Complete Scene Parsing for Autonomous Navigation in Unstructured Environments

Abstract

Recent developments in Machine Learning and Computer Vision have enabled progress in autonomous navigation. However, most of the existing research focuses on European driving situations, with not much progress made in the Indian context. Our paper aims to achieve complete spatial understanding for the Indian context. Our focus is directed towards Semantic Segmentation and Instance Segmentation. We aim to develop an autonomous navigation pipeline by a combination of both approaches. Using DeepLabv3+ for Semantic Segmentation we achieve an mIOU of 68.58%, and using Hybrid Task Cascade we achieve an Average Recall of 56.5%.