Hello I’m Soumyadip, I am presently working as a Sr. Computer Vision Engineer at Opencv University, mostly contributing to their blog, courses and projects(hopefully).
Previously, I worked as a Research Engineer at Infosys CAI, IIIT Delhi, focusing on Perception for the Autonomous Vehicle project ALIVE, under the guidance of Dr. Saket Anand and Dr. Sanjit Kaul. My main contributions were to the ADAS stack, HD-Map generation pipeline, Traffic Light Following (DL & Planning), and the development of a Virtual Testbed for AV testing.
I graduated on 2022, with a Bachelor of Technology (B. Tech) degree in the field of Electrical Engineering from IEM, Kolkata. During my graduation I worked as a research intern at IIT KGP under Dr. Debashish Chakravarty for landscape segmentation on satelite data and at Uni. of New South Wales(UNSW) under Dr. Tanmoy Dam worked on prior learning for GAN, generative clustering. I’m also a Kaggle Competition Expert, I predominantly participated in Object Detection and Segmentation competitions.
Skills: Python, C++, Carla, ROS, PyTorch, Linux, Git and W&B
Email ID: soumya997.sarkar@gmail.com ; soumyadips@iiitd.ac.in
💡 Open to opportunities [research or dev] in field of Robotics - Perception and Localization, Deep Learning
Projects:
Traffic Light Following
Implemented Traffic Light Following using C++ ROS package for Planning stack Behavior Tree. Trained YOLOP model for traffic light detections and Ported the model to Nvidia Orin. Integrated the model with the traffic light following stack. Conducted comprehensive testing of the P&C stack with Traffic Light Following in both the Carla and E2O platforms.
ADAS: Forward Collision Warning (FCW)
Designed and developed ADAS system, Forward Collision Warning (FCW) with Integrated Advanced Emergency Braking Systems (AEBS) maintaining the AIS standards. The project involved YOLOP object detection, tracking, and applying kinematic laws. The pipeline was tested in Carla and later deployed in Nvidia Orin.
XR-Testbed: Virtual AV testing
Worked on XR test-bed for autonomous vehicle testing. This involved RViz-based interface for efficient spawning and visualization of static and dynamic obstacles.
ADAS & DSM: Traffic Light Warning on Carla with DSM
Designed and developed ADAS system, Traffic Light Warning (TLW). The project involved YOLOP object detection, tracking, GMM Classifier, and applying kinematic laws. The following video is a showcase of the TLW and DSM on Carla. Mediapipe Facial Landmark detection was used for Drowsiness prediction and driver attention prediction.
Kaggle: TensorFlow - Great Barrier Reef [TOP 3%, Silver medal]
Problem statement was to accurately identify starfish by building an object detector trained on underwater videos of coral reefs. Trained FasterRCNN, YOLOv5. Introduced CLAHE based underwater image enhancemen. TTA and WBF was used for ensemble. Github
Kaggle: HuBMAP + HPA - Hacking the Human Body [TOP 6%, Bronze Medal]
Problem statement was, Semantic segmentation of 5 imbalanced medical tissue types using only 351 high-resolution images from 2 different train-test sources. Trained Swin Transformer Tiny with Uppernet decoder, CoaT. Used SWA based ensembling for same model of different folds and then using TTA on different models. Github
DDPM: Landscape Generation Using Diffusion Model
Scratch implemented DDPM using Pytorch. Two variants of Unet are implemented for DDPM, simple CNN based Unet and ViT based Unet. Experimented with Classifier Free Guidance(CFG). Github
Publications:
- A Novel Approach for Urban Unsupervised Segmentation Classification in SAR Polarimetry
- COVID-DeepNet: Deep Convolutional Neural Network Architecture Designed for Early Prognosis of COVID-19 Using Post-anterior View of Chest X-Rays
- Analysis of Depth Sensing and Lane Detection Algorithms for Advanced Driver Assistance Systems
Blogs:
- https://soumya997.github.io/
- https://www.kaggle.com/soumya9977/notebooks
- https://learnopencv.com/author/soumyadip/
For More information check out below links,
Resume|Kaggle|Gmail