cv

Software Engineer

NCR Corporation

Leveraged C# expertise to diagnose and resolve issues at Grocery and Fuel POS, ensuring optimal system functionality and a positive user experience.Additionally, developed new features to address evolving business requirements.

• Emerald POS

Research Assistant

ML Lab, International Institute of Information Technology (IIIT) Hyderabad

Working on deploying fully autonomous navigation systems on the road to detect objects under adverse weather conditions and in unstructured traffic.Working on the safety and robustness of semantic segmentation models.Developed simulation-based Labs for Discrete Mathematics course

• Work published at WACV 2024

Undergraduation

National Institute of Technology (NIT), Rourkela

Electrical Engineering

• Machine Learning
• Computer Vision
• C programming
• Soft Computing Techniques
• Digital Electronics
• Electrical Machines

People Choice Award

NCR London Center

Received the People's Choice Award from NCR London Center for a smart store prototype at the NCR Global Hackathon 2022.

IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather

IEEE/CVF Winter Conference on Applications of Computer Vision

We introduce the IDD-AW dataset, which provides 5000 pairs of high-quality images with pixel-level annotations, captured under rain, fog, low light, and snow in unstructured driving conditions. As compared to other adverse weather datasets, we provide i.) more annotated images, ii.) paired Near-Infrared (NIR) image for each frame, iii.) larger label set with a 4-level label hierarchy to capture unstructured traffic conditions. We benchmark state-of-the-art models for semantic segmentation in IDD-AW. We also propose a new metric called 'Safe mean Intersection over Union (Safe mIoU)' for hierarchical datasets which penalizes dangerous mispredictions that are not captured in the traditional definition of mean Intersection over Union (mIoU).

CNN based image resizing forensics for double compressed JPEG images

Elsevier, Journal of Information Security and Applications

This paper investigates a novel CNN-based architecture for image resizing forensics in the presence of Double-JPEG compression.