YOLO-based Panoptic Segmentation Network - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

YOLO-based Panoptic Segmentation Network

Abstract

Autonomous vehicles need information about their surroundings to safely navigate them. For this, the task of Panoptic Segmentation is proposed as a method of fully parsing the scene by assigning each pixel a label and instance id. Given the constraints of autonomous driving, this process needs to be done in a fast manner. In this paper, we propose the first panoptic segmentation network based on the YOLOv3 real-time object detection network by adding a semantic and instance segmentation branches. YOLO-panoptic is able to do real-time inference and achieves a performance similar to the state of the art methods in some metrics.
Fichier principal
Vignette du fichier
SE4ICPS_paper.pdf (7.66 Mo) Télécharger le fichier
SE4ICPS_paper_v2.pdf (7.66 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Licence : Copyright

Dates and versions

hal-03283640 , version 1 (12-07-2021)

Identifiers

Cite

Manuel Alejandro Diaz Zapata, Özgür Erkent, Christian Laugier. YOLO-based Panoptic Segmentation Network. COMPSAC 2021 - Intelligent and Resilient Computing for a Collaborative World 45th Anniversary Conference, Jul 2021, Madrid, Spain. pp.1-5, ⟨10.1109/COMPSAC51774.2021.00170⟩. ⟨hal-03283640⟩
95 View
280 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More