have also utilized the ”Intel OPENVINO” library for Age-Gender-Emotion detection.

Result of my implemented models:

Enter-exit count (See Video Demo)
Age-gender-emotion detection (See Video Demo)

Full-Stack Software Engineer (Nov 2018 - Nov 2019) at E-Horizon IT Ltd.

Major Accomplishments:

Developed a system called “Media Monitor & Archive” for a Government Agency.
- Server Environment: NodeJS
- Back-end: PHP, JavaScript
- Database: MySQL
- Front-end: HTML, Bootstrap, JQuery
Developed a social networking site called “Deshi Social Connection”.
- Server Environment: NodeJS
- Back-end: Javascript
- API: ExpressJS
- Database: MongoDB
- Front-end: HTML, Bootstrap, JQuery
Project Videos:
- Deshi Social Connection (See Video Demo)
- JobBook (See Video Demo)

Publications

Superpixel Based Inter-Frame Prediction for Video Coding

Md. Eimran Hossain Eimon, Md. Zahirul Islam, Md. Shahid Uz Zaman, Md. Al Mehedi Hasan, Boshir Ahmed. "Superpixel Based Inter-Frame Prediction for Video Coding", 5^th International Conference on Advance in Electrical Engineering (ICAEE)

Classification Based Inter-Frame Prediction in Video Compression

Md. Zahirul Islam, Md. Eimran Hossain Eimon, Boshir Ahmed, Md. Al Mehedi Hasan. "Classification Based Inter-Frame Prediction in Video Compression", 5^th International Conference on Advance in Electrical Engineering (ICAEE)

Awards

IEEE AWARD WINNING APP (Farmer Assistant) - 2016

The main purpose of the android application includes:

Ensure the exact amount of UREA in the cultivation of land.
Remove the limitations of use of LCC(Leaf Color Chart).
Help color-blind farmers.
Increase the production.
Minimize the production cost.
Reduce the environment pollution by using exact amount of UREA.

Eimran Hossain Eimon