RT Journal Article
A1 Wenqi Huang
A1 Fuzheng Zhang
A1 Aidong Xu
A1 Huajun Chen
A1 Peng Li

PB iet
T1 Fusion-based holistic road scene understanding
JN The Journal of Engineering
VO 2018
IS 16
SP 1623
OP 1628
AB This study addresses the problem of holistic road scene understanding based on the integration of visual and range data. To achieve the grand goal, the authors propose an approach that jointly tackles object-level image segmentation and semantic region labelling within a conditional random field (CRF) framework. Specifically, the authors first generate semantic object hypotheses by clustering 3D points, learning their prior appearance models, and using a deep learning method for reasoning their semantic categories. The learned priors, together with spatial and geometric contexts, are incorporated in CRF. With this formulation, visual and range data are fused thoroughly, and moreover, the coupled segmentation and semantic labelling problem can be inferred via graph cuts. The authors’ approach is validated on the challenging KITTI dataset that contains diverse complicated road scenarios. Both quantitative and qualitative evaluations demonstrate its effectiveness.
K1 semantic region labelling problem
K1 KITTI dataset
K1 conditional random field framework
K1 semantic object hypotheses
K1 deep learning method
K1 CRF framework
K1 object-level image segmentation
K1 fusion-based holistic road scene understanding
K1 3D point clustering
DO https://doi.org/10.1049/joe.2018.8319
UL https://digital-library.theiet.org/;jsessionid=fjcnkmcl9t6ih.x-iet-live-01content/journals/10.1049/joe.2018.8319
LA English
SN
YR 2018
OL EN