SASTRA University
Context During my undergraduate research at SASTRA University, I worked on computer vision and multimodal AI problems across two research directions: semantic segmentation of aerial imagery and dense video captioning for assistive vision. The common thread across both projects was visual understanding: how can deep learning systems interpret complex visual inputs and convert them into useful structured outputs, whether pixel-level land-cover labels or natural-language descriptions of video content? What I Built For my B.Tech thesis, I worked on semantic segmentation of high-resolution aerial imagery using the ISPRS Vaihingen and Potsdam benchmark datasets. The goal was to classify every pixel in urban aerial images into land-cover categories such as buildings, impervious surfaces, vegetation, trees, cars, and clutter. ...