Toggle Main Menu Toggle Search

Open Access padlockePrints

Depth-embedded instance segmentation network for urban scene parsing

Lookup NU author(s): Dr Tong XinORCiD, Dr Shidong WangORCiD


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


© 2022-IOS Press. All rights reserved. The ubiquitous availability of cost-effective cameras has rendered large scale collection of street view data a straightforward endeavour. Yet, the effective use of these data to assist autonomous driving remains a challenge, especially lack of exploration and exploitation of stereo images with abundant perceptible depth. In this paper, we propose a novel Depth-embedded Instance Segmentation Network (DISNet) which can effectively improve the performance of instance segmentation by incorporating the depth information of stereo images. The proposed network takes binocular images as input to observe the displacement of the object and estimate the corresponding depth perception without additional supervisions. Furthermore, we introduce a new module for computing the depth cost-volume, which can be integrated with the colour cost-volume to jointly capture useful disparities of stereo images. The shared-weights structure of Siamese Network is applied to learn the intrinsic information of stereo images while reducing the computational burden. Extensive experiments have been carried out on publicly available datasets (i.e., Cityscapes and KITTI), and the obtained results clearly demonstrate the superiority in segmenting instances with different depths.

Publication metadata

Author(s): Wang Z, Xin T, Wang S, Zhang H

Publication type: Article

Publication status: Published

Journal: Journal of Intelligent and Fuzzy Systems

Year: 2022

Volume: 42

Issue: 3

Pages: 1269-1279

Online publication date: 02/02/2022

Acceptance date: 02/04/2018

ISSN (print): 1064-1246

ISSN (electronic): 1875-8967

Publisher: IOS Press BV


DOI: 10.3233/JIFS-202230


Altmetrics provided by Altmetric