Detecting moving objects is of great importance for
autonomous unmanned vehicle systems, and a
challenging task especially in complex dynamic
environments. This paper proposes a novel approach
for the detection of moving objects and the
estimation of their motion states using consecutive
stereo image pairs on mobile platforms. First, we
use a variant of the semi-global matching algorithm
to compute initial disparity maps. Second, assisted
by the initial disparities, boundaries in the image
segmentation produced by simple linear iterative
clustering are classified into coplanar, hinge, and
occlusion. Moving points are obtained during
ego-motion estimation by a modified random sample
consensus) algorithm without resorting to
time-consuming dense optical flow. Finally, the
moving objects are extracted by merging superpixels
according to the boundary types and their
movements. The proposed method is accelerated on the
GPU at 20 frames per second. The data which we use
for testing and benchmarking is released, thus
completing similar data sets. It includes 812 image
pairs and 924 moving objects with ground truth for
better algorithms evaluation. Experimental results
demonstrate that the proposed method achieves
competitive results in terms of moving-object
detection and their motion state estimation in
challenging urban scenarios.
%0 Journal Article
%1 ITS2017
%A Chen, L.
%A Fan, L.
%A Xie, G.
%A Huang, K.
%A Nüchter, A.
%D 2017
%J IEEE Transactions on Intelligent Transportation Systems
%K imported myown
%N 11
%P 1--10
%R 10.1109/TITS.2017.2680538
%T Moving-Object Detection From Consecutive Stereo
Pairs Using Slanted Plane Smoothing
%U https://robotik.informatik.uni-wuerzburg.de/telematics/download/tits2017.pdf
%V 18
%X Detecting moving objects is of great importance for
autonomous unmanned vehicle systems, and a
challenging task especially in complex dynamic
environments. This paper proposes a novel approach
for the detection of moving objects and the
estimation of their motion states using consecutive
stereo image pairs on mobile platforms. First, we
use a variant of the semi-global matching algorithm
to compute initial disparity maps. Second, assisted
by the initial disparities, boundaries in the image
segmentation produced by simple linear iterative
clustering are classified into coplanar, hinge, and
occlusion. Moving points are obtained during
ego-motion estimation by a modified random sample
consensus) algorithm without resorting to
time-consuming dense optical flow. Finally, the
moving objects are extracted by merging superpixels
according to the boundary types and their
movements. The proposed method is accelerated on the
GPU at 20 frames per second. The data which we use
for testing and benchmarking is released, thus
completing similar data sets. It includes 812 image
pairs and 924 moving objects with ground truth for
better algorithms evaluation. Experimental results
demonstrate that the proposed method achieves
competitive results in terms of moving-object
detection and their motion state estimation in
challenging urban scenarios.
@article{ITS2017,
abstract = {Detecting moving objects is of great importance for
autonomous unmanned vehicle systems, and a
challenging task especially in complex dynamic
environments. This paper proposes a novel approach
for the detection of moving objects and the
estimation of their motion states using consecutive
stereo image pairs on mobile platforms. First, we
use a variant of the semi-global matching algorithm
to compute initial disparity maps. Second, assisted
by the initial disparities, boundaries in the image
segmentation produced by simple linear iterative
clustering are classified into coplanar, hinge, and
occlusion. Moving points are obtained during
ego-motion estimation by a modified random sample
consensus) algorithm without resorting to
time-consuming dense optical flow. Finally, the
moving objects are extracted by merging superpixels
according to the boundary types and their
movements. The proposed method is accelerated on the
GPU at 20 frames per second. The data which we use
for testing and benchmarking is released, thus
completing similar data sets. It includes 812 image
pairs and 924 moving objects with ground truth for
better algorithms evaluation. Experimental results
demonstrate that the proposed method achieves
competitive results in terms of moving-object
detection and their motion state estimation in
challenging urban scenarios.},
added-at = {2017-09-19T13:40:53.000+0200},
author = {Chen, L. and Fan, L. and Xie, G. and Huang, K. and Nüchter, A.},
biburl = {https://www.bibsonomy.org/bibtex/2a28529c501c1ab681130262005dc838f/nuechter76},
doi = {10.1109/TITS.2017.2680538},
interhash = {30afb745fe2c479d2f65e803fd3b61c5},
intrahash = {a28529c501c1ab681130262005dc838f},
issn = {1524-9050},
journal = {IEEE Transactions on Intelligent Transportation Systems},
keywords = {imported myown},
month = {November},
number = 11,
pages = {1--10},
timestamp = {2018-10-09T05:30:03.000+0200},
title = {Moving-Object Detection From Consecutive Stereo
Pairs Using Slanted Plane Smoothing},
url = {https://robotik.informatik.uni-wuerzburg.de/telematics/download/tits2017.pdf},
volume = 18,
year = 2017
}