Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: A fast, modular scene understanding system using context-aware object detection
Author: Cadena, C.
Dick, A.
Reid, I.
Citation: Proceedings of IEEE International Conference on Robotics and Automation, 2015 / vol.2015-June, iss.June, pp.4859-4866
Publisher: IEEE
Issue Date: 2015
Series/Report no.: IEEE International Conference on Robotics and Automation ICRA
ISSN: 1050-4729
Conference Name: 2015 IEEE International Conference on Robotics and Automation (ICRA 2015) (26 May 2015 - 30 May 2015 : Seattle, WA)
Statement of
Cesar Cadena, Anthony Dick and Ian D. Reid
Abstract: We propose a semantic scene understanding system that is suitable for real robotic operations. The system solves different tasks (semantic segmentation and object detections) in an opportunistic and distributed fashion but still allows communication between modules to improve their respective performances. We propose the use of the semantic space to improve specific out-of-the-box object detectors and an update model to take the evidence from different detection into account in the semantic segmentation process. Our proposal is evaluated with the KITTI dataset, on the object detection benchmark and on five different sequences manually annotated for the semantic segmentation task, demonstrating the efficacy of our approach.
Keywords: Semantics, detectors, context, benchmark testing, training, robots, object detection
Rights: © 2015 IEEE
RMID: 0030039012
DOI: 10.1109/ICRA.2015.7139874
Grant ID:
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107732.pdfRestricted Access2.72 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.