Addressing Occlusion in Panoptic Segmentation

Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite the gains in performance, image understanding algorithms are still not completely robust to partial occlusion. In this work, we propose a novel object classification method based on compositional modeling and explore its effect in the context of the newly introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection pipeline in UPSNet, a Mask R-CNN based design for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. We perform extensive experiments and showcase results on the complex COCO and Cityscapes datasets. The novel classification method shows promising results for object classification on occluded instances in complex scenes.

Level thesis:degree_level

masters

Department dc:contributor.department

Computer Engineering

Grantor dc:publisher

Virginia Tech

Year dc:date.issued

2021

Author dc:creator

• Sarkaar, Ajit Bhikamsingh

Chair dc:contributor.committeechair

• Abbott, A. Lynn

Committee members dc:contributor.committeemember

• Huang, Bert
• Jones, Creed F. III

• Deep learning (Machine learning)
• Image Segmentation
• Object Detection
• Image Classification
• Autonomous Systems

Statement dc:rights

• In Copyright

Licence dc:rights.uri

• http://rightsstatements.org/vocab/InC/1.0/

Dc Identifier Other

vt_gsexam:29107

OAI identifier oai:identifier

oai:vtechworks.lib.vt.edu:10919/101988