University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Semantically Coherent Co-segmentation and Reconstruction of Dynamic Scenes

Mustafa, Armin and Hilton, Adrian (2017) Semantically Coherent Co-segmentation and Reconstruction of Dynamic Scenes In: IEEE International Conference in Computer Vision & Pattern Recognition CVPR, 2017, 2017-07-21 - 2017-07-26, Honolulu, Hawaii.

cvprFinalOpenAccess.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (9MB) | Preview
Text (licence)
Available under License : See the attached licence file.

Download (33kB) | Preview


In this paper we propose a framework for spatially and temporally coherent semantic co-segmentation and reconstruction of complex dynamic scenes from multiple static or moving cameras. Semantic co-segmentation exploits the coherence in semantic class labels both spatially, between views at a single time instant, and temporally, between widely spaced time instants of dynamic objects with similar shape and appearance. We demonstrate that semantic coherence results in improved segmentation and reconstruction for complex scenes. A joint formulation is proposed for semantically coherent object-based co-segmentation and reconstruction of scenes by enforcing consistent semantic labelling between views and over time. Semantic tracklets are introduced to enforce temporal coherence in semantic labelling and reconstruction between widely spaced instances of dynamic objects. Tracklets of dynamic objects enable unsupervised learning of appearance and shape priors that are exploited in joint segmentation and reconstruction. Evaluation on challenging indoor and outdoor sequences with hand-held moving cameras shows improved accuracy in segmentation, temporally coherent semantic labelling and 3D reconstruction of dynamic scenes.

Item Type: Conference or Workshop Item (Conference Paper)
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
Date : 9 November 2017
DOI : 10.1109/CVPR.2017.592
Copyright Disclaimer : © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Contributors :
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 29 Mar 2017 09:33
Last Modified : 16 Jan 2019 17:13

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800