Complete Scene Parsing for Autonomous Navigation in Unstructured Environments

Please use this identifier to cite or link to this item: http://dspace.bits-pilani.ac.in:8080/jspui/handle/123456789/11851

Full metadata record

DC Field	Value	Language
dc.contributor.author	Rout, Bijay Kumar	-
dc.date.accessioned	2023-09-04T10:24:11Z	-
dc.date.available	2023-09-04T10:24:11Z	-
dc.date.issued	2020	-
dc.identifier.uri	https://ieeexplore.ieee.org/abstract/document/9081829	-
dc.identifier.uri	http://dspace.bits-pilani.ac.in:8080/xmlui/handle/123456789/11851	-
dc.description.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%.	en_US
dc.language.iso	en	en_US
dc.publisher	IEEE	en_US
dc.subject	Mechanical Engineering	en_US
dc.subject	Semantic segmentation	en_US
dc.subject	Instance Segmentation	en_US
dc.subject	Autonomous navigation	en_US
dc.subject	Indian Driving Dataset	en_US
dc.subject	Unstructured environment	en_US
dc.title	Complete Scene Parsing for Autonomous Navigation in Unstructured Environments	en_US
dc.type	Article	en_US
Appears in Collections:	Department of Mechanical engineering

Files in This Item:

There are no files associated with this item.